Vision Chips with In-pixel Processors for High-performance Low-power Embedded Vision Systems

Julien N.P. Martel; Piotr Dudek

Vision Chips with In-pixel Processors for High-performance Low-power Embedded Vision Systems

Julien N.P. Martel, Piotr Dudek

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

60 Downloads (Pure)

Abstract

We present the design of vision systems with in-pixel processors, specifically the cellular processor array architecture and implementation of the SCAMP-5 vision-chip. These sensor-processor devices provide a high-speed power-efficient solution to low-level vision processing in embedded systems. We discuss how these devices can be programmed and emulated, including a high-level domain specific language with a compiler responsible of taking care of the peculiarities of theses devices (e.g. analog errors). We discuss application examples, where such vision chips have been used to create systems that provide very low latencies and running on a low-power budget.

Original language	English
Title of host publication	Workshop on Architectures and Systems for Real-time Mobile Vision Applications (ASR-MOV), International Symposium on Code Generation and Optimization, CGO'16
Place of Publication	Barcelona, Spain
Number of pages	3
Publication status	Published - 12 Mar 2016

Access to Document

martel-cgo2016Final published version, 604 KB

Cite this

@inproceedings{b1c3c5cc82104c5d80ffce4b0834515d,

title = "Vision Chips with In-pixel Processors for High-performance Low-power Embedded Vision Systems",

abstract = "We present the design of vision systems with in-pixel processors, specifically the cellular processor array architecture and implementation of the SCAMP-5 vision-chip. These sensor-processor devices provide a high-speed power-efficient solution to low-level vision processing in embedded systems. We discuss how these devices can be programmed and emulated, including a high-level domain specific language with a compiler responsible of taking care of the peculiarities of theses devices (e.g. analog errors). We discuss application examples, where such vision chips have been used to create systems that provide very low latencies and running on a low-power budget.",

author = "Martel, {Julien N.P.} and Piotr Dudek",

year = "2016",

month = mar,

day = "12",

language = "English",

booktitle = "Workshop on Architectures and Systems for Real-time Mobile Vision Applications (ASR-MOV), International Symposium on Code Generation and Optimization, CGO'16",

}

Vision Chips with In-pixel Processors for High-performance Low-power Embedded Vision Systems. / Martel, Julien N.P.; Dudek, Piotr.
Workshop on Architectures and Systems for Real-time Mobile Vision Applications (ASR-MOV), International Symposium on Code Generation and Optimization, CGO'16. Barcelona, Spain, 2016.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Vision Chips with In-pixel Processors for High-performance Low-power Embedded Vision Systems

AU - Martel, Julien N.P.

AU - Dudek, Piotr

PY - 2016/3/12

Y1 - 2016/3/12

N2 - We present the design of vision systems with in-pixel processors, specifically the cellular processor array architecture and implementation of the SCAMP-5 vision-chip. These sensor-processor devices provide a high-speed power-efficient solution to low-level vision processing in embedded systems. We discuss how these devices can be programmed and emulated, including a high-level domain specific language with a compiler responsible of taking care of the peculiarities of theses devices (e.g. analog errors). We discuss application examples, where such vision chips have been used to create systems that provide very low latencies and running on a low-power budget.

AB - We present the design of vision systems with in-pixel processors, specifically the cellular processor array architecture and implementation of the SCAMP-5 vision-chip. These sensor-processor devices provide a high-speed power-efficient solution to low-level vision processing in embedded systems. We discuss how these devices can be programmed and emulated, including a high-level domain specific language with a compiler responsible of taking care of the peculiarities of theses devices (e.g. analog errors). We discuss application examples, where such vision chips have been used to create systems that provide very low latencies and running on a low-power budget.

M3 - Conference contribution

BT - Workshop on Architectures and Systems for Real-time Mobile Vision Applications (ASR-MOV), International Symposium on Code Generation and Optimization, CGO'16

CY - Barcelona, Spain

ER -

Vision Chips with In-pixel Processors for High-performance Low-power Embedded Vision Systems

Abstract

Access to Document

Fingerprint

Cite this