Video surveillance system, video processing apparatus, video processing method, and video processing program
AssigneeNEC Corporation
InventorsDaichi Hisada, Takeshi Moribe
Life of this patent
Estimating the term…
Abstract
A video processing apparatus includes a video analyzer that analyzes video data captured by a surveillance camera, detects an event belonging to a specific category, and outputs a detection result, a display controller that displays, together with a video of the video data, a category setting screen for setting a category of an event included in the video, and a learning data accumulator that accumulates, as learning data together with the video data, category information set in accordance with an operation by an operator to the category setting screen. The video analyzer performs learning processing by using the learning data accumulated in the learning data accumulator.
Claims13
A video processing system comprising:
- at least one memory storing a computer program;
- and
- at least one processor configured to execute the computer program to perform:
- detecting, from a video, a first region corresponding to a predetermined category by analyzing video data, the first region indicating an object;
- by looking up a camera event table in which pieces of category information of events that are highly likely to be included in videos captured by a camera is accumulated, displaying some category information candidates predicted in advance in a category information selection screen in which an operator inputs category information necessary for generating a new category associated with the video data, the new category being different from the predetermined category;
- generating the new category corresponding to a part of the object;
- and
- accumulating, as learning data, the category information input by the operator together with the video data,
- wherein the at least one processor is further configured to execute the computer program to perform:
- calculating a point given to the operator in accordance with a learning video count and a new category count, the learning video count indicating a number of learning videos to which the operator has selected a category and the new category count indicating a number categories generated as new categories;
- and
- saving the calculated point in association with the learning video count, the new category count, and an operator ID corresponding to the operator.
A video processing method for analyzing at least one video, the at least one video including an object, the video processing method comprising:
- detecting, from a video, a first region corresponding to a predetermined category by analyzing video data, the first region indicating an object;
- by looking up a camera event table in which pieces of category information of events that are highly likely to be included in videos captured by a camera is accumulated, displaying some category information candidates predicted in advance in a category information selection screen in which an operator inputs category information necessary for generating a new category associated with the video data, the new category being different from the predetermined category;
- generating the new category corresponding to a part of the object;
- and
- accumulating, as learning data, the category information input by the operator together with the video data;
- calculating a point given to the operator in accordance with a learning video count and a new category count, the learning video count indicating a number of learning videos to which the operator has selected a category and the new category count indicating a number categories generated as new categories;
- and
- saving the calculated point in association with the learning video count, the new category count, and an operator ID corresponding to the operator.
A non-transitory recording medium storing a computer program for analyzing at least one video, the at least one video including an object, the computer program executable by a computer to perform:
- detecting, from a video, a first region corresponding to a predetermined category by analyzing video data, the first region indicating an object;
- by looking up a camera event table in which pieces of category information of events that are highly likely to be included in videos captured by a camera is accumulated, displaying some category information candidates predicted in advance in a category information selection screen in which an operator inputs category information necessary for generating a new category associated with the video data, the new category being different from the predetermined category;
- generating the new category corresponding to a part of the object;
- and
- accumulating, as learning data, the category information input by the operator together with the video data;
- calculating a point given to the operator in accordance with a learning video count and a new category count, the learning video count indicating a number of learning videos to which the operator has selected a category and the new category count indicating a number categories generated as new categories;
- and
- saving the calculated point in association with the learning video count, the new category count, and an operator ID corresponding to the operator.
Dependencies are inferred from the claim text.