Omar Arif

Tracking multiple workers on construction sites using video cameras

This paper proposes a tracking scheme for tracking multiple workers on construction sites using video cameras. Prior work has compared several contemporary tracking algorithms on construction sites and identified several difficulties, one of which included the existence of interacting workforce. In order to address the challenge of multiple workers within the cameras field of view, the authors have developed a tracking algorithm based upon machine learning methods. The algorithm requires several sample templates of the tracking target and learns a general model that can be applied to other targets with similar geometry. A parameterized feature bank is proposed to handle the case of variable appearance content. The tracking initialization has been discussed for different types of video cameras. A multiple tracking management module is applied to optimize the system. The principal objective of this paper is to test and demonstrate the feasibility of tracking multiple workers from statically placed and dynamically moving cameras.

Non-rigid object localization and segmentation using eigenspace representation

This paper presents a novel non-rigid object localization and segmentation algorithm using an eigenspace representation. Previous approaches to eigenspace methods for object tracking use vectorized image regions as observations, whereas the proposed method uses each individual pixel as an observation. Localization using the pixel-wise eigenspace representation is robust to noise and occlusions. A unique feature of the approach is that it permits segmentation in addition to localization. Localization and segmentation are carried out by deriving a similarity function in the eigenspace. The algorithm is tested on synthetic and real world tracking examples to demonstrate the performance.

Visual tracking and segmentation using Time-of-Flight sensor

Time-of-Flight (TOF) sensors provide range information at each pixel in addition to intensity information. They are becoming more widely available and more affordable. This paper examines the utility of dense TOF range data for image segmentation and tracking. Energy based formulations for image segmentation are used, which consist of a data term and a smoothness term. The paper proposes novel methods to incorporate range information, obtained from the TOF sensor, into the data and the smoothness term of the energy. Graph cut is used to minimize the energy.

Kernel covariance image region description for object tracking

We propose a nonlinear covariance region descriptor for target tracking. The target object appearance and spatial information is represented using a covariance matrix in a target derived Hilbert space using kernel principal component analysis. A similarity measure is derived, which computes the similarity of a candidate image region to the learned covariance matrix. A variational technique is provided to maximize the similarity measure, which iteratively finds the best matched object region. Tracking performance is demonstrated on a variety of sequences containing noise, occlusions, illumination changes, background clutter, etc.

Kernel map compression using generalized radial basis functions

The use of Mercer kernel methods in statistical learning theory provides for strong learning capabilities, as seen in kernel principal component analysis and support vector machines. Unfortunately the computational complexity of the resulting method is of the order of the training set, which is quite large for many applications. This paper proposes a two step procedure for arriving at a compact and computationally efficient learning procedure. After learning, the second step takes advantage of the universal approximation capabilities of generalized radial basis function neural networks to efficiently approximate the empirical kernel maps. Sample applications demonstrate significant compression of the kernel representation with graceful performance loss.

Robust Density Comparison for Visual Tracking

This paper presents a technique to robustly compare two distributions represented by samples, without explicitly estimating the density. The method is based on mapping the distributions into a reproducing kernel Hilbert space, where eigenvalue decomposition is performed. Retention of only the top M eigenvectors minimizes the effect of noise on density comparison. A sample application of the technique is visual tracking, where an object is tracked by minimizing the distance between a model distribution and candidate distributions.

Kernel Map Compression for Speeding the Execution of Kernel-Based Methods

The use of Mercer kernel methods in statistical learning theory provides for strong learning capabilities, as seen in kernel principal component analysis and support vector machines. Unfortunately, after learning, the computational complexity of execution through a kernel is of the order of the size of the training set, which is quite large for many applications. This paper proposes a two-step procedure for arriving at a compact and computationally efficient execution procedure. After learning in the kernel space, the proposed extension exploits the universal approximation capabilities of generalized radial basis function neural networks to efficiently approximate and replace the projections onto the empirical kernel map used during execution. Sample applications demonstrate significant compression of the kernel representation with graceful performance loss.

Robust Density Comparison Using Eigenvalue Decomposition

Many problems in various fields require measuring the similarity between two distributions. Often, the distributions are represented through samples and no closed form exists for the distribution, or it is unknown what the best parametrization is for the distribution . Therefore, the traditional approach of first estimating the probability distribution using the samples, then comparing the distance between the two distributions is not feasible. In this chapter, a method to compute the similarity between two distributions, which is robust to noise and outliers, is presented. The method works directly on the samples without requiring the intermediate step of density estimation, although the approach is closely related to density estimation. The method is based on mapping the distributions into a reproducing kernel Hilbert space, where eigenvalue decomposition is performed. Retention of only the top M eigenvectors minimizes the effect of noise on density comparison.

Pre-image Problem in Manifold Learning and Dimensional Reduction Methods

Manifold learning and dimensional reduction methods provide a low dimensional embedding for a collection of training samples. These methods are based on the eigenvalue decomposition of the kernel matrix formed using the training samples. In [2] the embedding is extended to new test samples using the Nystrom approximation method. This paper addresses the pre-image problem for these methods, which is to find the mapping back from the embedding space to the input space for new test points. The relationship of these learning methods to kernel principal component analysis [6] and the connection of the out-of-sample problem to the pre-image problem [1] is used to provide the pre-image.

Non-linear eigenspace visual object tracking

This paper presents a visual object tracking algorithm using an eigenspace representation. Previous approaches to eigenspace methods for object tracking use vectorized image regions as observations. Here, feature vectors associated to pixels of the target template are considered to be individual observations of the target object. The collection of observations is learned using non-linear subspace projection to arrive at an eigenspace representation. This representation allows tracking pixel-wise but the pixels are tied together using subspace representation which provides a robust and compact representation of the object. Localization and segmentation are carried out by deriving a similarity function in the eigenspace representation. A gradient descent and mean-shift based techniques are derived to maximize the similarity function with respect to the transformation parameters. The de-noising and clustering capabilities of the eigenspace representation lead to a localization procedure that is robust to noise and partial occlusion. For fast moving objects and to recover from total occlusion, a probabilistic search strategy, based on particle filter, is also developed. A unique feature of our approach is that it permits segmentation in addition to localization when multiple templates of the target are given. The performance of the algorithm is tested on real world tracking examples.