Tracking objects in low frame rate videos
OwnerFatih Porikli, Oncel Tuzelinventors
Life of this patent
Estimating the term…
Abstract
A method tracks a moving object in a video acquired of a scene with a camera. A background model is maintained for each frame, and moving objects are detected according to changes in the background model. An object model is maintained for the moving object, and kernels are generated for the moving object. A mean-shift process is applied to each kernel in each frame to determine a likelihood of an estimated location of the moving object in each frame, according to the background models, the object model, and the mean shift kernels to track the moving object in the video.
Claims29
A method for tracking a moving object in a video acquired of a scene with a camera, comprising the steps of:
- acquiring a video of a scene, the video including a sequence of frames, each frame including a plurality of pixels, and for each frame, further comprising the steps of:
- maintaining a background model;
- detecting a moving object according to the background model;
- maintaining an object model for the moving object;
- assigning, to the moving object, a plurality of kernels according to a likelihood of a pathway of the moving object and a likelihood of the object model;
- applying, to each kernel, a mean-shift process to estimate a location of the kernel;
- combining the estimated locations of the plurality of kernels;
- and
- determining an estimated location of the moving object according to the combined estimated locations of the plurality of shift kernels to track the moving object in the video.
Dependencies are inferred from the claim text.