基于新型特征增强与融合的雾天目标检测方法.

To further improve the detection accuracy of objects in foggy scenes for deep learning networks, a foggy object detection method called NFF-YOLOX is proposed based on the YOLOX network. Firstly, a novel feature enhancement module was constructed by means of multiple branch convolution in the Neck structure. This module extracted more effective feature information while preserving the basic information features, enhanced the representation capability of target features and improved the network's ability to extract object features. Then, a novel feature fusion module was built using top-down and bottom-up network features from a bidirectional pyramid. This module allows the semantic information of object to flow from deep features to shallow features, with full fusion and extraction of detailed image features. Additionally, coordinate attention was introduced in the feature fusion module to accurately locate object during training and reduce the loss of object feature information. Finally, considering the issue of imbalanced positive and negative samples, a novel loss function was constructed by combining Focal loss with α-IOU. This loss function reduced the training loss and convergence time, thereby improved the recognition rate of foggy object by the network. The experimental results demonstrate that compared to six advanced object detection networks such as YOLOv7 and DETR, this method achieves higher foggy object detection accuracy on the real foggy datasets of RTTS. Specifically, when the intersection over union (IOU) is 0.5,the mean average precision (mAP) is improved by more than 1.30%, when IOU is 0.5 to 0.95 and step is 0.05,the mean average precision is improved by more than 2.99%. [ABSTRACT FROM AUTHOR]