A Pineapple Target Detection Method in a Field Environment Based on Improved YOLOv7
Source abstract
Abstract
The accurate detection of pineapples of different maturity levels in a complex field environment is the key step to achieving the early yield estimation and mechanized picking of pineapple. This study proposes a target detection model based on the improved YOLOv7 to achieve the accurate detection and maturity classification of pineapples in the field. First, the attention mechanism SimAM is inserted into the structure of the original YOLOv7 network to improve the feature extraction ability of the model. Then, the max-pooling convolution (MPConv) structure is improved to reduce the feature loss in the downsampling process. Finally, the non-maximum suppression (NMS) algorithm is replaced by the soft-NMS algorithm, with a better effect at improving the detection effect when pineapple is in occlusion or overlaps. According to the test, the mean average precision (mAP) and recall of the model proposed in this paper are 95.82% and 89.83%, which are 2.71% and 3.41% higher than those of the original YOLOv7, respectively. The maturity classification accuracy of the model and the detection performance under six different field scenarios were analyzed quantitatively. This method provides an effective scheme for the vision system of the field pineapple picking robot.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Smart Agriculture and AI · Date Palm Research Studies · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Engineering, South China Agricultural University, Guangzhou 510642, China
Funding
Science and Technology Planning Project of Guangdong Province of China
References (42)
Show source-provided references
1. Design of automatic pineapple harvesting machine based on binocular machine vision
2. Sensors and systems for fruit detection and localization: A review10.1016/j.compag.2015.05.021 ↗
3. Application of consumer RGB-D cameras for fruit detection and localization in field: A critical review10.1016/j.compag.2020.105687 ↗
4. Texture-based fruit detection10.1007/s11119-014-9361-x ↗
5. Detection and counting of immature green citrus fruit based on the Local Binary Patterns (LBP) feature using illumination-normalized images10.1007/s11119-018-9574-5 ↗
6. He, Z.L., Xiong, J.T., Lin, R., Zou, X.J., Tang, L.Y., Yang, Z.G., Liu, Z., and Song, G. (2017). A method of green litchi recognition in natural environment based on improved LDA classifier. Comput. Electron. Agric., 140.10.1016/j.compag.2017.05.029 ↗
7. Immature green citrus detection based on colour feature and sum of absolute transformed difference (SATD) using colour images in the citrus grove10.1016/j.compag.2016.04.009 ↗
8. A Detection Method for Apple Fruits Based on Color and Shape Features10.1109/ACCESS.2019.2918313 ↗
9. Recognition of green apples in an orchard environment by combining the GrabCut model and Ncut algorithm10.1016/j.biosystemseng.2019.09.006 ↗
10. Adaptive thresholding with fusion using a RGBD sensor for red sweet-pepper detection10.1016/j.biosystemseng.2015.12.002 ↗
11. Girshick, R. (2015). Fast R-CNN. IEEE international conference on computer vision (ICCV). arXiv.10.1109/ICCV.2015.169 ↗
12. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
13. Lucena, F., Breunig, F.M., and Kux, H. (2022). The Combined Use of UAV-Based RGB and DEM Images for the Detection and Delineation of Orange Tree Crowns with Mask R-CNN: An Approach of Labeling and Unified Framework. Future Internet, 14.10.3390/fi14100275 ↗
14. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
15. Kuznetsova, A., Maleva, T., and Soloviev, V. (2020). Using YOLOv3 Algorithm with Pre- and Post-Processing for Apple Detection in Fruit-Harvesting Robot. Agronomy, 10.10.3390/agronomy10071016 ↗
16. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
17. Reed, S., Fu, C.Y., and Berg, A.C. (2016). Ssd: Single shot multibox detector. European Conference on Computer Vision (ECCV). arXiv.
18. A Method of Green Citrus Detection in Natural Environments Using a Deep Convolutional Neural Network10.3389/fpls.2021.705737 ↗
19. Real-time kiwifruit detection in orchard using deep learning on Android™ smartphones for yield estimation10.1016/j.compag.2020.105856 ↗
20. Gai, R.L., Chen, N., and Yuan, H. (2021). A detection algorithm for cherry fruits based on the improved YOLO-v4 model. Neural Comput. Appl., prepublish.10.1007/s00521-021-06029-z ↗
21. Tu, S.Q., Pang, J., Liu, H.F., Zhuang, N., Chen, Y., Zheng, C., Wan, H., and Xue, Y.J. (2020). Passion fruit detection and counting based on multiple scale faster R-CNN using RGB-D images. Precis. Agric., prepublish.10.1007/s11119-020-09709-3 ↗
22. Apple detection during different growth stages in orchards using the improved YOLO-V3 model10.1016/j.compag.2019.01.012 ↗
23. Light-YOLOv3: Fast method for detecting green mangoes in complex scenes using picking robots10.1007/s10489-020-01818-w ↗
24. Fan, Y.C., Zhang, S.Y., Feng, K., Qian, K.C., Wang, Y.T., and Qin, S.Z. (2022). Strawberry Maturity Recognition Algorithm Combining Dark Channel Enhancement and YOLOv5. Sensors, 22.10.3390/s22020419 ↗
25. YOLOMuskmelon: Quest for Fruit Detection Speed and Accuracy Using Deep Learning10.1109/ACCESS.2021.3053167 ↗
26. Ji, W., Pan, Y., Xu, B., and Wang, J.C. (2022). A Real-Time Apple Targets Detection Method for Picking Robot Based on ShufflenetV2-YOLOX. Agriculture, 12.10.3390/agriculture12060856 ↗
27. Cui, Z., Sun, H.M., Yu, J.T., Yin, R.N., and Jia, R.S. (2021). Fast detection method of green peach for application of picking robot. Appl. Intelligence., prepublish.10.1007/s10489-021-02456-6 ↗
28. Yan, B., Fan, P., Lei, X.Y., Liu, Z.J., and Yang, F.Z. (2021). A Real-Time Apple Targets Detection Method for Picking Robot Based on Improved YOLOv5. Remote Sens., 13.10.3390/rs13091619 ↗
29. Fruit detection, segmentation and 3D visualisation of environments in apple orchards10.1016/j.compag.2020.105302 ↗
30. Liu, X., Li, G., Chen, W., Liu, B., Chen, M., and Lu, S. (2022). Detection of Dense Citrus Fruits by Combining Coordinated Attention and Cross-Scale Connection with Weighted Feature Fusion. Appl. Sci., 12.10.3390/app12136600 ↗
31. Research on spatial positioning system of fruits to be picked in feld based on binocular vision and SSD Model
32. Pineapple (Ananas comosus) fruit detection and localization in natural environment based on binocular stereo vision and improved YOLOv3 model10.1007/s11119-022-09935-x ↗
33. Real-time growth stage detection model for high degree of occultation using DenseNet-fused YOLOv410.1016/j.compag.2022.106694 ↗
34. Wu, D.L., Jiang, S., Zhao, E.L., Liu, Y.L., Zhu, H.C., Wang, W.W., and Wang, R.Y. (2022). Detection of Camellia oleifera Fruit in Complex Scenes by Using YOLOv7 and Data Augmentation. Appl. Sci., 12.10.3390/app122211318 ↗
35. Wang, C.Y., Bochkovskiy, A., and Liao, H. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object de-tectors. arXiv.
36. Wang, C.Y., Bochkovskiy, A., and Liao, H. (2021, January 20–25). Scaled-YOLOv4: Scaling cross stage partial network. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01283 ↗
37. Ding, X.H., Zhang, X.Y., Man, N.N., Han, J.G., Ding, G.G., and Sun, J. (2021, January 20–25). RepVGG: Making VGG-style ConvNets great again. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01352 ↗
38. Jiang, T.T., and Cheng, J.Y. (2019, January 15–17). Target Recognition Based on CNN with LeakyReLU and PReLU Activation Functions. Proceedings of the The 2019 IEEE Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC), Beijing, China.10.1109/SDPC.2019.00136 ↗
39. Ge, Z., Liu, S.T., Wang, F., Li, Z., and Sun, J. (2021). YOLOX: Exceeding YOLO series in 2021. arXiv.
40. Yang, L., Zhang, R.Y., Li, L., and Xie, X. (2021, January 18–24). SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks. Proceedings of the International Conference On Machine Learning(ICML), Virtual Event.
41. Santana, A., and Colombini, E. (2021). Neural Attention Models in Deep Learning: Survey and Taxonomy. arXiv.
42. Bodla, N., Singh, B., Chellappa, R., and Davis, L.S. (2017, January 22–29). Soft-NMS:Improving object detection with one line of code. Proceedings of the 2017 IEEE International Conference on Computer Vision(IC-CV), Venice, Italy.10.1109/ICCV.2017.593 ↗