Integer programming based crowd density estimation method
An integer programming, crowd density technology, applied in computing, computer parts, instruments, etc., can solve problems such as methods and target counts, etc., to achieve good robustness and improve detection accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0024] specific implementation plan
[0025] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the present invention will be further described below through specific embodiments and accompanying drawings.
[0026] The invention expresses the target counting in crowd density estimation as a regression problem, and the target positioning as an integer programming problem. First, train a codebook with K passwords through the K-means method, use the learned codebook to quantify local features, and normalize it to a vector x k ∈R K . Secondly, the corresponding relationship between the feature vector of each pixel and its density value is established, and the optimal density map is obtained by minimizing the real density value and the estimated density value. Finally, according to the known density map, the method of integer programming is used to solve the position of each target.
[0027] Aiming at the two pr...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 