PREPER: A Public Dataset with Key Performance Indicators for the Safety Evaluation of Deep Learning Visual Perception Systems for Self-Driving Cars

被引：0
|
作者：
Bakker, Jorg [1 ]
机构：
[1] Asymptot AB, Gothenburg, Sweden
来源：
SAE INTERNATIONAL JOURNAL OF CONNECTED AND AUTOMATED VEHICLES | 2025年 / 8卷 / 01期
关键词：
Safety; Pre-crash; Artificial; intelligence; Deep learning; Autonomous driving; Visual; perception; Evaluation; Validation; Test dataset; Key; performance indicator;
D O I：
10.4271/12-08-01-0002
中图分类号：
U [交通运输];
学科分类号：
08 ; 0823 ;
摘要：
Deep learning algorithms are being widely used in autonomous driving (AD) and advanced driver assistance systems (ADAS) due to their impressive capabilities in visual perception of the environment of a car. However, the reliability of these algorithms is known to be challenging due to their data-driven and black-box nature. This holds especially true when it comes to accurate and reliable perception of objects in edge case scenarios. So far, the focus has been on normal driving situations and there is little research on evaluating these systems in a safety-critical context like pre-crash scenarios. This article describes a project that addresses this problem and provides a publicly available dataset along with key performance indicators (KPIs) for evaluating visual perception systems under pre-crash conditions.
引用
收藏
页数：14
相关论文
共 37 条
  • [1] Markovian Model-Based Safety Analysis in Perception Systems Inside Self-Driving Cars
    Bautista Cesar
    IPSI BGD TRANSACTIONS ON INTERNET RESEARCH, 2022, 18 (01): : 9 - 16
  • [2] Assessing Public Perception of Self-Driving Cars: the Autonomous Vehicle Acceptance Model
    Hewitt, Charlie
    Politis, Ioannis
    Amanatidis, Theocharis
    Sarkar, Advait
    PROCEEDINGS OF IUI 2019, 2019, : 518 - 527
  • [3] Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues
    Gupta, Abhishek
    Anpalagan, Alagan
    Guan, Ling
    Khwaja, Ahmed Shaharyar
    Array, 2021, 10
  • [4] Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues
    Gupta, Abhishek
    Anpalagan, Alagan
    Guan, Ling
    Khwaja, Ahmed Shaharyar
    ARRAY, 2021, 10
  • [5] Deep Learning for Self-Driving Cars: Chances and Challenges Extended Abstract
    Rao, Qing
    Frtunikj, Jelena
    PROCEEDINGS 2018 IEEE/ACM 1ST INTERNATIONAL WORKSHOP ON SOFTWARE ENGINEERING FOR AI IN AUTONOMOUS SYSTEMS (SEFAIAS), 2018, : 35 - 38
  • [6] Predicting Steering Actions for Self-Driving Cars Through Deep Learning
    Ou, Chaojie
    Bedawi, Safaa Mahmoud
    Koesdwiady, Arief B.
    Karray, Fakhri
    2018 IEEE 88TH VEHICULAR TECHNOLOGY CONFERENCE (VTC-FALL), 2018,
  • [7] An Improved Deep Learning Solution for Object Detection in Self-Driving Cars
    Mobahi, Mina
    Sadati, Seyed Hossein
    2020 28TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2020, : 316 - 320
  • [8] Visual Global Localization Based on Deep Neural Netwoks for Self-Driving Cars
    Cavalcante, Thiago Goncalves
    Oliveira-Santos, Thiago
    De Souza, Alberto F.
    Badue, Claudine
    Forechi, Avelino
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [9] Deep Traffic Light Detection for Self-driving Cars from a Large-scale Dataset
    Kim, Jinkyu
    Cho, Hyunggi
    Hwangbo, Myung
    Choi, Jaehyung
    Canny, John
    Kwon, Youngwook Paul
    2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2018, : 280 - 285
  • [10] Lane and Traffic Sign Detection in Self-Driving Cars using Deep Learning
    Padmavathi B.
    Dhivya S.
    Datchanamoorthy K.
    Banu A.K.
    Karthikeyan S.M.
    International Journal of Vehicle Structures and Systems, 2024, 16 (01) : 45 - 49
1234