Techniques for automatically identifying secondary objects in a stereo-optical counting system
Techniques for distinguishing objects (e.g., an individual or an individual pushing a shopping cart) are disclosed. An object is detected in images of a scene. A height map is generated from the images, and the object is represented as height values in the height map. Based on height properties associated with another object, it is determined whether the other object is associated with the object. If so determined, the objects are classified separately.
1. A computer-implemented method for distinguishing objects in a scene, the method comprising:
detecting at least a first object and a second object in each of a plurality of images captured in an area;
determining, based on one or more properties associated with the first and second objects, whether the second object is associated with the first object; and
upon determining that the second object is associated with the first object:
classifying the second object as a shopping cart, and
including the shopping cart in a count of shopping carts that is maintained for the area.
2. The computer-implemented method of claim 1 , further comprising:
classifying the first object as an individual.
3. The computer-implemented method of claim 2 , further comprising:
tracking the individual in each of the plurality of images.
4. The computer-implemented method of claim 3 , wherein the plurality of images is captured in an area, and further comprising:
including the individual in a count of individuals that is maintained for the area.
5. The computer-implemented method of claim 1 , wherein determining that the second object is associated with the first object comprises evaluating the one or more properties of the second object against the one or more properties of the first object.
6. A system, comprising:
one or more processors; and
a memory comprising program code, which, when executed, performs an operation for distinguishing objects in a scene, comprising:
detecting at least a first object and a second object in each of a plurality of images captured in an area;
determining, based on one or more properties associated with the first and second objects, whether the second object is associated with the first object; and
upon determining that the second object is associated with the first object:
classifying the second object as a shopping cart, and
including the shopping cart in a count of shopping carts that is maintained for the area.
7. The system of claim 6 , wherein the operation further comprises:
classifying the first object as an individual.
8. The system of claim 7 , wherein the operation further comprises:
tracking the individual in each of the plurality of images.
9. The system of claim 8 , wherein the plurality of images is captured in an area, and wherein the operation further comprises:
including the individual in a count of individuals that is maintained for the area.
10. The system of claim 6 , wherein determining that the second object is associated with the first object comprises evaluating the one or more properties of the second object against the one or more properties of the first object.
11. A non-transitory computer-readable storage medium storing a plurality of instructions, which, when executed on one or more processors, performs an operation for distinguishing objects in a scene, comprising:
detecting at least a first object and a second object in each of a plurality of images captured in an area;
determining, based on one or more properties associated with the second object, whether the second object is associated with the first object; and
upon determining that the second object is associated with the first object:
classifying the second object as a shopping cart, and
including the shopping cart in a count of shopping carts that is maintained for the area.
12. The non-transitory computer readable storage medium of claim 11 , wherein the operation further comprises:
classifying the first object as an individual.
13. The non-transitory computer readable storage medium of claim 12 , wherein the operation further comprises:
tracking the individual in each of the plurality of images.
14. The non-transitory computer readable storage medium of claim 13 , wherein the plurality of images is captured in an area, and further comprising:
including the individual in a count of individuals that is maintained for the area.
15. The non-transitory computer readable storage medium of claim 11 , wherein determining that the second object is associated with the first object comprises evaluating the one or more properties of the second object against the one or more properties of the first object.