SlideShare ist ein Scribd-Unternehmen logo
1 von 39
Downloaden Sie, um offline zu lesen
UsingAI and edge computing
devices for traffic flow monitoring
Dr J. Barthélemy, Dr N. Verstaevel, Dr H. Forehead, Senior Prof. P. Perez,
Bilal Arshad, Dinh (Andrew) Che
Edge Computing with Jetson TX2
for Monitoring Flows of Pedestrian
and Vehicles
At SMART, we believe that People with good
information and good tools will make good
Decisions and change their world
2
The case of Liverpool
CBD is growing fast: new UoW campus, airport development,…
 What does it mean for the city and its community? What are the problems?
 Smart Cities and Suburbs Program: How can we use IoT to solve the problems?
3
Which problems?
Let’s ask the people! Pedestrians
- Where are they going?
- What are the most popular routes?
- What are the most congested locations?
- Impact of city activity?
Cyclists
- Which route are they taking?
- How can we improve bike usage?
Cars
- Live traffic?
4
Sensors locations
20 sensors
Image credit: OpenStreetMap
5
How about using CCTV?
6
Privacy!
Sensor requirements
• Mobile units + leveraging CCTV infrastructure
• Privacy is important!
– On board video analytics
– Only indicators transmitted (no raw data!)
• Real-time image processing
• LoRaWAN network
7
LoRaWAN: An IoT Network
Image credit: https://ttnmapper.org
• Long range
• Low power
• Low bandwidth (max 200 bytes/message)
• Open source
• Free for use by the community
8
History of the prototypes
9
The sensor
An edge computing device
Components
— NVIDIA Jetson TX2 for onboard processing
— Pycom LoPy 4 for data transmission on The Things Network
— Camera (USB webcam / existing CCTV)
10
The sensor
Actual state…
11
From the input to the dashboard
Image Acquisition
• CCTV/Webcam
Detection
• Deep Convolutional Neural Network
Tracking
• Kalman Filtering
Data transmission
• LoRaWAN/OneM2M
Dashboard/Database
Image credit: NVIDIA Corporation
Image credit: Pycom
12
Detection:YOLO v3
Inference: Jetson TX2Training: Titan Xp
• Fully convolutional DNN
• 106 hidden layers
• Detections at 3 scales
• 3 classes: person, bicycle, vehicles
• Pascal VOC and COCO datasets
cuDNN
FP16+ +
13
Detection:YOLO v3
Current training dataset
• 80.000 images from Pascal VOC, COCO
• 6 data augmentation techniques
480.000 images
14
Detection:YOLO v3
15
Tracking: Kalman Filtering
16
Prediction of O
in current frame
Position of O in previous frame
Detection D in current frame
𝐼𝑜𝑈 ≔ ≥ 𝛿
𝑥
𝑦
if D = O
Detection:YOLO v3
• Detecting locations of pedestrians and vehicles
• Number of objects of each type
17
VIRAT Video Dataset
Tracking: Kalman Filtering
• Associating IDs with the detections
• Trajectories
18
VIRAT Video Dataset
Final output
No image Privacy OK!
19
Liverpool Smart Pedestrian architecture
Fixed counters
Air quality x20
x5
x15
Mobile counters
Sensors IoT Core ApplicationsTransport
+
Forecasting
Analytics
Public
Dashboard
Liverpool IoT Core
Citizens app
20
● Open source service platform for M2M interoperability
based on the oneM2M standard.
● Follows a RESTful approach GET/POST/DELETE/SUBSCRIBE
● Access control policies
● Plugins
● Can be decentralised with multiple nodes
● Support different technologies:
○ Lora
○ Zigbee
○ Sigfox
○ Bluetooth Low Energy
○ Z-wave
OM2M Eclipse
21
Liverpool IoT Core
MQTT TTN
AE - TheThingsNetwork
App Id …
DATA
IN_Node
METADATA
MN_Node1
MN_...
Subscriptions
HTTP Rest API
Database
Inject
HTTP GET
Publish data Collect data Manage and secure data Store data
POA
22
The Things Network application
AE-TheThingsNetwork
CNT- App Id
CNT - DATA
CIN – DATA_...
CNT - METADATA
CIN – METADATA_...
23
Visual Sensor application
MN- SensorName
CNT- DATA
CIN –...
CIN –...
CNT- DESCRIPTOR
CNT- CONFIGURATION
CIN –...
CNT- SYSTEM
CIN –...
CNT- COMMAND
CIN –...
24
Dashboard
25
Dashboard
Trajectories of the detections (inside a building)
26
Dashboard
Heatmap of the maximum number of the detections (inside a building)
27
Dashboard
28
Next steps: Inferring network dynamics
Image credit: OpenStreetMap Image credit: Google Maps
29
Next steps:Algorithm transferability
Testing in Vietnam
30
Conclusions
It’s only the beginning!
• VS able to perform real time object detection and tracking
• Privacy compliant… but meaningful information
• Open data for people centric approach
– citizen applications
– city and traffic planners
• IoT core scalable and interoperable
– adding new sensors: air quality, noise, …
Traffic
modelling
AnalyticsDashboardCitizens app
31
But it’s already successful!
Best Local Government Initiative
Document title32
Keep InTouch
johan@uow.edu.au
linkedin.com/company/smart-
infrastructure-facility-university-
of-wollongong
@SMART_Facility
smart.uow.edu.au
uowblogs.com/smartinfrastructureSMART Infrastructure Facility
33
Image credit: https://towardsdatascience.com
YOLO v3 architecture
34
35
Image credit: Redmon, J. and Farhadi, A. (2018). YOLOv3: An Incremental Improvement
YOLO v3 performances
GPU and Edge computing
Image credit: NVIDIA Corporation
Dataset
Deep Neural Net
Trained model
deployment
Inference: Jetson
Image credit: NVIDIA Corporation
Training: Titan/DGX/Tesla
Image Acquisition
Detection
Tracking
Data transmission
Dashboard/Database
36
Architecture of the solution
Fixed
counters
Air quality x20
Noise level x20
x5
x15
Mobile
counters
Sensors IoT Core ApplicationsTransport
+
Private and
Public APIs Traffic
modelling
Analytics
Dashboard
Citizens app
37
Dashboard
Heatmap of the maximum number of detections
38
Dashboard
Trajectories of the detections
39

Weitere ähnliche Inhalte

Ähnlich wie SMART Seminar Series: "Using AI and edge computing devices for traffic flow monitoring". Presented by Dr Johan Barthelemy

A Full End-to-End Platform as a Service for Smart City Applications
A Full End-to-End Platform as a Service for SmartCity ApplicationsA Full End-to-End Platform as a Service for SmartCity Applications
A Full End-to-End Platform as a Service for Smart City ApplicationsCharalampos Doukas
 
Assignment 2- Smart City
Assignment 2- Smart CityAssignment 2- Smart City
Assignment 2- Smart CityNguyen Anh
 
Computer architecture for vision systems
Computer architecture for vision systemsComputer architecture for vision systems
Computer architecture for vision systemsutsav patel
 
Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Lviv Startup Club
 
Real-time, Sensor-based Monitoring of Shipping Containers
Real-time, Sensor-based Monitoring of Shipping ContainersReal-time, Sensor-based Monitoring of Shipping Containers
Real-time, Sensor-based Monitoring of Shipping Containersbenaam
 
5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdf
5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdf5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdf
5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdfSrinidhirkGowda
 
Ai and traffic management application v1.0
Ai and traffic management application v1.0Ai and traffic management application v1.0
Ai and traffic management application v1.0Jorge Sebastiao
 
Creating The World’s First
Creating The World’s First Creating The World’s First
Creating The World’s First Bristol Is Open
 
IoT beneath your feet - building smart roads and networks
IoT beneath your feet - building smart roads and networksIoT beneath your feet - building smart roads and networks
IoT beneath your feet - building smart roads and networksAlcatel-Lucent Enterprise
 
Arrow Tunis IOT 02-10-2018
Arrow Tunis IOT 02-10-2018Arrow Tunis IOT 02-10-2018
Arrow Tunis IOT 02-10-2018MOEZ SAMMOUDA
 
Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...
Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...
Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...Peter Labaziewicz
 
IRJET - Network Traffic Monitoring and Botnet Detection using K-ANN Algorithm
IRJET - Network Traffic Monitoring and Botnet Detection using K-ANN AlgorithmIRJET - Network Traffic Monitoring and Botnet Detection using K-ANN Algorithm
IRJET - Network Traffic Monitoring and Botnet Detection using K-ANN AlgorithmIRJET Journal
 
Harness the Power of Big Data with Oracle
Harness the Power of Big Data with OracleHarness the Power of Big Data with Oracle
Harness the Power of Big Data with OracleSai Janakiram Penumuru
 
User-Driven Cloud Transportation System for Smart Driving
User-Driven Cloud Transportation System for Smart DrivingUser-Driven Cloud Transportation System for Smart Driving
User-Driven Cloud Transportation System for Smart Drivingamg93
 
Io t research_arpanpal_iem
Io t research_arpanpal_iemIo t research_arpanpal_iem
Io t research_arpanpal_iemArpan Pal
 
Real time-image-processing-applied-to-traffic-queue-detection-algorithm
Real time-image-processing-applied-to-traffic-queue-detection-algorithmReal time-image-processing-applied-to-traffic-queue-detection-algorithm
Real time-image-processing-applied-to-traffic-queue-detection-algorithmajayrampelli
 
Autonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial IntelligenceAutonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial IntelligenceWiley Jones
 

Ähnlich wie SMART Seminar Series: "Using AI and edge computing devices for traffic flow monitoring". Presented by Dr Johan Barthelemy (20)

A Full End-to-End Platform as a Service for Smart City Applications
A Full End-to-End Platform as a Service for SmartCity ApplicationsA Full End-to-End Platform as a Service for SmartCity Applications
A Full End-to-End Platform as a Service for Smart City Applications
 
Assignment 2- Smart City
Assignment 2- Smart CityAssignment 2- Smart City
Assignment 2- Smart City
 
Computer architecture for vision systems
Computer architecture for vision systemsComputer architecture for vision systems
Computer architecture for vision systems
 
Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"Jorge Sebastiao "Using AI for Smart traffic Management"
Jorge Sebastiao "Using AI for Smart traffic Management"
 
Real-time, Sensor-based Monitoring of Shipping Containers
Real-time, Sensor-based Monitoring of Shipping ContainersReal-time, Sensor-based Monitoring of Shipping Containers
Real-time, Sensor-based Monitoring of Shipping Containers
 
5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdf
5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdf5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdf
5b50dc69-4ca7-41ee-a9dd-b4e8b220b4fe.pdf
 
Ai and traffic management application v1.0
Ai and traffic management application v1.0Ai and traffic management application v1.0
Ai and traffic management application v1.0
 
Creating The World’s First
Creating The World’s First Creating The World’s First
Creating The World’s First
 
IoT beneath your feet - building smart roads and networks
IoT beneath your feet - building smart roads and networksIoT beneath your feet - building smart roads and networks
IoT beneath your feet - building smart roads and networks
 
Arrow Tunis IOT 02-10-2018
Arrow Tunis IOT 02-10-2018Arrow Tunis IOT 02-10-2018
Arrow Tunis IOT 02-10-2018
 
Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...
Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...
Perceiving and understanding the world for ADAS and Autonomous _Peter Labazie...
 
Autonomous bus
Autonomous busAutonomous bus
Autonomous bus
 
IRJET - Network Traffic Monitoring and Botnet Detection using K-ANN Algorithm
IRJET - Network Traffic Monitoring and Botnet Detection using K-ANN AlgorithmIRJET - Network Traffic Monitoring and Botnet Detection using K-ANN Algorithm
IRJET - Network Traffic Monitoring and Botnet Detection using K-ANN Algorithm
 
Harness the Power of Big Data with Oracle
Harness the Power of Big Data with OracleHarness the Power of Big Data with Oracle
Harness the Power of Big Data with Oracle
 
ArjunCV
ArjunCVArjunCV
ArjunCV
 
User-Driven Cloud Transportation System for Smart Driving
User-Driven Cloud Transportation System for Smart DrivingUser-Driven Cloud Transportation System for Smart Driving
User-Driven Cloud Transportation System for Smart Driving
 
Io t research_arpanpal_iem
Io t research_arpanpal_iemIo t research_arpanpal_iem
Io t research_arpanpal_iem
 
Real time-image-processing-applied-to-traffic-queue-detection-algorithm
Real time-image-processing-applied-to-traffic-queue-detection-algorithmReal time-image-processing-applied-to-traffic-queue-detection-algorithm
Real time-image-processing-applied-to-traffic-queue-detection-algorithm
 
5G Enablers and Use Cases, an European Pespective
5G Enablers and Use Cases, an European Pespective5G Enablers and Use Cases, an European Pespective
5G Enablers and Use Cases, an European Pespective
 
Autonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial IntelligenceAutonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
Autonomous Vehicles: the Intersection of Robotics and Artificial Intelligence
 

Mehr von SMART Infrastructure Facility

SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...
SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...
SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...SMART Infrastructure Facility
 
SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...
SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...
SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...SMART Infrastructure Facility
 
SMART Seminar Series: "User-centric digital collaboration to build resilient ...
SMART Seminar Series: "User-centric digital collaboration to build resilient ...SMART Seminar Series: "User-centric digital collaboration to build resilient ...
SMART Seminar Series: "User-centric digital collaboration to build resilient ...SMART Infrastructure Facility
 
SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...
SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...
SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...SMART Infrastructure Facility
 
SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...
SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...
SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...SMART Infrastructure Facility
 
SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...
SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...
SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...SMART Infrastructure Facility
 
SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...
SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...
SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...SMART Infrastructure Facility
 
SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...
SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...
SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...SMART Infrastructure Facility
 
SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...
SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...
SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...SMART Infrastructure Facility
 
SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...
SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...
SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...SMART Infrastructure Facility
 
SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...
SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...
SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...SMART Infrastructure Facility
 
SMART Seminar Series: "Potential use of drones for infrastructure inspection ...
SMART Seminar Series: "Potential use of drones for infrastructure inspection ...SMART Seminar Series: "Potential use of drones for infrastructure inspection ...
SMART Seminar Series: "Potential use of drones for infrastructure inspection ...SMART Infrastructure Facility
 
SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...
SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...
SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...SMART Infrastructure Facility
 
SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...
SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...
SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...SMART Infrastructure Facility
 
SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...
SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...
SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...SMART Infrastructure Facility
 
SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"
SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"
SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"SMART Infrastructure Facility
 
SMART Seminar Series: "How to improve the order of evolutionary models in age...
SMART Seminar Series: "How to improve the order of evolutionary models in age...SMART Seminar Series: "How to improve the order of evolutionary models in age...
SMART Seminar Series: "How to improve the order of evolutionary models in age...SMART Infrastructure Facility
 
SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"
SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"
SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"SMART Infrastructure Facility
 
SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...
SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...
SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...SMART Infrastructure Facility
 
SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...
SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...
SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...SMART Infrastructure Facility
 

Mehr von SMART Infrastructure Facility (20)

SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...
SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...
SMART Seminar Series: "Cognitive Illusions in Virtual Reality: What do I mean...
 
SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...
SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...
SMART Seminar Series: "Trusted Autonomous Systems as System of Systems". Pres...
 
SMART Seminar Series: "User-centric digital collaboration to build resilient ...
SMART Seminar Series: "User-centric digital collaboration to build resilient ...SMART Seminar Series: "User-centric digital collaboration to build resilient ...
SMART Seminar Series: "User-centric digital collaboration to build resilient ...
 
SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...
SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...
SMART Seminar Series: "The Evolution of the Metric System: From Precious Lump...
 
SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...
SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...
SMART Seminar Series: "Blockchain and its Applications". Presented by Prof Wi...
 
SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...
SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...
SMART Seminar Series: "From an IoT cloud based architecture to Edge for dynam...
 
SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...
SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...
SMART Seminar Series: "Is bus bunching serious in Sydney? Preliminary finding...
 
SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...
SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...
SMART Seminar Series: "Keep it SMART, keep it simple! – Challenging complexit...
 
SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...
SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...
SMART Seminar Series: "Risk-based bridge assessment under changing load-deman...
 
SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...
SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...
SMART Seminar Series: "Deep Learning: Fundamentals and Practice". Presented b...
 
SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...
SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...
SMART Seminar Series: "Infrastructure Resilience: Planning for Future Extreme...
 
SMART Seminar Series: "Potential use of drones for infrastructure inspection ...
SMART Seminar Series: "Potential use of drones for infrastructure inspection ...SMART Seminar Series: "Potential use of drones for infrastructure inspection ...
SMART Seminar Series: "Potential use of drones for infrastructure inspection ...
 
SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...
SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...
SMART Seminar Series: "A journey in the zoo of Turing patterns: the topology ...
 
SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...
SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...
SMART Seminar Series: "Human behaviour modelling and simulation for crisis ma...
 
SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...
SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...
SMART Seminar Series: "Dealing with uncertainty: With the observer in the loo...
 
SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"
SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"
SMART Seminar Series: "Smart Cities: The Good, The Bad & The Ugly"
 
SMART Seminar Series: "How to improve the order of evolutionary models in age...
SMART Seminar Series: "How to improve the order of evolutionary models in age...SMART Seminar Series: "How to improve the order of evolutionary models in age...
SMART Seminar Series: "How to improve the order of evolutionary models in age...
 
SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"
SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"
SMART Seminar Series: "OneM2M – Towards end-to-end interoperability of the IoT"
 
SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...
SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...
SMART Seminar Series: "Blue-Green vs. Grey-Black infrastructure – which is be...
 
SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...
SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...
SMART Seminar Series: "Coastal Infrastructure, Urban Mobility and Vulnerabili...
 

Kürzlich hochgeladen

psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docxPoojaSen20
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...Poonam Aher Patil
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDThiyagu K
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
Role Of Transgenic Animal In Target Validation-1.pptx
Role Of Transgenic Animal In Target Validation-1.pptxRole Of Transgenic Animal In Target Validation-1.pptx
Role Of Transgenic Animal In Target Validation-1.pptxNikitaBankoti2
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxAreebaZafar22
 
ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701bronxfugly43
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfChris Hunter
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxVishalSingh1417
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17Celine George
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsTechSoup
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxheathfieldcps1
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxVishalSingh1417
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
Python Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxPython Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxRamakrishna Reddy Bijjam
 

Kürzlich hochgeladen (20)

psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docx
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Role Of Transgenic Animal In Target Validation-1.pptx
Role Of Transgenic Animal In Target Validation-1.pptxRole Of Transgenic Animal In Target Validation-1.pptx
Role Of Transgenic Animal In Target Validation-1.pptx
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701ComPTIA Overview | Comptia Security+ Book SY0-701
ComPTIA Overview | Comptia Security+ Book SY0-701
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptx
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Python Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docxPython Notes for mca i year students osmania university.docx
Python Notes for mca i year students osmania university.docx
 

SMART Seminar Series: "Using AI and edge computing devices for traffic flow monitoring". Presented by Dr Johan Barthelemy

  • 1. UsingAI and edge computing devices for traffic flow monitoring Dr J. Barthélemy, Dr N. Verstaevel, Dr H. Forehead, Senior Prof. P. Perez, Bilal Arshad, Dinh (Andrew) Che
  • 2. Edge Computing with Jetson TX2 for Monitoring Flows of Pedestrian and Vehicles At SMART, we believe that People with good information and good tools will make good Decisions and change their world 2
  • 3. The case of Liverpool CBD is growing fast: new UoW campus, airport development,…  What does it mean for the city and its community? What are the problems?  Smart Cities and Suburbs Program: How can we use IoT to solve the problems? 3
  • 4. Which problems? Let’s ask the people! Pedestrians - Where are they going? - What are the most popular routes? - What are the most congested locations? - Impact of city activity? Cyclists - Which route are they taking? - How can we improve bike usage? Cars - Live traffic? 4
  • 5. Sensors locations 20 sensors Image credit: OpenStreetMap 5
  • 6. How about using CCTV? 6 Privacy!
  • 7. Sensor requirements • Mobile units + leveraging CCTV infrastructure • Privacy is important! – On board video analytics – Only indicators transmitted (no raw data!) • Real-time image processing • LoRaWAN network 7
  • 8. LoRaWAN: An IoT Network Image credit: https://ttnmapper.org • Long range • Low power • Low bandwidth (max 200 bytes/message) • Open source • Free for use by the community 8
  • 9. History of the prototypes 9
  • 10. The sensor An edge computing device Components — NVIDIA Jetson TX2 for onboard processing — Pycom LoPy 4 for data transmission on The Things Network — Camera (USB webcam / existing CCTV) 10
  • 12. From the input to the dashboard Image Acquisition • CCTV/Webcam Detection • Deep Convolutional Neural Network Tracking • Kalman Filtering Data transmission • LoRaWAN/OneM2M Dashboard/Database Image credit: NVIDIA Corporation Image credit: Pycom 12
  • 13. Detection:YOLO v3 Inference: Jetson TX2Training: Titan Xp • Fully convolutional DNN • 106 hidden layers • Detections at 3 scales • 3 classes: person, bicycle, vehicles • Pascal VOC and COCO datasets cuDNN FP16+ + 13
  • 14. Detection:YOLO v3 Current training dataset • 80.000 images from Pascal VOC, COCO • 6 data augmentation techniques 480.000 images 14
  • 16. Tracking: Kalman Filtering 16 Prediction of O in current frame Position of O in previous frame Detection D in current frame 𝐼𝑜𝑈 ≔ ≥ 𝛿 𝑥 𝑦 if D = O
  • 17. Detection:YOLO v3 • Detecting locations of pedestrians and vehicles • Number of objects of each type 17 VIRAT Video Dataset
  • 18. Tracking: Kalman Filtering • Associating IDs with the detections • Trajectories 18 VIRAT Video Dataset
  • 19. Final output No image Privacy OK! 19
  • 20. Liverpool Smart Pedestrian architecture Fixed counters Air quality x20 x5 x15 Mobile counters Sensors IoT Core ApplicationsTransport + Forecasting Analytics Public Dashboard Liverpool IoT Core Citizens app 20
  • 21. ● Open source service platform for M2M interoperability based on the oneM2M standard. ● Follows a RESTful approach GET/POST/DELETE/SUBSCRIBE ● Access control policies ● Plugins ● Can be decentralised with multiple nodes ● Support different technologies: ○ Lora ○ Zigbee ○ Sigfox ○ Bluetooth Low Energy ○ Z-wave OM2M Eclipse 21
  • 22. Liverpool IoT Core MQTT TTN AE - TheThingsNetwork App Id … DATA IN_Node METADATA MN_Node1 MN_... Subscriptions HTTP Rest API Database Inject HTTP GET Publish data Collect data Manage and secure data Store data POA 22
  • 23. The Things Network application AE-TheThingsNetwork CNT- App Id CNT - DATA CIN – DATA_... CNT - METADATA CIN – METADATA_... 23
  • 24. Visual Sensor application MN- SensorName CNT- DATA CIN –... CIN –... CNT- DESCRIPTOR CNT- CONFIGURATION CIN –... CNT- SYSTEM CIN –... CNT- COMMAND CIN –... 24
  • 26. Dashboard Trajectories of the detections (inside a building) 26
  • 27. Dashboard Heatmap of the maximum number of the detections (inside a building) 27
  • 29. Next steps: Inferring network dynamics Image credit: OpenStreetMap Image credit: Google Maps 29
  • 31. Conclusions It’s only the beginning! • VS able to perform real time object detection and tracking • Privacy compliant… but meaningful information • Open data for people centric approach – citizen applications – city and traffic planners • IoT core scalable and interoperable – adding new sensors: air quality, noise, … Traffic modelling AnalyticsDashboardCitizens app 31
  • 32. But it’s already successful! Best Local Government Initiative Document title32
  • 35. 35 Image credit: Redmon, J. and Farhadi, A. (2018). YOLOv3: An Incremental Improvement YOLO v3 performances
  • 36. GPU and Edge computing Image credit: NVIDIA Corporation Dataset Deep Neural Net Trained model deployment Inference: Jetson Image credit: NVIDIA Corporation Training: Titan/DGX/Tesla Image Acquisition Detection Tracking Data transmission Dashboard/Database 36
  • 37. Architecture of the solution Fixed counters Air quality x20 Noise level x20 x5 x15 Mobile counters Sensors IoT Core ApplicationsTransport + Private and Public APIs Traffic modelling Analytics Dashboard Citizens app 37
  • 38. Dashboard Heatmap of the maximum number of detections 38