Method for indentifying pig walking postures based on ellipse fitting
A technology of ellipse fitting and recognition method, which is applied in character and pattern recognition, instruments, computer parts, etc., and can solve problems affecting the health of staff, inaccurate information, omissions, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0018] Design scheme flow chart of the present invention is as figure 1 shown. Specific steps are as follows.
[0019] 1. Use the image acquisition system to collect images of the pigs in the pigsty.
[0020] 2. Use the background subtraction method to detect the target pig in the image, and extract the outline of the target pig; use the morphological algorithm to process the extracted outline, respectively remove the spines in the pig body and fill the holes in the image to obtain a complete image pig body silhouette.
[0021] 3. Use the improved random ellipse detection algorithm to fit the ellipse of the pig body contour in the image and establish the coordinate system.
[0022] (1) Improved random ellipse detection algorithm
[0023] The existing randomized ellipse detection (Randomized Ellipse Detection, RED) algorithm has the defect of large error in pig posture recognition. This paper makes the following improvements to the RED algorithm: 1) Select the adaptive thre...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 