Abstract.A probabilistic method for tracking 3D articulated human figures in monocular image sequences is presented. Within a Bayesian framework, we define a generative model of image appearance, a robust likelihood function based on image graylevel differences, and a prior probability distribution over pose and joint angles that models how humans move. The posterior probability distribution over model parameters is represented using a discrete set of samples and is propagated over time using particle filtering. The approach extends previous work on parameterized optical flow estimation to exploit a complex 3D articulated motion model. It also extends previous work on human motion tracking by including a perspective camera model, by modeling limb self occlusion, and by recovering 3D motion from a monocular sequence. The explicit posterior probability distribution represents ambiguities due to image matching, model singularities, and perspective projection. The method relies only on a frame-to-frame assumption of brightness constancy and hence is able to track people under changing viewpoints, in grayscale image sequences, and with complex unknown backgrounds.

Abstract. This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an explicit probabilistic model from available training data is currently impractical. Instead we exploit methods from texture synthesis that treat images as representing an implicit empirical distribution. These methods replace the problem of representing the probability of a texture pattern with that of searching the training data for similar instances of that pattern. We extend this idea to temporal data representing 3D human motion with a large database of example motions. To make the method useful in practice, we must address the problem of efficient search in a large training set; efficiency is particularly important for tracking. Towards that end, we learn a low dimensional linear model of human motion that is used to structure the example motion database into a binary tree. An approximate probabilistic tree search method exploits the coefficients of this low-dimensional representation and runs in sub-linear time. This probabilistic tree search returns a particular sample human motion with probability approximating the true distribution of human motions in the database. This sampling method is suitable for use with particle filtering techniques and is applied to articulated 3D tracking of humans within a Bayesian framework. Successful tracking results are presented, along with examples of synthesizing human motion using the model.

When tracking a large number of targets, it is ofren computationally expensive to represenr the full joint distribution over target stares. In cases where the targets move independently, each target can instead be rracked with a separatefiker: However, this leads to a model-data association problem. Another approach to solve rhe problem with computational complexity is to track only thefirsr moment of the joint distribution, rhe probability hypothesis density (PHD). The integral ofthis distribution over any area S is the expectednumber of targets within S. Since no record of object identity is kept, the model-data association problem is avoided.The contribution of this paper is a panicle $her implementation of rhe PHD finer mentioned above. This PHD panicle filter is applied to tracking of mulriple vehicles in terrain, a non-linear tracking problem. Experiments show that thejilter can track a changing number of vehicles mbusrly, achieving near-real-rime performance.

This paper describes a framework for learning probabilistic models of objects and scenes and for exploiting these models for tracking complex, deformable, or

No abstract