Object analysis using motion history
A method for object analysis using motion history is provided. The method includes receiving video data comprising a plurality of frames of a scene comprising one or more elements, and processing the video data to produce a motion history image comprising motion history values of at least one of the elements. The method also includes identifying the one of the elements for further processing if a characteristic of the motion history image satisfies a criteria.
1. A method for object analysis using motion history comprising:
receiving video data comprising a plurality of frames of a scene comprising one or more elements;
processing the video data to produce a motion history image corresponding to a three-dimensional representation of the one or more elements as a plurality of motion history values, wherein the motion history values of at least one of the elements comprises timestamps; and
processing the motion history image of at least one of the elements to produce a motion history blob corresponding to a boundary of the motion history image of at least one of the elements, wherein certain criteria are applied to blobs and only those blobs that satisfy the criteria are tracked.
2. The method of claim 1 , further comprising:
ignoring the element if the characteristic of the motion history image does not satisfy the criteria.
3. The method of claim 1 , wherein the characteristic of the motion history image is a shape of the motion history blob, and the criteria is a shape criteria.
4. The method of claim 1 , wherein the characteristic of the motion history image is the difference between the maximum timestamp and the minimum timestamp of the motion history values within the motion history blob, and the criteria is a time duration criteria.
5. The method of claim 4 , wherein the time duration of the motion history image is measured in a number of frames in the motion history values within the motion history blob, and the time duration criteria is a number of frames.
6. The method of claim 1 , further comprising:
processing the motion history values within the motion history blob to determine one or more attributes of the element.
7. A computer system configured for object analysis using motion history, the computer system comprising:
a memory configured to store video data; and
a processor coupled to the memory configured to:
receive video data comprising a plurality of frames of a scene comprising one or more elements;
process the video data to produce a motion history image corresponding to a three-dimensional representation of the one or more elements as a plurality of motion history values, wherein the motion history values of at least one of the elements comprises timestamps; and
process the motion history image of at least one of the elements to produce a motion history blob corresponding to a boundary of the motion history image of at least one of the elements, wherein certain criteria are applied to blobs and only those blobs that satisfy the criteria are tracked.
8. The computer system of claim 7 , wherein the processor is further configured to:
ignore the element if the characteristic of the motion history image does not satisfy the criteria.
9. The computer system of claim 7 , wherein the characteristic of the motion history image is a shape of the motion history blob, and the criteria is a shape criteria.
10. The computer system of claim 7 , wherein the characteristic of the motion history image is the difference between the maximum timestamp and the minimum timestamp of the motion history values within the motion history blob, and the criteria is a time duration criteria.
11. The computer system of claim 10 , wherein the time duration of the motion history image is measured in a number of frames in the motion history values within the motion history blob, and the time duration criteria is a number of frames.
12. The computer system of claim 7 , wherein the processor is further configured to: process the motion history values within the motion history blob to determine one or more attributes of the element.
13. A non-transitory computer readable medium having stored thereon program instructions object analysis using motion history, that when executed by a computer system, direct the computer system to:
receive video data comprising a plurality of frames of a scene comprising one or more elements;
process the video data to produce a motion history image corresponding to a three-dimensional representation of the one or more elements as a plurality of motion history values, wherein the motion history values of at least one of the elements comprises timestamps; and
process the motion history image of at least one of the elements to produce a motion history blob corresponding to a boundary of the motion history image of at least one of the elements, wherein certain criteria are applied to blobs and only those blobs that satisfy the criteria are tracked.
14. The non-transitory computer readable medium of claim 13 , wherein the instructions further direct the computer system to:
ignore the element if the characteristic of the motion history image does not satisfy the criteria.
15. The non-transitory computer readable medium of claim 13 , wherein the characteristic of the motion history image is a shape of the motion history blob, and the criteria is a shape criteria.
16. The non-transitory computer readable medium of claim 13 , wherein the characteristic of the motion history image is the difference between the maximum timestamp and the minimum timestamp of the motion history values within the motion history blob, and the criteria is a time duration criteria.
17. The non-transitory computer readable medium of claim 16 , wherein the time duration of the motion history image is measured in a number of frames in the motion history values within the motion history blob, and the time duration criteria is a number of frames.
18. The non-transitory computer readable medium of claim 13 , wherein the processor is further configured to:
process the motion history values within the motion history blob to determine one or more attributes of the element.