Information processing apparatus, control method, and program
An information processing apparatus ( 2000 ) includes a first analyzing unit ( 2020 ), a second analyzing unit ( 2040 ), and an estimating unit ( 2060 ). The first analyzing unit ( 2020 ) calculates a flow of a crowd in a capturing range of a fixed camera ( 10 ) using a first surveillance image ( 12 ). The second analyzing unit ( 2040 ) calculates a distribution of an attribute of objects in a capturing range of a moving camera ( 20 ) using a second surveillance image ( 22 ). The estimating unit ( 2060 ) estimates an attribute distribution for a range that is not included in the capturing range of the moving camera ( 20 ).
1. An information processing apparatus comprising at least one processor configured to:
calculate a flow of a collection of objects in a capturing range of a fixed camera using a first surveillance image, the first surveillance image being generated by the fixed camera, the fixed camera being a camera a position of which is fixed;
calculate a distribution of an attribute of objects in a capturing range of a moving camera using a second surveillance image, the second surveillance image being generated by the moving camera, the moving camera being a camera a position of which is not fixed; and
estimate the distribution of the attribute of the objects for an estimation range including a range not included in the capturing range of the moving camera based on the distribution of the attribute of the objects in the capturing range of the moving camera and the flow of the collection of objects in the capturing range of the fixed camera.
2. The information processing apparatus according to claim 1 ,
wherein the at least one processor further configured to estimate the distribution of the attribute of the objects in the estimation range by moving the distribution of the attribute of the objects in the capturing range of the moving camera based on the flow of the collection of the objects in the capturing range of the fixed camera.
3. The information processing apparatus according to claim 2 ,
wherein in a case where the capturing ranges of the fixed camera and the moving camera do not overlap each other, the at least one processor further configured to estimate a flow of a collection of objects in the capturing range of the moving camera based on the flow of the collection of the objects in the capturing range of the fixed camera, and estimate the distribution of the attribute of the objects in the estimation range by moving the distribution of the attribute of the objects in the capturing range of the moving camera based on the estimated flow of the collection of the objects.
4. The information processing apparatus according to claim 2 ,
wherein the at least one processor further configured to:
acquire, in association with an attribute value of an object, a movement model which represents a feature of movement of that object;
calculate a flow of each collection of objects having a different attribute value based on the flow of the collection of the objects in the capturing range of the fixed camera and the movement model, and estimate the distribution of the attribute of the objects in the estimation range by moving the distribution of the attribute of the objects in the capturing range of the moving camera based on the flow of each collection of objects having a different attribute value.
5. The information processing apparatus according to claim 1 ,
wherein the at least one processor further configured to: calculate density of the collection of the objects in the capturing range of the fixed camera using the first surveillance image; and
estimate the number of objects having each attribute value for the estimation range by calculating density of a collection of objects in the estimation range as the same density as the density of the collection of the objects in the capturing range of the fixed camera.
6. The information processing apparatus according to claim 1 , wherein the at least one processor further configured to:
generate control information which indicates a location where a large number of objects having a predetermined attribute value are present in the estimated attribute distribution, or a location where reliability of the estimated attribute distribution is low.
7. The information processing apparatus according to claim 1 ,
wherein a collection of objects captured in the first surveillance image and a collection of objects captured in the second surveillance image have at least a part of objects in common.
8. The information processing apparatus according to claim 1 ,
wherein each object is a person, and
the attribute of each object is an age bracket, a sex, nationality, a group to which the object belongs, presence of belongings, or whether or not the object is a person having difficulty in walking.
9. The information processing apparatus according to claim 1 ,
wherein the capturing range of the fixed camera is wider than the capturing range of the moving camera.
10. A control method executed by a computer, comprising:
calculating a flow of a collection of objects in a capturing range of a fixed camera using a first surveillance image, the first surveillance image being generated by the fixed camera, the fixed camera being a camera a position of which is fixed;
calculating a distribution of an attribute of objects in a capturing range of a moving camera using a second surveillance image, the second surveillance image being generated by the moving camera, the moving camera being a camera a position of which is not fixed; and
estimating the distribution of the attribute of the objects for an estimation range including a range not included in the capturing range of the moving camera based on the distribution of the attribute of the objects in the capturing range of the moving camera and the flow of the collection of objects in the capturing range of the fixed camera.
11. A non-transitory computer-readable storage medium storing a program that causes a computer to execute:
calculating a flow of a collection of objects in a capturing range of a fixed camera using a first surveillance image, the first surveillance image being generated by the fixed camera, the fixed camera being a camera a position of which is fixed;
calculating a distribution of an attribute of objects in a capturing range of a moving camera using a second surveillance image, the second surveillance image being generated by the moving camera, the moving camera being a camera a position of which is not fixed; and
estimating the distribution of the attribute of the objects for an estimation range including a range not included in the capturing range of the moving camera based on the distribution of the attribute of the objects in the capturing range of the moving camera and the flow of the collection of objects in the capturing range of the fixed camera.