Low-Light Image Object Detection Based on Improved YOLOv5 Algorithm

Aiming at the low detection accuracy of existing object detection algorithms in a low-light environment, a dual-channel low-light image object detection algorithm called YOLOv5_DC according to an enhanced YOLOv5 algorithm is suggested. First, we synthesize low-light images using Gamma transformation and superimposing Gaussian noise to expand the dataset and promote the network's generalization. Second, a feature enhancement module is proposed. The channel attention method is used to integrate the low-level characteristics of the improved image and the original image to decrease the effect of noisy features and increase the network's feature extraction capabilities. Finally, a feature location module is added to the neck network to boost the response value of the feature map in the target area, allowing the network to focus more on the target area and improve the network detection capabilities. The experimental results show that the proposed YOLOv5_DC algorithm achieves higher detection accuracy. On the low-light object detection dataset known as ExDark*, the mean average precision (mAP) @0. 5 of the proposed algorithm reaches 71. 85%, which is 1. 28 percentage points higher than the original YOLOv5 algorithm.