Distributed Algorithms for Feature Extraction Off-loading in Multi-Camera Visual Sensor Networks
This addresses the challenge of efficient computational off-loading in visual sensor networks for applications like tracking and recognition, representing an incremental improvement in distributed optimization methods.
The paper tackles the problem of minimizing task completion times for real-time visual analysis in multi-camera networks by formulating it as an optimization problem and proposing distributed algorithms. The results show that distributed optimization can achieve low completion times, with predictable and stable performance enhanced by sparse central coordination.
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.