Remnant quick detecting method based on history pixel set matching degree
A detection method and a technique for remnants, applied in the field of video surveillance, can solve problems such as difficult re-detection, poor adaptability to complex scenes, and slow detection speed
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2013-08-28
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention belongs to the technical field of video surveillance, and in particular relates to a method for quickly detecting remnants based on the matching degree of historical pixel sets. Background technique
[0002] As people pay more attention to the safety of public places, more and more public places such as squares, railway stations, and airports have installed video surveillance systems. However, due to the large number of cameras used in video surveillance systems, it is difficult for monitoring personnel to Suspicious behaviors are discovered at the first time, causing incidents that endanger public safety to occur from time to time. Therefore, the intelligent monitoring system came into being and became a research hotspot in recent years. Among them, the remnant object detection is an important part of the intelligent monitoring system, which is used to automatically monitor whether there are suspicious objects in the scene. Remains det...
Examples
Embodiment Construction
[0049] Such as figure 1 A method for quickly detecting remnants based on the matching degree of historical pixel sets is shown, which is characterized in that the method includes the following steps:
[0050] Step 1. Video information reception: using a data processor to receive the video information to be processed collected by the video acquisition device, the data processor is connected to the video acquisition device; the video information to be processed includes a plurality of image data frame, and the plurality of image data frames are arranged from front to back according to the time sequence received by the data processor.
[0051] Step 2, establishment of an adaptive background model: use the data processor to process the first N image data frames in the video information to be processed in step 1 from front to back, and establish an adaptive background model for moving object detection. A background model; the adaptive background model is a codebook model, and N is...