Abstract
The missed detection of orchard fruit recognition by robots is too high in the complex natural environment, because of different occlusion factors. Based on this practical problem, the apple fruit images collected from real orchard is taken as the research object, and an improved yolov5s fruit detection model is proposed based on automatic determination of occlusion information. On one hand, an algorithm for automatic judgment based on fruit occlusion information is added in the model training stage. In order to reduce the missed detection rate caused by non-maximum suppression (NMS), the unlabeled apple fruits are divided into three categories for training: no occlusion, branches and leaves occlusion, and fruit occlusion. On the other hand, improves the detection accuracy of occluded targets by introducing DIoU Loss and adding CBAM attention module in the original YOLOv5s network. Meanwhile, reduces false detection by adding false detection processing based on relative distance and intersection ratio after model NMS. Finally, the experimental results show that the proposed idea is feasible, the missed detection is significantly reduced, and the comprehensive evaluation index value (F1) reaches 97.8%. In compared with original yolov5s, the proposed method reduces missed detection rate from 6.5% to 2.0% without affecting the false detection rate, which is more suitable for robotic picking and yield estimation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, Q.I., Nuske, S., Bergerman, M., et al.: Automated crop yield estimation for apple orchards. In: Proceedings of International Symposium of Experimental Robotics, Springer International Publishing, pp. 745–758 (2013). https://doi.org/10.1007/978-3-319-00065-7_50
Ji, W., Zhao, D., Cheng, F., et al.: Automatic recognition vision system guided for apple harvesting robot. Comput. Electr. Eng. 38(5), 1186–1195 (2012)
Gongal, A., Amatya, S., Karkee, M., et al.: Sensors and systems for fruit detection and localization: a review. Comput. Electron. Agric. 116(C), 8–19 (2015)
Peng, H.X., Huang, B., Shao, Y.Y.: General improved SSD model for picking object recognition of multiple fruits in natural environment. Trans. Chinese Soc. Agric. Eng.(Trans. CSAE) 34(16), 155–162 (2018)
Sun, J., He, X.F., Ge, X., et al.: Detection of key organs in tomato based on deep migration learning in a complex background. Agriculture 8(12), 8196 (2018)
Häni, N., Roy, P., Isler, V.: A comparative study of fruit detection and counting methods for yield mapping in apple orchards. J. Field Robot. 37(2), 263–282 (2020)
Chu, X., Zheng, A., Zhang, X., et al.: Detection in crowded scenes: one proposal, multiple predictions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12214–12223 (2020)
Tian, Y., Yang, G., Wang, Z., et al.: Apple detection during different growth stages in orchards using the improved YOLO-V3 model. Comput. Electron. Agric. 157, 417–426 (2019)
Saleh, K., Szénási, S., Vámossy, Z.: Occlusion handling in generic object detection: a review. In: 2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI), pp. 000477–000484 (IEEE, 2021)
Gao, F., Fu, L., Zhang, X., et al.: Multi-class fruit-on-plant detection for apple in SNAP system using Faster R-CNN. Comput. Electron. Agric. 176, 105634 (2020)
Wang, X., Xiao, T., Jiang, Y., et al.: Repulsion loss: detecting pedestrians in a crowd. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7774–7783 (2018)
Rong, W., Li, Z., Zhang, W., et al.: An improved CANNY edge detection algorithm. In: 2014 IEEE International Conference on Mechatronics and Automation, pp. 577–582. IEEE (2014)
Liu, Y., Lu, B., Peng, J., et al.: Research on the use of YOLOv5 object detection algorithm in mask wearing recognition. World Sci. Res. J. 6(11), 276–284 (2020)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: Convolutional Block Attention Module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Zheng, Z., Wang, P., Liu, W., et al.: Distance-IoU Loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), pp. 12993–13000 (2020)
Ren, S.Q., He, K.M., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 91–99. ACM (2015)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.: YOLOv4: optimal speed and accuracy of object detection [EB/OL]. [2020–10–23]. https://arxiv.org/abs/2004 10934
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Y., Ye, L., Zhao, J., Min, H. (2023). Fruit Detection Based on Automatic Occlusion Prediction and Improved YOLOv5s. In: Sun, F., Li, J., Liu, H., Chu, Z. (eds) Cognitive Computation and Systems. ICCCS 2022. Communications in Computer and Information Science, vol 1732. Springer, Singapore. https://doi.org/10.1007/978-981-99-2789-0_2
Download citation
DOI: https://doi.org/10.1007/978-981-99-2789-0_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-2788-3
Online ISBN: 978-981-99-2789-0
eBook Packages: Computer ScienceComputer Science (R0)