A Real-Time Apple Targets Detection Method for Picking Robot Based on Improved YOLOv5

Abstract

The apple target recognition algorithm is one of the core technologies of the apple picking robot. However, most of the existing apple detection algorithms cannot distinguish between the apples that are occluded by tree branches and occluded by other apples. The apples, grasping end-effector and mechanical picking arm of the robot are very likely to be damaged if the algorithm is directly applied to the picking robot. Based on this practical problem, in order to automatically recognize the graspable and ungraspable apples in an apple tree image, a light-weight apple targets detection method was proposed for picking robot using improved YOLOv5s. Firstly, BottleneckCSP module was improved designed to BottleneckCSP-2 module which was used to replace the BottleneckCSP module in backbone architecture of original YOLOv5s network. Secondly, SE module, which belonged to the visual attention mechanism network, was inserted to the proposed improved backbone network. Thirdly, the bonding fusion mode of feature maps, which were inputs to the target detection layer of medium size in the original YOLOv5s network, were improved. Finally, the initial anchor box size of the original network was improved. The experimental results indicated that the graspable apples, which were unoccluded or only occluded by tree leaves, and the ungraspable apples, which were occluded by tree branches or occluded by other fruits, could be identified effectively using the proposed improved network model in this study. Specifically, the recognition recall, precision, mAP and F1 were 91.48%, 83.83%, 86.75% and 87.49%, respectively. The average recognition time was 0.015 s per image. Contrasted with original YOLOv5s, YOLOv3, YOLOv4 and EfficientDet-D0 model, the mAP of the proposed improved YOLOv5s model increased by 5.05%, 14.95%, 4.74% and 6.75% respectively, the size of the model compressed by 9.29%, 94.6%, 94.8% and 15.3% respectively. The average recognition speeds per image of the proposed improved YOLOv5s model were 2.53, 1.13 and 3.53 times of EfficientDet-D0, YOLOv4 and YOLOv3 and model, respectively. The proposed method can provide technical support for the real-time accurate detection of multiple fruit targets for the apple picking robot.

How the Small Object Detection via Machine Learning and UAS-Based Remote-Sensing Imagery Can Support the Achievement of SDG2: A Case Study of Vole Burrows

“…Numerous studies searched for a reason causing small object miss-detection and false detection [65]. Several studies compare YOLOv5 and YOLOv3, but only after improving the initial anchor box size of the original YOLOv5network to avoid misrecognition of small objects [66]. However, in our study, the targets are small and probably not in contrast to YOLOv5, therefore this model could not outperform the 3rd version of YOLO.…”

Detection of mold on the food surface using YOLOv5

“…Although tremendous progress has been made in the field of object detection recently, it remains a difficult task to detect and identify objects accurately and quickly. Yan et al (2021) named the YOLOv5 as the most powerful object detection algorithm in present times. In the current study, the overall performance of YOLOv5 was better than YOLOv4 and YOLOv3.…”

“…There are some other studies that used the same model for the detection of safety helmets ( Zhou et al, 2021 ) and tree leaves ( Wang and Yan, 2021 ). Again, the YOLOv5 outperformed the R–CNN and other YOLO in terms of speed and accuracy in a number of studies ( Yan et al, 2021 ; Wang and Yan, 2021 ; Chen et al, 2021 ; Kuznetsova et al, 2020 ). As a result, we decided to convey the current research using the YOLOv5.…”

“…In some recent studies, YOLOv5 was used to detect various objects. The YOLOv5 model was used by Yan et al (2021) and Kuznetsova et al (2020) to detect apples in orchards by harvesting robots. In both studies, the detection speed and accuracy were notable compared to other YOLO models.…”

A Fast Aircraft Detection Method for SAR Images Based on Efficient Bidirectional Path Aggregated Attention Network

“…By using multi-scale pooling to construct features on multiple receptive fields to learn the multi-scale characteristics of aircraft. The detailed internal structure of the YOLOv5s backbone network can be referred to the introduction in [24,25].…”