3D Convolutional Neural Network for Low-Light Image Sequence Enhancement in SLAM

被引:5
|
作者
Quan, Yizhuo [1 ,2 ]
Fu, Dong [1 ]
Chang, Yuanfei [1 ]
Wang, Chengbo [1 ]
机构
[1] Chinese Acad Sci, Aerosp Informat Reaserch Inst, 9 Dengzhuang South Rd, Beijing 100094, Peoples R China
[2] Univ Chinese Acad Sci, 19 A Yuquan Rd, Beijing 100049, Peoples R China
关键词
visual inertial system; low-light image sequence enhancement; 3D convolutional neural network; DYNAMIC HISTOGRAM EQUALIZATION; LOCALIZATION; VISION; ROBUST;
D O I
10.3390/rs14163985
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Typical visual simultaneous localization and mapping (SLAM) systems rely on front-end odometry for feature extraction and matching to establish the relations between adjacent images. In a low-light environment, the image obtained by a camera is dim and shows scarce information, hindering the extraction of sufficient stable feature points, consequently undermining visual SLAM. Most existing methods focus on low-light enhancement of a single image, neglecting the strong temporal correlation across images in visual SLAM. We propose a method that leverages the temporal information of an input image sequence to enhance the low-light image and employed the enhanced result to improve the feature extraction and matching quality of visual SLAM. Our method trains a three-dimensional convolutional neural network to estimate pixelwise grayscale transformation curves to obtain a low-light enhancement image. Then, the grayscale transformation curves are iteratively applied to obtain the final enhanced result. The training process of the network does not require any paired reference images. We also introduced a spatial consistency loss for the enhanced image to retain the content and texture of the original image. We further integrated our method into VINS-Mono and compared with similar low-light image enhancement methods on the TUM-VI public dataset. The proposed method provides a lower positioning error. The positioning root-mean-squared error of our method is 19.83% lower than that of Zero-DCE++ in low-light environments. Moreover, the proposed network achieves real-time operation, being suitable for integration into a SLAM system.
引用
收藏
页数:21
相关论文
共 50 条
  • [41] Low-Light Image Enhancement Using a Simple Network Structure
    Matsui, Takuro
    Ikehara, Masaaki
    [J]. IEEE ACCESS, 2023, 11 : 65507 - 65516
  • [42] FRN: Fusion and recalibration network for low-light image enhancement
    Kavinder Singh
    Ashutosh Pandey
    Akshat Agarwal
    Mohit Kumar Agarwal
    Aditya Shankar
    Anil Singh Parihar
    [J]. Multimedia Tools and Applications, 2024, 83 : 12235 - 12252
  • [43] ATTENTION-BASED NETWORK FOR LOW-LIGHT IMAGE ENHANCEMENT
    Zhang, Cheng
    Yan, Qingsen
    Zhu, Yu
    Li, Xianjun
    Sun, Jinqiu
    Zhang, Yanning
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2020,
  • [44] A Joint Network for Low-Light Image Enhancement Based on Retinex
    Jiang, Yonglong
    Zhu, Jiahe
    Li, Liangliang
    Ma, Hongbing
    [J]. COGNITIVE COMPUTATION, 2024,
  • [45] Feature spatial pyramid network for low-light image enhancement
    Song, Xijuan
    Huang, Jijiang
    Cao, Jianzhong
    Song, Dawei
    [J]. VISUAL COMPUTER, 2023, 39 (01): : 489 - 499
  • [46] Deep Color Consistent Network for Low-Light Image Enhancement
    Zhang, Zhao
    Zheng, Huan
    Hong, Richang
    Xu, Mingliang
    Yan, Shuicheng
    Wang, Meng
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 1889 - 1898
  • [47] Unsupervised Decomposition and Correction Network for Low-Light Image Enhancement
    Jiang, Qiuping
    Mao, Yudong
    Cong, Runmin
    Ren, Wenqi
    Huang, Chao
    Shao, Feng
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (10) : 19440 - 19455
  • [48] Low-Light Image Enhancement Based on Generative Adversarial Network
    Abirami, R. Nandhini
    Vincent, P. M. Durai Raj
    [J]. FRONTIERS IN GENETICS, 2021, 12
  • [49] Low-Light Image Enhancement Network Guided by Illuminance Map
    Huang, Shuying
    Li, Wei
    Yang, Yong
    Wan, Weiguo
    Lai, Houzeng
    [J]. Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2024, 36 (01): : 92 - 101
  • [50] INTEGRATION-AND-DIFFUSION NETWORK FOR LOW-LIGHT IMAGE ENHANCEMENT
    Tang, Pengliang
    Guo, Xiaoqiang
    Ju, Guodong
    Shen, Liangheng
    Men, Aidong
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 1664 - 1668