Pedestrian detection model training method based on AdaBoost classifier
A pedestrian detection and model training technology, applied in the field of pedestrian detection, can solve the problems of not fully mining the effect, only focusing on feature design and classifier selection, ignoring the reasonable use of training sample information, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0038] Such as figure 1 As shown, the present embodiment provides a pedestrian detection model training method based on AdaBoost classifier:
[0039] 1. Determination of the initial training set of positive and negative samples:
[0040] First, select an appropriate standard dataset for pedestrian detection, such as the INRIA dataset, which includes positive images containing pedestrians and negative images that do not contain pedestrians. According to the annotation file of the data set, the 64*128 pedestrian image is obtained from the block diagram of the positive sample image and copied after mirror symmetry processing, and the extracted image integral channel feature [2] proposed in literature 3 (described in detail in point 4 later) ), that is, after reverse symmetric replication of all positive sample pedestrian images, they are added to the positive sample training set. The positive sample training set is formed in the above way Among them, N=2416, in the negative s...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com