Monitoring video analysis system and monitoring video analysis method
A monitoring video analysis system includes a wearable camera that is held or possessed by a user, and a back end server that receives a captured video. The wearable camera records a captured video by capturing a video of a scene for each ten minutes. The back end server determines a face of a person appearing in n (n is an integer of two or more) captured videos by using a plurality of captured videos of the scene for each 10 minutes, and displays a thumbnail list UI in which the determined face of the person is registered, on a monitor.
1. A monitoring video analysis system comprising;
a wearable camera, which, in operation, is held or possessed by a user,
wherein the wearable camera, in operation, generates and records a plurality of video files including captured video of a scene, each of the video files being captured during a respective time period among a plurality of predetermined time periods,
wherein each of the predetermined time periods has a same duration, and
wherein the wearable camera, in operation, continuously generates and records the video files including the captured video of the scene such that there is no blank time zone in which the video of the scene is not captured from a beginning of a first one of the time periods to an end of a last one of the time periods; and
a server, which, in operation, receives the video files recorded by the wearable camera,
wherein the server, in operation, determines one or more objects appearing in at least n of the video files, generates a list including the one or more objects, causes the list including the one or more objects to be displayed on a monitor and causes the at least n of the video files to be continuously reproduced on the monitor, and
wherein n is an integer of two or more.
2. The system of claim 1 ,
wherein the server, in operation, excludes an object which is selected from the one or more objects included in the list by an operation of the user, from targets of processing of acquiring a position of the object in a frame image.
3. The system of claim 1 ,
wherein the server, in operation, displays on the monitor a thumbnail image of each of the one or more objects included in the list.
4. The system of claim 1 ,
wherein the server, in operation, holds as metadata coordinate values of the one or more objects in each frame image of a plurality of frame images constituting the captured video.
5. The system of claim 1 ,
wherein the at least one of the one or more objects is a face of a person.
6. A monitoring video analysis method utilizing a server and a wearable camera that is held or possessed by a user, the method comprising:
generating and recording a plurality of video files including captured video of a scene, each of the video files being captured during a respective time period among a plurality of predetermined time periods by the wearable camera,
wherein each of the predetermined time periods has a same duration, and
wherein the generating and recording is performed such that there is no blank time zone in which the video of the scene is not captured from a beginning of a first one of the time periods to an end of a last one of the time periods;
receiving, by the server, the video files recorded by the wearable camera;
determining, by the server, one or more objects appearing in at least n of the video files wherein n is an integer of two or more;
generating, by the server, a list including the one or more objects;
displaying on a monitor the list including the one or more objects;
continuously reproducing on the monitor the at least n of the video files.
7. The monitoring video analysis method of claim 6 , further comprising:
receiving by the server a user selection of an object in the list including the one or more objects;
acquiring a position in a frame image of each of the one or more objects other than the object selected by the user selection.
8. The monitoring video analysis method of claim 7 , further comprising displaying character information regarding the one or more objects.
9. The monitoring video analysis system of claim 1 , wherein the server, in operation, receives a user selection of an object in the list including the one or more objects, and acquires a position in a frame image of each of the one or more objects other than the object selected by the user selection.
10. The monitoring video analysis system of claim 9 , wherein the server, in operation, causes character information regarding the one or more objects to be displayed.
11. The monitoring video analysis method of claim 6 , wherein n is greater than or equal to three.
12. The monitoring video analysis method of claim 6 , wherein each of the predetermined time periods overlaps another one of the predetermined time periods.
13. The monitoring video analysis system of claim 1 , wherein n is greater than or equal to three.
14. The monitoring video analysis system of claim 1 , wherein each of the predetermined time periods overlaps another one of the predetermined time periods.