A self correcting low-light object detection method based on pyramid edge enhancement

A low-light target detection method was proposed to overcome the problem of low overall brightness，contrast and limited edge features in low-light images，which lead to poor recognition and local⁃ ization of target detection algorithms. Firstly，a low-light enhancement network was designed to utilize the advantages of image Gaussian pyramid，Retinex and dark-channel defogging in low-light image enhance⁃ ment，and edge contour features were added to the dark-channel defogging algorithm to enhance the over⁃ all luminance contrast while highlighting the edge features of the target. Secondly，to improve the accura⁃ cy of feature extraction in the feature extraction section of RTDETR，a lightweight self correcting feature extraction network was designed to generate and correct the feature maps generated by the backbone fea⁃ ture extraction network with smaller computational complexity，thereby improving the accuracy of object detection. The experimental results on the ExDark dataset shows that compared with the benchmark RT⁃ DETR，the mAP improves by 2. 34%，the recall improves by 2. 09%，the parameter amount reduces by 4. 95 M，the model size reduces by 13. 31 MB，and the proposed method is able to effectively improve the performance of the target detection in the low-light scene. © 2024 Chinese Academy of Sciences. All rights reserved.