The Research on Navel Oranges Detection Systems of Harvesting Robots Based on an Improved YOLOv5

As a typical intelligent agricultural equipment, the harvesting robot integrates various advanced technologies such as robotic, recognition and control. Because of the need the complexity of agricultural scenes, the major bottleneck restricting the performance of harvesting robots is the accuracy of the detection system. In this paper, we proposed a method for navel orange recognition based on the attention mechanism the selection of detection frames. Firstly, the attention mechanism module was incorporated into the feature extraction network to obtain important features. Then, the overlapping area and centroid distance between the target frame and detection frame were considered. And DIoU-NMS was used instead of NMS to improve the localization accuracy. Finally, a dataset based on navel oranges has been collected, with a total sample size of 811 images. The training-set and dataset have been randomly differentiated according to 4:1. The results showed that the improved YOLOv5 research algorithm can obtain 99.4% average accuracy, which is a 7.4% improvement compared to the YOLOv51 algorithm. The new improved YOLOv5 algorithm provided a more accurate and faster method for the navel orange detection.