IEEE Transactions on Pattern Analysis and Machine Intelligence · 2006 · 66 citations · 36 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionMotion EstimationObject DetectionObject RecognitionShape AnalysisVariational InferenceVisual TrackingBoltzmann DistributionBoltzmann EquationsBoltzmann MachinesHuman DetectionMarkov Random Field ModelsObjectsPedestrian DetectionProbabilistic Analysis
The large shape variability and partial occlusions challenge most object detection and tracking methods for nonrigid targets such as pedestrians. This paper presents a new approach based on a two-layer statistical field model that characterizes the prior of the complex shape variations as a Boltzmann distribution and embeds this prior and the complex image likelihood into a Markov field. A probabilistic variational analysis of this model reveals a set of fixed-point equations characterizing the equilibrium of the field. It leads to computationally efficient methods for calculating the image likelihood and for training the model. Based on that, effective algorithms for detecting nonrigid objects are developed. This new approach has several advantages. First, it is intrinsically suitable for capturing local nonrigidity. In addition, due to the distributed likelihood, this approach is robust to partial occlusions. Moreover, the two-layer structure provides large flexibility of modeling the image observations, which makes the new method robust to clutters. Extensive experiments demonstrate its effectiveness.
36
Histograms of Oriented Gradients for Human Detection
Navneet Dalal, Bill Triggs · 2005 · 31.9K citations · Full text
Rapid object detection using a boosted cascade of simple features
Paul Viola, Michael Jones · 2005 · 18.2K citations
Active Shape Models-Their Training and Application
T.F. Cootes, Chris Taylor, D. H. Cooper et al. · Computer Vision and Image Understanding · 1995 · 7.2K citations · Full text