Version 1
: Received: 20 December 2021 / Approved: 22 December 2021 / Online: 22 December 2021 (10:33:21 CET)
Version 2
: Received: 9 March 2022 / Approved: 9 March 2022 / Online: 9 March 2022 (10:02:00 CET)
How to cite:
Wang, W.; Zhang, Y.; He, J.; Chen, Z.; Li, D.; Ma, C.; Ba, Y.; Baima, Q.; Li, X.; Song, R. Research on Yak Body Ruler and Weight Measurement Method Based on Deep Learning and Binocular Vision. Preprints2021, 2021120349 (doi: 10.20944/preprints202112.0349.v2).
Wang, W.; Zhang, Y.; He, J.; Chen, Z.; Li, D.; Ma, C.; Ba, Y.; Baima, Q.; Li, X.; Song, R. Research on Yak Body Ruler and Weight Measurement Method Based on Deep Learning and Binocular Vision. Preprints 2021, 2021120349 (doi: 10.20944/preprints202112.0349.v2).
Cite as:
Wang, W.; Zhang, Y.; He, J.; Chen, Z.; Li, D.; Ma, C.; Ba, Y.; Baima, Q.; Li, X.; Song, R. Research on Yak Body Ruler and Weight Measurement Method Based on Deep Learning and Binocular Vision. Preprints2021, 2021120349 (doi: 10.20944/preprints202112.0349.v2).
Wang, W.; Zhang, Y.; He, J.; Chen, Z.; Li, D.; Ma, C.; Ba, Y.; Baima, Q.; Li, X.; Song, R. Research on Yak Body Ruler and Weight Measurement Method Based on Deep Learning and Binocular Vision. Preprints 2021, 2021120349 (doi: 10.20944/preprints202112.0349.v2).
Abstract
In order to solve the labor-intensive and time-consuming problem in the process of measuring yak body ruler and weight in yak breeding industry in Qinghai Province, a non-contact method for measuring yak body ruler and weight was proposed in this experiment, and key technologies based on semantic segmentation, binocular ranging and neural network algorithm were studied to boost the development of yak breeding industry in Qinghai Province. Main conclusions: (1) Study yak foreground image extraction, and implement yak foreground image extraction model based on U-net algorithm; select 2263 yak images for experiment, and verify that the accuracy of the model in yak image extraction is over 97%. (2) Develop an algorithm for estimating yak body ruler based on binocular vision, and use the extraction algorithm of yak body ruler related measurement points combined with depth image to estimate yak body ruler. The final test shows that the average estimation error of body height and body oblique length is 2.6%, and the average estimation error of chest depth is 5.94%. (3) Study the yak weight prediction model; select the body height, body oblique length and chest depth obtained by binocular vision to estimate the yak weight; use two algorithms to establish the yak weight prediction model, and verify that the average estimation error of the model for yak weight is 10.7% and 13.01% respectively.
Keywords
yak; semantic segmentation; binocular vision; body size; weight stimation
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Commenter: WenZhi Wang
Commenter's Conflict of Interests: Author
(2) Revise the author order of the paper
(3) Upload images in the paper