Multiscale apple recognition method based on improved CenterNet

Traditional apple-picking robots are unable to detect apples in real-time in complex environments. In order to improve detection efficiency, a fast CenterNet apple recognition method for multiple apple targets in dense scenes is proposed. This method can quickly and accurately identify multiple apple targets in dense scenes. The backbone network mainly consists of resnet-44 fully convolutional network, region of interest network (RPN), and region of interest (ROI). The experimental results show that the improved YoloV5 network model has a higher recognition accuracy of 94.1% and 95.8% for apple in the night environment, which improves the recognition accuracy of the occluded features and the features in the dark light, and the model is more robust in the actual data set.