Application of Image Restoration and Object Detection Techniques in Fruit-Picking Robots

Qiong Yang; Jiana Meng; Yuhai Yu; Siwei Han; Guijun Luo

doi:10.62051/ijcsit.v2n3.26

Authors

Qiong Yang
Jiana Meng
Yuhai Yu
Siwei Han
Guijun Luo

DOI:

https://doi.org/10.62051/ijcsit.v2n3.26

Keywords:

RealSR, YOLOv5, VGG, ResNet.

Abstract

This paper focuses on the problem that existing apple picking robots are unable to accurately recognize targets in complex and unstructured orchard environments. The target detection algorithm of the robot is optimized based on YOLOv5 and ResNet neural network model. First, considering the low resolution of the robot's own binocular camera, this paper adopts the RealSR model to process the image with super-resolution. Then, the YOLOv5 model is chosen as the optimized target detection algorithm, which can obtain the number, location, ripeness and quality information of apples in the image through training. Secondly, by comparing the VGG and ResNet models, which are widely used in the field of image classification, the ResNet model is finally chosen as the main body for recognizing and classifying different fruits, and its correct rate can reach more than 97%.

Downloads

Download data is not yet available.

References

Sivakumar, Dharini, Yuming Jiang, and Elhadi M. Yahia. "Maintaining mango (Mangifera indica L.) fruit quality during the export chain." Food Research International 44.5 (2011): 1254-1263.

Cai Jianrui, et al. "Toward real-world single image super-resolution: A new benchmark and a new model." Proceedings of the IEEE/CVF international conference on computer vision. 2019.

Dou Zhan; Zhou Hang; Liu Zhe; Hu Yuanhao; Wang Pengchao; Zhang Jianwen; Wang Qianlin; Chen Liangchao; Diao Xu; Li Jinghai. An Improved YOLOv5s Fire Detection Model.[J]. Fire Technology, 2023: 1-32.

Yaodi Li; Jianxin Xue; Mingyue Zhang; Junyi Yin; Yang Liu; Xindan Qiao; Decong Zheng; Zezhen Li. YOLOv5-ASFF: A Multistage Strawberry Detection Algorithm Based on Improved YOLOv5[J]. Agronomy, 2023, Vol.13(1901): 1901.

Bansal, Kanishk | Singh, Amar. Development of VGG-16 transfer learning framework for geographical landmark recognition[J]. Intelligent Decision Technologies,2023, Vol.17(3): 1-12.

Weiqiang Fan; Xiaoyu Li; Zhongchao Liu. Fusion of visible and infrared images using GE-WA model and VGG-19 network[J]. Scientific Reports,2023,Vol.13(1): 190.

Omar El Ariss; Kaoning Hu. ResNet-Based Parkinson's Disease Classification[J]. IEEE Transactions on Artificial Intelligence, 2023, Vol.4(5): 1258-1268.