Abstract
Large datasets are required for deep learning to achieve good performance. However, there is a lack of sufficient training datasets in many research fields, which may become a shortcoming of computer vision applications. This article provided a new data augmentation method for making training small datasets, which could be divided into two steps: 1. Unbalanced sampling based on information density. 2. Splicing images to form a dataset. Different information density dataset combinations had been used for testing the model generalization. The enhanced loss function which consisted of label smoothing loss and cross-entropy loss had been used to minimize the model preference during training models. Finally, with the same amount of data, the Mean Absolute Error (MAE) of the model with our sampling method could get 55% increase compared with the traditional sampling method. The best MAE could reach 0.98 if the splicing method had been adopted. The results showed that this augmented method was suitable for scenarios with small sample size, especially video datasets. To get the best performance, the splicing method was a nice choice to optimal model generalization performance.
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
Similar content being viewed by others
References
Kamilaris, A., Prenafeta-Boldú, F.X.: Deep learning in agriculture: a survey. Comput. Electron. Agric. 147, 70–90 (2018)
Tianhao, Z., Yansen, L., Zhiyi, H.: Applying image recognition and counting to reserved live pigs statistics. Comput. Appl. Software. 12 (2016)
Bruijning, M., Visser, M.D., Hallmann, C.A., Jongejans, E.: Trackdem: automated particle tracking to obtain population counts and size distributions from videos in r. Methods Ecol. Evol. 9(4), 965–73 (2018)
Chabot, D., Dillon, C., Francis, C.: An approach for using off-the-shelf object-based image analysis software to detect and count birds in large volumes of aerial imagery. Avian Conserv. Ecol. 13(1) (2018)
Norouzzadeh, M.S., et al.: Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning. Proc. Natl. Acad. Sci. 115(25), E5716–E25 (2018)
Tian, M., Guo, H., Chen, H., Wang, Q., Long, C., Ma, Y.: Automated pig counting using deep learning. Comput. Electron. Agric. 163, 104840 (2019)
Baweja, H.S., Parhar, T., Mirbod, O., Nuske, S.: Stalknet: a deep learning pipeline for high-throughput measurement of plant stalk count and stalk width. In: Hutter, M., Siegwart, R. (eds.) Field and Service Robotics, pp. 271–284. Springer International Publishing, Cham (2018). https://doi.org/10.1007/978-3-319-67361-5_18
Chen, G., Shen, S., Wen, L., Luo, S., Bo, L. (eds.): Efficient pig counting in crowds with keypoints tracking and spatial-aware temporal response filtering. In: 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2020)
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)
DeVries, T., Taylor, G.W.: Dataset augmentation in feature space. ar**v preprint ar**v:170205538. (2017)
Moosavi-Dezfooli, S.-M., Fawzi, A., Frossard, P. (eds.): Deepfool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Psota, E.T., Mittek, M., Pérez, L.C., Schmidt, T., Mote, B.: Multi-pig part detection and association with a fully-convolutional network. Sensors. 19(4), 852 (2019)
Inoue, H.: Data augmentation by pairing samples for images classification. ar**v preprint ar**v:180102929. (2018)
Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. ar**v preprint ar**v:170404861. (2017)
Lukasik, M., Bhojanapalli, S., Menon, A., Kumar, S. (eds.): Does label smoothing mitigate label noise?. In: International Conference on Machine Learning. PMLR (2020)
BloodAxe. pytorch-toolbelt. (2021)
Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. Proc. AAAI Conf. Artif. Intell. 34(07), 13001–13008 (2020). https://doi.org/10.1609/aaai.v34i07.7000
Acknowledgements
This work is supported by China Scholarship Council (No. 201906765023) and Hubei Chenguang Talented Youth Development Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, W., Wang, H., Ni, F. (2022). A New Augmented Method for Processing Video Datasets Based on Deep Neural Network. In: Liang, Q., Wang, W., Mu, J., Liu, X., Na, Z. (eds) Artificial Intelligence in China. Lecture Notes in Electrical Engineering, vol 854. Springer, Singapore. https://doi.org/10.1007/978-981-16-9423-3_16
Download citation
DOI: https://doi.org/10.1007/978-981-16-9423-3_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9422-6
Online ISBN: 978-981-16-9423-3
eBook Packages: Computer ScienceComputer Science (R0)