Methods of modifying search areas
First Claim
Patent Images
1. A method of evaluating a search area for encoding video, said method comprising:
- receiving video captured by an image capture device, the video comprising video frame components;
receiving sensor data from a plurality of sensors, the sensor data including information about a spatial disposition of the image capture device, a movement of the image capture device, a zoom state of the image capture device, and a field of view (FOV) of the image capture device;
generating, using the sensor data, an optical flow field associated with a video frame component of the video frame components;
obtaining a first initial search area within the video frame component;
determining, based on the optical flow filed, a bias of the first initial search area;
adjusting, based on the optical flow field, the first initial search area to determine a first search area within the video frame component, wherein adjusting the first initial search area includes, based on the bias of the first initial search area;
adjusting a number of sides of a boundary of the first initial search area from a first number to a second number that is different from the first number;
oradjusting the boundary of the first initial search area by a first ratio in one direction and adjusting the boundary of the first initial search area by a second ratio in another direction, the first ratio being different from the second ratio;
providing a second initial search area of the video frame component; and
adjusting the second initial search area based on the optical flow field to yield a second search area.
1 Assignment
0 Petitions
Accused Products
Abstract
Methods and systems for evaluating a search area for encoding video are provided. The method comprises receiving video captured by an image capture device, the video comprising video frame components. Additionally, the method comprises receiving optical flow field data associated with the video frame component, wherein at least a portion of the optical flow field data is captured by sensors. The method also comprises determining a search area based on the optical flow field data.
55 Citations
17 Claims
-
1. A method of evaluating a search area for encoding video, said method comprising:
-
receiving video captured by an image capture device, the video comprising video frame components; receiving sensor data from a plurality of sensors, the sensor data including information about a spatial disposition of the image capture device, a movement of the image capture device, a zoom state of the image capture device, and a field of view (FOV) of the image capture device; generating, using the sensor data, an optical flow field associated with a video frame component of the video frame components; obtaining a first initial search area within the video frame component; determining, based on the optical flow filed, a bias of the first initial search area; adjusting, based on the optical flow field, the first initial search area to determine a first search area within the video frame component, wherein adjusting the first initial search area includes, based on the bias of the first initial search area; adjusting a number of sides of a boundary of the first initial search area from a first number to a second number that is different from the first number;
oradjusting the boundary of the first initial search area by a first ratio in one direction and adjusting the boundary of the first initial search area by a second ratio in another direction, the first ratio being different from the second ratio; providing a second initial search area of the video frame component; and adjusting the second initial search area based on the optical flow field to yield a second search area. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 16, 17)
-
-
14. A non-transitory computer readable medium containing program instructions for evaluating a search area for encoding video, said computer readable medium comprising:
-
program instructions for receiving video captured by an image capture device, the video comprising video frame components; program instructions for receiving sensor data from a plurality of sensors, the sensor data including information about a spatial disposition of the image capture device, a movement of the image capture device, a zoom state of the image capture device, and a field of view (FOV) of the image capture device; program instructions for generating, using the sensor data, an optical flow field associated with a video frame component of the video frame components; program instructions for obtaining a first initial search area within the video frame component; program instructions for determining a bias of the first initial search area based on the optical flow field; program instructions for adjusting, based on the optical flow field, the first initial search area to determine a first search area within the video frame component, wherein adjusting the first initial search area includes, based on the bias of the first initial search area; adjusting a number of sides of a boundary of the first initial search area from a first number to a second number that is different from the first number;
oradjusting the boundary of the first initial search area by a first ratio in one direction and adjusting the boundary of the first initial search area by a second ratio in another direction, the first ratio being different from the second ratio; program instructions for providing a second initial search area of the video frame component; and program instructions for adjusting the second initial search area based on the optical flow field to yield a second search area.
-
-
15. A system for evaluating a search area for encoding video, said system comprising:
-
an image capture device configured to capture a video; one or more sensors configured to obtain sensor data; and one or more processors, individually or collectively configured to; receive the video captured by the image capture device, the video comprising video frame components; receive the sensor data from the one or more sensors, the sensor data including information about a spatial disposition of the image capture device, a movement of the image capture device, a zoom state of the image capture device, and a field of view (FOV) of the image capture device; generate, using the sensor data, an optical flow field associated with a video frame component of the video frame components; obtain a first initial search area within the video frame component; determine, according to the optical flow field, a bias of the first initial search area; and adjust, based on the optical flow field, the first initial search area to determine a first search area within the video frame component, wherein adjusting the first initial search area includes, based on the bias of the first initial search area; adjusting a number of sides of a boundary of the first initial search area from a first number to a second number that is different from the first number;
oradjusting the boundary of the first initial search area by a first ratio in one direction and adjusting the boundary of the first initial search area by a second ratio in another direction, the first ratio being different from the second ratio; provide a second initial search area of the video frame component; and adjust the second initial search area based on the optical flow field to yield a second search area.
-
Specification