Camera blockage detection for autonomous driving systems
AssigneeNVIDIA Corporation
InventorsXiaoyan Mu, Xiaohan Hu
Life of this patent
Estimating the term…
Abstract
Systems and methods for detecting blockages in images are described. An example method may include receiving a plurality of images captured by a camera installed on an apparatus. The method may include identifying one or more candidate blocked regions in the plurality of images. Each of the candidate blocked regions may contain image data caused by blockages in the camera's field-of-view. The method may further include assigning scores to the one or more candidate blocked regions based on relationships among the one or more candidate blocked regions in the plurality of images. In response to a determination that one of the scores is above a predetermined blockage threshold, the method may include generating an alarm signal for the apparatus.
Claims20
A method comprising:
- identifying, based at least on image data corresponding to a plurality of images captured using a camera, candidate blocked regions in the plurality of images, wherein at least one candidate blocked regions being caused by one or more blockages in a field-of-view of the camera;
- determining whether to maintain or create a region tracker in a blockage region map for tracking the at least one candidate blocked region based at least on relationships between the at least one candidate blocked region and others of the candidate blocked regions;
- determining camera blockage information based at least on the region tracker;
- and
- in response to a determination that the camera blockage information indicates that camera blockage is above a predetermined blockage threshold, performing one or more operations based at least on the camera blockage information.
One or more processors comprising processing circuitry to perform operations comprising:
- identifying, based at least on image data corresponding to a plurality of images captured using a camera, candidate blocked regions in the plurality of images, at least one candidate blocked region being caused by blockages in a field-of-view of the camera;
- determining whether to maintain or create a region tracker in a blockage region map for tracking the at least one candidate blocked region based at least on relationships between the at least one candidate blocked region and others of the candidate blocked regions;
- determining camera blockage information based at least on the region tracker;
- and
- in response to a determination that the camera blockage information indicates that camera blockage is above a predetermined blockage threshold, performing one or more operations based at least on the camera blockage information.
A system comprising:
- a camera to capture a plurality of images;
- and
- one or more processors comprising processing circuitry to:
- identify candidate blocked regions in the plurality of images, at least one candidate blocked region corresponding to a blockage caused in a field-of-view of the camera,
- determine whether to maintain or create a region tracker in a blockage region map for tracking the at least one candidate blocked region based at least on relationships between the at least one candidate blocked region and others candidate blocked regions,
- determine camera blockage information based at least on the region tracker, and
- in response to a determination that the camera blockage information indicates that camera blockage is above a predetermined blockage threshold, perform one or more operations using the system and based at least on the camera blockage information.
Dependencies are inferred from the claim text.