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
  • [41] Perceptual brightness-based inverse tone mapping for high dynamic range imaging
    An, Gwon Hwan
    Ahn, Yong Deok
    Lee, Siyeong
    Kang, Suk-Ju
    DISPLAYS, 2018, 54 : 1 - 8
  • [42] Enhanced Tone Mapping of High Dynamic Range to Correspond to Illumination Changes
    Jang, Young-Min
    Cho, Jae-Hyun
    Kim, Ji-Geun
    Kim, Bruce C.
    Cho, Sang-Bock
    2014 INTERNATIONAL SOC DESIGN CONFERENCE (ISOCC), 2014, : 258 - 259
  • [43] Adversarial and Adaptive Tone Mapping Operator for High Dynamic Range Images
    Cao, X.
    Lai, K.
    Yanushkevich, S. N.
    Smith, M. R.
    2020 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2020, : 1814 - 1821
  • [44] High-Dynamic-Range Integrated NV Magnetometers
    Wang, Tianning
    Liu, Zhenhua
    Liu, Yankang
    Wang, Bo
    Shen, Yuanyuan
    Qin, Li
    MICROMACHINES, 2024, 15 (05)
  • [45] Tone mapping for high dynamic range image using a probabilistic model
    Song, Ming-Li
    Wang, Hui-Qiong
    Chen, Chun
    Ye, Xiu-Qing
    Gu, Wei-Kang
    Ruan Jian Xue Bao/Journal of Software, 2009, 20 (03): : 734 - 743
  • [46] Multiscale Morphological Tone Mapping Operator for High Dynamic Range Images
    Zhang, Yinghui
    Wang, Ke
    Deng, Xiaojuan
    Li, Hongwei
    THIRD INTERNATIONAL SYMPOSIUM ON IMAGE COMPUTING AND DIGITAL MEDICINE (ISICDM 2019), 2019, : 254 - 258
  • [47] RAM-BASED TONE MAPPING FOR HIGH DYNAMIC RANGE IMAGES
    Shen, Jianbing
    Sun, Hanqiu
    Zhao, Hanli
    Jin, Xiaogang
    ICME: 2009 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-3, 2009, : 1110 - +
  • [48] High dynamic range tone mapping operators for the visualization of scientific imageries
    Duan, Jiang
    Qiu, Guoping
    ATLANTIC EUROPE CONFERENCE ON REMOTE IMAGING AND SPECTROSCOPY, PROCEEDINGS, 2006, : 1 - +
  • [49] HIGH DYNAMIC RANGE IMAGE TONE MAPPING BY OPTIMIZING TONE MAPPED IMAGE QUALITY INDEX
    Ma, Kede
    Yeganeh, Hojatollah
    Zeng, Kai
    Wang, Zhou
    2014 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2014,
  • [50] HIGH DYNAMIC RANGE INTELLIGENT EFFECTS
    Yeh, Wei-Ming
    PROCEEDINGS OF 2014 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS (ICMLC), VOL 2, 2014, : 481 - 486