Moving object detection method and device based on space-time background model
A moving target and background model technology, applied in the field of intelligent video surveillance, can solve the problems of multiple false detections and the background update speed is not fast enough, and achieve the effect of improving the detection rate and the accuracy rate.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0033] Embodiment 1, a moving target detection method based on a spatiotemporal background model, refer to the attachment figure 1 .
[0034] The moving target detection method of the present invention specifically includes the following steps:
[0035] Step 1: Perform background modeling according to the collected 3000 frames of images to obtain a temporal background model;
[0036] ① Converted to a background image, assuming that the gray value of the pixel at point (x, y) in the sequence is: Y = {y 1 (x,y),y 2 (x,y),...,y 3000 (x,y)};
[0037] ②Calculate these sampling values, namely the mean value μ and standard deviation δ of the aforementioned pixel gray values:
[0038] μ = X i = 1 3000 y i
[0039] δ = 1 3000 X i = 1 3000 ( y i - μ ) 2
[0040] I in the formula represents the i-th sampling point,
[0041] If δ <20, use the Gaussian model as the temporal background model of the pixel. If δ≥20, use K-mea...
Example Embodiment
[0057] Embodiment 2, a moving target detection device based on a spatiotemporal background model, refer to the attachment figure 2 .
[0058] The moving target detection device of the present invention includes an image acquisition module 1, a temporal background modeling module 2, a moving target detection module 3, a spatial background modeling module 4, a moving target confirmation module 5, and a background model update module 6. The image acquisition module 1 is used to collect monitoring images, the temporal background modeling modeling module 2 is used to establish the temporal background model in step 1, and the moving target detection module 3 is used to extract the initial movement from the temporal background model in step 2. Target, the spatial background modeling module 4 is used to calculate the corresponding background area of each initial target and establish a corresponding spatial background model, and the moving target confirmation module 5 is used to place ...
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