Omar Arif

... Omar Arif and Patricio Antonio Vela School of Electrical and Computer Engineering Georgia Institute of Technology, Atlanta, GA 30332 omararif@gatech.edu, pvela@ece.gatech.edu ... Localization using the pixel-wise eigenspace representation is robust to noise and occlusions. ...

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.

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 camera’s field of view, the authors have developed a

Accidents during ground operations at airports result in substantial losses to the air transportation industry. Automated monitoring of airport ground operations can lead to cost effective strategies to reduce such accidents, either through pro-active warning systems or through feedback for improved training. This paper reviews ongoing work by the authors on automated surveillance in heavily mechanized industries with a focus on the application of the algorithms to airport monitoring. In particular, the focus is automated surveillance of airport ground operations in non-movement areas.

... me settle down initially. Thanks to Tauseef-ur-Rehman, Taimoor Khawaja, Ali Hashmi, Aleem, Farooq Akram, Salman, Qaisar Chaudary, and Irtezaa for their help and support. Many thanks to my old friend Uzair Hashmi, who remained in contact with me all these years. ...

Online contour-based tracking is considered through the estimation perspective. We propose a recursive dynamic filtering solution to the tracking problem. The state of the target is described by a pose state which represents the ensemble movement and a shape state which represents the local deformations. The shape state of the filter is described implicitly by a probability field with prediction and correction mechanisms expressed accordingly. The filtering procedure decouples the pose and shape estimation. Experiments conducted with objective measures of quality demonstrate improved tracking.

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 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 and the connection of the out-of-sample problem to the pre-image problem is used to provide the pre-image.

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.

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.