Research and Implementation of Yak Image Foreground Extraction Based on Android

Important factors like body size and weight parameters indicate Yak’s growth and development stage. The traditional manual measurement method creates a large workload and difficulties in measurement conditions, which may affect the growth and development of the yak. The Android-based measurement in capturing yak’s body size and weight has many advantages. For instance, the device used in the measurements is portable, it does not require physical contact with the yak, and it has high measurement accuracy. This paper focuses on the studies of the implementation of yak foreground extraction on portable devices. This extraction process comprises three steps: 1. Preprocess the yak’s image, 2. Use the Sobel Edge Detection Algorithm to extract the margin of the yak, 3. Delete the smaller zones in the image to obtain a complete yak foreground image. After the preliminary test, the yak foreground image extraction algorithm could efficiently complete the extraction process accurately. Thus, this study has laid a solid foundation for further implementation of the yak body and weight measurement on portable devices.

[1]  Stefano Cagnoni,et al.  Introduction to the special issue on evolutionary computer vision and image understanding , 2006, Pattern Recognit. Lett..

[2]  Siwei Luo,et al.  An improved Bayesian matting method based on image statistic characteristics , 2015, International Conference on Graphic and Image Processing.

[3]  Renaud Keriven,et al.  Trimap Segmentation for Fast and User-Friendly Alpha Matting , 2005, VLSM.

[4]  J.C. Pedraza-Ortega,et al.  EEG data collection using visual evoked, steady state visual evoked and motor image task, designed to brain computer interfaces (BCI) development , 2019, Data in brief.

[5]  Ahmed M. Elgammal,et al.  Introduction to computer vision and image understanding the special issue on video analysis , 2009, Comput. Vis. Image Underst..

[6]  David Salesin,et al.  A Bayesian approach to digital matting , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Kamel Besbes,et al.  Didactic satellite based on Android platform for space operation demonstration and development , 2018 .

[8]  D. Wang,et al.  Molecular Typing of Cryptosporidium Species Identified in Fecal Samples of Yaks (Bos Grunniens) of Qinghai Province, China , 2019, Journal of Parasitology.

[9]  Yu-an Zhang,et al.  Foreground Dectection of Yaks of Deep Color Based on Gray Images , 2018, 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).

[10]  Xiao Chen,et al.  Selective Image Matting with Scalable Variance and Model Rectification , 2017, ICPCSEE.

[11]  A. Dugdale,et al.  Effects of season and body condition on appetite, body mass and body composition in ad libitum fed pony mares. , 2011, Veterinary journal.

[12]  Mirza Omer Beg,et al.  Towards energy aware object-oriented development of android applications , 2019, Sustain. Comput. Informatics Syst..

[13]  Bir Bhanu,et al.  Editorial introduction to the special issue on "Image Understanding for Real-World Distributed Video Networks" - Computer Vision and Image Understanding Journal , 2015, Comput. Vis. Image Underst..