AI deep learning-based bird detection for UAM and aircraft
2022-26-1228
05/26/2022
- Event
- Content
- Abstract - Safety of flight during takeoff, flight and landing is one of the important considerations for airborne vehicles. Bird strike is defined as a collision between a bird and aircraft during takeoff, flight and landing of airborne vehicles. When bird strike happens, it can result in damage to aircraft structure and loss of thrust which impacts safety of flight. The nature of aircraft damage can differ depending on the size of the aircraft. For smaller aircrafts, it can result in penetration into flight deck windscreens or damage to control surfaces. In case of larger aircraft, it can result in hazardous effects because of engine ingestion. Many deep learning algorithms have evolved for object detection and classification in the recent years. You Only Look Once [YOLO] and single shot detector [SSD] are top two state of art object detection algorithms that are extensively used in real world applications. The Xilinx® Deep Learning Processor Unit (DPU) is a programmable engine dedicated for convolutional neural network. There is a specialized instruction set for DPU, which enables DPU to work efficiently for many convolutional neural networks. This paper focusses on using a multicore Xilinx SOC to perform CNN inference on FPGA which is programmed as a deep processing unit [DPU] in safety critical avionics system. It presents a study of object detection performance in real-time when used in autonomous flying scenario for example to detect and alert the pilots about birds that may collide with the aircraft during takeoff, flight and landing phases. Two deep learning algorithms YOLO and SSD are evaluated for bird detection on hand engineered image set which consist of birds of known number in varying size and different visibility conditions. Model comprising of COCO dataset are used for both the algorithms. The inference from the two deep learning algorithms are compared based on accuracy in detection and classification of objects, time taken for running the FPGA inference, assessment of number of false positives and localization errors. Keywords— YOLO, SSD, DPU, Object detection, region proposal, convolutional neural network
- Citation
- K, M., "AI deep learning-based bird detection for UAM and aircraft," SAE Technical Paper 2022-26-1228, 2022, .