• shareshare
  • link
  • cite
  • add
auto_awesome_motion View all 5 versions
Publication . Conference object . 1997

Model-Based Object Tracking in Cluttered Scenes with Occlusions

Frédéric Jurie;
Open Access
Published: 07 Sep 1997
Publisher: HAL CCSD
Country: France

International audience; We propose an efficient method for tracking 3D modelled objects in cluttered scenes. Rather than tracking objects in the image, our approach relies on the object recognition aspect of tracking. Candidate matches between image and model features define volumes in the space of transformations. The volumes of the pose space satisfying the maximum number of correspondences are those that best align the model with the image. Object motion defines a trajectory in the pose space. We give some results showing that the presented method allows tracking of objects even when they are totally occluded for a short while, without supposing any motion model and with a low computational cost (below 200 ms per frame on a basic workstation). Furthermore, this algorithm can also be used to initialize the tracking.

Subjects by Vocabulary

ACM Computing Classification System: ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION

Microsoft Academic Graph classification: 3D single-object recognition Video tracking Pose Trajectory Artificial intelligence business.industry business Computer vision Computer science Motion estimation Tracking (particle physics) Cognitive neuroscience of visual object recognition


Hough transforms, image matching, image sequences, intelligent control, motion estimation, object recognition, probability, robot vision, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]

Related Organizations

d1 2 d 1