Abnormal face detecting method for embedded digital video recorder (DVR) system

Abstract

The invention belongs to the technical field of video frequency image analysis and particularly discloses an abnormal face detecting method for embedded DVR system. In the invention, face detection and background identification technology is applied in a digital signal processor (DSP) processing step of the embedded DVR so as to determine that whether people exist in a current image and whether facial features are clear and not sheltered, and if abnormal facial features are detected, an alarm signal is sent to remind related personnel to pay more attention to the current conditions. When the method of the invention is adopted, the technology of detecting whether normal faces exit in a scene is achieved simply by a mode of image processing, and alarm effect that lawbreakers are prevented from committing a crime at an ATM machine of self-service banking by shielding faces is achieved when the method is used in combination with the embedded DVR.

Description

technical field [0001] The invention belongs to the technical field of video image analysis, in particular to an abnormal human face detection method used in an embedded DVR system. Background technique [0002] At present, DVR (hard disk video recorder or digital video recorder) has replaced analog video recorder and is used in various fields. DVR is usually composed of VI (video acquisition), DSP (digital signal processing), VS (video storage) and VO (video output), etc. Partial composition. The traditional DVR only completes the work of video compression and storage in the DSP part. [0003] Intelligence, networking and integration are the latest development direction in the field of DVR. A big application in intelligence is face detection and recognition. Face detection technology emerged in the 1960s and 1970s. After decades of development, a variety of technologies have been used. From the initial template matching technology to the current various methods, both acc...

AI Technical Summary

Problems solved by technology

However, the current face detection technology cannot solve this problem.

[0005] First of all, the problem to be solved is when to start the detection, because only when someone does the operation, that is, when there is someone in front of the camera, the detection can start, and if there is no one, the detection cannot be carried out; secondly, it takes a period of detection to draw a conclusion, It cannot be solved only by one frame of image, because the current face detection limit is still relatively high, and generally only positive face detection can be performed, but the actual situation is that there is no guarantee that a positive face image can always be obtained, so It must be detected for a period of time before a conclusion can be drawn; again, how to solve the problem of multiple detections by the same person or one detection by multiple people, because different people operate in front of the ATM for different lengths of time, one person leaves after another person leaves Come over, it should be regarded as two inspections, so as to achieve the purpose of not missing inspections

[0006] Based on the above reasons, the current face detection cannot meet the special application mentioned above, and can only be used for simple applications with strict restrictions.

Images