Low-light multimodal object detection: A survey
Year: 2025
Type: article
Abstract: This survey aims to gain an in-depth understanding of the current state of research on multimodal object detection in low-light environments. Firstly, we introduce the background of multimodal object detection in low-light environments, discuss the challenges faced by this task, and provide an overview of existing related review literature. Secondly, we comprehensively introduce the multimodal sensor combinations and their specific models, benchmark datasets, and evaluation criteria currently applicable to multimodal object detection tasks in low-light environments. In addition, we conduct a comprehensive investigation of multimodal detection methods such as visible-infrared and visible-LiDAR, as well as other multimodal detection methods, and conduct in-depth analysis and discussion on the potential and challenges of each method. Finally, we present a quantitative comparison of the most advanced methods on widely used benchmark datasets and discuss research trends, important issues, and future research directions.
Source: Computer Science Review
Authors: Gang Li, Yonggui Wang, Bin He, Tao Pang, Mingke Gao
Institutions: Tongji University, Shanghai Institute of Computing Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $4,190
Funders: Shanghai Key Basic Research Program, National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality, China Aerospace Science and Technology Corporation, Chinese Aeronautical Establishment, National University's Basic Research Foundation of China, Fundamental Research Funds for the Central Universities
OpenAlex ID: W4413884699