Detection and counting of overlapped apples based on convolutional neural networks

Abstract

Automatic identification picking robot is an important research content of agricultural modernization development. In order to overcome the difficulty of picking robots for accurate visual inspection and positioning of apples in a complex orchard, a detection method based on an instance segmentation model is proposed. To reduce the number of model parameters and improve the detection speed, the backbone feature extraction network is replaced from the Resnet101 network to the lightweight GhostNet network. Spatial Pyramid Pooling (SPP) module is used to increase the receptive field to enhance the semantics of the output network. Compared with Resnet101, the parameter quantity of the model is reduced by 90.90%, the detection speed is increased from 5 frames/s to 10 frames/s, and the detection speed is increased by 100%. The detection result is that the accuracy rate is 91.67%, the recall rate is 97.82%, and the mAP value is 91.68%. To solve the repeated detection of fruits due to the movement of the camera, the Deepsort algorithms was used to solve the multi-tracking problems. Experiments show that the algorithm can effectively detect the edge position information and categories of apples in different scenes. It can be an automated apple-picking robot. The vision system provides strong technical support.