Systems, methods, and computer program products for object detection and analysis of an image
AssigneeDevon Energy Corporation
InventorsAmos James Hall, Jared Lee Markes, Beau Travis Rollins, Michael Alan Adler, Jr.
Life of this patent
Estimating the term…
Abstract
Systems, methods, and computer program products of intelligent image analysis using object detection models to identify objects and locate and detect features in an image are disclosed. The systems, methods, and computer program products include automated learning to identify the location of an object to enable continuous identification and location of an object in an image during periods when the object may be difficult to recognize or during low visibility conditions.
Claims15
A computing system comprising:
- one or more processors;
- one or more computer readable storage media operably coupled to at least one of the processors;
- and
- program instructions stored on the one or more computer readable storage media for execution by at least one of the processors to cause the computing system to perform the action of:
- learning an object's location in an image by clustering a group of objects detected in previously captured images by a centroid for each detected object;
- calculating a geometric average of the cluster;
- and
- determining whether each of the previously captured images was captured in a lighting condition that meets or exceeds a lighting threshold, wherein in response to a determination that a lighting threshold is not met for one or more of the images, the one or more computer readable storage media includes additional program instructions for execution by at least one of the processors, further causing the computing system to perform the action of:
- determining if a minimum threshold of image iterations is met or exceeded.
A computer-implemented method of learning an object's location in an image through a clustering technique, the method comprising:
- grouping, by a computing system, detected objects by a centroid for each detected object, thereby creating a cluster;
- calculating a geometric average of the cluster;
- and
- determining whether images used to create the cluster were captured in lighting conditions that meets or exceeds a minimum lighting threshold wherein in response to a determination that a minimum lighting threshold is not met for any of the images, the method further comprises:
- determining if a minimum threshold of image iterations is met or exceeded.
A computer program product for learning an object's location in an image through a clustering technique, the computer program product stored in a computer readable storage medium, comprising program code that, when executed by the computing system, causes the computing system to perform actions comprising:
- grouping detected objects by a centroid for each detected object, thereby creating a cluster;
- calculating a geometric average of the cluster;
- and
- determining whether images including the detected objects used to create the cluster were captured in lighting conditions that meets or exceeds a minimum lighting threshold, wherein in response to a determination that a minimum lighting threshold is not met for one or more of the images, the computer program product includes additional program code that, when executed by the computing system, further causes the computing system to perform the action of:
- determining if a minimum threshold of image iterations is met or exceeded.
A computing system comprising:
- one or more processors;
- one or more computer readable storage media operably coupled to at least one of the processors;
- and
- program instructions stored on the one or more computer readable storage media for execution by at least one of the processors to cause the computing system to perform the action of:
- learning an object's location in an image by clustering a group of objects detected in previously captured images by a centroid for each detected object;
- calculating a geometric average of the cluster;
- and
- determining whether each of the previously captured images was captured in a lighting condition that meets or exceeds a lighting threshold, wherein in response to a determination that each of the images were captured in lighting conditions that meet or exceed the lighting threshold, the one or more computer readable storage media includes additional program instructions for execution by at least one of the processors, further cause the computing system to perform the action of:
- updating a database with the calculated geometric average and thereby learning the object's location in the image.
A computer-implemented method of learning an object's location in an image through a clustering technique, the method comprising:
- grouping, by a computing system, detected objects by a centroid for each detected object, thereby creating a cluster;
- calculating a geometric average of the cluster;
- and
- determining whether images used to create the cluster were captured in lighting conditions that meet or exceed a minimum lighting threshold, wherein in response to a determination that a minimum lighting threshold is met or exceeded for each of the images, the computer program product includes additional program code that, when executed by the computing system, further causes the computing system to perform the action of updating a database with the calculated geometric average and thereby learning the object's location in the image.
A computer program product for learning an object's location in an image through a clustering technique, the computer program product stored in a computer readable storage medium, comprising program code that, when executed by the computing system, causes the computing system to perform actions comprising:
- grouping detected objects by a centroid for each detected object, thereby creating a cluster;
- calculating a geometric average of the cluster;
- and
- determining whether images including the detected objects used to create the cluster were captured in lighting conditions that meet or exceed a minimum lighting threshold, wherein in response to a determination that a minimum lighting threshold is met or exceeded for each of the images, the computer program product includes additional program code that, when executed by the computing system, further causes the computing system to perform the action of:
- updating a database with the calculated geometric average and thereby learning the object's location in the image.
Dependencies are inferred from the claim text.