Determining Vision Graphs for Distributed Camera Networks Using Feature Digests

Abstract

We propose a decentralized method for obtaining the vision graph for a distributed, ad-hoc camera network, in which each edge of the graph represents two cameras that image a sufficiently large part of the same environment. Each camera encodes a spatially well-distributed set of distinctive, approximately viewpoint-invariant feature points into a fixed-length "feature digest" that is broadcast throughout the network. Each receiver camera robustly matches its own features with the decompressed digest and decides whether sufficient evidence exists to form a vision graph edge. We also show how a camera calibration algorithm that passes messages only along vision graph edges can recover accurate 3D structure and camera positions in a distributed manner. We analyze the performance of different message formation schemes, and show that high detection rates (> 0.8) can be achieved while maintaining low false alarm rates (< 0.05) using a simulated 60-node outdoor camera network.

Processing Geotagged Image Sets for Collaborative Compositing and View Construction

“…Vision graphs [3] have been a useful tool for visualizing sensor locations and processing the constructed graph structure. These graphs consist of sensors (vertices) and connections (edges) between them if there is some form of connectivity between sensors.…”

“…The main points of the introduced work are the following: being lightweight; building and analyzing local vision graphs [3] and applying pre-filtering steps to find corresponding image groups before computing content-based correspondences; filtering matched interest points based on feature-differences and interest point distances and based on extra, local image features (e.g. LBP, texture, edge histogram) to reduce the quantity of interest points and features (retaining only approx.…”

Calibrating Distributed Camera Networks

“…In the rest of this section, we summarize our basic approach to estimating the vision graph, which is more fully described in [7]. First, each camera detects a set of distinctive feature points in its image that are likely to match other images of the same scene.…”

“…Therefore, for a fixed L, there is a tradeoff between sending many features (thus increasing the chance of matches with overlapping images) and coding the feature descriptors accurately (thus reducing false or missed matches). These tradeoffs are analyzed in detail in [7]. We note that our concept of a feature digest seems related to Jannotti and…”

“…Section III reviews approaches to estimating the vision graph for a distributed camera network, in which each camera is represented by a node, and an edge appears between two nodes if the two cameras jointly image a sufficiently large part of the environment. We emphasize an algorithm we recently proposed in [7]. In Section IV we review approaches for distributed estimation of the calibration parameters of all cameras in the network based on the vision graph.…”