• No results found

Sistemi rinconfigurabili a basso consumo per il monitoraggio distribuito

N/A
N/A
Protected

Academic year: 2021

Share "Sistemi rinconfigurabili a basso consumo per il monitoraggio distribuito"

Copied!
24
0
0

Loading.... (view fulltext now)

Full text

(1)

Sistemi rinconfigurabili a basso

consumo per il monitoraggio

distribuito

Tutor: prof. Luca Benini

(2)

Outline

„

Wireless Video sensor Node

„

Wireless Video sensor Network, WVN

„

Power issue

„

Energy Harvesting

„

PIR Sensor

„

Multomodal low cost system

„

Application of video surveillance

(3)

Wireless Video Sensor Network (WVSN)

„

WSN with cameras for ambient monitoring

‰

Unobtrusive

‰

No cables (remote locations)

„

Power availability issue

‰

Battery powered

‰

Sustainable operation

„

Processing

„

Wireless communication

„

Multimodal surveillance networks

‰

Augment information

‰

Reduce power consumption

„

Energy harvesting techniques to extend node lifetime

(4)

Power issue

„

Energy consumption issue

‰

Image acquisition and processing

‰

Wireless transmission of recorded transmission

„

Several techniques can be used to extend

network lifetime

‰

Multimodal surveillance

‰

Energy harvesting

‰

Local processing of images

‰

Resource Manger

(5)

Energy efficient

Multimodal sensing

Energy harvesting

Local computation

„

Energy efficient Wireless Video Sensor Node

‰

Combines three modalities

A Pyroelectric InfraRed (PIR) sensor provides a low

power wake up signal. Sensor sensibility is modulated

according to available energy and image contrast.

A PhotoVoltaic (PV) module is used to harvest energy

from the environment.

Images are locally classified using Support Vector

Machines (SVM) to detect relevant event and limit

wireless transmission of undesired images

(6)

Wireless Video Sensor Node

„

Samrt Camera =Camera + intelligence

„

The basis for new applications

‰

Such as: detection, tracking, scene analysis

APPLICATIONS:

• Automotive

• Mobile Comm.

• Surveillance

• Consumer

(7)

Wireless Video Sensor Node –

(II)

„

Low cost

„

Low power consumption

„

Local "intelligence" (on-board image

processing capability)

„

A reconfigurable architecture to achieve

flexibility

„

Wireless connectivity

„

Increase battery live

(8)

Wireless Video Sensor Node –

(III)

Processing unit

Technology

Processor approach:

DSP,

Media Processor,

GPU,

ARM

Programmable Logic

approach:

CPLD,

FPGA,

(9)

Application

with

smart

camera

People Detection

MICRO Current Frame Background

Subtraction Winows Transfer Feature Extraction Embedded Support Vector Machine(ERSVM) Background FPGA

(10)

Application –

People detection II

ARM9 – STR912

¾

Three frame difference: background subtraction

¾

Region of Interest (ROI) detection (128x64 pixels)

¾

Feature extraction: average gray value over column and row (192 features)

(11)

„

Sensor conditioning circuits: band pass filter

(0.2-12Hz) + amplifier (1500x) + trigger

generator

‰

Low power: 1.5mW

Detects changes in incident IR radiation

‰

Moving bodies

„

PIR output dependencies

‰

Speed

‰

Temperature

‰

Distance

Sensors PIR

+ + Out Vdd GND Sensitive elements Lens array Incident radiation Absorbing structure

(12)
(13)

Typical use of PIR Sensor

VIDEO

PROCESSING

Wireless

Transceiver

2.4GHz

SLEEP MODE

(14)
(15)

Application III –

abandoned /removed

object detection with PIR Sensor

Active without video sensor

NO EVENTS! Sleep mode, only

PIR active

EMPTY SCENE PIR->START VIDEO PROCESSING

(16)

Application IV –

ZigBee WSN

PIR-CAMERA

Zibgee comunication

Scalable topology

(17)

Application IV –

ZigBee WSN

PIR-CAMERA

„

Power consumption measurement

„

Extended battery life

(18)

Energy Harvesting &

MPC ( ETH-

ZURICH)

Model Predictive Control for rates and other

parameters

Distributed MPC

Control the PIR sensitivity

(19)

Resource Manager for embedded system (SCALOPES

EU PRPJECT & STM)

„

Hw Design &

Implementation

‰

Thermal sensor

‰

Power Islands

‰

Clock gating

‰

Clock scaling

„

Sw Design

‰

Porting of the Linux

RM layer on SPEAr

platform

‰

Adding RM feature to

the IPs driver

SPEAR ARCH-DRIVER ƒNormal Mode ƒSlow Mode ƒDoze Mode ƒSleep Mode ƒFreq. of Cores ƒFreq of DDR ƒFreq of Perif CPUIDLE CPUFREQ ACPI-DRIVER RM-DRIVER GOVERNORS GENERIC INFRASTRUCTURE SPECIFIC SPEAR GOVERNOS USER LEVEL INTERFACES APPLICATIONS/ SURVEILLANCE APPLICATION •/sys/devices/system/cpu/cpuidle •/sys/devices/system/cpu/cpufreq

Objective

:

A Linux-based RM infrastructure for the configurable

SPEAR platform

(multi-core processor + domain specific configurable

(20)

Collaborations

„

PROJECTS

‰

EU PROJECT:

„

Scalopes ‘09-’10

„

SensactionAAL ‘08 – ‘09

‰

National PROJECT:

„

SUMMIT ‘07-’08

„

PRIIN

„

Industrial

‰

STMicroelectronics ( Microcontroller, Vision, SCALOPES)

‰

Datalogic ( wireless applications, SUMMIT)

„

Accademic

‰

ETH – Zurich ( 6 months intership) (MPC & Energy harvesting)

‰

EPFL (Andrea Acquaviva - reconfigurable architecture )

‰

University of Trento ( Support Vector Machine)

‰

PoliMI ( SCALOPES porjects)

(21)

Publication

„

Journals:

‰ Transactions on HiPEAC-1, Lecture Notes in Computer Science (LNCS),

Springer-Verlag Berling Heidelberg New York Titolo: Exploration of Reconfiguration Strategies for Environmentally Powered DevicesAutori: Alex E. Susu, Michele Magno, Andrea Acquaviva, David Atienza, Giovanni De Micheli

‰ Rivista: Journal of Real-Time Image Processing Titolo: A low-power wireless video sensor

node for distributed object detectionAutori: Aliaksei Kerhet, Michele Magno, Francesco Leonardi, Andrea Boni and Luca Benini

ƒ

Conferences:

ƒ Congresso: Advanced Video and Signal based Surveillance Titolo: Distributed Video Surveillance Using Hardware-Friendly Sparse Large Margin Classifiers Autori: Aliaksei Kerhet, Francesco Leonardi, Andrea Boni, Paolo Lombardo, Michele Magno, Luca Benini

Luogo: Londra Data: Settembre 2007

ƒ Congresso: 11th EUROMICRO Conference on Digital System Design Titolo: A Solar-powered Video Sensor Node for Energy Efficient Multimodal SurveillanceAutori: Magno, Michele; Brunelli, Davide; Zappi, Piero; Benini, LucaLuogo: ParmaData: Settembre 2008

ƒ Congresso: Workshop on Multi-camera and Multi-modal Sensor Fusion Algorithms and Applications (M2SFA2) Titolo: Multi-modal Video Surveillance aided by Pyroelectric Infrared Sensors Autori: Michele Magno; Federico Tombari; Davide Brunelli; Luigi Di Stefano; Luca Benini Luogo: Marsiglia Data: Ottobre 2008

(22)

Publication

(II)

ƒ Congresso: Sixth IEEE International Conference on Advanced Video and Signal Based

Surveillance Titolo: Multimodal Abandoned/Removed Object Detection for Low Power Video Surveillance SystemsAutori: Michele Magno; Federico Tombari; Davide Brunelli; Luigi Di Stefano; Luca BeniniLuogo: GenovaData: Settembre 2009

ƒ Congresso: Third ACM/IEEE International Conference on Distributed Smart Cameras

(ICDSC 2009) Titolo: Adaptive Power Control for Solar Harvesting Multimodal Wireless Smart Camera Autori: Michele Magno, Davide Brunelli, Lothar Thiele and Luca Benini Luogo: Como

Data: Agosto 2009

POSTERS:

‰ Congresso: International Conference on Distributed Smart Cameras Titolo: A Low-Power

Configurable Wireless Video Sensor Node for Distributed Vision Applications Autori: MAGNO M., L. BENINILuogo: Vienn aData: Settembre 2007

‰ Congresso: Fifth European conference on Wireless Sensor Networks, EWSN 2008 Titolo: A

Self-powered Video Node Triggered by PIR Sensors Autori: M. Magno, D. Brunelli, P. Zappi and L. Benini Luogo: Bologna Data: Gennaio 2008

‰ Congresso: 6th European Conference on Wireless Sensor Networks Titolo: Detection of

abandoned/removed objects with a video sensor node aided by Infrared Sensor Autori: Michele Magno, Davide Brunelli, Luca Benini Luogo: Cork, Ireland Data: Febbraio 2009

(23)

Publication

(III) –

Work in progress

ƒ Congresso: The 9th ACM/IEEE International Conference on Information Processing in Sensor

Networks (IPSN2010) Titolo Energy Efficient Cooperative Multimodal Ambient Monitoring Autori: Magno M., Zappi P., Brunelli D., L. BENINI

STATUS: Submitted

TITOLO: Energy aware multimodal video surveillance embedded system. Autori: Magno M., Lanza A. Brunelli D., Di Stefano L., Benini L.

TITOLO: Resource manager for video surveillance embedded system. Autori: Magno M., Brunelli D., Benini L.

(24)

Conclusion and Future Work

„

Energy efficient wireless video node

‰

Multimodal surveillance

‰

Local preprocessing

„

Multi sensor node for distributed surveillance

‰

Video processing application

‰

Data fusion for more energy efficiency

„

Energy Harvesting video sensor node

„

Resource manager

„

Future work

‰

Augment information from low-power sensors

‰

Distributed policies for collaborative surveillance

‰

New vision algorithms

References

Related documents

Practitioners at risk of poor performance would undergo a more detailed assess- ment process focused on rigorous testing, with poor performers targeted for remediation or removal

On the one hand, it is convenient to reduce the width of the reset pulse in order to increase the circuit speed and also for not loosing during this active time in the

Considering the young age of women who undergo this radical surgery, and the related fertility improvement, the aims of our study were to analyze the obstetric complications and

We assessed the scale ’ s validity in a confirmatory factor analysis framework, investigating whether the scale measures what it was intended to measure (content, structural,

We also found a counterintuitive correlation in the ASD group between maintenance of precedents on Round 4 when speaking to the new matcher and on duration difference: for those

Understand importance of the total daily dose (TDD) of insulin Be able to calculate an insulin sensitivity factor.. Set up an insulin