Automatic monitoring method of cow ruminant behavior based on spatio-temporal context learning

Yujuan Chen, Dongjian He, Huaibo Song

Abstract


Automatic monitoring of cow rumination has great significance in the development of modern animal husbandry. In order to solve the problem of high real-time requirement of ruminant behavior monitoring, a tracking method based on STC (Spatio-Temporal Context) learning was carried out. On the basis of cow’s mouth region extraction, the spatial context model between target object and its local surrounding background was built based on their spatial correlations by solving the deconvolution problem, and the learned spatial context model was used to update the STC learning model for the next frame. Tracking in the next frame was formulated by computing a confidence map as a convolution problem that integrates the STC learning information, and the best object location could be estimated by maximizing the confidence map. Then the target scale was estimated based on the confidence evaluation. Finally, accurate tracking of the mouth movement trajectory was realized. To verify the effectiveness of the proposed method, the performance of the algorithm was tested using 20 video sequences. Besides, the tracking results were compared with the Mean-shift algorithm. The results showed that the average success rate of STC learning monitoring algorithm was 85.45%, which was 9.45% higher than the Mean-shift algorithm, the detection rate of STC learning monitoring algorithm was 18.56 s per video, which was 22.08% higher than that of the Mean-shift algorithm. The results showed that the fast tracking method based on STC learning monitoring algorithm is effective and feasible.
Keywords: dairy cow, rumination, intelligent monitoring, STC learning, Mean-shift
DOI: 10.25165/j.ijabe.20181104.3509

Citation: Chen Y J, He D J, Song H B. Automatic monitoring method of cow ruminant behavior based on spatio-temporal context learning. Int J Agric & Biol Eng, 2018; 11(4): 179-185.

Keywords


dairy cow, rumination, intelligent monitoring, STC learning, Mean-shift

Full Text:

PDF

References


Yan X, Dong G, Xu W, Liu A, Jose G, Wang Y, et al. Analysis of influence factors on cow’s rumination and activity in Beijing. Acta Veterinaria Et Zootechnica Sinica, 2016; 47(5): 955–961. (in Chinese)

Shao D. Researches on variation of the rumination and its influencing factors in lactating cows. 2015; Jilin University. (in Chinese)

Bao Y, Chen X, Zhang L. Analysis of differential diagnosis of cow ruminant disease. Agricultural Development and Equipments, 2016; 22(1): 164–159. (in Chinese)

Wu Y, Xie X, Han Z. Research on target tracking algorithm based on particle filter and Mean-Shift. International Conference on Frontiers of Mechanical Engineering and Materials Engineering, 2013; pp.1050–1053.

Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003; 25(5): 564–577.

Chen W, Zhang X, Luo S. Video vehicle tracking based on improved Mean-Shift algorithm. Advanced Materials Research, 2011; 179-180: 1408–1411.

Chen D. The research and design of target detecting and tracking system based on DSP. Yanshan University, 2016, (in Chinese)

Huang J, Gao Y, Li Y, Chen J, Jiang J. Algorithm research on motion area segmentation based on improved frame differences. IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2015; pp.1152–1155.

Cui N, Zhang L, Wang X, Yang F, Lu B. Application of adaptive high-degree cubature Kalman filter in target tracking. Acta Aeronautica et Astronautica Sinica, 2015; 36(12): 3885–3895. (in Chinese)

Li H, Fan H. Research of several background modeling based on background subtraction. Industrial Control Computer, 2012; 25(7): 62–64. (in Chinese)

Zuo Q, Qi Y. A novel spatial–temporal optical flow method for estimating the velocity fields of a fluid sequence. Visual Computer, 2015; 33(3): 1–10.

Barron J L, Fleet D J, Beauchemin S S. Performance of optical flow techniques. International Journal of Computer Vision, 1994; 12(1): 43–77.

Sugisaka M, Sato S. Improvement of the precision of the gradient method and object tracking using optical flow. Artificial Life and Robotics, 2004; (4): 182–184.

Xia J, Rao W, Huang W, Lu Z. Automatic multi-vehicle tracking using video cameras: An improved CAMShift approach. KSCE Journal of Civil Engineering, 2013; 17(6): 1462–1470.

Wang Z, Yang X, Xu Y, Yu S. CamShift guided particle filter for visual tracking. Pattern Recognition Letters, 2008; 30(4): 407–413.

Wang J, Liu Y, Wu M. Cam Shift tracking algorithm based on speed-up robust features. Journal of Computer Applications, 2013; 33(2): 499–502. (in Chinese)

Zhang K, Zhang L, Yang M. Real-time compressive tracking. Computer Vision-ECCV 2012. Spring Berlin Heideberg, 2012; pp.864–877.

Zhang K, Zhang L, Yang M. Fast compressive tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014; 36(10): 2002–2015.

Zhang K, Zhang L, Liu Q, Zhang D, Yang M. Fast visual tracking via dense spatio-temporal context learning. Computer Vision-ECCV 2014. Springer International Publishing, 2014; pp.127–141.

Lu J, Chen Y, Zou Y, Zou G. Long-term tracking based on spatio-temporal context. Journal of Shanghai Jiaotong University (Science), 2017; 22(4): 504–512.

Wang C, Shen Y, Wang Y, Zhu Z. Gesture tracking and recognition based on spatio-temporal context. Computer Engineering and Applications, 2016; 52(9): 202–207. (in Chinese)

Li N, Wu X, Xu D, Guo H, Feng W. Spatio-temporal context analysis within video volumes for anomalous-event detection and localization. Neurocomputing, 2015; 155: 309–319.

Kamal A. H. M, Montse Parada. Translation based estimation technique to handle occlusion while using mean-shift in tracking. Research Journal of Applied Sciences, 2009; 4(4): 129–133.

Chen K, Song K, Choi K, Guo Y. Optimized meanshift target reference model based on improved pixel weighting in visual tracking. Journal of Electronics (China), 2013; 30(3): 283–289.

Lu R, Huang X, Xu W, Shen L. Meanshift tracking with kalman filter and rotation-invariant features. Applied Mechanics and Materials, 2013; 2617(380): 1824–1828.

Jatoth R, Gopisetty S, Hussain M. Performance analysis of Alpha Beta filter, kalman filter and meanshift for object tracking in video sequences. International Journal of Image, Graphics and Signal Processing (IJIGSP), 2015; 7(3): 24–30.

Hou P, Xu J, Zhao J, Zhan X, Fan G. A novel model based on LBP and meanshift for UAV image segmentation. Applied Mechanics and Materials, 2014; 701–702: 270–273.

Mohcine B, Benayad N. Object detection and segmentation using adaptive meanshift blob tracking algorithm and graph cuts theory. Image Processing and Communications Challenges 5. Springer International Publishing, 2014: 143–151.

Zhao H. Image denoising algorithm based on multi-scale Meanshift. Journal of Jilin University: Engineering and Technology Edition, 2014; 44(5): 1417–1422. ( in Chinese)

Li B, Zeng Z, Chen J. Vehicle classification and tracking based on particle swarm optimization and meanshift. Advanced Materials Research, 2010; 121–122: 417–422.

Wu J, Song S, An W. Mean Shift method for multi-channel image segmentation. Packaging Engineering, 2015; 36(21): 89–94. (in Chinese)

Wang X, Wu W, Qian Y. Trajectory clustering based customer movement tracking in a supermarket. CAAI Transactions on Intelligent Systems, 2015; (2): 187–192. (in Chinese)




Copyright (c) 2018



2023-2026 Copyright IJABE Editing and Publishing Office