Crowd scale statistical method based on color and HAAR feature fusion
A technology of feature fusion and statistical methods, which is applied to the counting, calculation, and counting of randomly distributed items, and can solve problems such as single overlap, occlusion, inability to ensure single feature acquisition, missed detection of people, false detection, etc. To achieve the effect of reducing the error
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0088] A method for population size statistics based on the fusion of color and HAAR features includes the following steps:
[0089] Step 1 data preprocessing
[0090] For different scenarios, the following processing methods can generally be used: histogram equalization, gray scale stretching, homomorphic filtering, etc. The invention adopts gray scale stretching to enhance contrast.
[0091] Step 1.1 Collect a collection of video image sequences, assuming that N samples are selected for sampling;
[0092] Step 1.2 Perform gray-scale stretching on each image pixel: the size of each image pixel is x, and the upper and lower thresholds are x respectively 1 , X 2
[0093] when x x 1 : f ( x ) = y 1 x 1 * x
[0094] when x 1 ≤ x ≤ x 2 : f ( x ) = y 2 - y 1 x 2 - x 1 * ( x - x 1 ) + y 1
[0095] when x > x 2 : f ( x ) = 255...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap