Calibration of video object classification
View Patent ↗Techniques for calibrating a classification system, wherein one or more objects in at least one video are classified, are provided. At least one view associated with the at least one video is obtained. The at least one view is partitioned into at least one region. A given object is classified in accordance with its location in reference to the at least one region. In an additional embodiment, one or more object models are obtained. At least one normalized size of the one or more objects is defined within at least one view associated with the at least one video in accordance with the one or more object models. The one or more objects are classified in accordance with the at least one defined normalized size.
1. A method for calibrating a classification system, wherein one or more objects in at least one video are classified, the method comprising:
obtaining at least one view associated with the at least one video;
partitioning the at least one view into at least one region, such that a given object is classified in accordance with its location in reference to the at least one region; and
when the at least one region is initially specified as corresponding to a first type of object, automatically decreasing a classification probability associated with the given object being the first type of object when at least one other object is classified in the at least one region as being a second type of object, and automatically increasing a classification probability associated with the given object being the second type of object for the at least one region.
2. The method of claim 1 , wherein the at least one region is associated with a specific class.
3. The method of claim 1 , wherein the at least one region is not associated with a specific class.
4. The method of claim 1 , further comprising the step of adjusting a probability that the given object belongs to a specific class, such that the probability is in accordance with a location of the given object in one or more frames of the at least one video and the at least one region.
5. The method of claim 4 , wherein the given object is classified in accordance with the adjusted probability in combination with at least one of a probability based on a size of the given object, a probability based on a velocity of the given object, and a probability based on a level of deformation of the given object.
6. A computer program product for calibrating a classification system, wherein one or more objects in at least one video are classified, the computer program product comprising a computer-readable non-transitory storage medium including one or more programs, which when executed by a computer implement the steps of claim 1 .
7. An apparatus for calibrating a classification system, wherein one or more objects in at least one video are classified, the apparatus comprising:
a memory; and
at least one processor coupled to the memory and operative to: obtain at least one view associated with the at least one video; partition the at least one view into at least one region, such that a given object is classified in accordance with its location in reference to the at least one region; and when the at least one region is initially specified as corresponding to a first type of object, automatically decrease a classification probability associated with the given object being the first type of object when at least one other object is classified in the at least one region as being a second type of object, and automatically increase a classification probability associated with the given object being the second type of object for the at least one region.
8. The apparatus of claim 7 , wherein the at least one region is associated with a specific class.
9. The apparatus of claim 7 , wherein the at least one region is not associated with a specific class.
10. The apparatus of claim 7 , wherein the at least one processor is further operative to adjust a probability that the given object belongs to a specific class, such that the probability is in accordance with a location of the given object in one or more frames of the at least one video and the at least one region.
11. The apparatus of claim 10 , wherein the given object is classified in accordance with the adjusted probability in combination with at least one of a probability based on a size of the given object, a probability based on a velocity of the given object, and a probability based on a level of deformation of the given object.