Robust tracking of humans and vehicles in cluttered scenes with occlusions

Oberti, Franco; Calcagno, Salvatore; Zara, M.; Regazzoni, Carlo S.

doi:10.1109/icip.2002.1039049

Cited by 23 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a robust model has to be designed with a sufficient degree of flexibility in order to be representative and effective for all typologies of objects. The model here presented takes origin from an existing work presented in [45] where shape information under the form of high curvature points (i.e. corners [30]) is used to estimate the center of mass of each blob in situation of occlusions.…”

Section: The Shape Based Static Modelmentioning

confidence: 99%

Self-organizing shape description for tracking and classifying multiple interacting objects

Marchesotti

Regazzoni

2006

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Section: The Shape Based Static Modelmentioning

confidence: 99%

Self-organizing shape description for tracking and classifying multiple interacting objects

Marchesotti

Regazzoni

2006

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

“…Oberti et al in [8] use a variation of the GHT to track objects by comparing the observed corners with the model of the object (i.e. the GHT).…”

Section: Analogies Between Ght-based Tracking and Mhstmentioning

confidence: 99%

MAP Particle Selection in Shape-Based Object Tracking

Dore

Regazzoni

Musso³

2007

2007 IEEE International Conference on Image Processing

View full text Add to dashboard Cite

The Bayesian filtering for recursive state estimation and the shape-based matching methods are two of the most commonly used approaches for target tracking. The Multiple Hypothesis Shape-based Tracking (MHST) algorithm, proposed by the authors in a previous work, combines these two techniques using the Particle Filter algorithm. The state of the object is represented by a vector of the target corners (i.e. points in the image with high curvature) and the multiple state configurations (particles) are propagated in time with a weight associated to their probability. In this paper we demonstrate that, in the MHST, the likelihood probability used to update the weights is equivalent to the voting mechanism for Generalized Hough Transform (GHT)-based tracking. This statement gives an evident explanation about the suitability of a MAP (Maximum a Posteriori) estimate from the posterior probability obtained using MHST. The validity of the assertion is verified on real sequences showing the differences between the MAP and the MMSE estimate.

show abstract

“…In the case that there is a dense situation in observations set and K observations 1 n to K n contributed with the model element m to vote for …”

Section: The Global Position Estimation (Voting)mentioning

confidence: 99%

“…Oberti et al [1] proposed an algorithm to track multiple objects by modeling them using corners information. The method is applied to the output of a detection-and-tracking system to learn the object model adaptively when the object is completely isolated.…”

Section: Introductionmentioning

confidence: 99%