Personnel counting method, system and apparatus based on face detection and identification technology

Abstract

The invention provides a personnel counting method, system and apparatus based on face detection and identification technology. The method comprises the steps of segmenting N face images out in a frame video and processing the face images into face data which is stored as a new face data list; comparing each line of new face data with a history face data list in a line-by-line manner, and judging whether the similarity value is larger than a threshold value; if the similarity value is smaller than the threshold value, adding the new face data to the history face data list and adding 1 to the total number of the personnel; then continuously comparing the next line until the comparison of the whole new face data list is finished; and removing face data, surpassing effective time limit Tc, in the history face data list, and then going on to process the next video frame until the whole video is processed. High-precision personnel counting is realized conveniently and rapidly with low cost, and passing speed of the personnel is not influenced, so that the personnel counting method, system and apparatus are especially suitable for superlarge-human-traffic occasions, such as markets, railway stations, airport passageways and the like.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and in particular relates to a people counting method, system and device based on face detection and recognition technology. Background technique [0002] At present, there are many methods used to realize people counting, some of which use infrared and piezoelectric technology, and need to install specific sensing devices, such as infrared transceivers, piezoelectric sensors, etc., the system deployment is inconvenient, the cost is high, and the sensing device is easy Damage, difficult maintenance, and low accuracy; there are also access control devices installed at checkpoints, which can only be passed by swiping cards or buttons. This type of solution has high counting accuracy, but the implementation cost is very high, and the speed of personnel is limited. [0003] On the other hand, the face detection technology is quite mature, and it can effectively detect sideways faces. At the...

AI Technical Summary

Problems solved by technology

[0004] At present, there is a method of counting people using face detection, but when face detection is performed on a video, the same person may be detected dozens or hundreds of times within a period of time, resulting in inaccurate counting; there are also people counting methods It is simply by increasing the frame-taking interval, such as taking one frame in 3 seconds for face detection, it is possible to lose the person who appears in the shot instantly

can not achieve good results

Images