Automatic animal detection from Kinect sensed images for livestock monitoring and assessment

Zhu, Qiming and Ren, Jinchang and Barclay, David and McCormack, Samuel and Thomson, Willie; (2015) Automatic animal detection from Kinect sensed images for livestock monitoring and assessment. In: 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM). IEEE, GBR, pp. 1154-1157. ISBN 9781509001545

Full text not available in this repository.Request a copy from the Strathclyde author

Abstract

In this paper, Kinect based sensors are used to enable automatic animal detection for monitoring and assessment the growth of livestock. Benefitted from the fast developing 3-D machine vision devices and techniques, it is liable to detect the object using the point cloud data. In the present work, a Kinect sensor is installed on the roof of the pig pen to obtain the 3-D data. After thresholding the depth of each pixel, a depth image is generated where the objects within the depth range are extracted. Several shape based constraints are then applied to refine the detected object regions for accurate estimation of the size and weights for further process. Experimental results have validated the efficacy of the proposed approach.

ORCID iDs

Zhu, Qiming ORCID logoORCID: https://orcid.org/0000-0003-0088-4822, Ren, Jinchang ORCID logoORCID: https://orcid.org/0000-0001-6116-3194, Barclay, David, McCormack, Samuel ORCID logoORCID: https://orcid.org/0000-0002-2059-0672 and Thomson, Willie;