Hong Kong Applied Science and Technology Research Institute Company, Limited

Hong Kong Applied Science and Technology Research

Tai Pang Wu

Zhiqian Li

Kenneth Kwan Yee Wong

Chun Man Lawrence Mak

Xiao Zhou

This invention, which relates to retrieving an object from a video or a photo where the object matches a hand-drawn sketch, discloses a method for automatically estimating a perceptual bias level with respect to a feature of the sketch. The method allows estimation based on the sketch alone without involving an extra database. In one embodiment, the method comprises using an expectation-maximization tensor voting (EMTV) method to analyze a statistical distribution of the feature. The statistical distribution is analyzed by forming an objective function having the statistical distribution's information parameterized by the perceptual bias level, and then maximizing the objective function according to a set of iterative update rules. In another embodiment, the method for automatically estimating a perceptual bias level is incorporated into a method for retrieving one or more objects from an image or video database where the one or more objects match a hand-drawn sketch.

Perceptual bias level estimation for hand-drawn sketches in sketch-photo matching

A computer-implementable method for creating a summary video with depth information, comprising: recognizing moving objects from the input original video; generating an animated moving object cutout for each of the recognized moving objects by duplicating and stacking successive frames in the input original video containing images of the respective moving object; constructing a scene background by using texture of scenes in the input original video and estimating any missing portion; rendering a Dynamic 3D Scene by using depth information of foreground objects in the input original video and the scene background to create a three-dimensional scene and overlaying the animated moving object cutouts on to the three-dimensional scene according to their respective longitude, latitude, and depth locations in the three-dimensional scene; and synthesizing the summary video, by using the Dynamic 3D Scene.

Growing community of inventors

Hong Kong, China

Tai Pang Wu