Optimization of Computer Vision Software Models for Deployment to Performance Constrained Embedded Processors

2022-01-0179

03/29/2022

Event
WCX SAE World Congress Experience
Authors Abstract
Content
Computer vision (CV), a form of artificial intelligence (AI), is a foundational technology within the automotive industry for an increasing number of applications including active safety, motion control, and driver distraction monitoring. State-of-the-art CV models often rely on the use of Deep Neural Networks (DNNs) to achieve high levels of accuracy. While necessary for their accuracy, DNNs are computationally complex. For example, when compared to other AI model architectures, they have a large memory footprint and must perform a high number of operations to create an output or prediction. To meet performance goals in the face of such constraints, high performance processors such as Graphics Processing Units (GPUs) are typically required to run CV models on-board automobiles, creating a major hurdle to the deployment of CV applications. This paper proposes and analyzes a method for optimizing and compressing DNN-based CV models to enable their deployment to lower performance processors - such as Central Processing Units (CPUs) - more commonly used in automotive applications. Several real-world case-studies are put forward which demonstrate the effectiveness of the method including a seventeen-fold reduction in model size and a three-fold reduction in inference latency for AI-powered object detection on an automotive CPU.
Meta TagsDetails
Citation
Rocci, B., "Optimization of Computer Vision Software Models for Deployment to Performance Constrained Embedded Processors," SAE Technical Paper 2022-01-0179, 2022, .
Additional Details
Publisher
Published
Mar 29, 2022
Product Code
2022-01-0179
Content Type
Technical Paper
Language
English