VIDEO IMAGE PROCESSING AND MOTION DETECTION

• US 20200134813A1
• Filed: 10/24/2018
• Published: 04/30/2020
• Est. Priority Date: 10/24/2018
• Status: Active Grant

• Current Assignee: Alarm.com Inc. (Alarm.com Holdings, Inc.)
• Original Assignee: Wearless Tech Inc.
• Inventors: Palmer, Victor Jared, Pavagada Nagaraja, Pavan Kumar
• Granted Patent: US 10,803,580 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/30 Noise filtering
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/75 Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
• CPC Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

A system for detecting motion in one or more images of a video feed captured by an image capture device. The system collects the multiple images of the video feed and segments each image into multiple portions or cells. Multiple cell groups are determined based on the images, with each cell group including information relating to contents of set of a common portion of the multiple images. A difference metric is calculated for each of the cell groups and at least one level of change of values of the difference metric is determined. The at least one level of change is data representing the video feed that is compared with a still-scene data model associated with the image capture device to determine a respective probability that each of the cell groups includes motion. Motion is identified for those cell groups that have a probability greater than or equal to a threshold value. The system generates a transformed video feed including the video feed and a visual indication of the motion.

Claims

1. A method comprising:

collecting, by a processing device, a plurality of images of a video feed generated by a first image capture device over a first time period;

determining a plurality of cell groups based on the plurality of images, wherein a first cell group of the plurality of cell groups comprises information relating to contents of a set of first cells of the plurality of images, wherein each of the first cells corresponds to a different time in the first time period;

calculating a first difference metric corresponding to one or more comparisons of the information relating to contents of the set of first cells of the first cell group;

determining one or more levels of change corresponding to values of the first difference metric relating to the set of first cells;

determining, based on a comparison of the one or more levels of change and a still-scene data model corresponding to the first image capture device, a probability that the first cell group comprises motion;

determining the first probability is greater than or equal to a threshold value;

generating a transformed video feed comprising a video feed and a visual indication of the motion; and

causing an output of the transformed video feed.

2. The method of claim 1, further comprising generating the still-scene data model based at least in part on one or more sensor parameters corresponding to the first image capture device and a model video feed corresponding to a still-scene environment.

3. The method of claim 1, wherein the first difference metric is based on a comparison of a first parameter for each pair of first cells in the first cell group.

4. The method of claim 3, wherein a first value of the first difference metric is a sum of absolute values of pixel intensity differences between a first pair of first cells of the first cell group.

5. The method of claim 1, wherein each of the set of first cells comprises a common portion of the plurality images captured at a plurality of different times over the first time period.

6. The method of claim 1, further comprising:

comparing information associated with at least one of the one or more levels of change to a predetermined pattern associated with a first activity;

identifying a match between the information associated with the at least one of the one or more levels of change to the predetermined pattern associated with the first activity; and

categorizing the video feed as comprising the first activity, wherein the first activity comprises respiratory activity.

7. The method of claim 1, wherein first difference metric is calculated based on a comparison of a plurality of pairs comprising each combination of the first cells of the set of first cells.

8. A system comprising:

a processing device; and

memory to store computer-executable instructions that, if executed, cause the processing device to;

collect a plurality of images of a video feed generated by a first image capture device over a first time period;

determine a plurality of cell groups based on the plurality of images, wherein a first cell group of the plurality of cell groups comprises information relating to contents of a set of first cells of the plurality of images;

calculate a first difference metric based on the information relating to contents of the set of first cells of the first cell group;

determine one or more levels of change of values of the first difference metric relating to the set of first cells;

determine, based on a comparison of the one or more levels of change and a still-scene data model corresponding to the first image capture device, a probability that the first cell group comprises motion;

determine the first probability is greater than or equal to a threshold value;

generate a transformed video feed comprising a video feed and a visual indication of the motion; and

cause an output of the transformed video feed, wherein the output comprises an alert indicating the motion.

9. The system of claim 8, the processing device to:

generate the still-scene data model based at least in part on one or more parameters corresponding to the first image capture device and a model video feed corresponding to a still-scene environment.

10. The system of claim 8, the processing device to compare a first parameter of a pair of first cells of the first cell group to calculate the first difference metric.

11. The system of claim 8, the processing device to generate a plurality of still-scene data models each corresponding to a different image capture device.

12. The system of claim 8, wherein the first parameter is a pixel intensity value of pixels of each of the first cells of the pair of first cells.

13. The system of claim 8, wherein the still-scene data model comprises a representation of sensor noise associated with the image capture device.

14. A non-transitory computer-readable storage device storing computer-executable instructions that, if executed by a processing device, cause the processing device to:

store a plurality of images of a video feed generated by a first image capture device corresponding to a first time period;

segment a first image of the plurality of images into a grid comprising a plurality of cells, wherein each cell represents a portion of contents of the first image;

determine a plurality of cell groups based on the plurality of images, wherein a first cell group of the plurality of cell groups comprises information relating to a first portion of the contents of a set of first cells of the plurality of images;

calculate a first difference metric based on the information relating to the contents of the set of first cells of the first cell group;

determine at least one level of change of values of the first difference metric relating to the set of first cells;

determine, based on a comparison of the at least one level of change and a still-scene data model corresponding to the first image capture device, a probability that the first cell group comprises motion;

determine the first probability is greater than or equal to a threshold value;

generate a transformed video feed comprising a video feed and a visual indication of the motion; and

cause an output of the transformed video feed, wherein the transformed video feed comprises a heat-map indication corresponding to the motion.

15. The non-transitory computer-readable storage device of claim 14, the processing device to generate the still-scene data model based at least in part on one or more parameters corresponding to the first image capture device and a model video feed corresponding to a still-scene environment.

16. The non-transitory computer-readable storage device of claim 14, the processing device to compare a first parameter of a pair of first cells of the first cell group to calculate the first difference metric.

17. The non-transitory computer-readable storage device of claim 14, the processing device to generate a plurality of still-scene data models each corresponding to a different image capture device.

18. The non-transitory computer-readable storage device of claim 14, wherein the still-scene data model comprises a representation of sensor noise associated with the image capture device.

19. The non-transitory computer-readable storage device of claim 14, the processing device to:

compare information associated with at least one of the one or more levels of change to a predetermined pattern associated with a first activity;

identify a match between the information associated with the at least one of the one or more levels of change to the predetermined pattern associated with the first activity; and

categorize the video feed as comprising the first activity, wherein the first activity comprises respiratory activity.

20. The non-transitory computer-readable storage device of claim 14, wherein the first difference metric is calculated based on a comparison of a plurality of pairs comprising each combination of first cells of the set of first cells.