In-Sensor Visual Devices for Perception and Inference

Yanan Liu; Hepeng Ni; Chao Yuwen; Xinyu Yang; Yuhang Ming; Huixin Zhong; Yao Lu; Liang Ran

doi:10.1007/978-981-99-4287-9_1

In-Sensor Visual Devices for Perception and Inference

Yanan Liu, Hepeng Ni, Chao Yuwen, Xinyu Yang, Yuhang Ming, Huixin Zhong, Yao Lu, Liang Ran

Research output: Chapter or section in a book/report/conference proceeding › Chapter or section

Abstract

The traditional machine vision systems use separate architectures for perception, memory, and processing. This approach may hinder the growing demand for high image processing rates and low power consumption. On the other hand, in-sensor computing performs signal processing at the pixel level, directly utilizing collected analogue signals without sending them to other processors. This means that in-sensor computing may offer a solution for achieving highly efficient and low-power consumption visual signal processing. This can be achieved by integrating sensing, storage, and computation onto focal planes with novel circuit designs or new materials. This chapter aims to describe the proposed image processing algorithms and neural networks of in-sensor computing, as well as their applications in machine vision and robotics. The goal of this chapter is to help developers, researchers, and users of unconventional visual sensors understand their functioning and applications, especially in the context of autonomous driving.

Original language	English
Title of host publication	Autonomous Driving Perception
Editors	R. Fan, S. Guo, M. J. Bocus
Place of Publication	Singapore
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	1-35
Number of pages	35
ISBN (Electronic)	9789819942879
ISBN (Print)	9789819942862
DOIs	https://doi.org/10.1007/978-981-99-4287-9_1
Publication status	Published - 7 Oct 2023

Publication series

Name	Advances in Computer Vision and Pattern Recognition
Volume	Part F1566
ISSN (Print)	2191-6586
ISSN (Electronic)	2191-6594

Bibliographical note

Funding Information:
This work is funded by National Natural Science Foundation of China (grant 62202285), EPSRC FARSCOPE CDT for future robotics and autonomous system, and China Scholarship Council (grant 201700260083).

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1007/978-981-99-4287-9_1

Cite this

Liu, Y., Ni, H., Yuwen, C., Yang, X., Ming, Y., Zhong, H., Lu, Y., & Ran, L. (2023). In-Sensor Visual Devices for Perception and Inference. In R. Fan, S. Guo, & M. J. Bocus (Eds.), Autonomous Driving Perception (pp. 1-35). (Advances in Computer Vision and Pattern Recognition; Vol. Part F1566). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-4287-9_1

In-Sensor Visual Devices for Perception and Inference. / Liu, Yanan; Ni, Hepeng; Yuwen, Chao et al.
Autonomous Driving Perception. ed. / R. Fan; S. Guo; M. J. Bocus. Singapore: Springer Science and Business Media Deutschland GmbH, 2023. p. 1-35 (Advances in Computer Vision and Pattern Recognition; Vol. Part F1566).

Research output: Chapter or section in a book/report/conference proceeding › Chapter or section

Liu, Y, Ni, H, Yuwen, C, Yang, X, Ming, Y, Zhong, H, Lu, Y & Ran, L 2023, In-Sensor Visual Devices for Perception and Inference. in R Fan, S Guo & MJ Bocus (eds), Autonomous Driving Perception. Advances in Computer Vision and Pattern Recognition, vol. Part F1566, Springer Science and Business Media Deutschland GmbH, Singapore, pp. 1-35. https://doi.org/10.1007/978-981-99-4287-9_1

@inbook{cbe0b9f8d3cb42ce9fb19af1db5a93c9,

title = "In-Sensor Visual Devices for Perception and Inference",

abstract = "The traditional machine vision systems use separate architectures for perception, memory, and processing. This approach may hinder the growing demand for high image processing rates and low power consumption. On the other hand, in-sensor computing performs signal processing at the pixel level, directly utilizing collected analogue signals without sending them to other processors. This means that in-sensor computing may offer a solution for achieving highly efficient and low-power consumption visual signal processing. This can be achieved by integrating sensing, storage, and computation onto focal planes with novel circuit designs or new materials. This chapter aims to describe the proposed image processing algorithms and neural networks of in-sensor computing, as well as their applications in machine vision and robotics. The goal of this chapter is to help developers, researchers, and users of unconventional visual sensors understand their functioning and applications, especially in the context of autonomous driving.",

author = "Yanan Liu and Hepeng Ni and Chao Yuwen and Xinyu Yang and Yuhang Ming and Huixin Zhong and Yao Lu and Liang Ran",

note = "Funding Information: This work is funded by National Natural Science Foundation of China (grant 62202285), EPSRC FARSCOPE CDT for future robotics and autonomous system, and China Scholarship Council (grant 201700260083). ",

year = "2023",

month = oct,

day = "7",

doi = "10.1007/978-981-99-4287-9_1",

language = "English",

isbn = "9789819942862",

series = "Advances in Computer Vision and Pattern Recognition",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "1--35",

editor = "R. Fan and S. Guo and Bocus, {M. J.}",

booktitle = "Autonomous Driving Perception",

address = "Germany",

}

TY - CHAP

T1 - In-Sensor Visual Devices for Perception and Inference

AU - Liu, Yanan

AU - Ni, Hepeng

AU - Yuwen, Chao

AU - Yang, Xinyu

AU - Ming, Yuhang

AU - Zhong, Huixin

AU - Lu, Yao

AU - Ran, Liang

N1 - Funding Information: This work is funded by National Natural Science Foundation of China (grant 62202285), EPSRC FARSCOPE CDT for future robotics and autonomous system, and China Scholarship Council (grant 201700260083).

PY - 2023/10/7

Y1 - 2023/10/7

N2 - The traditional machine vision systems use separate architectures for perception, memory, and processing. This approach may hinder the growing demand for high image processing rates and low power consumption. On the other hand, in-sensor computing performs signal processing at the pixel level, directly utilizing collected analogue signals without sending them to other processors. This means that in-sensor computing may offer a solution for achieving highly efficient and low-power consumption visual signal processing. This can be achieved by integrating sensing, storage, and computation onto focal planes with novel circuit designs or new materials. This chapter aims to describe the proposed image processing algorithms and neural networks of in-sensor computing, as well as their applications in machine vision and robotics. The goal of this chapter is to help developers, researchers, and users of unconventional visual sensors understand their functioning and applications, especially in the context of autonomous driving.

AB - The traditional machine vision systems use separate architectures for perception, memory, and processing. This approach may hinder the growing demand for high image processing rates and low power consumption. On the other hand, in-sensor computing performs signal processing at the pixel level, directly utilizing collected analogue signals without sending them to other processors. This means that in-sensor computing may offer a solution for achieving highly efficient and low-power consumption visual signal processing. This can be achieved by integrating sensing, storage, and computation onto focal planes with novel circuit designs or new materials. This chapter aims to describe the proposed image processing algorithms and neural networks of in-sensor computing, as well as their applications in machine vision and robotics. The goal of this chapter is to help developers, researchers, and users of unconventional visual sensors understand their functioning and applications, especially in the context of autonomous driving.

UR - http://www.scopus.com/inward/record.url?scp=85175176319&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-4287-9_1

DO - 10.1007/978-981-99-4287-9_1

M3 - Chapter or section

AN - SCOPUS:85175176319

SN - 9789819942862

T3 - Advances in Computer Vision and Pattern Recognition

SP - 1

EP - 35

BT - Autonomous Driving Perception

A2 - Fan, R.

A2 - Guo, S.

A2 - Bocus, M. J.

PB - Springer Science and Business Media Deutschland GmbH

CY - Singapore

ER -

In-Sensor Visual Devices for Perception and Inference

Abstract

Publication series

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this