The DCN-BiFPN Object Detection Algorithm based on YOLOv8

Aiming at the problems of traditional target detection algorithms such as high demand for model equipment, low detection accuracy, high leakage rate of overlapping targets, and repeated detection of the same target, we propose an improved multilayer deformable convolution as well as a method for fusing attention mechanisms, and use improved BiFPN feature pyramid feature fusion in the network constructed using this method. First, the improved deformable convolution is used to replace part of the ordinary convolution in the original network to enhance the ability of the modified network to extract feature targets from irregular targets; second, the improved cascade feature fusion module is used to enhance the ability of the neural network to represent features at different scales and semantic levels, and by using the improved cascade feature module, it makes the network able to extract features from feature maps at different levels or scales. features, followed by using the weighted bidirectional feature pyramid network connectivity module to stitch the feature maps of different layers along the channel dimension, which is used to enrich the network's representation capability of the target, and finally, the hybrid attention mechanism is added to the network, which reduces the interference of the background as well as non-target objects on the target, and improves the network's accuracy of target detection. The experimental results show that the improved model in this paper improves over the original model by 3.3\% and 4.7\% in mAP50 and mAP50-95.