Monitoring video analysis system and monitoring video analysis method
A monitoring video analysis system includes a wearable camera and a back end server that receives video data files of a captured video. The back end server detects an object appearing in frames constituting the received video data file, for each frame. The back end server stores a position of the object detected for each frame, for each object, as tracking information. The back end server displays the object detected for each frame, on monitor, by using identifiable solid-line border.
1. A monitoring video analysis system comprising:
a camera; and
a server that receives a video having a plurality of frames captured by the camera,
wherein the server
receives, from a user, an input indicating an input position in a first frame of the plurality of frames constituting the received video,
detects at least one object appearing in a proximity of the indicated input position in subsequent frames, after the first frame, of the plurality of frames constituting the received video,
stores position information of the at least one object detected for each frame of the subsequent frames of the received video,
displays, on a monitor, the at least one object in a double line border in the first frame before tracking,
displays, on the monitor, the at least one object in a single line border in the subsequent frames after tracking,
in response to receiving user selection of the double line border, refrains from performing mask processing on the at least one object in all the subsequent frames, and
in response to receiving user selection of the single line border in one frame of the subsequent frames, refrains from performing the mask processing on the at least one object in the one frame of the subsequent frames in which the single line border is selected.
2. The system of claim 1 , wherein if the server does not detect an object appearing in the proximity of the indicated input position, the server displays a region in the proximity of the indicated input position in an identifiable display mode.
3. The system of claim 2 , wherein the server does not perform the mask processing in the display mode, the mask processing making an object unrecognizable.
4. A monitoring video analysis method of a monitoring video analysis system including a camera and a server that receives a video captured by the camera, the method causing the server to:
receive a video having a plurality of frames captured by the camera;
receive, from a user, an input indicating an input position in a first frame of the plurality of frames constituting the received video,
detect at least one object appearing in a proximity of the indicated input position in subsequent frames, after the first frame, of the plurality of frames constituting the received video,
store position information of the at least one object detected for each frame of the subsequent frames of the received video,
display, on a monitor, the at least one object in a double line border in the first frame before tracking,
in response to receiving user selection of the double line border, refrain from performing mask processing on the at least one object in all the subsequent frames, and
in response to receiving user selection of the single line border in one frame of the subsequent frames, refrain from performing the mask processing on the at least one object in the one frame of the subsequent frames in which the single line border is selected.
5. A monitoring video analysis system, comprising:
a camera that is used by a user; and
a server that receives a video having a plurality of frames captured by the camera,
wherein the server
receives, from a user, an input indicating an input position in a first frame of the plurality of frames constituting the received video,
detects at least one object appearing in a proximity of the indicated input position in subsequent frames, after the first frame, of the plurality of frames constituting the received video,
stores position information of the at least one object detected for each frame of the subsequent frames of the received video,
displays, on a monitor, the at least one object in a first border type in the first frame before tracking,
displays, on the monitor, the at least one object in a second border type, different from the first border type, in the subsequent frames after tracking,
in response to receiving user selection the first border type, refrains from performing mask processing on the at least one object in all the subsequent frames, and
in response to receiving user selection of the second border type in one frame of the subsequent frames, refrains from performing the mask processing on the at least one object in the one frame of the subsequent frames in which the second border type is selected.
6. The system of claim 5 , wherein if the server does not detect an object appearing in the proximity of the indicated input position, the server displays a region in the proximity of the indicated input position in an identifiable display mode.
7. The system of claim 6 , wherein the server does not perform the mask processing in the display mode, the mask processing making an object unrecognizable.