Method and apparatus for image enhancement and edge verification using at least one additional image

Abstract

An image processing system comprises an image processor configured to perform first and second edge detection operations on respective first and second images to obtain respective first and second edge images, to apply a joint edge weighting operation using edges from the first and second edge images, to generate an edge mask based on results of the edge weighting operation, to utilize the edge mask to obtain a third edge image, and to generate a third image based on the third edge image. By way of example only, in a given embodiment the first image may comprise a first depth image generated by a depth imager, the second image may comprise a two-dimensional image of substantially the same scene as the first image, and the third image may comprise an enhanced depth image having enhanced edge quality relative to the first depth image.

Description

technical field [0001] The present invention relates generally to image processing, and more particularly to processing of images such as depth maps and other types of depth maps. Background technique [0002] A number of different techniques are known for detecting edges in images. Such techniques generally produce acceptable results when applied to high-resolution images, such as photographs or other two-dimensional (2D) images produced by digital cameras. However, many important machine vision applications make use of devices such as structured light (SL) cameras or time-of-flight (T o F) A three-dimensional (3D) image produced by a depth imager such as a camera. These depth images are often low resolution images and often include noisy and blurred edges. [0003] Conventional edge detection techniques generally do not perform well when applied to depth images. For example, these conventional techniques can miss important edges in a given depth image or locate multipl...

AI Technical Summary

Problems solved by technology

The resulting detected edges are of poor quality and thus undermine the effectiveness of subsequent image processing operations such as feature extraction, pattern recognition, gesture recognition, object recognition, and tracking

Images