Date of Graduation

5-2015

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Engineering (PhD)

Degree Level

Graduate

Department

Computer Science & Computer Engineering

Advisor/Mentor

Cristophe Bobda

Committee Member

David Andrews

Second Committee Member

John Gauch

Third Committee Member

Chaim Goodman-Strauss

Keywords

Answer set programming, Distributed smart camera networks, Embedded smart cameras, FPGA-based systems, Multi-optimization

Abstract

Smart camera networks are real-time distributed embedded systems able to perform computer vision using multiple cameras. This new approach is a confluence of four major disciplines (computer vision, image sensors, embedded computing and sensor networks) and has been subject of intensive work in the past decades. The recent advances in computer vision and network communication, and the rapid growing in the field of high-performance computing, especially using reconfigurable devices, have enabled the design of more robust smart camera systems. Despite these advancements, the effectiveness of current networked vision systems (compared to their operating costs) is still disappointing; the main reason being the poor coordination among cameras entities at runtime and the lack of a clear formalism to dynamically capture and address the self-organization problem without relying on human intervention. In this dissertation, we investigate the use of a declarative-based modeling approach for capturing runtime self-coordination. We combine modeling approaches borrowed from logic programming, computer vision techniques, and high-performance computing for the design of an autonomous and cooperative smart camera. We propose a compact modeling approach based on Answer Set Programming for architecture synthesis of a system-on-reconfigurable-chip camera that is able to support the runtime cooperative work and collaboration with other camera nodes in a distributed network setup. Additionally, we propose a declarative approach for modeling runtime camera self-coordination for distributed object tracking in which moving targets are handed over in a distributed manner and recovered in case of node failure.

Download

Share

COinS