Sie sind auf Seite 1von 21

Project Advisor:

Dr. Jerry Gao

Team:

• Bharat Bhushan

• Mithra Desinguraj
A Street Cleanliness Assessment
System for Smart City using Mobile • Kavin Pradeep Sriram Kumar

and Cloud • Sonal Gupta.

San Jose State University

Spring 2017
Introduction - Problem
 Streets are the nerves of any city and society.
 Keeping streets clean is a challenge for any city admins.
 Street cleanliness assessment is essential but..

 Problem:
 Manual.
 Offline data collection.
 Time consuming.
 No real-time visibility.
 High Cost.
Introduction - Solution
 Proposed Solution:
 Smart City Street Assessment system using Mobile and
Cloud.
 Automated using mobile and cloud.
 Real to near-real time data collection.
 Less time.
 Real-time visibility with single pane of glass.
 Cost Effective.
 Integration with other city services.
 Public contribution via mobile (crowd sourcing).
 Self Learning (Machine Learning)
 API driven.
 Mobile.
Smart City Street Cleaning Infrastructure
Cleaning Model - Layers
Cleaning Model - Areas
San Jose City
(95)
City

Willow Alum South


Central
20 24 Glen 16 Rock 35
Areas with
No. of Blocks

123 110 94 109 78 194 89 115 35 78


Blocks with 101 45

No. of Streets

Streets with
No. of Grid Pts

Individual
Photo Points.
Cleaning Model – Grid
Grid Point Model
Picture Point: Multiple Images are captured in each direction (F,B,L,R) on
either side of the street and sent to Cloud along with location data.
INode : Represent Intersection. There are several Image points between nodes.
SNode : Represent Sub Intersection. Used to divide large blocks.

Grid Point : Represent logical radius to assess both sides of the street. It can
have one or more Pic points. Collectively produces the cleanliness level across
the street.

Block with Cleanliness Indicator: Block is collection of several Grid points.


Red – Level 4 (very dirty)
Orange – Level 3
Yellow - Level2
Green – Level 1(Not visible, looks clean)
Computation – Point Level
 Pictures taken every ~20ft., sent to cloud and fed to detection engine and level is generated.
 Based on level detected, its marked -Red (4), Orange (3),Yellow (2) and Green (1).
 Results are stored in DB with image reference, date time and resulting.
 Assessment area is defined by the city admin. Every point is part of one assessment area.
 Four images are captured at every point, one in each direction.
Computation – Street level
 From each point on a street between start (S) and end (E) points, all numbers would be
averaged to generate overall assessment of the street.
 Assessment would be done for every street generating the aggregate value.
 Results are stored in DB with image reference, date time and level.
 Each street is a part of one block.
 Grid based analysis and part of the block.

 (S) (E)
Computation – Block level
 Grid based analysis.
 Aggregate of all the points in the block.
 Assessment would be based on every street in the block and the aggregate value.
 Results are stored in DB with image reference, date time and level.
 Block can have any number of streets, everything is based on each data points.
Computation – Area level
Assumptions:
 Fixed image resolution.
 Vehicle speed is approx.15mph.
 Picture set covers 20ft. of distance.
 Pictures are collected every ~2-4 sec.
 Multiple set of pictures are collected every time.
 Stable Network connectivity for real time update.
 Offline image transmission (batch transfer option).
Infrastructure
Cloud
Edge

Images sent to
Cloud via Mobile or
City Wi-Fi (batch)
Image Core DB
Service Processing Engine (MySQL) Residents
App

Web App Reports


Queuing Data
Detection
Storage Engine Analytics
Mobile App
Admin Cleaning
Edge Device
App Dept.

Edge Storage

Cloudlet
Map Service
External
System Architecture
Mobile Client Street Cleaning UI Street Cleaning Dashboard
(MS)
Street Cleaning Reports Street Cleaning Detection Engine
Controller
Mobile Street Cleaning Detection Analytics
Streets Blocks
Stations
MS Computing Street Cleaning DB service
Historical Engine DB Application DB
MS Monitoring (NoSQL) (MySQL)

Street Cleaning Service Manager Street Cleaning Security


MS Repo Admin Feedback Dispatch ACL/Authentication

MS Security Role Based Authorization.


Street Cleaning Monitoring
Performance Alerts Encryption/Session Mgmt.

Street Cleaning Service Protocols

Mobile Station ServiceRequest DB Connection Control UI Connection


Connection Module Module Module Module
Mobile Station (App Simulation)
Cloud (Tested with AWS)
 Test t2.micro instances.
 Running Separate services on different instance.
 Mobile web, Apache Tomcat, MySQL, Java.
Database
UI – Dashboard
UI – Map View
UI – Analytics - Cleanliness

Das könnte Ihnen auch gefallen