Video redaction method and system
AssigneeConduent Business Services, LLC
InventorsRobert P. Loce, Matthew Adam Shreve, Shagan Sah
Life of this patent
Estimating the term…
Abstract
Disclosed is a method and system for generating redacted video of a scene captured using a video camera and augmenting a manual review process of the redacted video of the scene. According to an exemplary embodiment, a video of the scene is redacted via probability-based analysis to detect and obscure privacy sensitive objects included in the captured video. A manual review process of the generated redacted video is augmented to use the object detection probability to enhance the reviewing video frame rate to expedite the manual review process.
Claims26
A computer-implemented method of generating a redacted video of a nonredacted video of a scene captured using a video camera and augmenting a manual review process of the redacted video of the scene, the method comprising:
- a) a video acquisition module acquiring the nonredacted video of the scene captured using the video camera, the nonredacted video including a plurality of nonredacted video frames;
- b) an object detection module detecting one or more objects present in one or more of the plurality of nonredacted video frames, each of the detected objects associated with a predetermined object category to be redacted in the generated redacted video and each of the detected objects associated with a respective object detection probability value indicating a probability the detected object belongs to the associated predetermined object category;
- c) a redaction module redacting one or more of the detected one or more objects associated with the predetermined object categories by performing one or more of obfuscating the detected object and removing the detected object, and the redaction module generating the redacted video, the redacted video including, at least in part, one or more redacted video frames including one or more redacted detected objects;
- and
- d) a manual review module outputting the redacted video to a user interface for viewing by a user at an adaptively controlled frame rate as a function of the object detection probabilities values associated with the detected one or more objects included in a redacted video frame for manual review.
An image processing system for generating a redacted video of a nonredacted scene captured using a video camera and augmenting a manual review process of the redacted video of the scene, the image processing system comprising:
- a video acquisition module acquiring the nonredacted video of the scene captured using the video camera, the nonredacted video including a plurality of nonredacted video frames;
- an object detection module detecting one or more objects present in one or more of the plurality of nonredacted video frames, each of the detected objects associated with a predetermined object category to be redacted in the generated redacted video and each of the detected objects associated with a respective object detection probability value indicating a probability the detected object belongs to the associated predetermined object category;
- a redaction module redacting one or more of the detected one or more objects associated with the predetermined object categories by performing one or more of obfuscating the detected object and removing the detected object, and the redaction module generating the redacted video, the redacted video including, at least in part, one or more redacted video frames including one or more redacted detected objects;
- and
- a manual review module outputting the redacted video to a user interface for viewing by a user at an adaptively controlled frame rate as a function of the object detection probabilities values associated with the detected one or more objects included in a redacted video frame for manual review.
An image processing system for generating a redacted video of a nonredacted scene captured using a video camera and augmenting a manual review process of the redacted video of the scene, the image processing system comprising:
- a video acquisition module acquiring the nonredacted video of the scene captured using the video camera, the nonredacted video including a plurality of nonredacted video frames;
- an object detection module detecting one or more objects present in one or more of the plurality of nonredacted video frames, each of the detected objects associated with a predetermined object category to be redacted in the generated redacted video;
- a redaction module redacting one or more of the detected one or more objects associated with the predetermined object categories by performing one or more of obfuscating the detected object and removing the detected object, and the redaction module generating the redacted video, the redacted video including, at least in part, one or more redacted video frames including one or more redacted detected objects;
- and
- a manual review module outputting the redacted video to a user interface for viewing by a user at an adaptively controlled frame rate as a function of one or more of an area of the redacted video frame covered by the detected one or more objects, a size of the detected one or more objects included in the redacted video frame, a number of the one or more objects included in the redacted video frame, an object category of the one or more objects included in the redacted video frame, a motion characteristic of the one or more objects included in the redacted video frame, a scene change detection associated with the redacted video frame and a scene recognition detection associated with the redacted video frame.
Dependencies are inferred from the claim text.