In this paper, we address the problem of learning an adaptive appearance model for object tracking. In particular, a class of tracking techniques called “tracking by detection” have been shown to give promising results at realtime speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrades the classifier and can cause further drift. In this paper we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems, and can therefore lead to a more robust tracker with fewer parameter tweaks. We present a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. 1.

We propose a novel tracking algorithm that can work robustly in a challenging scenario such that several kinds of appearance and motion changes of an object occur at the same time. Our algorithm is based on a visual tracking decomposition scheme for the efficient design of observation and motion models as well as trackers. In our scheme, the observation model is decomposed into multiple basic observation models that are constructed by sparse principal component analysis (SPCA) of a set of feature templates. Each basic observation model covers a specific appearance of the object. The motion model is also represented by the combination of multiple basic motion models, each of which covers a different type of motion. Then the multiple basic trackers are designed by associating the basic observation models and the basic motion models, so that each specific tracker takes charge of a certain change in the object. All basic trackers are then integrated into one compound tracker through an interactive Markov Chain Monte Carlo (IMCMC) framework in which the basic trackers communicate with one another interactively while run in parallel. By exchanging information with others, each tracker further improves its performance, which results in increasing the whole performance of tracking. Experimental results show that our method tracks the object accurately and reliably in realistic videos where the appearance and motion are drastically changing over time. 1.

We address the problem of tracking and recognizing faces in real-world, noisy videos. We track faces using a tracker that adaptively builds a target model reflecting changes in appearance, typical of a video setting. However, adaptive appearance trackers often suffer from drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, our tracker introduces visual constraints using a combination of generative and discriminative models in a particle filtering framework. The generative term conforms the particles to the space of generic face poses while the discriminative one ensures rejection of poorly aligned targets. This leads to a tracker that significantly improves robustness against abrupt appearance changes and occlusions, critical for the subsequent recognition phase. Identity of the tracked subject is established by fusing pose-discriminant and person-discriminant features over the duration of a video sequence. This leads to a robust video-based face recognizer with state-of-the-art recognition performance. We test the quality of tracking and face recognition on realworld noisy videos from YouTube as well as the standard Honda/UCSD database. Our approach produces successful face tracking results on over 80 % of all videos without video or person-specific parameter tuning. The good tracking performance induces similarly high recognition rates: 100 % on Honda/UCSD and over 70 % on the YouTube set containing 35 celebrities in 1500 sequences. 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

We propose a biologically inspired framework for visual tracking based on discriminant center surround saliency. At each frame, discrimination of the target from the background is posed as a binary classification problem. From a pool of feature descriptors for the target and background, a subset that is most informative for classification between the two is selected using the principle of maximum marginal diversity. Using these features, the location of the target in the next frame is identified using top-down saliency, completing one iteration of the tracking algorithm. We also show that a simple extension of the framework to include motion features in a bottom-up saliency mode can robustly identify salient moving objects and automatically initialize the tracker. The connections of the proposed method to existing works on discriminant tracking are discussed. Experimental results comparing the proposed method to the state of the art in tracking are presented, showing improved performance. 1.

Abstract- In this paper, we propose a robust vehicle tracker for Infrared (IR) videos motivated by the recent advance in compressive sensing (CS). The new eL1-PF tracker solves a sparse model representation of moving targets via L1 regularized least squares. The sparsemodel solution addresses real-world environmental challenges such as image noises and partial occlusions. To further improve tracking performance for frame-toframe sequences involving large target pose changes, two extensions to the original L1 tracker are introduced (eL1). First, in the particle filter (PF) framework, pose information is explicitly modelled into the state space which significantly improves the effectiveness of particle sampling and propagation. Second, a probabilistic template update scheme is designed, which helps

Abstract. We use segmentations to match images by shape. To address the unreliability of segmentations, we give a closed form approximation to an average over all segmentations. Our technique has many extensions, yielding new algorithms for tracking, object detection, segmentation, and edge-preserving smoothing. For segmentation, instead of a maximum a posteriori approach, we compute the “central ” segmentation minimizing the average distance to all segmentations of an image. Our methods for segmentation and object detection perform competitively, and we also show promising results in tracking and edge–preserving smoothing. 1

Offline tracking of visual objects is particularly helpful in the presence of significant occlusions, when a frameby-frame, causal tracker is likely to lose sight of the target. In addition, the trajectories found by offline tracking are typically smoother and more stable because of the global optimization this approach entails. In contrast with previous work, we show that this global optimization can be performed in O(MNT) time for T frames of video at M × N resolution, with the help of the generalized distance transform developed by Felzenszwalb and Huttenlocher[13]. Recognizing the importance of this distance transform, we extend the computation to a more general lower envelope algorithm in certain heterogeneous l1distance metric spaces. The generalized lower envelope algorithm is of complexity O(MN(M +N)) and is useful for a more challenging offline tracking problem. Experiments show that trajectories found by offline tracking are superior to those computed by online tracking methods, and are computed at 100 frames per second.

Abstract. Automatic delineation of the prostate boundary in transrectal ultrasound (TRUS) can play a key role in image-guided prostate intervention. However, it is a very challenging task for several reasons, especially due to the large variation of the prostate shape from the base to the apex. To deal with the problem, a new method for incrementally learning the patient-specific local shape statistics is proposed in this paper to help achieve robust and accurate boundary delineation over the entire prostate gland. The proposed method is fast and memory efficient in that new shapes can be merged into the shape statistics without recomputing using all the training shapes, which makes it suitable for use in real-time interventional applications. In our work, the learned shape statistics is incorporated into a modified sequential inference model for tracking the prostate boundary. Experimental results show that the proposed method is more robust and accurate than the active shape model using global population-based shape statistics in delineating the prostate boundary in TRUS. 1

Recently, sparse representation has been applied to visual tracking to find the target with the minimum reconstruction error from the target template subspace. Though effective, these L1 trackers require high computational costs due to numerous calculations for ℓ1 minimization. In addition, the inherent occlusion insensitivity of the ℓ1 minimization has not been fully utilized. In this paper, we propose an efficient L1 tracker with minimum error bound and occlusion detection which we call Bounded Particle Resampling (BPR)-L1 tracker. First, the minimum error bound is quickly calculated from a linear least squares equation, and serves as a guide for particle resampling in a particle filter framework. Without loss of precision during resampling, most insignificant samples are removed before solving the computationally expensive ℓ1 minimization function. The BPR technique enables us to speed up the L1 tracker without sacrificing accuracy. Second, we perform occlusion detection by investigating the trivial coefficients in the ℓ1 minimization. These coefficients, by design, contain rich information about image corruptions including occlusion. Detected occlusions enhance the template updates to effectively reduce the drifting problem. The proposed method shows good performance as compared with several state-of-the-art trackers on challenging benchmark sequences. 1.