Application of Minnan folk light and shadow animation in built environment in object detection algorithm

For the problems of deep convolutional neural network model with many parameters and memory resource consumption, a lightweight network-based algorithm for building detection of Minnan folk light SAR images is proposed. Firstly, based on the rotating target detection algorithm R-centernet, the Ghost ResNet network is constructed to reduce the number of model parameters by replacing the traditional convolution in the backbone network with Ghost convolution. Secondly, a channel attention module integrating width and height information is proposed to enhance the network's ability to accurately locate salient regions in folk light images.CARAFE upsampling is used to replace the DCN module in the network to fully incorporate feature map information during upsampling to improve target detection. Finally, the constructed dataset of rotated and annotated light and shadow SAR images is trained and tested using the improved R-centernet algorithm. The experimental results show that the improved algorithm improves the accuracy by 3.8%, the recall by 1.2%, and the detection speed by 12 frames/second compared with the original R-centernet algorithm.