The Library
Introspection of 2D object detection using processed neural activation patterns in automated driving systems
Tools
Yatbaz, Hakan Yekta, Dianati, Mehrdad, Koufos, Konstantinos and Woodman, Roger (2023) Introspection of 2D object detection using processed neural activation patterns in automated driving systems. In: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Paris, France, 02-06 Oct 2023 ISBN 2473-9944. doi:10.1109/ICCVW60793.2023.00437 ISSN 9798350307443.
|
PDF
WRAP-introspection-2D-object-detection-processed-neural-activation-patterns-automated-driving-systems-2023.pdf - Accepted Version - Requires a PDF viewer. Download (1480Kb) | Preview |
Official URL: https://doi.org/10.1109/ICCVW60793.2023.00437
Abstract
While deep neural network (DNN) models have become extremely popular for object detection in automated driving systems (ADS), the dynamic and varied nature of the road traffic environment can still lead to model failures. To address this issue, researchers have recently explored introspection mechanisms, a.k.a, self-assessment, for monitoring the quality of perception in ADS. Subsequently, depending on the situation, these mechanisms can either hand over control to the human driver in SAE Level 3, or initiate a minimum risk maneuver in SAE Level 4 ADS. State-of-the-art introspection mechanisms for ADS train a neural network to learn the relationship between the raw neural activation patterns of the underlying DNN-based perception function per frame and the calculated mean average precision. In this paper, we show that the use of raw activation patterns may contain misleading information for introspecting 2D object detection in ADS. To this end, we investigate how to optimally pre-process these patterns for improving the error detection performance. We evaluate the developed mechanism with and without pre-processing of the raw neural activation patterns and compare its performance with a state-of-the-art algorithm highlighting that for the Berkeley Deep Drive (BDD) dataset, pre-processing reduced the ratio of missed errors by 14% and improved the overall detection performance by 3%."
Item Type: | Conference Item (Paper) | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software T Technology > TA Engineering (General). Civil engineering (General) T Technology > TE Highway engineering. Roads and pavements T Technology > TK Electrical engineering. Electronics Nuclear engineering T Technology > TL Motor vehicles. Aeronautics. Astronautics |
|||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > WMG (Formerly the Warwick Manufacturing Group) | |||||||||
Library of Congress Subject Headings (LCSH): | Automated vehicles, Intelligent transportation systems , Motor vehicles -- Automatic control , Neural networks (Computer science) , Computer vision , Image processing , Integrated sensing and communications systems, Pattern recognition systems, Pattern perception | |||||||||
Publisher: | IEEE | |||||||||
ISBN: | 2473-9944 | |||||||||
ISSN: | 9798350307443 | |||||||||
Official Date: | 25 December 2023 | |||||||||
Dates: |
|
|||||||||
DOI: | 10.1109/ICCVW60793.2023.00437 | |||||||||
Status: | Peer Reviewed | |||||||||
Publication Status: | Published | |||||||||
Re-use Statement: | © 2023. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |||||||||
Access rights to Published version: | Restricted or Subscription Access | |||||||||
Date of first compliant deposit: | 12 September 2023 | |||||||||
Date of first compliant Open Access: | 13 September 2023 | |||||||||
RIOXX Funder/Project Grant: |
|
|||||||||
Conference Paper Type: | Paper | |||||||||
Title of Event: | 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) | |||||||||
Type of Event: | Workshop | |||||||||
Location of Event: | Paris, France | |||||||||
Date(s) of Event: | 02-06 Oct 2023 | |||||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year