Laser & Optoelectronics Progress, Volume. 60, Issue 4, 0404001(2023)
Low-Light Image Object Detection Based on Improved YOLOv5 Algorithm
Fig. 1. YOLOv5 network structure
Fig. 2. Low-light image and enhanced images. (a) ExDark dataset; (b) LIME; (c) EnlightenGAN; (d) DEC_ZERO
Fig. 3. Feature visualization results of low-light images and enhanced images
Fig. 4. Feature enhancement module based on channel attention mechanism
Fig. 5. Feature location module
Fig. 6. YOLOv5_DC overall network structure
Fig. 7. Normal illumination image and synthetic low-light image. (a) Normal illumination image; (b) synthetic low-light image
|
|
|
|
|
Get Citation
Copy Citation Text
Ziting Shu, Zebin Zhang, Yaozhe Song, Mengmeng Wu, Xiaobing Yuan. Low-Light Image Object Detection Based on Improved YOLOv5 Algorithm[J]. Laser & Optoelectronics Progress, 2023, 60(4): 0404001
Category: Detectors
Received: Nov. 16, 2021
Accepted: Dec. 24, 2021
Published Online: Feb. 14, 2023
The Author Email: Yuan Xiaobing (yuanxb@mail.sim.ac.cn)