FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1570236437> ?p ?o ?g. }

• W1570236437 abstract "Stereo vision inherently comes with high computational complexity, which previously limited its deployment to high-performance, centralized imaging systems. But recent advances in embedded systems and algorithm design have paved the way for its adoption for and migration into smart camera networks, which notoriously suffer from limited processing and energy resources. Such networks consist of a collection of relatively low-cost smart camera motes, which—in their simplest form—integrate a microcontroller, an image sensor, and a radio into a single, embedded unit capable of sensing, computation, and wireless communication. When deployed in an in- or outdoor environment, they form ad-hoc or mesh networks that can perform a wide range of applications. Their application areas range from ambient intelligence, building automation, elderly care, autonomous surveillance, and traffic control to smart homes. The underlying network tasks include object localization, target tracking, occupancy sensing, object detection and classification. Stereo vision can bring increased performance and robustness to several of these tasks possibly even at overall reductions in energy consumption and prolonged network lifetime. This chapter will provide a brief description of the building blocks, characteristics, limitations and applications of smart camera networks. We will then present a discussion of their requirements and constraints with respect to stereo vision paying special attention to differences to conventional stereo vision systems. The main issue arises from the high data rate, which image sensors particularly in a stereoscopic configuration generate. Conventional centralized computing systems can easily handle such rates. But for smart camera networks, their resource constraints pose a serious challenge to effective acquisition and processing of this high-rate data. Two possible approaches to address this problem have emerged in recent publications: one suggests the design of a custom image processor whereas the other solution proposes utilization of off-the-shelf, general-purpose microprocessors in conjunction with resolution-scaled image sensors. Our discussion focuses on these two state-of-the-art stereo architectures. NXP's WiCa mote is the primary example deploying a dedicated image processor, while Stanford's MeshEye mote pioneered the idea of resolution-scaled stereo vision. More specifically, the WiCa mote deploys an application-specific image processor based on a vector single-instruction, multiple-data architecture, which is able to process the data streams of two VGA camera modules. In contrast, Stanford's MeshEye mote deploys a low-resolution stereo vision system requiring only a general-purpose 32-bit ARM7 processor. Additionally, it hosts a VGA camera module for more detailed image acquisition." @default.
• W1570236437 created "2016-06-24" @default.
• W1570236437 creator A5033524975 @default.
• W1570236437 date "2008-11-01" @default.
• W1570236437 modified "2023-10-04" @default.
• W1570236437 title "Stereo Vision in Smart Camera Networks" @default.
• W1570236437 cites W1966011245 @default.
• W1570236437 cites W1977594609 @default.
• W1570236437 cites W1988004593 @default.
• W1570236437 cites W2014101702 @default.
• W1570236437 cites W2024340245 @default.
• W1570236437 cites W2037971948 @default.
• W1570236437 cites W2048619613 @default.
• W1570236437 cites W2052200821 @default.
• W1570236437 cites W2080669761 @default.
• W1570236437 cites W2099853900 @default.
• W1570236437 cites W2129243715 @default.
• W1570236437 cites W2160808807 @default.
• W1570236437 cites W2170140722 @default.
• W1570236437 cites W2170389000 @default.
• W1570236437 cites W331974224 @default.
• W1570236437 doi "https://doi.org/10.5772/5907" @default.
• W1570236437 hasPublicationYear "2008" @default.
• W1570236437 type Work @default.
• W1570236437 sameAs 1570236437 @default.
• W1570236437 citedByCount "5" @default.
• W1570236437 countsByYear W15702364372013 @default.
• W1570236437 countsByYear W15702364372014 @default.
• W1570236437 crossrefType "book-chapter" @default.
• W1570236437 hasAuthorship W1570236437A5033524975 @default.
• W1570236437 hasBestOaLocation W15702364371 @default.
• W1570236437 hasConcept C121684516 @default.
• W1570236437 hasConcept C154945302 @default.
• W1570236437 hasConcept C161334170 @default.
• W1570236437 hasConcept C185078393 @default.
• W1570236437 hasConcept C31972630 @default.
• W1570236437 hasConcept C35861506 @default.
• W1570236437 hasConcept C41008148 @default.
• W1570236437 hasConcept C68537008 @default.
• W1570236437 hasConceptScore W1570236437C121684516 @default.
• W1570236437 hasConceptScore W1570236437C154945302 @default.
• W1570236437 hasConceptScore W1570236437C161334170 @default.
• W1570236437 hasConceptScore W1570236437C185078393 @default.
• W1570236437 hasConceptScore W1570236437C31972630 @default.
• W1570236437 hasConceptScore W1570236437C35861506 @default.
• W1570236437 hasConceptScore W1570236437C41008148 @default.
• W1570236437 hasConceptScore W1570236437C68537008 @default.
• W1570236437 hasLocation W15702364371 @default.
• W1570236437 hasLocation W15702364372 @default.
• W1570236437 hasOpenAccess W1570236437 @default.
• W1570236437 hasPrimaryLocation W15702364371 @default.
• W1570236437 hasRelatedWork W2096668200 @default.
• W1570236437 hasRelatedWork W2124872487 @default.
• W1570236437 hasRelatedWork W2377835371 @default.
• W1570236437 hasRelatedWork W2701765543 @default.
• W1570236437 hasRelatedWork W2905493506 @default.
• W1570236437 hasRelatedWork W2980335902 @default.
• W1570236437 hasRelatedWork W307265996 @default.
• W1570236437 hasRelatedWork W4307261122 @default.
• W1570236437 hasRelatedWork W812480148 @default.
• W1570236437 hasRelatedWork W1992486622 @default.
• W1570236437 isParatext "false" @default.
• W1570236437 isRetracted "false" @default.
• W1570236437 magId "1570236437" @default.
• W1570236437 workType "book-chapter" @default.