David Suter

Joint Detection and Estimation of Multiple Objects From Image Observations

The problem of jointly detecting multiple objects and estimating their states from image observations is formulated in a Bayesian framework by modeling the collection of states as a random finite set. Analytic characterizations of the posterior distribution of this random finite set are derived for various prior distributions under the assumption that the regions of the observation influenced by individual objects do not overlap. These results provide tractable means to jointly estimate the number of states and their values from image observations. As an application, we develop a multi-object filter suitable for image observations with low signal-to-noise ratio (SNR). A particle implementation of the multi-object filter is proposed and demonstrated via simulations.

Fast Supervised Hashing with Decision Trees for High-Dimensional Data

Supervised hashing aims to map the original features to compact binary codes that are able to preserve label based similarity in the Hamming space. Non-linear hash functions have demonstrated their advantage over linear ones due to their powerful generalization capability. In the literature, kernel functions are typically used to achieve non-linearity in hashing, which achieve encouraging retrieval perfor- mance at the price of slow evaluation and training time. Here we propose to use boosted decision trees for achieving non-linearity in hashing, which are fast to train and evaluate, hence more suitable for hashing with high dimensional data. In our approach, we first propose sub-modular formulations for the hashing binary code inference problem and an efficient GraphCut based block search method for solving large-scale inference. Then we learn hash func- tions by training boosted decision trees to fit the binary codes. Experiments demonstrate that our proposed method significantly outperforms most state-of-the-art methods in retrieval precision and training time. Especially for high- dimensional data, our method is orders of magnitude faster than many methods in terms of training time.

Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model

We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel principal component analysis (KPCA) based feature extraction and factorial conditional random field (FCRF) based motion modeling. Silhouette data is represented more compactly by nonlinear dimensionality reduction that explores the underlying structure of the articulated action space and preserves explicit temporal orders in projection trajectories of motions. FCRF models temporal sequences in multiple interacting ways, thus increasing joint accuracy by information sharing, with the ideal advantages of discriminative models over generative ones (e.g., relaxing independence assumption between observations and the ability to effectively incorporate both overlapping features and long-range dependencies). The experimental results on two recent datasets have shown that the proposed framework can not only accurately recognize human activities with temporal, intra-and inter-person variations, but also is considerably robust to noise and other factors such as partial occlusion and irregularities in motion styles.

Adaptive Object Tracking Based on an Effective Appearance Filter

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.

Learning and Matching of Dynamic Shape Manifolds for Human Action Recognition

In this paper, we learn explicit representations for dynamic shape manifolds of moving humans for the task of action recognition. We exploit locality preserving projections (LPP) for dimensionality reduction, leading to a low-dimensional embedding of human movements. Given a sequence of moving silhouettes associated to an action video, by LPP, we project them into a low-dimensional space to characterize the spatiotemporal property of the action, as well as to preserve much of the geometric structure. To match the embedded action trajectories, the median Hausdorff distance or normalized spatiotemporal correlation is used for similarity measures. Action classification is then achieved in a nearest-neighbor framework. To evaluate the proposed method, extensive experiments have been carried out on a recent dataset including ten actions performed by nine different subjects. The experimental results show that the proposed method is able to not only recognize human actions effectively, but also considerably tolerate some challenging conditions, e.g., partial occlusion, low-quality videos, changes in viewpoints, scales, and clothes; within-class variations caused by different subjects with different physical build; styles of motion; etc

Robust adaptive-scale parametric model estimation for computer vision

Robust model fitting essentially requires the application of two estimators. The first is an estimator for the values of the model parameters. The second is an estimator for the scale of the noise in the (inlier) data. Indeed, we propose two novel robust techniques: the two-step scale estimator (TSSE) and the adaptive scale sample consensus (ASSC) estimator. TSSE applies nonparametric density estimation and density gradient estimation techniques, to robustly estimate the scale of the inliers. The ASSC estimator combines random sample consensus (RANSAC) and TSSE, using a modified objective function that depends upon both the number of inliers and the corresponding scale. ASSC is very robust to discontinuous signals and data with multiple structures, being able to tolerate more than 80 percent outliers. The main advantage of ASSC over RANSAC is that prior knowledge about the scale of inliers is not needed. ASSC can simultaneously estimate the parameters of a model and the scale of the inliers belonging to that model. Experiments on synthetic data show that ASSC has better robustness to heavily corrupted data than least median squares (LMedS), residual consensus (RESC), and adaptive least Kth order squares (ALKS). We also apply ASSC to two fundamental computer vision tasks: range image segmentation and robust fundamental matrix estimation. Experiments show very promising results.

Robust Optic Flow Computation

This paper formulates the optic flow problem as a set of over-determined simultaneous linear equations. It then introduces and studies two new robust optic flow methods. The first technique is based on using the Least Median of Squares (LMedS) to detect the outliers. Then, the inlier group is solved using the least square technique. The second method employs a new robust statistical method named the Least Median of Squares Orthogonal Distances (LMSOD) to identify the outliers and then uses total least squares to solve the optic flow problem. The performance of both methods are studied by experiments on synthetic and real image sequences. These methods outperform other published methods both in accuracy and robustness.

Assessing the performance of corner detectors for point feature tracking applications

Abstract In this paper we assess the performance of a variety of corner (point) detecting algorithms for feature tracking applications. We analyze four different types of corner extractors, which have been widely used for a variety of applications (they are described later in the paper). We use corner stability and corner localization properties as measures to evaluate the quality of the features extracted by the four detectors. For effective assessment of the corner detectors, first, we employed image sequences with no motion (simply static image sequences), so that the appearance and disappearance of corners in each frame is purely due to image plane noise and illumination conditions. The second stage included experiments on sequences with small motion. The experiments were devised to make the testing environment ideal to analyze the stability and localization properties of the corners extracted. The corners detected from the initial frame are then matched through the sequence using a corner matching strategy. We employed two different types of matchers, namely the GVM (Gradient Vector Matcher) and the Product Moment Coefficient Matcher (PMCM). Each of the corner detectors was tested with each of the matching algorithms to evaluate their performance in tracking (matching) the features. The experiments were carried out on a variety of image sequences with and without motion.

A General Two-Step Approach to Learning-Based Hashing

Most existing approaches to hashing apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form. This tight coupling restricts the flexibility of the method to respond to the data, and can result in complex optimization problems that are difficult to solve. Here we propose a flexible yet simple framework that is able to accommodate different types of loss functions and hash functions. This framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods. Our framework decomposes the hashing learning problem into two steps: hash bit learning and hash function learning based on the learned bits. The first step can typically be formulated as binary quadratic problems, and the second step can be accomplished by training standard binary classifiers. Both problems have been extensively studied in the literature. Our extensive experiments demonstrate that the proposed framework is effective, flexible and outperforms the state-of-the-art.

Visual tracking of numerous targets via multi-Bernoulli filtering of image data

This paper presents a novel Bayesian method to track multiple targets in an image sequence without explicit detection. Our method is formulated based on finite set representation of the multi-target state and the recently developed multi-Bernoulli filter. Experimental results on sport player and cell tracking studies show that our method can automatically track numerous targets, and it outperforms the state-of-the-art in terms of false positive (false alarm) and false negative (missing) rates as detection error measures, and in terms of label switching rate and lost tracks ratio as tracking error measures.