Display options
Cite
Ponn T, Kröger T, Diermeyer F. Performance Analysis of Camera-based Object Detection for Automated Vehicles. Sensors (Basel). 2020;20(13)doi: 10.3390/s20133699.
Ponn, T., Kröger, T., & Diermeyer, F. (2020). Performance Analysis of Camera-based Object Detection for Automated Vehicles. Sensors (Basel, Switzerland), 20(13), . https://doi.org/10.3390/s20133699
Ponn, Thomas, et al. "Performance Analysis of Camera-based Object Detection for Automated Vehicles." Sensors (Basel, Switzerland) vol. 20,13 (2020). doi: https://doi.org/10.3390/s20133699
Ponn T, Kröger T, Diermeyer F. Performance Analysis of Camera-based Object Detection for Automated Vehicles. Sensors (Basel). 2020 Jul 01;20(13). doi: 10.3390/s20133699. PMID: 32630350; PMCID: PMC7374332.
Copy Download .nbib Format: NLM
Share it on

Sensors (Basel). 2020 Jul 01;20(13). doi: 10.3390/s20133699.

Performance Analysis of Camera-based Object Detection for Automated Vehicles.

Sensors (Basel, Switzerland)

Thomas Ponn, Thomas Kröger, Frank Diermeyer

Affiliations

  1. Institute of Automotive Technology, Technical University of Munich, 85748 Garching, Germany.

PMID: 32630350 PMCID: PMC7374332 DOI: 10.3390/s20133699

Abstract

For a safe market launch of automated vehicles, the risks of the overall system as well as the sub-components must be efficiently identified and evaluated. This also includes camera-based object detection using artificial intelligence algorithms. It is trivial and explainable that due to the principle of the camera, performance depends highly on the environmental conditions and can be poor, for example in heavy fog. However, there are other factors influencing the performance of camera-based object detection, which will be comprehensively investigated for the first time in this paper. Furthermore, a precise modeling of the detection performance and the explanation of individual detection results is not possible due to the artificial intelligence based algorithms used. Therefore, a modeling approach based on the investigated influence factors is proposed and the newly developed SHapley Additive exPlanations (SHAP) approach is adopted to analyze and explain the detection performance of different object detection algorithms. The results show that many influence factors such as the relative rotation of an object towards the camera or the position of an object on the image have basically the same influence on the detection performance regardless of the detection algorithm used. In particular, the revealed weaknesses of the tested object detectors can be used to derive challenging and critical scenarios for the testing and type approval of automated vehicles.

Keywords: artificial intelligence; automated vehicles; camera sensor; computer vision; critical scenarios; explainable artificial intelligence (AI); object detection; safety

References

  1. IEEE Trans Pattern Anal Mach Intell. 2017 Jun;39(6):1137-1149 - PubMed
  2. IEEE Trans Pattern Anal Mach Intell. 2020 Feb;42(2):318-327 - PubMed
  3. Sensors (Basel). 2019 Nov 08;19(22): - PubMed
  4. Nat Mach Intell. 2020 Jan;2(1):56-67 - PubMed

Publication Types