High Precision - Low-Cost Apple Feature Recognition Model

Yilin Lian; Xuexue Song; Wei Wei

doi:10.54097/fbgy3h20

Authors

Yilin Lian
Xuexue Song
Wei Wei

DOI:

https://doi.org/10.54097/fbgy3h20

Keywords:

Deep learning, Target detection, Fast R-CNN, K-means.

Abstract

This paper addresses the image recognition problem in apple-picking robots and proposes a high-precision, low-cost apple feature recognition model to improve efficiency and accuracy. First, based on object detection algorithms, the study develops an apple contour recognition model using morphological methods, alongside a K-means clustering model for data analysis. These models are used to determine the approximate spatial distribution of apple positions and classify apple maturity levels. Second, by integrating apple contour recognition with numerical simulation optimization techniques, the distribution range of apple quality is estimated. Finally, simulation experiments conducted on a given dataset demonstrate that the identified apple positions, maturity, and calculated quality align closely with empirical data, validating the model's effectiveness.

Downloads

Download data is not yet available.

References

[1] Wang L, Liu J, Gao J M. Spatial distribution pattern and interannual dynamic changes of apples in China [J]. China Agricultural Information, 2019, 31(04): 84-93.

[2] Chen Q, Yin C K, Guo Z L, et al. Research status and development trends of key technologies in apple picking robots [J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(04): 1-15

[3] Qi J W. Research on apple target recognition and positioning algorithm based on deep learning [J]. Electronic Technology & Software Engineering, 2022, (08): 189-92.

[4] SA I, GE Z, DAYOUB F, et al. DeepFruits: A Fruit Detection System Using Deep Neural Networks [J]. Sensors (Basel, Switzerland), 2016, 16.

[5] BARGOTI S, UNDERWOOD J P. Deep fruit detection in orchards [J]. 2017 IEEE International Conference on Robotics and Automation (ICRA), 2016: 3626-33.

[6] TIAN Y, YANG G, WANG Z, et al. Apple detection during different growth stages in orchards using the improved YOLO-V3 model [J]. Comput Electron Agric, 2019, 157: 417-26.

[7] Wu X, Qi Z Y, Wang L J, et al. Apple detection method based on lightweight YOLOv3 convolutional neural network [J]. Journal of Agricultural Mechanization Research, 2020, 51(08): 17-25.

[8] Tian B K. Research on apple detection, classification, and localization technology under complex environments based on deep learning [D], 2020.

[9] Zhu Z, Liang D, Zhang S, et al. Traffic-sign detection and classification in the wild[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2110-2118.

[10] Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge[J]. International journal of computer vision, 2015, 115: 211-252.

[11] Selvaraju R R, Cogswell M, Das A, et al. Grad-cam: Visual explanations from deep networks via gradient-based localization[C]//Proceedings of the IEEE international conference on computer vision. 2017: 618-626.

[12] Chen H, Chen Z, Chai Z, et al. A single-side neural network-aided canonical correlation analysis with applications to fault diagnosis[J]. IEEE Transactions on Cybernetics, 2021, 52(9): 9454-9466.

[13] Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.

[14] Mou Q S. Research on a universal fruit picking detection model based on deep learning [D], 2021.