Object identification detection method based on multiresolution frame
A multi-resolution, object recognition technology, applied in the field of computer vision, can solve problems such as viewing angle changes, translation changes, illumination changes, etc., achieve good target recognition and detection results, and solve the effect of long object detection time
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0022] The present invention proposes an object recognition and detection method based on a multi-resolution framework, combining the fast robust feature descriptor (SURF) with the simple model Bag-of-word (word bag model) model and SVM (support vector model) commonly used in text classification machine) to construct a supervised learning binary object classifier based on SURF features; on the basis of the above classifiers, the SVM classifier based on SURF features is combined with the multi-resolution theory of images, and different resolutions Object detection in space. The present invention can effectively solve the problems caused by scale change, rotation change, translation change, illumination change, viewing angle change, etc. in object recognition and detection. To solve the problem that the object detection time is too long, the position of the object can be detected accurately and quickly.
[0023] The present invention is an object recognition and detection metho...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
