System and method for compressing video data

1. A method of compressing video data, the method comprising:

configuring an object of interest detector to detect whether objects of interest are located in the video data according to one or more classifiers c;

training the one or more classifiers c to identify the objects of interest for a specific application using data collected from a plurality of video capture devices in a video processing system by applying one or more machine learning methods;

configuring an encoder to transform an image region I using a non-linear transformation Φ(I) into an ordered set of basis transformation parameters {right arrow over (θ)}, where {right arrow over (θ)}=Φ(I) and I≈Φ −1 ({right arrow over (θ)});

collecting video data at a video capture device;

applying the non-linear transformation Φ(I) to the image region I from the video data to generate compressed video data comprising the set of basis transformation parameters {right arrow over (θ)} associated with the objects of interest; and

sending the compressed video data from the video capture device to the video processing system to enable the video processing system to decode and reconstruct the video using Φ c −1 ({right arrow over (θ i )}), for each object of interest i associated with the corresponding object classifier c.

2. The method of claim 1 , further comprising ignoring at least a portion of the transformed data associated with background information in preparing the compressed video data.

3. The method of claim 1 , further comprising transporting the compressed video data to an object of interest processing device in the video processing system.

4. The method of claim 3 , wherein the compressed video data is transported wirelessly from the video capture device to the object of interest processing device.

5. The method of claim 3 , wherein the object of interest processing device is associated with a cloud-based service.

6. The method of claim 3 , wherein the compressed video data is transported using at least one of: i) a wired communication connection, and ii) a portable data storage device.

7. The method of claim 3 , further comprising storing the compressed video data.

8. The method of claim 1 , further comprising storing uncompressed video data.

9. The method of claim 1 , further comprising providing the compressed video data to an intelligent traffic system (ITS) controller interface via an ITS object interface.

10. The method of claim 1 , wherein identifying the at least one object of interest comprises decomposing the video data to generate an encoded stream comprising one or more models associated with the objects of interest, the encoded stream enabling the reconstruction of the video data.

11. The method of claim 1 , further comprising sending at least one background feature to an object of interest processing device to enable reconstruction of the video data using the compressed video data.

12. The method of claim 11 , further comprising subsequently sending additional background information to capture changes to the at least one background feature.

13. The method of claim 1 , further comprising receiving data generated by a learning platform, the data comprising at least one of: i) a new classifier, and ii) a modification to an existing classifier.

14. A non-transitory computer readable medium comprising computer executable instructions for:

configuring an object of interest detector to detect whether objects of interest are located in the video data according to one or more classifiers c;

training the one or more classifiers c to identify the objects of interest for a specific application using data collected from a plurality of video capture devices in a video processing system by applying one or more machine learning methods;

configuring an encoder to transform an image region I using a non-linear transformation Φ(I) into an ordered set of basis transformation parameters {right arrow over (θ)}, where {right arrow over (θ)}=Φ(I) and I≈Φ −1 ({right arrow over (θ)});

collecting video data at a video capture device;

applying the non-linear transformation Φ(I) to the image region I from the video data to generate compressed video data comprising the set of basis transformation parameters {right arrow over (θ)}associated with the objects of interest; and

sending the compressed video data from the video capture device to the video processing system to enable the video processing system to decode and reconstruct the video using Φ c −1 ({right arrow over (θ i )}), for each object of interest i associated with the corresponding object classifier c.

15. A video compression module comprising at least one processor and at least one memory, the at least one memory comprising computer executable instructions for:

configuring an object of interest detector to detect whether objects of interest are located in the video data according to one or more classifiers c;

training the one or more classifiers c to identify the objects of interest for a specific application using data collected from a plurality of video capture devices in a video processing system by applying one or more machine learning methods;

configuring an encoder to transform an image region I using a non-linear transformation Φ(I) into an ordered set of basis transformation parameters {right arrow over (θ)}, where {right arrow over (θ)}=Φ(I) and I≈Φ −1 ({right arrow over (θ)});

collecting video data at a video capture device;

applying the non-linear transformation Φ(I) to the image region I from the video data to generate compressed video data comprising the set of basis transformation parameters {right arrow over (θ)}associated with the objects of interest; and

sending the compressed video data from the video capture device to the video processing system to enable the video processing system to decode and reconstruct the video using Φ c −1 ({right arrow over (θ i )}), for each object of interest i associated with the corresponding object classifier c.

16. The video compression module of claim 15 , further comprising instructions for ignoring at least a portion of the transformed data associated with background information in preparing the compressed video data.

17. The video compression module of claim 15 , further comprising instructions for transporting the compressed video data to an object of interest processing device in the video processing system.

18. The video compression module of claim 15 , wherein identifying the at least one object of interest comprises decomposing the video data to generate an encoded stream comprising one or more models associated with the objects of interest, the encoded stream enabling the reconstruction of the video data.

19. The video compression module of claim 15 , further comprising instructions for sending at least one background feature to an object of interest processing device to enable reconstruction of the video data using the compressed video data.

20. The video compression module of claim 19 , further comprising instructions for subsequently sending additional background information to capture changes to the at least one background feature.

21. The method of claim 1 , further comprising:

reconstructing the video using Φ c −1 ({right arrow over (θ i )}); and

using the compressed video data in the specific application.

22. The method of claim 1 , further comprising:

using the machine learning platform to apply the one or more machine learning methods to the compressed video data and other data collected from the plurality of other video capture devices in the video processing system, to refine the non-linear transformation Φ(I) and to refine the one or more classifiers c, with features from the compressed video data and the other data; and

sending an update for the object of interest detector Φ(I) and/or the encoder to the video capture device based on the refining for subsequent video processing.

23. The video compression module, of claim 15 , further comprising instructions for:

reconstructing the video using Φ c −1 ({right arrow over (θ i )})and

using the compressed video data in the specific application.

24. The video compression module of claim 15 , further comprising instructions for:

using the machine learning platform to apply the one or more machine learning methods to the compressed video data and other data collected from the plurality of other video capture devices in the video processing system, to refine the non-linear transformation Φ(I) and to refine the one or more classifiers c, with features from the compressed video data and the other data; and

sending an update for the object of interest detector Φ(I) and/or the encoder to the video capture device based on the refining for subsequent video processing.