Abstract
Accurate detection of wheat heads outdoors is a great challenge. Wheat color and shape distinctions, as well as overlaps and wind blurring in wheat photos, make it difficult to detect wheat heads. We propose a Bag of Tricks for Wheat Detection (BTWD), finding that a reasonable combination of some tricks will bring great improvement to the wheat detection results, and apply it on different networks such as YOLO v5x, YOLO v3, EfficientDet-D5, Faster R-CNN, etc. BTWD has greatly enhanced comparison with the original network without tricks. YOLO v5x with BTWD achieves 77.07% in average mAP, in comparison, only 70.78% without it on the Global Wheat Head Detection (GWHD) dataset.
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
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Improving object detection with one line of code. CoRR abs/1704.04503 (2017). http://arxiv.org/abs/1704.04503
David, E., et al.: Global wheat head detection (GWHD) dataset: a large and diverse dataset of high resolution RGB labelled images to develop and benchmark wheat head detection methods. arXiv preprint arXiv:2005.02162 (2020)
DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)
Jocher, G., et al.: ultralytics/yolov5: v3.0, August 2020. https://doi.org/10.5281/zenodo.3983579
Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3 (2013)
Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 658–666 (2019)
Solovyev, R., Wang, W.: Weighted boxes fusion: ensembling boxes for object detection models. arXiv preprint arXiv:1910.13302 (2019)
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781–10790 (2020)
Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6023–6032 (2019)
Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-IoU loss: faster and better learning for bounding box regression. In: AAAI, pp. 12993–13000 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, Y., Hu, Y., Li, L. (2020). BTWD: Bag of Tricks for Wheat Detection. In: Bartoli, A., Fusiello, A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science(), vol 12540. Springer, Cham. https://doi.org/10.1007/978-3-030-65414-6_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-65414-6_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65413-9
Online ISBN: 978-3-030-65414-6
eBook Packages: Computer ScienceComputer Science (R0)