Tomato Fruit Target Detection Based on Improved YOLOv7
To solve fruit overlap,occlusion and recognition difficulty caused by small-size fruit for agricultural picking robots,an improved YOLOv7 network was proposed for tomato fruit target detection.Firstly,SimAM and CA attention modules were added to YOLOv7 network structure to improve the feature extraction capability.Secondly,the tensor splicing operation of the feature fusion network and the weighted Bidirection Feature Pyramid Network were combined to improve the feature fusion capability.The NMS algorithm was replaced by Soft-NMS algorithm to increase the detection ability in the overlapping area.Finally,CIOU Loss was replaced by EIOU Loss to optimize network performance.The results showed that the improved YOLOv7 network mAP value reached 96.7%;the accuracy reached 96.2%;the recall rate reached 99.0%,which met the network requirements for tomato detection accuracy.
NETL
NSTL
万方数据
