In this paper, we propose a foggy weather object detection model based on an attention mechanism, to address the problem of low detection accuracy, missed detection and false detection when general object detection models are applied directly to foggy scenes. Firstly, to enhance the detection network's multi-scale expression ability and sensitivity to the target, a residual module that integrates the attention mechanism replaces the BottleNeck module of the backbone network. This design improves the network's ability to extract features and locate targets at a fine-grained level. Secondly, the CIOU loss function replaces the original loss function, improving the stability of the bounding box regression process. Thirdly, the K-means++ clustering algorithm is used to generate anchors suitable for the dataset in this paper. Furthermore, the object detection dataset in foggy scenes is further enriched based on the atmospheric scattering model. Experimental results indicate that the proposed method's mAP in light fog, medium fog and dense fog scenes is increased by 7.4%, 6.05% and 6.36%, respectively, compared to the original YOLOv5s. This improvement in accuracy significantly reduces the missed detection rate and false detection rate, effectively enhancing object detection performance in foggy weather.
As a high precision target detection model, YOLOX still has the disadvantage of slow detection speed and is difficult to apply to the work scene with limited computing resources. Thus, an efficient target detection network, called YOLOX-Lite, which balances detection speed and detection accuracy, is proposed in this paper. Firstly, the mixed efficient channel attention module is designed to realize the adaptive refinement of spatial features and channel features in the network. Then the feature extraction ability of YOLOX-Lite network can be improved. Secondly, the optimized MobileNetv3 is used as the backbone network to replace Darknet53, so as to significantly reduce the computational complexity of the backbone network in feature extraction. Finally, efficient down_ sampler with focus is designed, which can efficiently integrate the low dimensional details in the backbone network with the high-dimensional semantic information in the neck layer. At the same time, when constructing the neck layer, the depth separable convolution is combined with PANet. It can reduce a lot of computing overhead caused by excessive multiplexing of standard convolutions. The experimental results on PASCAL VOC and TT100K datasets show that the mAP values of YOLOX Lite are 84.3% and 88.1% respectively, and the FPS value reaches 56.7. Thus, while ensuring the network detection accuracy, the detection speed of YOLOX Lite is increased by about 17% compared with the original YOLOX.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.