A method for associatively querying the specific content of infrared video images
A technology related to query and video images, applied in special data processing applications, instruments, electrical digital data processing, etc., to achieve the effects of improving control and access, improving retrieval speed, and simple feature extraction methods
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2018-08-10
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to an image and video processing method in the fields of video identification and image retrieval, in particular to technologies applied to intelligent video monitoring technology and related fields of video retrieval. Background technique
[0002] Because infrared imaging has the characteristics of passive work, strong anti-interference ability, strong target recognition ability, and all-weather work, it has been widely used in reconnaissance and surveillance in military and civilian fields. Infrared reconnaissance and surveillance equipment generates large amounts of image and video data. Many useful information in the data can only be obtained through the process of removing the false and saving the true, and removing the dross and extracting the essence. How to quickly find the content you care about in these data is an urgent problem to be solved. In order to find video clips of specific content in the infrared video of mass...
Examples
Embodiment Construction
[0019] refer to figure 1 In the embodiments described below, according to the present invention, the process flow of the method for associating and querying specific content of infrared video images is as follows:
[0020] Step S1, the shot boundary detection module uses a sliding window to intercept the infrared video segment, calculates the two-dimensional histogram frame difference between adjacent frame images and the sliding window threshold, compares the frame difference with the sliding window threshold, and determines the infrared video Shot boundary, identify the shot boundary, and establish a shot boundary index;
[0021] Step S2, the key frame extraction module calculates the SCCR value of the content change rate of each video shot and the corresponding judgment threshold, uses the video shot content change rate identification and judgment method to extract the key frame image in the video shot, identifies the key frame image, and establishes the key frame image in...