High-Dynamic-Range Tone Mapping in Intelligent Automotive Systems

被引:6
|
作者
Shopovska, Ivana [1 ]
Stojkovic, Ana [1 ]
Aelterman, Jan [1 ]
Van Hamme, David [1 ]
Philips, Wilfried [1 ]
机构
[1] Univ Ghent, IMEC, IPI, B-9000 Ghent, Belgium
关键词
high dynamic range; tone mapping; deep learning; object detection; autonomous driving; OBJECT DETECTION; OPERATOR; NETWORK;
D O I
10.3390/s23125767
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Intelligent driver assistance systems are becoming increasingly popular in modern passenger vehicles. A crucial component of intelligent vehicles is the ability to detect vulnerable road users (VRUs) for an early and safe response. However, standard imaging sensors perform poorly in conditions of strong illumination contrast, such as approaching a tunnel or at night, due to their dynamic range limitations. In this paper, we focus on the use of high-dynamic-range (HDR) imaging sensors in vehicle perception systems and the subsequent need for tone mapping of the acquired data into a standard 8-bit representation. To our knowledge, no previous studies have evaluated the impact of tone mapping on object detection performance. We investigate the potential for optimizing HDR tone mapping to achieve a natural image appearance while facilitating object detection of state-of-the-art detectors designed for standard dynamic range (SDR) images. Our proposed approach relies on a lightweight convolutional neural network (CNN) that tone maps HDR video frames into a standard 8-bit representation. We introduce a novel training approach called detection-informed tone mapping (DI-TM) and evaluate its performance with respect to its effectiveness and robustness in various scene conditions, as well as its performance relative to an existing state-of-the-art tone mapping method. The results show that the proposed DI-TM method achieves the best results in terms of detection performance metrics in challenging dynamic range conditions, while both methods perform well in typical, non-challenging conditions. In challenging conditions, our method improves the detection F2 score by 13%. Compared to SDR images, the increase in F2 score is 49%.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Adapting iterative retinex computation for high-dynamic-range tone mapping
    Pan, Shengdong
    An, Xiangjing
    He, Hangen
    JOURNAL OF ELECTRONIC IMAGING, 2013, 22 (02)
  • [2] Tone mapping for high-dynamic-range images using localized gamma correction
    Qiao, Motong
    Ng, Michael K.
    JOURNAL OF ELECTRONIC IMAGING, 2015, 24 (01)
  • [3] A high-dynamic-range CMOS image sensor for automotive applications
    Schanz, M
    Nitta, C
    Bussmann, A
    Hosticka, BJ
    Wertheimer, RK
    IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2000, 35 (07) : 932 - 938
  • [4] Gamut Mapping in a High-Dynamic-Range Color Space
    Preiss, Jens
    Fairchild, Mark D.
    Ferwerda, James A.
    Urban, Philipp
    COLOR IMAGING XIX: DISPLAYING, PROCESSING, HARDCOPY, AND APPLICATIONS, 2014, 9015
  • [5] Evaluation of HDR tone mapping algorithms using a high-dynamic-range display to emulate real scenes
    Kuang, Jiangtao
    Heckaman, Rod
    Fairchild, Mark D.
    FIFTEENTH COLOR IMAGING CONFERENCE: COLOR SCIENCE AND ENGINEERING SYSTEMS, TECHNOLOGIES, AND APPLICATIONS, FINAL PROGRAM AND PROCEEDINGS, 2007, : 299 - 303
  • [6] Evaluating tone mapping algorithms for rendering non-pictorial (scientific) high-dynamic-range images
    Park, Sung Ho
    Montag, Ethan D.
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2007, 18 (05) : 415 - 428
  • [7] High-dynamic-range image rendering using hybrid tone mapping and automatic k factor decision
    Jung, Cheolkon
    Fang, Ying
    Jiao, Licheng
    JOURNAL OF ELECTRONIC IMAGING, 2013, 22 (03)
  • [8] Tone mapping for high dynamic range displays
    Meylan, Laurence
    Daly, Scott
    Suesstrunk, Sabine
    HUMAN VISION AND ELECTRONIC IMAGING XII, 2007, 6492
  • [9] Tone mapping-based high-dynamic-range image compression: study of optimization criterion and perceptual quality
    Narwaria, Manish
    Da Silva, Matthieu Perreira
    Le Callet, Patrick
    Pepion, Romuald
    OPTICAL ENGINEERING, 2013, 52 (10)
  • [10] Evaluation of HDR tone-mapping algorithms using a high-dynamic-range display to emulate real scenes
    Kuang, Jiangtao
    Heckaman, Rodney
    Fairchild, Mark D.
    JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY, 2010, 18 (07) : 461 - 468