Abstract
The background models are crucially important for the object extraction for moving objects detection in a video. The Gaussian mixture model (GMM) is one of popular methods in the background models. Gaussian mixture model which applied to the pig target detection has some shortcomings such as low efficiency of algorithm, misjudgment points and ghosts. This study proposed an improved algorithm based on adaptive Gaussian mixture model, to overcome the deficiencies of the traditional Gaussian mixture model in pig object detection. Based on Gaussian mixture background model, this paper introduced two new parameters of video frames m and T0. The Gaussian distribution was scanned once every m frames, the excessive Gaussian distribution was deleted to improve the convergence speed of the model. Meanwhile, using different learning rates to suppress ghosts, a higher decreasing learning rate was adopted to accelerate the background modeling before T0, the background model would become stable as the time continued and a smaller learning rate could be used. In order to maintain a stable background and reduce noise interference, a fixed learning rate after T0 was used. Results of experiments indicated that this algorithm could quickly build the initial background model, detect the moving target pigs, and extract the complete contours of the target pigs’. The algorithm is characterized by good robustness and adaptability. Keywords: object detection, individual pig, Gaussian mixture mode, background model, contours, behavioral trait DOI: 10.25165/j.ijabe.20171005.3136 Citation: Li Y Y, Sun L Q, Zou Y B, Li Y. Individual pig object detection algorithm based on Gaussian mixture model. Int J Agric & Biol Eng, 2017; 10(5): 186–193.
Highlights
The key elements of the natural pig behavior traits include feed and water intake frequency, and excretion frequency
In order to increase the modeling convergence speed, this paper presents an improved algorithm using adaptive method to adjust the number of Gaussian distribution models, and using the adaptive learning rate to eliminate or reduce misjudgment points and ghosts
In order to accelerate the elimination of misjudgment points and ghosts, this paper proposes an adaptive learning rate strategy: with setting a threshold value of the frame number T0, different learning rates are adopted in updating for the frames before T0 and it is kept non-variant after frames T0, as shown in Equation (11): α
Summary
2017 Li Y Y, et al Individual pig object detection algorithm based on Gaussian mixture model Vol 10 No. 187 a robust estimation for small sample training sets and determines the prior distribution of mean vector and covariance matrix to solve the parameter estimation problem. It uses pixel space variation mix ratio to improve the classification accuracy rate. In order to increase the modeling convergence speed, this paper presents an improved algorithm using adaptive method to adjust the number of Gaussian distribution models, and using the adaptive learning rate to eliminate or reduce misjudgment points and ghosts
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have