YOLO-P: An efficient method for pear fast detection in complex orchard picking environment

Abstract

IntroductionFruit detection is one of the key functions of an automatic picking robot, but fruit detection accuracy is seriously decreased when fruits are against a disordered background and in the shade of other objects, as is commmon in a complex orchard environment.MethodsHere, an effective mode based on YOLOv5, namely YOLO-P, was proposed to detect pears quickly and accurately. Shuffle block was used to replace the Conv, Batch Norm, SiLU (CBS) structure of the second and third stages in the YOLOv5 backbone, while the inverted shuffle block was designed to replace the fourth stage’s CBS structure. The new backbone could extract features of pears from a long distance more efficiently. A convolutional block attention module (CBAM) was inserted into the reconstructed backbone to improve the robot’s ability to capture pears’ key features. Hard-Swish was used to replace the activation functions in other CBS structures in the whole YOLOv5 network. A weighted confidence loss function was designed to enhance the detection effect of small targets.ResultAt last, model comparison experiments, ablation experiments, and daytime and nighttime pear detection experiments were carried out. In the model comparison experiments, the detection effect of YOLO-P was better than other lightweight networks. The results showed that the module’s average precision (AP) was 97.6%, which was 1.8% higher than the precision of the original YOLOv5s. The model volume had been compressed by 39.4%, from 13.7MB to only 8.3MB. Ablation experiments verified the effectiveness of the proposed method. In the daytime and nighttime pear detection experiments, an embedded industrial computer was used to test the performance of YOLO-P against backgrounds of different complexities and when fruits are in different degrees of shade.DiscussionThe results showed that YOLO-P achieved the highest F1 score (96.1%) and frames per second (FPS) (32 FPS). It was sufficient for the picking robot to quickly and accurately detect pears in orchards. The proposed method can quickly and accurately detect pears in unstructured environments. YOLO-P provides support for automated pear picking and can be a reference for other types of fruit detection in similar environments.

IoT, UAV, BCI Empowered Deep Learning models in Precision Agriculture

“…▪UAV; RGB-D camera; YOLOv5sfor detection, and improved DeepLabv3+ (MobileNet v2) for semantic segmentation ▪ACC = 85.50% -94.52% ▪Grape detection, instance segmentation ▪RGB camera; Mask R-CNN with ResNet 101 as the backbone ▪F1 = 91% (Santos et al, 2020) ▪Pear (fruit) detection ▪RGB camera; YOLO-P F1 = 96.1% (Sun et al, 2023) be adapted in the next few years to aerial systems. For example, a great many algorithms exist for in-lane orchard navigation for ground autonomous systems (small-sized tractors, (Emmi et al, 2021)) and it should be possible to adapt them with minimal modifications.…”

Orchard monitoring based on unmanned aerial vehicles and image processing by artificial neural networks: a systematic review

“…For example, the authors ( Kestur et al., 2019 ) proposed a deep convolutional neural network architecture for mango detection using semantic segmentation named MangoNet. Also, the authors ( Koirala et al., 2021 ) call the network YOLO used MangoYOLO, and ( Sun et al., 2023 ) named YOLOP the modified YOLO v5 for pear fruit detection. The authors ( Kerkech et al., 2020 ) proposed a deep convolutional neural network architecture for vine disease detection named VddNet with a parallel architecture based on the VGG encoder.…”

Tomato Health Monitoring System: Tomato Classification, Detection, and Counting System Based on YOLOv8 Model With Explainable MobileNet Models Using Grad-CAM++

“…The research combined YOLOv7 with MobileNetV3 in extracting features and reducing parameters in identifying rice pests and diseases; the prediction accuracy reached 93.7% [8]. The research on improving the YOLOv5 model by using robots to detect pears in day and night states achieved an accuracy of 97.6%, 1.8% higher than the conventional method [9]. The study combined YOLOv5, ShuffleNet and MobileNet to achieve high accuracy in identifying diseases on peach leaves, resulting in an accuracy higher than 5.6% [10].…”