Intelligent high resolution video system
An automated electronic video surveillance system enables a high-resolution mega-pixel camera to capture high quality, detailed, magnified images at multiple locations, simultaneously with an overview of the whole scene. A preferred embodiment requiring no moving parts provides full 360-degree continuous viewing with up to 5× all-digital zoom capability. The system performs continuous surveillance and active resolution allocation in the form of a feedback control subsystem that dynamically allocates resources so that important details within a scene receive appropriate scrutiny, while uninteresting areas are imaged at a lower resolution.
1. A method of reducing the amount of video data of a scene captured by a video camera for display or storage, comprising:
capturing the scene by the video camera to obtain high resolution video data representing the scene with a high image resolution;
sampling, by a processor, the high resolution video data to obtain low resolution video data representing at least a part of the scene with a low image resolution where the low image resolution is lower than the high image resolution;
analyzing, by the processor, the low resolution video data to detect a region of interest within the scene, the region of interest including an object of interest;
sampling, by the processor, the high resolution video data in the region of interest within the scene to obtain region of interest video data with a first image resolution where the first image resolution is higher than the low image resolution, and wherein the first image resolution is determined based on a speed of the object of interest; and
providing the low resolution video data with the region of interest video data to display or store the scene.
2. The method of claim 1 , wherein resolution comprises at least one of spatial resolution and temporal resolution.
3. The method of claim 2 , wherein the first image resolution is substantially the same as the high image resolution.
4. The method of claim 2 , further comprising analyzing the region of interest video data to obtain more information.
5. The method of claim 2 , further comprising sampling the high resolution video data in the region of interest within the scene to obtain a further region of interest video data with a second image resolution where the second image resolution is higher than the first image resolution; and analyzing the further region of interest video data for more information.
6. The method of claim 4 , wherein the information comprises any of facial recognition, object identification, people identification, and vehicle identification.
7. The method of claim 2 , in which the region of interest video data represents a windowed view of the region of interest which includes a magnified view portion of the scene.
8. The method of claim 4 , wherein the information is recognition of an object in the region of interest, the object having a motion; and further comprising
determining regions of interest for speculative processing from the motion of the object.
9. The method of claim 1 , further comprising:
transmitting through a communication medium for delivery to a destination the low resolution video data with the region of interest video data in combination as a video stream representing the scene and the windowed view of the detected region of interest in the scene at the different image resolutions.
10. A video surveillance system having a reduced amount of video data of a scene captured by a video camera for display or storage, comprising:
a video camera operable to capture the scene to obtain high resolution video data representing the scene with a high image resolution;
a processor; and
a computer-readable storage device storing program instructions that, when executed by the processor, cause the system to perform operations comprising:
sampling the high resolution video data using averaging of neighboring pixels to obtain low resolution video data representing at least a part of the scene with a low image resolution where the low image resolution is lower than the high image resolution;
analyzing the low resolution video data to detect a region of interest within the scene, the region of interest including an object of interest;
sampling the high resolution video data in the region of interest within the scene to obtain region of interest video data with a first image resolution where the first image resolution is higher than the low image resolution, and wherein the first image resolution is determined based on a speed of the object of interest; and
providing the low resolution video data with the region of interest video data to display or store the scene.
11. The video surveillance system of claim 10 , wherein resolution comprises at least one of spatial resolution and temporal resolution.
12. The video surveillance system of claim 11 , wherein the first image resolution is substantially the same as the high image resolution.
13. The video surveillance system of claim 11 , wherein the system to perform operations further comprises analyzing the region of interest video data to obtain more information.
14. The video surveillance system of claim 11 , wherein the system to perform operations further comprises sampling the high resolution video data in the region of interest within the scene to obtain a further region of interest video data with a second image resolution which resolution is higher than the first image resolution; and analyzing the further region of interest video data for more information.
15. The video surveillance system of claim 13 , wherein the information comprises any of facial recognition, object identification, people identification, and vehicle identification.
16. The video surveillance system of claim 11 , wherein the region of interest video data represents a windowed view of the region of interest which includes a magnified view portion of the scene.
17. The video surveillance system of claim 13 , wherein the information is recognition of an object in the region of interest, the object having a motion; and wherein the system to perform operations further comprises
determining regions of interest for speculative processing from the motion of the object.
18. The video surveillance system of claim 10 , wherein the system to perform operations further comprises:
transmitting through a communication medium for delivery to a destination the low resolution video data with the region of interest video data in combination as a video stream representing the scene and the windowed view of the detected region of interest in the scene at the different image resolutions.
19. A method of reducing the amount of video data of a scene captured by a video camera for display or storage, comprising:
selecting, by a user through a user interface to a processor, a region of interest within the scene, the region of interest including an object of interest;
capturing the scene by the video camera to obtain high resolution video data representing the scene with a high image resolution;
sampling, by a processor, the high resolution video data using averaging of neighboring pixels to obtain low resolution video data representing at least a part of the scene with a low image resolution where the low image resolution is lower than the high image resolution;
sampling, by the processor, the high resolution video data in the region of interest within the scene to obtain region of interest video data with a first image resolution where the first image resolution is higher than the low image resolution, and wherein the first image resolution is determined based on a speed of the object of interest; and
providing the low resolution video data with the region of interest video data to display or store the scene.
20. The method of claim 19 , wherein resolution comprises at least one of spatial resolution and temporal resolution.