Author:
Bai Qiang,Gao Ronghua,Wang Rong,Li Qifeng,Yu Qinyang,Zhao Chunjiang,Li Shuqin
Abstract
AbstractBehavior is one of the important factors reflecting the health status of dairy cows, and when dairy cows encounter health problems, they exhibit different behavioral characteristics. Therefore, identifying dairy cow behavior not only helps in assessing their physiological health and disease treatment but also improves cow welfare, which is very important for the development of animal husbandry. The method of relying on human eyes to observe the behavior of dairy cows has problems such as high labor costs, high labor intensity, and high fatigue rates. Therefore, it is necessary to explore more effective technical means to identify cow behaviors more quickly and accurately and improve the intelligence level of dairy cow farming. Automatic recognition of dairy cow behavior has become a key technology for diagnosing dairy cow diseases, improving farm economic benefits and reducing animal elimination rates. Recently, deep learning for automated dairy cow behavior identification has become a research focus. However, in complex farming environments, dairy cow behaviors are characterized by multiscale features due to large scenes and long data collection distances. Traditional behavior recognition models cannot accurately recognize similar behavior features of dairy cows, such as those with similar visual characteristics, i.e., standing and walking. The behavior recognition method based on 3D convolution solves the problem of small visual feature differences in behavior recognition. However, due to the large number of model parameters, long inference time, and simple data background, it cannot meet the demand for real-time recognition of dairy cow behaviors in complex breeding environments. To address this, we developed an effective yet lightweight model for fast and accurate dairy cow behavior feature learning from video data. We focused on four common behaviors: standing, walking, lying, and mounting. We recorded videos of dairy cow behaviors at a dairy farm containing over one hundred cows using surveillance cameras. A robust model was built using a complex background dataset. We proposed a two-pathway X3DFast model based on spatiotemporal behavior features. The X3D and fast pathways were laterally connected to integrate spatial and temporal features. The X3D pathway extracted spatial features. The fast pathway with R(2 + 1)D convolution decomposed spatiotemporal features and transferred effective spatial features to the X3D pathway. An action model further enhanced X3D spatial modeling. Experiments showed that X3DFast achieved 98.49% top-1 accuracy, outperforming similar methods in identifying the four behaviors. The method we proposed can effectively identify similar dairy cow behaviors while improving inference speed, providing technical support for subsequent dairy cow behavior recognition and daily behavior statistics.
Funder
Technological Innovation Capacity Construction of Beijing Academy of Agricultural and Forestry Sciences
Publisher
Springer Science and Business Media LLC
Reference38 articles.
1. Brouwers, S. P., Simmler, M., Savary, P. & Scriba, M. F. Towards a novel method for detecting atypical lying down and standing up behaviours in dairy cows using accelerometers and machine learning. Smart Agric. Technol. 4, 100199 (2023).
2. Wang, J., Zhang, Y., Bell, M. & Liu, G. Potential of an activity index combining acceleration and location for automated estrus detection in dairy cows. Inf. Process. Agric. 9, 288–299 (2022).
3. Krieger, S. et al. Prediction of calving in dairy cows using a tail-mounted tri-axial accelerometer: A pilot study. Biosyst. Eng. 173, 79–84 (2018).
4. Chen, C., Zhu, W. & Norton, T. Behaviour recognition of pigs and cattle: Journey from computer vision to deep learning. Comput. Electron. Agric. 187, 106255 (2021).
5. Wang, R. et al. Detection method of cow estrus behavior in natural scenes based on improved YOLOv5. Agriculture 12, 1339 (2022).
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献