Occluding Contour Detection and Storage for Digital Photography

Technology #9978

Questions about this technology? Ask a Technology Manager

Download Printable PDF

Categories
Inventors
Professor William Freeman
Department of EECS, MIT
External Link (billf.mit.edu)
Ce Liu
CSAIL, MIT
Managed By
Daniel Dardani
MIT Technology Licensing Officer
Patent Protection

Occluding contour detection and storage for digital photography

US Patent 2006-0204040

Occluding contour detection and storage for digital photography

US Patent Pending 7,715,589

Applications

This technology relates to computer vision and image processing, specifically for contour detection. It has applications in the digital photography market for enhancing photo quality and improving editing techniques.

Problem Addressed  

Consumers of digital photography have come to have high expectations of the rapidly expanding market, including artifact-free photographs and the ability to easily edit their digital pictures. Today’s high-resolution cameras allow the smallest relative motions to be detected. The analysis of these motion-based depth cues is useful for processing enhanced photographs of the 3D world. The Inventors have developed an efficient technique to store information regarding the relative motion objects in a scene for superior in- and off-camera processing and image editing. This technique specifically applies to occluding contour detection, which enhances edge perception in still images for enhanced 3D image processing. 

Technology

In occluding contour detection, cues obtained from a static 2D image are combined with cues based on the relative motion of objects in the image. These pieces of local evidence are integrated globally using dynamic programming to determine contours in the image. This process is initiated once an image of a scene is captured, upon which local pixel-wise flow fields are obtained to determine a warped image. This image is then compared to the original to form a disparity map, which is integrated with static image cues to produce a product image map. This map is processed with a tracking technique to reveal occluding contours, which may then be used with the original image for subsequent processing and editing. This evidence can also be integrated across time by tracking the moving contours, allowing evidence gathered at one time to influence the interpretation of that contour some few seconds later, perhaps using a particle filter. Integrating over time and across space allows the occluding contours to be identified robustly. This technology quickly calculates and tracks the occluding contours in the camera around the time of the photographic exposure, and stores that information in a compact manner along with the image.

Advantages

  • Information stored efficiently in terms of time and space
  • Robust detection of occluding contours in images for enhanced 3D processing and editing