Target object identifying device, target object identifying method and target object identifying program
Monitoring target matching means 71 matches monitoring targets shown in video captured by one or more imaging devices, and identifies monitoring targets estimated to be the same monitoring target, as an identified monitoring target. Target object identifying means 72 identifies a desired target object from one or more identified monitoring targets captured, using imaging times of each of the one or more identified monitoring targets.
1. A target object identifying device comprising:
at least one memory configured to store instructions; and
at least one processor configured to execute the instructions to perform:
matching monitoring targets shown in a video;
determining, as a target object, a monitoring target whose time width between an earliest imaging time and a latest imaging time in a predetermined period, is greater than or equal to a long term stay determination time;
generating a determination condition for specifying the long term stay determination time based on statistics of stay time of monitoring targets not identified as the target object;
calculating, as the statistics, a stay time mean based on maximum imaging time interval or time interval of the imaging time of the monitoring targets not identified as the target object, and calculating a time which is a constant multiple of the stay time mean as the long term stay determination time; and
determining, as the target object, the monitoring target whose time width is greater than or equal to the calculated long term stay determination time by using the calculated long term stay determination time as a threshold value.
2. The target object identifying device according to claim 1 , further comprising a multiple of imaging devices capturing the video.
3. The target object identifying device according to claim 2 , wherein
the long stay determination time is calculated based on the movement speed of each monitoring target subjected to the statistics and the distance between the imaging devices.
4. The target object identifying device according to claim 1 , wherein
the at least one processor is further configured to perform:
calculating, as the statistics, a stay time mean and variance based on maximum imaging time interval or time interval of the imaging time of the monitoring targets not identified as the target object, and calculating a threshold of the time interval in which a predetermined proportion of people are determined as long stayers, as the long term stay determination time.
5. A target object identifying method comprising:
matching monitoring targets shown in a video;
determining, as a target object, a monitoring target whose time width between an earliest imaging time and a latest imaging time in a predetermined period, is greater than or equal to a long term stay determination time;
generating a determination condition for specifying the long term stay determination time based on statistics of stay time of monitoring targets not identified as the target object;
calculating, as the statistics, a stay time mean based on maximum imaging time interval or time interval of the imaging time of the monitoring targets not identified as the target object, and calculating a time which is a constant multiple of the stay time mean as the long term stay determination time; and
determining, as the target object, the monitoring target whose time width is greater than or equal to the calculated long term stay determination time by using the calculated long term stay determination time as a threshold value.
6. The target object identifying method according to claim 5 , comprising
matching the monitoring targets shown in the video, the video captured by a multiple of imaging devices.
7. The target object identifying method according to claim 6 ,
wherein the long stay determination time is calculated based on the movement speed of each monitoring target subjected to the statistics and the distance between the imaging devices.
8. A non-transitory recording medium storing a computer program, the computer program causing a computer to perform:
matching monitoring targets shown in a video;
determining, as a target object, a monitoring target whose time width between an earliest imaging time and a latest imaging time in a predetermined period, is greater than or equal to a long term stay determination time;
generating a determination condition for specifying the long term stay determination time based on statistics of stay time of monitoring targets not identified as the target object;
calculating, as the statistics, a stay time mean based on maximum imaging time interval or time interval of the imaging time of the monitoring targets not identified as the target object, and calculating a time which is a constant multiple of the stay time mean as the long term stay determination time; and
determining, as the target object, the monitoring target whose time width is greater than or equal to the calculated long term stay determination time by using the calculated long term stay determination time as a threshold value.
9. The non-transitory recording medium according to claim 8 , wherein the computer program causes the computer to perform:
controlling a multiple of imaging devices to capture the video.
10. The non-transitory recording medium according to claim 9 , wherein
the long stay determination time is calculated based on the movement speed of each monitoring target subjected to the statistics and the distance between the imaging devices.