Real-time citrus variety detection in orchards based on complex scenarios of improved YOLOv7

Abstract

Variety detection provides technical support for selecting XinHui citrus for use in the production of XinHui dried tangerine peel. Simultaneously, the mutual occlusion between tree leaves and fruits is one of the challenges in object detection. In order to improve screening efficiency, this paper introduces a YOLO(You Only Look Once)v7-BiGS(BiFormer&GSConv) citrus variety detection method capable of identifying different citrus varieties efficiently. In the YOLOv7-BiGS network model, initially, the BiFormer attention mechanism in the backbone of the YOLOv7-based network strengthens the model’s ability to extract citrus’ features. In addition, the introduction of the lightweight GSConv convolution in place of the original convolution within the ELAN of the head component effectively streamlines model complexity while maintaining performance integrity. To environment challenge validate the effectiveness of the method, the proposed YOLOv7-BiGS was compared with YOLOv5, YOLOv7, and YOLOv8. In the comparison of YOLOv7-BiGS with YOLOv5, YOLOv7, and YOLOv8, the experimental results show that the precision, mAP and recell of YOLOv7-BiGS are 91%, 93.7% and 87.3% respectively. Notably, compared to baseline methods, the proposed approach exhibited significant enhancements in precision, mAP, and recall by 5.8%, 4.8%, and 5.2%, respectively. To evaluate the efficacy of the YOLOv7-BiGS in addressing challenges posed by complex environmental conditions, we collected occluded images of Xinhui citrus fruits from the Xinhui orchard base for model detection. This research aims to fulfill performance criteria for citrus variety identification, offering vital technical backing for variety detection endeavors.