Tomato Detection System based on YOLOv8 and 
Improved GrabCut

Ziling Zheng; Zongxu Wu; Zhi Cao; Hanzhi Zhu; Weihua Zhang; Qi Li

doi:10.70711/aitr.v2i8.6645

Tomato Detection System based on YOLOv8 and Improved GrabCut

Ziling Zheng, Zongxu Wu, Zhi Cao, Hanzhi Zhu, Weihua Zhang, Qi Li

Abstract

This study proposes an intelligent detection system that integrates YOLOv8 object detection, GrabCut image segmentation, and
multi feature analysis to address the low efficiency and large errors of manual visual evaluation of tomato maturity in traditional agriculture.
The system uses YOLOv8 to achieve rapid tomato localization (detection speed ? 30 FPS), combined with GrabCut algorithm to obtain accurate segmentation masks (IoU ? 0.8), extract color, texture, and morphological features to construct a maturity evaluation model. The experiment shows that the classification accuracy of the system maturity reaches 92.3%, which can be deployed on the RK3399Pro edge computing
platform, and has the potential of real-time processing and agricultural scene application.

Keywords

Tomato maturity testing; YOLOv8; GrabCut algorithm; Feature fusion; Edge computing

Full Text:

PDF

Included Database

References

[1] Jones T, et al. Advances in Spectral Imaging for Disease Detection in Wheat[J]. Agricultural Technology Review, 2022, 45(4):214-229.

[2] Chen L Y, Chen Y Q, Xi J T, et al. Knowledge from the Original Network: Restore a Better Pruned Network with Knowledge

Distillation[J]. Complex & Intelligent Systems, 2021, 8.

[3] Zhang S G, Chen S L, Zhao Z. Improved YOLOv8 Algorithm for Crop Leaf Pest and Disease Recognition[J]. Chinese Journal of Agricultural Chemistry, 2024, 45(7):255-260.

[4] Produo G, Arantes L, Martinelli O, et al. Maturity and Level of Knowledge Management in the Company: An Application of Nonaka

and Takeuchi Model and Fuzzy Logic[J]. Gesto & Produo, 2021, 28.

[5] You Y L, Xu W, Tannenbaum A, et al. Behavioral Analysis of Anisotropic Diffusion in Image Processing[J]. IEEE Transactions on Image Processing, 1996, 5(11):1539-1553.

[6] Otsu N. A Threshold Selection Method from Gray-Level Histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979,

9(1):62-66.

[7] Long J, Shelhamer E, Darrell T. Fully Convolutional Networks for Semantic Segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, MA, USA: IEEE, 2015:3431-3440.

[8] He K M, Gkioxari G, Dollar P, et al. Mask R-CNN[J].2018.

DOI: http://dx.doi.org/10.70711/aitr.v2i8.6645

Refbacks

There are currently no refbacks.