Video image fuzzy anomaly detection method based on machine learning
A video image and machine learning technology, applied in the field of intelligent transportation, can solve the problems of aging equipment, easy omission or negligence, time-consuming and labor-intensive, etc., and achieve the effect of strong robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0013] refer to figure 1 and figure 2 , the present embodiment adopts the following technical solutions:
[0014] 1. First, the high-definition video color image is converted to a grayscale image. When converted to grayscale, the grayscale value is the average of the pixel values of the three channels to balance the requirements of each channel for detection accuracy.
[0015] 2. In video surveillance video images, clear images account for the majority and blurred images account for a minority, so 6,000 blurred images are collected as positive samples, and 3,000 clear images are used as negative samples. and non-blurred artificial classification into two categories, compute gradient histogram features for each image. The traditional histogram of gradient (HOG) algorithm is used to estimate the motion of pedestrians and achieves better recognition results. The HOG algorithm is a descriptor that is sensitive to changes in the orientation of the image space. By using the gr...
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