Monitoring device

Abstract

The invention provides a monitoring device, which is applied for effective monitor by determining the delay population which is significant for safety management and security. The monitoring device comprises an image acquiring unit (1) for acquiring images adjacent to a monitoring area, a delay detecting unit having a background making part (2), a long-term change extracting part (3), a short-term change extracting part (4) and a short-term change accumulating part (5); a track extracting part (6) for extracting motion track from the short-term changes in the time sequence or from the time sequence storage information extracted from the short-term changes; a population judging part (7) for judging whether the number of detected persons inside the monitoring area is one or more than more according to the delay and motion track generating time and generating places; and a delay warning part (8) for warning after a determination that one person is delayed inside the monitoring area and thus effectively monitoring the person.

Description

technical field [0001] The present invention relates to a surveillance device that acquires images within a surveillance area using a surveillance camera or the like, and notifies a monitor or the like after processing the acquired images. Background technique [0002] In order to reduce the burden on the monitors who perform safety checks by observing the surveillance cameras with the naked eye, image recognition is performed on the captured images to detect abnormal behaviors such as behaviors of people and dangerous behaviors that may cause accidents at the time of the accident, and notify the monitors Alarm monitoring systems are gaining popularity. [0003] The abnormal behavior in which the person in the above-mentioned abnormal behavior has been staying in a specific place, for example, for a surveillance system for the purpose of safety management, may mean that the person is in a state of immobility due to an accident or injury, while for a surveillance system for t...

AI Technical Summary

Problems solved by technology

For example, if there is one person on the entrance and exit platform of an escalator, and the shadow of this one person is very long, the area of ​​the background difference becomes larger due to the influence of the shadow. In fact, the passenger is free for one person, but it may be misunderstood. Judged as crowded

Also, when the shadows of structures such as handrails are long, even though there is no passenger on the entrance / exit platform, the area of ​​the background difference becomes larger due to the shadows of structures such as handrails. In this case, actually Not even one passenger is free, but it may be misjudged as crowded

Therefore, in the technique disclosed in Patent Document 1, it is impossible to accurately determine whether the number of people in the monitoring area is 0, 1, or 2 or more.

[0018] In addition, when using another criterion disclosed in Patent Document 1, that is, the criterion that the larger the area of ​​the difference between frames is, the higher the degree of congestion is, for example, when a passenger falls and tries to get up, the passenger may The area of ​​the difference between the frames becomes larger due to the movement of the frame, and it may happen that there is actually only one passenger idle, but it is misjudged as a crowded situation

Also, in contrast to this, in the case where many passengers cannot move due to extreme crowding, the area of ​​the difference between frames becomes narrow because the movements of the passengers are small, and it is actually crowded because there are many people, but there is still May be falsely identified as idle

Therefore, when the technology disclosed in Patent Document 1 is applied to the estimation of the number of people, since it is impossible to distinguish between a situation with few passengers and a situation with many passengers, it is impossible to accurately determine whether the number of people in the monitoring area is 0, 1, or 2. above

[0019] Based on the above reasons, it is difficult to correctly judge whether the number of people in the surveillance area is 0, 1, or more than 2 people using the technology of Patent Document 1

[0020] On the other hand, the above-mentioned Non-Patent Documents 1 and 2 are very good technologies such as person recognition technology for distinguishing the movement of people from the action of the escalator, but they do not distinguish between 0 people, 1 person, or 2 or more people This classification assumes that the number of people in the surveillance area is estimated, and it does not take into account the number of people in the surveillance area to reduce the alarm when there are no persons in the background image, etc.

Images