Distributed image search in camera sensor networks

Abstract

Recent advances in sensor networks permit the use of a large number of relatively inexpensive distributed computational nodes with camera sensors linked in a network and possibly linked to one or more central servers. We argue that the full potential of such a distributed system can be realized if it is designed as a distributed search engine where images from different sensors can be captured, stored, searched and queried. However, unlike traditional image search engines that are focused on resource-rich situations, the resource limitations of camera sensor networks in terms of energy, bandwidth, computational power, and memory capacity present significant challenges. In this paper, we describe the design and implementation of a distributed search system over a camera sensor network where each node is a search engine that senses, stores and searches information. Our work involves innovation at many levels including local storage, local search, and distributed search, all of which are designed to be efficient under the resource constraints of sensor networks. We present an implementation of the search engine on a network of iMote2 sensor nodes equipped with low-power cameras and extended flash storage. We evaluate our system for a dataset comprising book images, and demonstrate more than two orders of magnitude reduction in the amount of data communicated and up to 5x reduction in overall energy consumption over alternate techniques.

A scalable search engine for mass storage smart objects

“…A query can be any form of keyword search using a ranking function (e.g., tfidf) identifying the top-k most relevant files. The proposed search engine can be used in sensors to search for relevant objects in their surroundings [17,23], in cameras to search pictures by using tags [22], in personal smart dongles to secure the querying of documents and files hosted in an untrusted Cloud [4,12] or in smart meters to perform analytic tasks (i.e., top-k queries) over sets of events (i.e., terms) captured during time windows (i.e., files) [3]. Hence, this engine can be thought of as a generalized Google desktop or Spotlight embedded in smart objects.…”

“…Unfortunately, state-of-the-art indexing techniques either consume a lot of RAM or produce a large quantity of random fine-grain updates. Few pioneer works already considered the problem of embedding a search engine in sensors equipped with Flash storage [17,20,22,23], but they target small data collections (i.e., hundreds to thousands of files) with a query execution time which remains proportional to the number of indexed documents. By construction these search engines cannot meet insertion performance and query scalability at the same time.…”

“…Camera sensors tag photographs and provide search capabilities to retrieve them [22]. Smart objects maintain the description of the surrounding objects [23] enabling the Internet of Things [1], e.g.…”

A visual sensor network for object recognition: Testbed realization

“…The work in [10] presents a distributed image search system on a network of iMote2 sensor nodes equipped with extended flash storage. The system is based on SIFT [11] local features, which are extremely slow to compute on such hardware.…”

“…As in [10], the hardware building blocks which we decide to adopt are, to the best of our knowledge, much less powerful than the reference hardware in the literature. The reference testbed is built on commercial hardware and entails the complete pipeline of object recognition visual tasks including fast feature detection and feature description implemented on sensor nodes, features delivery to a sink through a multi-hop communication protocol, and features matching, implemented at a central controller.…”