Abstract. In this paper, we adaptively model the appearance of objects based on Mixture of Gaussians in a joint spatial-color space (the approach is called SMOG). We propose a new SMOG-based similarity measure. SMOG captures richer information than the general color histogram because it incorporates spatial layout in addition to color. This appearance model and the similarity measure are used in a framework of Bayesian probability for tracking natural objects. In the second part of the paper, we propose an Integral Gaussian Mixture (IGM) technique, as a fast way to extract the parameters of SMOG for target candidate. With IGM, the parameters of SMOG can be computed efficiently by using only simple arithmetic operations (addition, subtraction, division) and thus the computation is reduced to linear complexity. Experiments show that our method can successfully track objects despite changes in foreground appearance, clutter, occlusion, etc.; and that it outperforms several colorhistogram based methods. 1

Abstract—In this paper, a multitarget tracking system for collocated video and acoustic sensors is presented. We formulate the tracking problem using a particle filter based on a state-space approach. We first discuss the acoustic state-space formulation whose observations use a sliding window of direction-of-arrival estimates. We then present the video state space that tracks a target’s position on the image plane based on online adaptive appearance models. For the joint operation of the filter, we combine the state vectors of the individual modalities and also introduce a time-delay variable to handle the acoustic-video data synchronization issue, caused by acoustic propagation delays. A novel particle filter proposal strategy for joint state-space tracking is introduced, which places the random support of the joint filter where the final posterior is likely to lie. By using the Kullback-Leibler divergence measure, it is shown that the joint operation of the filter decreases the worst case divergence of the individual modalities. The resulting joint tracking filter is quite robust against video and acoustic occlusions due to our proposal strategy. Computer simulations are presented with synthetic and field data to demonstrate the filter’s performance. Index Terms—Acoustic tracking, multimodal data fusion, particle filtering, visual tracking. I.

While face recognition (FR) from a single still image has been studied extensively [13], [57], FR based on a video sequence is an emerging topic, evidenced by the growing increase in the literature. It is predictable that with the ubiquity of video sequences, FR based on video sequences will become more and more popular. In this chapter, we also address FR based on a group of still images (also referred to as multiple still images). Multiple still images

Abstract. This paper presents a method to recover the 3D configuration of a face in each frame of a video. The 3D configuration consists of the three translational parameters and the three orientation parameters which correspond to the yaw, pitch and roll of the face. Such information is important for applications like face modeling, recognition, expression analysis, etc. which require head stabilization. The approach combines the structural advantages of geometric modeling with the statistical advantages of a particle-filter based inference. The face is modeled as the curved surface of a cylinder which is free to translate and rotate arbitrarily. The geometric modeling takes care of pose and self-occlusion while the statistical modeling handles moderate occlusion and illumination variations. Experimental results on multiple datasets are provided to show the efficacy of the approach. The insensitivity of our approach to calibration parameters (focal length) is also shown. 1

In this survey, we present a brief analysis of single camera object detection and tracking methods. We also give a comparison of their computational complexities. These methods are designed to perform accurately under difficult conditions such as erratic motion, drastic illumination change, and noise contamination.

This paper introduces a two view tracking method which uses the homography relation between the two views to handle occlusions. An adaptive appearance-based model is incorporated in a particle filter to realize robust visual tracking. Occlusion is detected using robust statistics. When there is occlusion in one view, the homography from this view to other views is estimated from previous tracking results and used to infer the correct transformation for the occluded view. Experimental results show the robustness of the two view tracker. 1.

We address the problem of seeking the global mode of a density function using the mean shift algorithm. Mean shift, like other gradient ascent optimisation methods, is susceptible to local maxima, and hence often fails to find the desired global maximum. In this work, we propose a multi-bandwidth mean shift procedure that avoids this problem, which we term annealed mean shift, as it shares similarities with the annealed importance sampling procedure. The bandwidth of the algorithm plays the same role as the temperature in annealing. We observe that the over-smoothed density function with a sufficiently large bandwidth is uni-modal. Using a continuation principle, the influence of the global peak in the density function is introduced gradually. In this way the global maximum is more reliably located. Generally, the price of this annealing-like procedure is that more iterations are required. Since it is imperative that the computation complexity is minimal in real-time applications such as visual tracking. We propose an accelerated version of the mean shift algorithm. Compared with the conventional mean shift algorithm, annealed mean shift can significantly decrease the number of iterations required for convergence. The proposed algorithm is applied to the problems of visual tracking and object localisation. We empirically show on various data sets that the proposed algorithm can reliably find the true object location when the starting position of mean shift is far away from the global maximum, in contrast with the conventional mean shift algorithm that will usually get trapped in a spurious local maximum.

We propose a similarity measure based on a Spatial-color Mixture of Gaussians (SMOG) appearance model for particle filters. This improves on the popular similarity measure based on color histograms because it considers not only the colors in a region but also the spatial layout of the colors. Hence, the SMOG-based similarity measure is more discriminative. To efficiently compute the parameters for SMOG, we propose a new technique, with which the computational time is greatly reduced. We also extend our method by integrating multiple cues to increase the reliability and robustness. Experiments show that our method can successfully track objects in many difficult situations.

In this chapter, we address the problem of tracking a face and its facial features in real video sequences, considering two approaches. The first approach is based on a particle filter tracker capable of tracking the 3D head pose of a person. In this case, the distribution of observations is derived from an eigenspace decomposition. The second approach introduces an appearanceadaptive tracker capable of tracking both the 3D head pose and facial animations. It consists of an online adapted observation model of the face texture, together with adaptive dynamics in the sense that they are guided by a deterministic search in a state space. This approach extends the concept of online appearance models to the case of tracking 3D non-rigid face motion (3D head pose and facial animations). Experiments on real video sequences show the effectiveness of the developed methods. Accurate tracking was obtained even in the presence of perturbing factors such as significant head pose or local facial occlusions. 1

Abstract. The sparse representation has been widely used in many areas and utilized for visual tracking. Tracking with sparse representation is formulated as searching for samples with minimal reconstruction errors from learned template subspace. However, the computational cost makes it unsuitable to utilize high dimensional advanced features which are often important for robust tracking under dynamic environment. Based on the observations that a target can be reconstructed from several templates, and only some of the features with discriminative power are significant to separate the target from the background, we propose a novel online tracking algorithm with two stage sparse optimization to jointly minimize the target reconstruction error and maximize the discriminative power. As the target template and discriminative features usually have temporal and spatial relationship, dynamic group sparsity (DGS) is utilized in our algorithm. The proposed method is compared with three state-of-art trackers using five public challenging sequences, which exhibit appearance changes, heavy occlusions, and pose variations. Our algorithm is shown to outperform these methods. 1