D-YOLO a robust framework for object detection in adverse weather conditions

arXiv:2403.09233v1 Announce Type: new
Abstract: Adverse weather conditions including haze, snow and rain lead to decline in image qualities, which often causes a decline in performance for deep-learning based detection networks. Most existing approaches attempts to rectify hazy images before performing object detection, which increases the complexity of the network and may result in the loss in latent information. To better integrate image restoration and object detection tasks, we designed a double-route network with an attention feature fusion module, taking …

abstract arxiv complexity cs.cv detection eess.iv framework image images networks object performance rain robust snow type weather yolo