Behavior-induced health condition monitoring of caged chickens using binocular vision

The interface of the binocular vision system. [Display omitted] •A real-time behaviors information detection method using binocular vison system.•An improved active contour model to segment images of caged chickens accurately.•Relationship-exploration between behaviors information and health conditi...

Full description

Saved in:
Bibliographic Details
Published in:Computers and electronics in agriculture 2019-01, Vol.156, p.254-262
Main Authors: Xiao, Linfang, Ding, Keyan, Gao, Yingwang, Rao, Xiuqin
Format: Article
Language:English
Subjects:
Active contour model
Algorithms
Behavior information
Binocular vision
Caged chicken
Chickens
Color
Condition monitoring
Contours
Data processing
Health
Human behavior
Image reconstruction
Image segmentation
Morphology
Shape
Three dimensional bodies
Three dimensional motion
Vision systems
Weight
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The interface of the binocular vision system. [Display omitted] •A real-time behaviors information detection method using binocular vison system.•An improved active contour model to segment images of caged chickens accurately.•Relationship-exploration between behaviors information and health condition of chickens. The behaviors of chicken can reflect its health condition. However, the existing behaviors information acquisition directly depending on human observation is tedious, laborious and inaccurate. This paper aims to present an automatic behaviors information monitoring method for caged chicken using the binocular vision system. First, a 2-Dimension image segmentation algorithm based on active contour model was improved to accurately segment the chicken head and body. Specifically, ‘S’ weight of HSV color model and ‘a’ weight of Lab color model were used as the fundamental images for chicken body and head segmentation, respectively. Binary operation and morphology processing were utilized to obtain the rough segmentation results, which were regarded as the initial contour of the active contour model. In order to eliminate the interference of cage, we improved the active contour model by integrating with gray morphology and Gaussian filter operations. Second, the 3D image reconstruction was carried out using pairs of rectified images obtained from the binocular cameras. Thus, 3D contours of chicken body and head can be extracted from the above 2D segmentation and 3D reconstruction results. Third, motion parameters derived from eating and drinking behaviors of chicken were computed from the 3D space. Finally, the relationship between behaviors information and health condition was explored. The experimental results showed that the proposed method can monitor the health condition of the caged chicken in real-time.
ISSN:0168-1699
1872-7107
DOI:10.1016/j.compag.2018.11.022