Santhosh Sunderrajan

University of California, Santa Barbara | UCSB · Department of Electrical and Computer Engineering

Tracking and re-identification in wide-area camera networks is a challenging problem due to non-overlapping visual fields, varying imaging conditions and appearance changes. We consider the problem of person re-identification and tracking, and propose a novel clothing context aware color extraction method that is robust to such changes. Annotated s...

Camera networks provide opportunities for practical video surveillance and monitoring, but tracking people across the network presents many computational and modeling hurdles that researchers have yet to surmount.

This paper proposes a distributed multi-camera tracking algorithm with interacting particle filters. We propose a novel algorithm for multi-view appearance modeling by sharing training samples between the views. Motivated by incremental learning, we create an intermediate data representation between two camera views with generative subspaces as poi...

This paper presents a novel and computationally efficient multiobject tracking-by-detection algorithm with interacting particle filters. The proposed online tracking methodology could be scaled to hundreds of objects and could be completely parallelized. For every object, we have a set of two particle filters, i.e. local and global. The local parti...

Humans use context and scene knowledge to easily localize moving objects in conditions of complex illumination changes, scene clutter and occlusions. In this paper, we present a method to leverage human knowledge in the form of annotated video libraries in a novel search and retrieval based setting to track objects in unseen video sequences. For ev...

This dissertation addresses the challenges in large scale deployment of wide-area camera networks and automated analysis of resulting big data. Analysis of such data is limited due to communication bottlenecks and low computational power at individual nodes. Specific focus is on distributed tracking and search/retrieval. For object tracking in ove...

In a wide-area camera network, cameras are often placed such that their views do not overlap. Collaborative tasks such as tracking and activity analysis still require discovering the network topology including the extrinsic calibration of the cameras. This work addresses the problem of calibrating a fixed camera in a wide-area camera network in a g...

This paper addresses the novel and challenging problem of aligning camera views that are unsynchronized by low and/or variable frame rates using object trajectories. Unlike existing trajectory-based alignment methods, our method does not require frame-to-frame synchronization. Instead, we propose using the intersections of corresponding object traj...

This paper proposes a context-aware object search and retrieval in a wide area distributed camera network. With the proliferation of smart cameras in urban networks, it is a challenge to process this big data in an efficient manner. A novel graph based model is proposed to establish relationship between moving objects in the scene and provide a sys...

Wide-area wireless camera networks are being increasingly deployed in many urban scenarios. The large amount of data generated from these cameras pose significant information processing challenges. In this work, we focus on representation, search and retrieval of moving objects in the scene, with emphasis on local camera node video analysis. We dev...

For the instance search task, we are given a set of query images with the corresponding textual meta-data and objects masks to retrieve video shots containing query objects from FLICKR video database. We extract meaningful regions in the key-frames using Maximally Stable Extremal Regions (MSER) and use SIFT descriptors for representation. We use st...

We detect seven activities defined by TRECVID SED task such as CellToEar, Embrace, ObjectPut, PeopleMeet, Peo-pleSplitUp, PersonRuns, and Pointing. We employ two different strategies to detect these activities based on their characteristics. Activities like CellToEar, Embrace, ObjectPut, and Pointing are the results of articulated motion of human p...

This paper proposes a distributed algorithm for object tracking in a camera sensor network. At each camera node, an efficient online multiple instance learning algorithm is used to model object's appearance. This is integrated with particle filter for camera's image plane tracking. To improve the tracking accuracy, each camera node shares its parti...

This project addresses the problem of human tracking in a camera network. A distributed tracking algorithm that fuses the tracking information across multiple cameras with overlapping field of views, is presented. The fused information is fed back to each camera to improve its local tracking accuracy. For this purpose, an efficient on-line multiple...

We present a novel approach for image segmentation using genetic algorithm (GA) implemented in cellular neural networks (CNNUM). This paper also demonstrates how the cellular neural universal machine architecture can be extended to image segmentation. It uses the highly parallel nature of the CNN structure and its speed outperforms traditional digi...