Algorithms for distributed feature extraction in multi-camera visual sensor networks

Abstract

Real-time visual analysis tasks, like tracking and recognition, require swift execution of computationally intensive algorithms. Visual sensor networks can be enabled to perform such tasks by augmenting the sensor network with processing nodes and distributing the computational burden in a way that the cameras contend for the processing nodes while trying to minimize their task completion times. In this paper, we formulate the problem of minimizing the completion time of all camera sensors as an optimization problem. We propose algorithms for fully distributed optimization, analyze the existence of equilibrium allocations, evaluate the effect of the network topology and of the video characteristics, and the benefits of central coordination. Our results demonstrate that with sufficient information available, distributed optimization can provide low completion times, moreover predictable and stable performance can be achieved with additional, sparse central coordination.

Efficient distribution of visual processing tasks in multi-camera visual sensor networks

“…Throughout the section, we compare TTP to Greedy proposed in [11]. Greedy differs from TTP in that each sensor s ∈ D i always revises its assignment from (x i s , d i s ) to (x i+1 s , d i+1 s ) = (x s , d s ).…”

“…Our system model is similar to that in [11]. We consider a visual sensor network (VSN) consisting of a set of sensor nodes S, |S| = S, and a set of processing nodes N , |N | = N .…”

GreenEyes: Networked energy-aware visual analysis

“…In [17] we proposed algorithms for distributed feature processing for several visual sensors that share a pool of processing nodes, and showed that algorithms that require little coordination may perform reasonably well.…”