Vehicle detection based on remote sensing image of Yolov3

The recognition and classification of remote sensing satellite images have unique value and significance in many fields. Based on the yolov3 deep learning neural network, this paper first adjusts the network model to make it suitable for small target detection on remote sensing images, then uses k-means algorithm to calculate the grid size of Yolo network model suitable for vehicles, and then uses yolov3 to train the data which is the satellite remote sensing image set, The network model for vehicle detection in the satellite remote sensing images is obtained, and the model is tested. Finally, the vehicle detection model suitable for remote sensing image is obtained. Through the research and analysis of the experimental results, it can be seen that this method can effectively detect the vehicles in the remote sensing image and ensure the high detection accuracy of the experimental results.