GHAFNet: Global-context hierarchical attention fusion method for traffic object detection

Small-object detection has become a hot issue in complex traffic scenes. A global context multilevel fusion attention detection method for small-object detection is proposed in this paper. First, a global context feature fusion network model is designed with cross-stage partial DarkNet (CSPDarkNet) as the backbone to capture the global context semantic information and refine the local information. To further refine the local information, a hierarchical hybrid attention module is designed that uses global average pooling to obtain the \(\varvec{H}\) $\mathit{H}$ direction weight matrix, fuse it with the \(\varvec{W}\) $\mathit{W}$ direction weight matrix, fuse the results with the channel direction weight matrix, and finally obtain a feature map with multidimensional weights. Second, to increase the receptive field of the multidimensional weighted feature map, atrous convolution is added in the spatial pyramid pooling (SPP) module. To improve the small-object detection accuracy, a 160 \(\times \) $\times$ 160 small-object detection head is added. Finally, the Focal-EIOU (efficient intersection over union) loss function is adopted to better converge in the training process. Full experiments have been carried out in the open traffic datasets Cityscapes and KITTI, and this paper proposed model is the best-performing method.