Visible light and infrared detection result integration based moving target detection method
A technology for infrared detection and moving targets, which is applied in image data processing, instruments, calculations, etc., and can solve problems such as poor detection effect and poor target detection effect.
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2014-10-29
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention relates to a moving target detection method, in particular to a moving target detection method based on fusion of visible light and infrared detection results. Background technique
[0002] Moving target detection is the basic work of video surveillance. Its main task is to segment and extract the region of motion change from the background image in the video sequence for subsequent target tracking and behavior analysis. The target detection method can effectively overcome the multiple influences of illumination changes, background motion, camera shake, etc., and accurately extract moving targets, which is of great significance. Most of the existing methods are studied on single-source sensor imaging, and the main detection methods are pixel-based detection methods and feature-based detection methods.
[0003] The document "ViBe: a powerful random technique to estimate the background in video sequence. ICASSP, 2009, 4:945-948" discloses ...
Examples
Embodiment Construction
[0045] The specific steps of the moving target detection method based on the fusion of visible light and infrared detection results of the present invention are as follows:
[0046] 1. Visible light image foreground detection.
[0047] (a) Model initialization and pixel classification.
[0048] For the first frame image of visible light, N pixel values are randomly selected from the eight domains of pixel points (x, y), and the background model {B n ,n=12,...,N} corresponds to the position point.
[0049] Pixel matching starts from the second frame image. At time t, judge the current frame I t Pixel i(x,y) at (x,y) is connected to background sample B n The pixel b(x,y) of the matching state:
[0050]
[0051] Among them, dis() represents the Euclidean distance between the current pixel and the background pixel, D d =20 represents the distance threshold.
[0052] When the distance threshold D is satisfied d times less than T c When (T c = 2), mark this pixel as for...