Traffic Violation Detector using object Detection
A Presentation On
Department Of Computer Science & Engineering
Shri Ram Murti Smarak College Of Engineering , Technology & Research,Bareilly
Presented by:-
Shraddha Kasaudhan
Deeksha Gangwar
Tarang Jain
Outlines
1. Introduction of project
2. Introduction of object detection
3. Applications
4. Problem
5. Data set
6. Solutions
7. Output of OCR
8. Work in progress second (II)
9. Conclusion
10.References
Traffic Violation
Detector using
Object Detection
Traffic Violation Detector:
• Basically traffic violation is an act when a
vehicle violates the traffic rules.
•With the growth of the number of vehicles,
the number of traffic accidents is rapidly
rising.
• The traffic violation detector can ensure a
smooth traffic flow.
• A complete traffic violation detection system
is realized in python with OpenCV.
• It can detect violations, such as running
red lights, speeding etc. in real time.
Artificial
Intelligence•Object detection is a computer
technology that deals with
detecting objects of a certain class
in images and videos.
•Object detection has applications
in many areas of computer vision,
including image retrieval and video
surveillance
Introduction of
object detection
Applications
Self driving cars:-
One of the best examples of
why you need object
detection is for autonomous
driving is In order for a car
to decide what to do in next
step whether accelerate,
apply brakes or turn, it
needs to know.
Optical Character
Recognition (OCR):-
OCR is a method that
converts the images into
machine-encoded text.
Tracking objects:-
Object detection system is
also used in tracking the
objects, for example
tracking a ball during a
football match, tracking
movement of a cricket bat
Applications
Human Diligence
Man Power
Manual Labour
Corruption
Problems:
Due to increasing growth of
population and vehicles in smart and
metropolitan cities people face lot of
problem at the traffic management of
the business towns.
Data set :-
Common Object in Context(COCO):-
• It is a dataset which contains
2,00,000 images and more than
5,00,000 object annotations in 80
categories.
• The average number of objects is
7.2 per images.
Solution
Step 1:-
•Creating an Object Detection Web
application Using Visual Studio code.
•Create Webpage
•Create main file by Python as a backend
•Create Database
•Connectivity of WebPages and database
Step 2:-
•Creating an Object Detection using Tensor flow.
•Create a virtual machine using Anaconda.
•Install the Object Detection API Library.
•Install and launch an object detection web
application.
•Test the web application with uploaded images.
Step 3:-
Creating an Optical Character Recognition using
Nanonet API .
• Clone the Repo.
•Get your free API Key.
• Set the API key as an Environment Variable.
• Create a New Model.
• Add Model Id as Environment Variable.
• Upload the Training Data.
• Train Model.
• Get Model State.
• Make Prediction.
OCR Detection Output
Work progress second(II)
1. Upload and result
2. Detection
3. Result template
Project output on web application
Conclusion
•An efficient less time consuming vehicle number plate
detection method is projected which performed on
multifaceted image.
•Our anticipated algorithm is mainly based on Indian
automobile number plate system. Extraction of number plate
accuracy may be increased for low ambient light image.
References
• https://cloud.google.com/solutions/creating-object-detection-
application-tensorflow
• https://en.wikipedia.org/wiki/Object_detection
• https://www.analyticsvidhya.com/blog/2018/12/guide-
convolutional-neural-network-cnn/
• https://www.academia.edu/Documents/in/Object_Detection
•https://www.researchgate.net/publication/271545712_A_video-
based_traffic_violation_detection_system/link/54d2248c0cf28370d0e1c44
6/do wnload
Thank You

Traffic Violations Detector using object detection -part2

  • 1.
    Traffic Violation Detectorusing object Detection A Presentation On Department Of Computer Science & Engineering Shri Ram Murti Smarak College Of Engineering , Technology & Research,Bareilly Presented by:- Shraddha Kasaudhan Deeksha Gangwar Tarang Jain
  • 2.
    Outlines 1. Introduction ofproject 2. Introduction of object detection 3. Applications 4. Problem 5. Data set 6. Solutions 7. Output of OCR 8. Work in progress second (II) 9. Conclusion 10.References
  • 3.
  • 4.
    Traffic Violation Detector: •Basically traffic violation is an act when a vehicle violates the traffic rules. •With the growth of the number of vehicles, the number of traffic accidents is rapidly rising. • The traffic violation detector can ensure a smooth traffic flow.
  • 5.
    • A completetraffic violation detection system is realized in python with OpenCV. • It can detect violations, such as running red lights, speeding etc. in real time.
  • 6.
    Artificial Intelligence•Object detection isa computer technology that deals with detecting objects of a certain class in images and videos. •Object detection has applications in many areas of computer vision, including image retrieval and video surveillance Introduction of object detection
  • 7.
    Applications Self driving cars:- Oneof the best examples of why you need object detection is for autonomous driving is In order for a car to decide what to do in next step whether accelerate, apply brakes or turn, it needs to know. Optical Character Recognition (OCR):- OCR is a method that converts the images into machine-encoded text. Tracking objects:- Object detection system is also used in tracking the objects, for example tracking a ball during a football match, tracking movement of a cricket bat Applications
  • 8.
    Human Diligence Man Power ManualLabour Corruption Problems: Due to increasing growth of population and vehicles in smart and metropolitan cities people face lot of problem at the traffic management of the business towns.
  • 9.
    Data set :- CommonObject in Context(COCO):- • It is a dataset which contains 2,00,000 images and more than 5,00,000 object annotations in 80 categories. • The average number of objects is 7.2 per images.
  • 10.
    Solution Step 1:- •Creating anObject Detection Web application Using Visual Studio code. •Create Webpage •Create main file by Python as a backend •Create Database •Connectivity of WebPages and database
  • 11.
    Step 2:- •Creating anObject Detection using Tensor flow. •Create a virtual machine using Anaconda. •Install the Object Detection API Library. •Install and launch an object detection web application. •Test the web application with uploaded images.
  • 12.
    Step 3:- Creating anOptical Character Recognition using Nanonet API . • Clone the Repo. •Get your free API Key. • Set the API key as an Environment Variable. • Create a New Model. • Add Model Id as Environment Variable. • Upload the Training Data. • Train Model. • Get Model State. • Make Prediction.
  • 13.
  • 14.
    Work progress second(II) 1.Upload and result
  • 15.
  • 16.
  • 17.
    Project output onweb application
  • 18.
    Conclusion •An efficient lesstime consuming vehicle number plate detection method is projected which performed on multifaceted image. •Our anticipated algorithm is mainly based on Indian automobile number plate system. Extraction of number plate accuracy may be increased for low ambient light image.
  • 19.
    References • https://cloud.google.com/solutions/creating-object-detection- application-tensorflow • https://en.wikipedia.org/wiki/Object_detection •https://www.analyticsvidhya.com/blog/2018/12/guide- convolutional-neural-network-cnn/ • https://www.academia.edu/Documents/in/Object_Detection •https://www.researchgate.net/publication/271545712_A_video- based_traffic_violation_detection_system/link/54d2248c0cf28370d0e1c44 6/do wnload
  • 20.