Visual tracking using the Earth Mover's Distance between Gaussian mixtures and Kalman filtering
Image and Vision Computing
Localized earth mover's distance for robust histogram comparison
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Displacement interpolation using Lagrangian mass transport
Proceedings of the 2011 SIGGRAPH Asia Conference
Motion segmentation by model-based clustering of incomplete trajectories
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part II
Visual tracking by adaptive kalman filtering and mean shift
SETN'10 Proceedings of the 6th Hellenic conference on Artificial Intelligence: theories, models and applications
A novel framework for motion segmentation and tracking by clustering incomplete trajectories
Computer Vision and Image Understanding
Supervised earth mover's distance learning and its computer vision applications
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Tensor-SIFT Based Earth Mover's Distance for Contour Tracking
Journal of Mathematical Imaging and Vision
A survey of appearance models in visual object tracking
ACM Transactions on Intelligent Systems and Technology (TIST) - Survey papers, special sections on the semantic adaptive social web, intelligent systems for health informatics, regular papers
Hi-index | 0.14 |
The Earth Mover's Distance (EMD) is a similarity measure that captures perceptual difference between two distributions. Its computational complexity, however, prevents a direct use in many applications. This paper proposes a novel Differential EMD (DEMD) algorithm based on the sensitivity analysis of the simplex method and offers a speedup at orders of magnitude compared with its brute-force counterparts. The DEMD algorithm is discussed and empirically verified in the visual tracking context. The deformations of the distributions for objects at different time instances are accommodated well by the EMD, and the differential algorithm makes the use of EMD in real-time tracking possible. To further reduce the computation, signatures, i.e., variable-size descriptions of distributions, are employed as an object representation. The new algorithm models and estimates local background scenes as well as foreground objects to handle scale changes in a principled way. Extensive quantitative evaluation of the proposed algorithm has been carried out using benchmark sequences and the improvement over the standard Mean Shift tracker is demonstrated.