Browse Topic: Cameras

Items (696)
Find
Next-Gen Driver Health and Wellness Platform for Fatigue Detection and Emotional Wellbeing Monitoring2026-26-06391/16/2026
Driver fatigue and emotional distress are major contributors to traffic accidents, especially among long-haul and professional drivers, making their detection a critical area in road safety and public health. While existing research has explored various sensor-based and wearable solutions to monitor driver states, these approaches often suffer from high cost, intrusiveness, or limited scalability. Camera-based systems have recently gained attention for being less invasive and more practical for real-world deployment; however, many still depend on multiple sensors or cloud-based processing, which raise concerns around energy consumption, privacy, and integration complexity. To address these gaps, we present a sustainable, camera-only Driver Health and Wellness Platform for real-time fatigue detection and emotional wellbeing monitoring. The system leverages a single in-cabin camera and applies lightweight, edge-optimized computer vision models to analyze facial features, eye dynamics
Iqbal, Shoaib, Imteyaz, Shahma
Video 2 Scenario: A Novel Method to Generate Edge Case Traffic Scenarios from Dashcam Videos2026-26-06661/16/2026
This paper presents Video 2 Scenario, a systematic and cost-effective method to generate edge case scenarios derived from road events captured in dash camera videos. Current methods for obtaining real-world scenarios rely on supplementary sensor data like LiDAR, GPS and radar, which require expensive sensor setups for data collection. Other scenario generation methods rely on manual effort by human experts, which can be laborious and time-consuming. Our proposed methodology utilizes state-of-the-art deep learning models to extract vehicle trajectories, road layouts and other scenario-specific elements and reconstructs a scenario in the format of simulation scripts. The scripts are then refined by replaying the scenario multiple times in a simulation with attached virtual sensors to minimize the discrepancy between the subsequently obtained simulated video data and the original dash camera video data. The refined simulation scripts ensure that critical edge case scenarios are replicated
Ramalingam, Surya Prasath, Priyadarshi, Marut, Khan, Parvej, Kumar, Vaibhav, Pandey, Gaurav, Lohani, Bharat
Adaptability Survey and analysis of Camera Monitoring Systems (CMS) on Various Driving Population for Passenger Vehicles in Indian Driving Scenario2026-26-06011/16/2026
This paper presents a comprehensive survey and data collection study on the adaptability of Camera Monitoring Systems (CMS) for passenger vehicles. With the growing demand for enhanced safety, automation, and driver assistance technologies, Camera Monitoring Systems (CMS) has emerged as a key component in modern automotive design. This study aims to explore the current state of camera-based monitoring in passenger vehicles, focusing on their adaptability through survey data collection of various driving population and analysis. This paper evaluates the acceptance of CMS configurations in replacement to conventional rear view mirrors through Position of Monitor, Clarity, CMS Adaptiveness to eyes, Comfort while turning, Merging into moving traffic, Monitoring Rear Traffic, while Getting Out of Car, while Overtaking, Coverage Area and Overall Acceptance. The findings offer valuable insights for manufacturers, engineers, and researchers working toward the evolution of intelligent vehicle
Sinha, Ankit, Tambolkar, Sonali Ameya, Belavadi Venkataramaiah, Shamsundara, Kauffmann, Maximilian
Mapless Yet Accurate: Trajectory Prediction for traffic agents using online HD Map Reconstruction for Autonomous Driving2026-26-00391/16/2026
Accurate trajectory prediction of traffic agents is vital for enabling safer and more reliable autonomous driving. High-definition (HD) and standard-definition (SD) maps play a critical role in this process by providing detailed lane topology and directional cues essential for forecasting the movement of surrounding traffic agents. However, creating HD maps is both expensive and resource-intensive, often relying on complex SLAM systems and specialized sensors, while SD maps, though more readily available, lack the precision needed for accurate navigation in autonomous driving. In this work, we present a novel framework for trajectory prediction that uses online reconstruction of HD maps using images from vehicle-mounted cameras, offering a more scalable and cost-effective solution. Our method achieves notable improvements in prediction accuracy, especially in scenarios lacking access to pre-built maps. Additionally, we propose a new evaluation metric that emphasizes safety by
Upreti, Minali, Girijal, Rahul, B A, NaveenKumar, Thontepu, Phani, Ghosh, Shankhanil, Chakraborty, Bodhisattwa
Computer Vision Aided Methodology for Steering Position Detection2026-26-06311/16/2026
Steering angle is a critical parameter in vehicle dynamics, traditionally measured using Steering Angle Sensors (SAS). However, external sensors used for development testing often pose challenges due to their bulk, installation complexity, and additional costs. With the upcoming regulatory requirements related to driver drowsiness detection, vehicles will incorporate cameras in near future. This study explores an innovative approach to repurpose the same camera for steering angle measurement, eliminating the need for dedicated sensors and reducing costs significantly. The proposed method utilizes colored tapes or visible markers affixed to the steering wheel, with a strategically placed camera capturing steering movement. Depending on requirements, various types of cameras (including thermal) can be deployed at different positions (front, back, or side). The vehicle's ECU employs an advanced object detection algorithm to track the movement of these markers, subsequently calculating the
TP, Amal, Priyadasini, Shishira
Feature-Based Stereo Vision for Ship-Deck LandingF-0081-2025-02135/20/2025
In this paper, we develop a new feature-based algorithm using stereo cameras to estimate stochastic ship-deck motion at high sea states. Unlike our previous algorithms, this algorithm is able to estimate the motion of arbitrary ship structures without prior information on the ship's visual appearance or geometry. The algorithm requires an initial pose and suffers from drift over time, which was resolved by fusing it with our previous 2D feature-based vision algorithm. The combined vision algorithm is validated using a simulated ship featuring 3D ship structures and 2D flight deck markings representative of a DDG-51 ship. The results indicate that the algorithm can accurately estimate the pose of a simulated ship undergoing Sea-State 6 motion. The vision algorithm was further validated in a simple free-flight test.
Chopra, Inderjit
Inflight Measurements of the Empennage of an Ultralight Coaxial HelicopterF-0081-2025-02465/20/2025
The empennage of a helicopter is largely responsible for its stability in forward flight. Its performance is mainly determined by its aerodynamics. In this paper, the empennage of a CoAX 2D ultralight research helicopter is analyzed in detail. For this purpose, the helicopter was equipped with flow measurement devices and flight tests were performed, covering different flight conditions. Measurements from a nose boom as well as the pilot’s control inputs and helicopter's position are available for evaluation. For the empennage in particular, seven-hole flow probes were mounted on it and various cameras were used to record the movement of the surface tufts.
Rottmann, Lukas, Paintner, Rafael, Müller, Daniel, Hunold, Julian
SAE TOMORROW TODAY: How AI Alignment Makes AVs Safer134951/10/2025
In order for AVs to perform safely and reliably, we need to teach them the language of human preference and expectations--and accelerating AI alignment can do just that. Enter Kognic, the industry-leading annotation platform for sensor-fusion datasets (e.g., camera, radar, and LIDAR data). By helping companies gather, organize, and refine massive datasets used for training AI models, Kognic is helping to ensure that AD/ADAS perform reliably and meet safety standards--all while minimizing costs and optimizing teams. To learn more, we sat down with Daniel Langkilde, Co-Founder and CEO, to discuss why the future of autonomous driving depends on effectively managing AI-driven datasets and how Kognic is leading dataset management for safety-critical AI. We'd love to hear from you. Share your comments, questions and ideas for future topics and guests to podcast@sae.org. Don't forget to take a moment to follow SAE Tomorrow Today--a podcast where we discuss emerging technology and trends in
Hineman, Marcie
Cat’s Eye-Inspired Vision System for Autonomous RoboticsTBMG-5218012/1/2024
Researchers led by Professor Young Min Song from the Gwangju Institute of Science and Technology (GIST) have unveiled a vision system inspired by feline eyes to enhance object detection in various lighting conditions. Featuring a unique shape and reflective surface, the system reduces glare in bright environments and boosts sensitivity in low-light scenarios. By filtering unnecessary details, this technology significantly improves the performance of single-lens cameras, representing a notable advancement in robotic vision capabilities.
Volumetric Wake Investigation of a Free-Flying Quadcopter using Shake-The-Box Lagrangian Particle TrackingF-0080-2024-11615/7/2024
The Shake-The-Box technique was applied to experimentally quantify the time-resolved volumetric flow field around a free-flying quadcopter UAV with an overall span of about 0.5 m. State-of-the-art LED illumination and high-speed camera equipment was combined with modern Lagrangian tracer particle tracking and data assimilation techniques, facilitating a measurement volume larger than 1.5m3. The setup allowed for both hover and limited maneuvering of the quadcopter, while resolving even small details of the complex interactional aerodynamics. In hover out of ground effect, the four individual rotor wakes merged into a single jet within a few rotor radii below the rotor planes. Evaluating the mass and momentum fluxes over suitable control volumes yields accurate estimates for the quadcopter's total thrust, the asymmetric thrust distribution between front and back rotors, and the entrainment of external flow through turbulent mixing. Hover in ground effect decreases the power requirement
Wolf, Claus Christian, Schröder, Andreas, Strübing, Tobias, Bosbach, Johannes, Heintz, Alexander, Schwarz, Clemens, Schanz, Daniel
Advancing Cockpit Safety: Cost-Effective Flight Data Monitoring with Deep LearningF-0080-2024-12395/7/2024
The rotorcraft community faces significantly higher accident rates compared to fixed-wing commercial aircraft, underscoring the critical need for enhanced safety measures. While Helicopter Flight Data Monitoring programs hold promise in improving safety, their widespread adoption remains limited, partly due to challenges associated with the acquisition and analysis of flight data. This paper proposes a Deep Learning (DL) solution to address safety concerns within the rotorcraft community by efficiently acquiring and analyzing flight data for a more automated and comprehensive safety assessment. Specifically, we leverage data obtained with cost-effective off-the-shelf cameras, and process it through Convolutional Neural Networks for automated detection and classification of gauges from several helicopters' cockpits. Our DL pipeline integrates a classifier for helicopter identification, an object detector for cockpit gauges detection and classification, and a network to infer the reading
Khelifi, Amine, Johnson, Charles C., Thompson, Lacey, Bouaynaya, Nidhal C., Carannante, Giuseppina, Trabelsi, Mohamed Ali
Localisation of Ultra-short Sound Emissions from Automotive Components by Using the Sound Field Scanning Method2025-01-00925/5/2023
Design verification and quality control of automotive components require the analysis of the source location of ultra-short sound events, for instance the engaging event of an electromechanical clutch or the clicking noise of the aluminium frame of a passenger car seat under vibration. State-of-the-art acoustic cameras allow for a frame rate of about 100 acoustic images per second. Considering that most of the sound events introduced above can be far less than 10ms, an acoustic image generated at this rate resembles an hard-to-interpret overlay of multiple sources on the structure under test along with reflections from the surrounding test environment. This contribution introduces a novel method for visualizing impulse-like sound emissions from automotive components at 10x the frame rate of traditional acoustic cameras. A time resolution of less than 1ms eventually allows for the true localization of the initial and subsequent sound events as well as a clear separation of direct from
Rittenschober, Thomas
Hybrid 3D Sound Intensity and Simulation for Optimizing Acoustic Output of Truck Rear Axles2025-01-01055/5/2023
This study presents a novel methodology for optimizing the acoustic performance of rotating machinery by combining scattered 3D sound intensity data with numerical simulations, focusing on the rear axle of a truck. Using Scan&Paint 3D, sound intensity data is rapidly acquired over a large spatial area with the assistance of a 3D sound intensity probe and infrared stereo camera. The experimental data is then integrated into far-field radiation simulations, enabling detailed analysis of the acoustic behavior and accurate predictions of far-field sound radiation. This hybrid approach offers a significant advantage for assessing complex acoustic sources, allowing for quick and reliable evaluation of noise mitigation solutions. While the current application focuses on the truck's rear axle far-field radiation, the same method can be extended to predict in-cabin sound pressure, providing a versatile solution for many industrial problems.
Fernandez Comesana, Daniel, Vael, Georges, Robin, Xavier, Orselli, Joseph, Schmal, Jared
Suction Cup Quality Predication by Digital Image Correlation2023-01-00674/11/2023
Vacuum suction cups are used as transforming handles in stamping lines, which are essential in developing automation and mechanization. However, the vacuum suction cup will crack due to fatigue or long-term operation or installation angle, which directly affects production productivity and safety. The better design will help increase the cups' service life. If the location of stress concentration can be predicted, this can prevent the occurrence of cracks in advance and effectively increase the service life. However, the traditional strain measurement technology cannot meet the requirements of tracking large-field stains and precise point tracking simultaneously in the same area, especially for stacking or narrow parts of the suction cups. The application must allow multiple measurements of hidden component strain information in different fields of view, which would add cost. In this study, a unique multi-camera three-dimensional digital image correlation (3D-DIC) system was designed
Guo, Bicheng, Zheng, Xiaowan, Fang, Siyuan, Yang, Lianxiang
Medical Lasers: When the Laser Application Requires Utmost SafetyTBMG-4695111/1/2022
Panoptic Based Camera and Lidar Fusion for Distance Estimation in Autonomous Driving Vehicles2022-28-030710/5/2022
Position estimation of the surrounding objects seen by the sensors mounted on an autonomous vehicle is a key module and it is typically carried out with the camera-lidar fusion owing to the high accuracy in depth estimation from lidar point cloud. In typical automotive LIDAR with 64 scanner points or less, at distances above 100m, the object detection with LIDAR is not dependable as the number of LIDAR clusters will be sparse, while the high-resolution camera can offer better detection even at the distances above 100m. Calculation of the position can be best achieved if there is a reliable means to get the corresponding LIDAR points for the detection in camera. To address this, we are proposing a novel a grid-based approach, in which a grid is created in the point cloud by calculating object’s position derived from camera detections. The correspondence between Camera pixels and LIDAR point cloud tends to suffer when the object of interest is occluded (eg.by other vehicles, guard rails
Jose, Edwin, P, Aparna M, Patil, Mrinalini, Thayyil Ravi, Arunkrishna, Rajan, Manoj
Deere advances in-field autonomy22TOFHP08_018/1/2022
While stereo cameras and computer vision guide Deere's “limited release” 8R autonomous tractor, Bear Flag's lidar tech will augment future machines. Q&A with Deere's Joe Liefer John Deere got “really serious” about autonomy in 2019, according to Joe Liefer, senior product manager of autonomy at John Deere Intelligent Solutions Group. Three years later - after forming an in-house development team and acquiring some tech-startup expertise - the machinery maker revealed a fully autonomous tractor at CES 2022 that it claims is ready for large-scale production. Based on Deere's 8R tractor, the machine combines a TruSet-enabled chisel plow, GPS guidance system, advanced AI and six pairs of stereo cameras that enable 360-degree obstacle detection and distance calculation. The autonomous 8R tractor also continuously checks its position relative to a geofence and is accurate to within less than 1 inch (25 mm), Deere claims. Farmers monitor and control it from a smartphone app.
Shaping Light Enables 2D Microscopes to Capture 4D DataTBMG-459846/1/2022
Super temporal resolution microscopy allows imaging of fluorescent molecules 20 times faster than traditional lab cameras normally allow. A general method has been developed to let a microscope capture 3D spatial information along with the fourth dimension: molecular movement over time. This will help scientists who study dynamic processes view where molecules of interest are located and how fast they move; for example, within living cells.
An Autonomous Ground Based Multi Sensor Data Fused TDR Prediction and Monitoring System2022-26-12275/26/2022
According to a study conducted by IATA, EASA and ICAO, runway excursions are common type of incidents that leads to major accidents. Runway excursion predominantly occur due to incorrect utilization of the touchdown zone (TDZ). A ground-based multi-sensor data fused touchdown region (TDR) prediction and monitoring system is proposed in this paper. This system autonomously analyses real-time environmental data with remote sensing capability around the runway site, gathers real-time information on flight critical parameters of approaching aircraft through an ADS-B Out data link, predicts ideal TDR over the runway TDZ for a particular aircraft, and estimates the expected contemporaneous TDR based on the monitored current approach profile. If the ideal and expected TDR do not overlap, there is a chance for an excursion. In such cases, the flight parameter that needs corrective action is determined and notified to the pilot. In order to analyze dynamic environmental data, mathematical
Nagonda, Ajay Nagarajan, Manjunath, Karthik
Vehicle Feature Recognition Method Based on Image Semantic Segmentation2022-01-01653/29/2022
In the process of truck overload and over-limit detection, it is necessary to detect the characteristics of the vehicle's size, type, and wheel number, etc. In addition, in some vehicle visual load recognition systems, the vehicle load can be calculated by detecting the vibration frequency of specific parts of vehicle or the change in the length of the suspension during the vehicle's forward process. Therefore, it is very important to quickly and accurately identify vehicle features through the camera. This paper proposes a vehicle feature recognition method based on image semantic segmentation and Python, which can identify the length, height, number of wheels and vibration frequency at specific parts of the vehicle based on the vehicle driving video captured by the roadside camera. The process of vehicle recognition is as follows: First, build a convolutional neural network based on the image semantic segmentation model SegNet and use the data set to train it, and use the Python
Wang, Chu, Ding, Shousheng
Road Crossing Assistance Method Using Object Detection Based on Deep Learning 2022-01-01693/29/2022
This paper describes a method for assisting pedestrians to cross a road. As motorization develops, pedestrian protection techniques are becoming more and more important. Advanced driving assistance systems (ADAS) are improving rapidly to provide even greater safety. However, since the accident risk of pedestrians remains high, the development of an advanced walking assistance system for pedestrian protection may be an effective means of reducing pedestrian accidents. Crossing a road is one of the highest risk events, and is a complex phenomenon that consists of many dynamically changing elements such as vehicles, traffic signals, bicycles, and the like. A road crossing assistance system requires three items: real-time situational recognition, a robust decision-making function, and reliable information transmission. Edge devices equipped with autonomous systems are one means of achieving these requirements. Situational recognition when crossing a road must identify the pedestrian
Kawamura, Hiroaki, Shintani, Kohei, Mima, Hiroki, Taniguchi, Mashio
Monocular Camera System for Detecting a Small Object at Far Range2022-01-00733/29/2022
For the autonomous driving and ADAS, we have been developing the new vision system. It focuses on detecting the small object at far ranges and makes the vehicle to keep smooth running by avoiding the object in advance. This system is based on the high-resolution monocularcamera with narrow FOV and the core algorithms for object-detection and lane-detection. Since we have already developed the prototype system, we have applied it to a field test. The test results are: for traffic cones and arbitrary objects at 50 - 150 [m], the detection rate is 95.6% for n=90, the ghost rate is 0% for n=53 and the range accuarcy is 7.1 [m] for n=72. To attain this performance, we also have developed the support technologies for detecting a three layer cone and the obscure side line of an object.
Miyahara, Shunji
Computer Vision-Based V2X Collaborative Perception2022-01-00823/29/2022
In this paper, we present the computer vision-based V2X collaborative perception. Our system uses a forward-looking camera in the Host Vehicle. The camera detects road users such as pedestrians, vehicles, and motorcycles. Such information includes object type, relative location, direction, and speed. This information is used to compose proxy Basic Safety Messages on behalf of the detected objects. Early adopters of the V2X technology can experience the benefits of enhanced V2X market penetration. The outcome of adopting our concept will result in an inflated V2X market penetration rate leading to earlier safety, mobility, and situational awareness improvements. The ultimate goal is for all road participants to be fully aware of each other. The novelty of our work is the integration of computer vision-based detection and LTE-V V2X communications, in addition to implementing the concept for pedestrians and bicyclists. A similar concept will work for other sensors such as radar and LiDARs
Miucic, Radovan, Rajab, Samer
KDepthNet: Mono-Camera based Depth Estimation for Autonomous Driving 2022-01-00793/29/2022
Object avoidance for autonomous driving is a vital factor in safe driving. Having the accurate depth of each barrier in the scene can contribute to obstacle prevention. In recent years, precise depth estimation systems can be attributed to notable advances in Deep Neural Networks and hardware facilities/equipment. There are several depth estimation methods for autonomous vehicles which usually utilize lasers, structured light and other reflections on the object surface to capture depth point clouds, complete surface modelling and estimate scene depth maps. However, estimating precise depth maps is still challenging. Indeed, it usually requires heavy time cost, abundant manpower and huge computing devices. Consequently, image-based depth calculation has turned into the mainstream of study and can be applied for a broad range of applications. A vast majority of camera depth estimation methods intend to determine the depth map of the whole input image using binocular cameras or a 3D
Tavakolian, Niloofar, Fekri, Pedram, Zadeh, Mehrdad, Dargahi, Javad
A Comparison of Luminance Estimation Software to Measured Values2022-01-09663/29/2022
Mapping the luminance values of a visual scene is of broad interest to accident reconstructionists, human factors professionals, and lighting experts. Previous work has shown that pixel intensity captured by consumer-grade digital still cameras can be calibrated to estimate luminance. Suway and Suway presented a methodology for estimating luminance from digital images and video of a scene. This method requires the capture of dark images close in time to the capture of the image that will be used to estimate luminance. Additionally, Suway’s method requires the specific camera and lens combination used to be calibrated for luminance estimation. The methodology presented by Suway forms the basis for a software application, called Nitere, that calculates the relationship between pixel intensity and luminance for a camera lens combination and can therefore estimate real-world luminance values from pixel intensity for a properly calibrated camera and lens combination. In this paper, the
Carter, Neal, Suway, Jeff
Geometric Derivation of Camera Equations 2022-01-10043/29/2022
Photogrammetry, camera matching, and model-based image matching are commonly used techniques to analyze video for accident reconstruction and other forensic applications. Investigators are often tasked with determining the speed of a vehicle, person, or other object in a video of an incident, or with taking measurements from photographs. All such calculations are based on fundamental geometric principles governing image projection inside a camera. Most treatments in the literature express the image projection equations either in very simple terms for specific cases or in compact matrix notation that is difficult to apply. The purpose of this paper is to present a geometric derivation of the image projection equations in a straightforward form that can be readily applied by a qualified investigator without the need for specialized software. In addition, a simple brute force optimization procedure is described to perform camera matching and model-based image matching. Examples are
Funk, James
Strategy to adopt ISO/SAE 21434 Cyber security assurance level in the organization2022-01-01423/29/2022
Automotive cyber security standard ISO/SAE 21434 specifies the requirements for cyber security risk management of road vehicle’s electrical and electronic systems, including their components and interfaces. This standard has introduced a new classification scheme, cybersecurity assurance level (CAL), that helps in validating the process rigor needed for mitigating different threat scenarios. CAL values can range from 1(Least stringent process rigor) to 4 (most stringent process rigor). CAL provides assurance that the assets of an item or component are adequately protected against the relevant threat scenarios by defining the scope of various processes at different phases of the Secure Development Life Cycle (SDLC). CAL values can be determined at the earlier stages of the SDLC (cybersecurity concept phase) through the knowledge of attack vectors and attack severity specific to a system. The CAL value can be used as a reference to define the scope of rigor in the design, development
Agrawal, Vivek, Achuthan, Balasubramanian
Accuracy and Validation of 360-Degree Camera Use in Photogrammetry2022-01-10033/29/2022
Accident scene data obtained from photographs and videos are vital material for forensic analysts. They allow to precisely determine the orientation and location of evidence as seen on such images. For that reason, the term digital evidence was adopted and is commonly used among analysts in conjunction with retro-projection methods as an aid to reconstruct the events and inputs leading up to the investigation in question. Photogrammetry is a retro-projection method commonly used by analysts to match scene photographs with calibrated control points obtained from three-dimensional point cloud data collected at the subject site and visualized on the scene images. From this merger, the photographs allow for the determination of the point at which the camera was positioned that took the subject image. In general, the point cloud data allows for increased accuracy during the photogrammetry process. Video footage obtained from the scenes can be exported as frames and then used in the same
Morales, Roberto C.
A More Robust Method for Digital Video Camera Calibration for Luminance Estimation2022-01-09683/29/2022
Mapping the luminance values of a visual scene is of broad interest to accident reconstructionists, human factors professionals, and lighting experts. Such mappings are useful for a variety of purposes, including determining the effectiveness and appropriateness of lighting installations, and performing visibility analyses for accident case studies. Previous work has shown that pixel intensity captured by consumer-grade digital still cameras can be calibrated to estimate luminance. Taking a digital still image and converting this image into a luminance map even further reduces the time required for luminance measurement. Suway and Suway previously presented a methodology for estimating luminance from digital images and video of a scene. In this paper, the authors update this methodology for calculating luminance from a digital video camera. The updated calibration method results in more accurate luminance estimation over the entire range of the camera’s sensor, particularly in low
Suway, Jeffrey, Suway, Steven
Luminance Estimation with Exemplar Digital Camera2022-01-09653/29/2022
Mapping the luminance values of a visual scene is of broad interest to accident reconstructionists, human factors professionals, and lighting experts. Previous work has shown that pixel intensity captured by consumer-grade digital still cameras can be calibrated to estimate luminance. Suway and Suway presented a methodology for estimating luminance from digital images and video of a scene. This method requires the capture of dark images close in time to the capture of the image that will be used to estimate luminance. Additionally, Suway’s method requires the specific camera and lens combination used to be calibrated for luminance estimation. In this paper, the authors present results of estimating luminance with an exemplar camera and taking exemplar dark images. The analysis was completed with the commercially available luminance estimation software, Nitere. The resulting luminance estimates were compared to luminance values measured with a Westboro photonics P501U and our methods
Suway, Jeffrey, Carter, Neal
Development of a Built-in Type Dashboard Camera with Reliability and Usability 2022-01-01203/29/2022
Dashcam, which is considered essential parts of vehicles in Korea, are installed in most vehicles for reasons such as accidents, evidence of threatened driving of other vehicles, and insurance premiums. Aftermarket dashcam have been developed with many improvements such as higher resolution camera and LCD application, but still have problems in usability and durability. The first problem is a separate device mounted on the top of the windshield, which obstructs the driver's view and may injure the driver due to a collision impact. In addition, the connection of the power supply may cause a vehicle breakdown such as a fire due to a worker's mistake or a product defect. Secondly, in order to view the stored video, it is troublesome to remove the SD card and check it on the computer. Moreover, since the LCD is so small, it is difficult to search and play the desired video from the list in many saved files. The third problem is durability and reliability, when operating in the high
Jeong, DongHyuk
New Tools & Technologies21AVEP05_105/1/2021
OmniVision Technologies (Santa Clara, Calif.) has unveiled the first group of OmniVision automotive image sensor families compatible with the modular NVIDIA (Santa Clara, Calif.) DRIVE AGX AI computing platform for self-driving vehicles. OmniVision created drivers and camera modules using its OX08B40 image sensor for front-view automotive applications, including ADAS and Level 3+ autonomous systems. Likewise, drivers and camera modules are now available for its OX03F10 and OX03C10 viewing camera image sensors, allowing the development of surround view systems (SVSs), rearview cameras (RVCs) and e-mirror camera monitoring systems with NVIDIA DRIVE. In addition, OmniVision's OV2311 and a new 5MP sensor are the exclusive driver monitoring system (DMS) image sensors for the NVIDIA DRIVE Hyperion turnkey evaluation architecture. Regardless of the application, OmniVision offers platform software drivers for its image sensors, as well as complete camera modules that customers can easily
Human Body Orientation from 2D Images2021-01-00824/6/2021
This work presents a method to estimate the human body orientation using 2D images from a person view; the challenge comes from the variety of human body poses and appearances. The method utilizes OpenPose neural network as a human pose detector module and depth sensing module. The modules work together to extract the body orientation from 2D stereo images. OpenPose is proven to be efficient in detecting human body joints, defined by COCO dataset, OpenPose can detect the visible body joints without being affected by backgrounds or other challenging factors. Adding the depth data for each point can produce rich information to the process of 3D construction for the detected humans. This 3D point’s setup can tell more about the body orientation and walking direction for example. The depth module used in this work is the ZED camera stereo system which uses CUDA for high performance depth computation. One of the possible applications for this method is for social robots where the robot has
Abughalieh, Karam, Alawneh, Shadi
Predicting Desired Temporal Waypoints from Camera and Route Planner Images using End-To-Mid Imitation Learning2021-01-00884/6/2021
This study is focused on exploring the possibilities of using camera and route planner images for autonomous driving in an end-to-mid learning fashion. The overall idea is to clone the humans’ driving behavior, in particular, their use of vision for ‘driving’ and map for ‘navigating’. The notion is that we humans use our vision to ‘drive’ and sometimes, we also use a map such as Google/Apple maps to find direction in order to ‘navigate’. We replicated this notion by using end-to-mid imitation learning. In particular, we imitated human driving behavior by using camera and route planner images for predicting the desired waypoints and by using a dedicated control to follow those predicted waypoints. Besides, this work also places emphasis on using minimal and cheaper sensors such as camera and basic map for autonomous driving rather than expensive sensors such Lidar or HD Maps as we humans do not use such sophisticated sensors for driving. Also, even after decades of research, the
Arul Doss, Aravind Chandradoss, Guvenc, Levent
Object Detection and Tracking for Autonomous Vehicles in Adverse Weather Conditions2021-01-00794/6/2021
Object detection and tracking is a central aspect of perception for autonomous vehicles. While there has been significant development in this field in recent years, many perception algorithms still struggle to provide reliable information in challenging weather conditions which include night-time, direct sunlight, glare, fog, etc. To achieve full autonomy, there is a need for a robust perception system capable of handling such challenging conditions. In this paper, we attempt to bridge this gap by proposing an algorithm that combines the strength of automotive radars and infra-red thermal cameras. We show that these sensors complement each other well and provide reliable data in poor visibility conditions. We demonstrate the advantages of a thermal camera over a visible-range camera in these situations and employ YOLOv3 for object detection. The proposed system utilizes a modified Track-Oriented Multiple Hypothesis Tracking (MHT) algorithm which uses data from these sensors to keep
Bhadoriya, Abhay Singh, Vegamoor, Vamsi Krishna, Rathinam, Sivakumar
Visual SLAM in Long-Range Autonomous Parking Application Based on Instance-Aware Semantic Segmentation via Multi-Task Network Cascades and Metric Learning Scheme2021-01-00774/6/2021
Long-range Autonomous Parking is becoming an attractive application in terms of demands. The vehicle is capable of driving autonomously into the appointed parking slot when the driver leaves it at the drop-off spot. In this application, the ability of accurate localization has become a key issue, especially in GPS-denied environments. This paper proposes a method of localization and mapping for Long-range Autonomous Parking, which is achieved by Visual SLAM based on deep learning algorithms. Firstly, we propose an instance segmentation via multi-task network cascades, and even in a complex visual environment, the main roadway instances of interest in the parking lot IPM image can be detected, such as parking corners, speed bumps. Then we combine the information of wheel encoders to build a global semantic map of the parking lot. Vehicles can often rely on semantic map matching to achieve high-precision localization. However, without a good initial position, it is difficult to infer an
Yan, Yixiong, Hang, Yang, Hu, Tianren, Yu, Hao, Lai, Feng
INRS Researchers Design the World’s Fastest UV CameraTBMG-386313/1/2021
Imagine being able to snap a picture of extremely fast events on the order of a picosecond. Compressed ultrafast photography (CUP) captures the entire process in real time and unparalleled resolution with just one click. The spatial and temporal information is first compressed into an image and then, using a reconstruction algorithm, it is converted into a video.
Hyperspectral Cameras and Data QualityTBMG-386293/1/2021
Hyperspectral imaging combines both imaging and spectroscopy. There are many different optical architectures that are used to make hyperspectral systems, but the end goal is the same – to make an image where each pixel in the image contains information from many spectral bands (many different colors or wavelengths).
High-Brightness Source of Coherent Light Spanning From the UV to THzTBMG-386273/1/2021
An international team of scientists reports a novel technique for a high-brightness coherent and few-cycle duration source spanning seven optical octaves from the UV to the THz.
Nanothermometers Improve Temperature ImagingTBMG-385452/1/2021
NIST researchers are in the early stages of a massive undertaking to design and build a fleet of tiny ultra-sensitive thermometers. If they succeed, their system will be the first to make real-time measurements of temperature on the microscopic scale in an opaque 3D volume — which could include medical implants. The project is called Thermal Magnetic Imaging and Control (Thermal MagIC), and the researchers say it could revolutionize temperature measurements in many fields, including biology and medicine. Thermal MagIC will work by using nanometer-sized objects whose magnetic signals change with temperature. The objects would be incorporated into the liquids or solids being studied — the melted plastic that might be used as part of an artificial joint replacement, for example. A remote sensing system would then pick up these magnetic signals, meaning the system being studied would be free from wires or other bulky external objects.
Manufacturing Ultra-Thin Camera LensesTBMG-384902/1/2021
In the future, camera lenses could be thousands of times thinner and significantly less resource-intensive to manufacture using new technology for making the artificial materials known as metasurfaces. These materials consist of a multitude of interacting nanoparticles that together can control light. Meta-surfaces can be used for optical components in portable electronics, sensors, cameras, or space satellites. The new technology for making such planar surfaces is based on a plastic that is already used today to create other microstructures.
Cameras Capture Asteroid Debris RetrievalTBMG-383541/1/2021
Space Dynamics Laboratory Utah State University Logan, UT
Next-Generation Computer Chip Has Two HeadsTBMG-383331/1/2021
Engineers have developed a next-generation circuit that allows for smaller, faster, and more energy-efficient devices that could have major benefits for artificial intelligence systems. The technology uses a 2D material for a logic-in-memory architecture, or a single architecture that combines logic operations with a memory function.
Autonomous HVAC System Measures Facial TemperatureTBMG-383391/1/2021
COVID-19 is changing the way indoor spaces are used, presenting challenges for those who manage those spaces, from homes to offices and factories. Not least among these challenges is heating and cooling — the largest consumer of energy in American homes and commercial buildings. There’s a need for smarter, more flexible climate control that keeps people comfortable without heating and cooling entire empty buildings.
Technology Aids Surgeon-Guided Robotic HandsTBMG-3819512/1/2020
Steady hands and uninterrupted, sharp vision are extremely critical when performing surgery on delicate structures like the brain or hair-thin blood vessels. While surgical cameras have tremendously improved what surgeons see during operative procedures, the steady hand remains to be enhanced. New surgical technologies, including surgeon-guided robotic hands, cannot prevent accidental injuries when operating close to fragile tissue.
3D Camera Merges Depth and Spectral DataTBMG-3820312/1/2020
The compact Hyperspectral Stripe Projector (HSP) combines the HSP, a monochrome sensor array, and sophisticated programming to give users a more complete picture of an object’s shape and composition. It captures four-dimensional information from an image — three spatial and one spectral — in real time.
Robot Takes Contact-Free Measurements of Patients’ Vital SignsTBMG-3817212/1/2020
During the coronavirus pandemic, one of the riskiest parts of a healthcare worker’s job is assessing people who have symptoms of COVID-19. Researchers are reducing that risk by using robots to remotely measure patients’ vital signs. The robots, which are controlled by a handheld device, can also carry a tablet that allows doctors to ask patients about their symptoms without being in the same room.
Earphone Tracks Facial Expressions, Even with a FacemaskTBMG-3818212/1/2020
Researchers have invented an earphone that can continuously track full facial expressions by observing the contour of the cheeks — and can then translate expressions into emojis or silent speech commands. With the ear-mounted device (called C-Face), users could express emotions to online collaborators without holding cameras in front of their faces — an especially useful communication tool as much of the world engages in remote work or learning.
High-Resolution X-Ray Camera SystemTBMG-3820012/1/2020
A large-area detector without any dead space capable of handling a large dynamic range does not currently exist. Current large-area detectors have dead zones created by abutting several modules together. These detectors are counting detectors, which are good only for low-flux operations.
Lenslet-Based Integral Field SpectrographTBMG-3799111/1/2020
An integral field spectrograph (IFS) is an instrument combining spectrographic and imaging capabilities. IFSs provide spectral information over a 2D field of view. In lenslet-based IFS designs, a lenslet array is placed in the spectrograph entrance plane. All beams generated by the lenslet array are fed through a dispersive element and imaged by a camera, resulting in a spectrum for each individual lenslet.
Items per page:
1 – 50 of 696