Scribd
Upload
64 views12 pages

Real Time Detection of Road Anomalies: Group Members Guide

The document describes a project aimed at developing a prototype for real-time road anomaly detection. The project's objectives are to design an intelligent data gathering system to detect potholes and inform drivers and authorities. The methodology uses YOLO object detection to analyze images and detect potholes. APIs were developed to add, delete, display, and check pothole locations in a database. The results and discussion are presented, followed by conclusions that the alert application notifies drivers of potholes and shares locations with officials to facilitate repairs.

Uploaded by

Bharath
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
64 views12 pages

Real Time Detection of Road Anomalies: Group Members Guide

The document describes a project aimed at developing a prototype for real-time road anomaly detection. The project's objectives are to design an intelligent data gathering system to detect potholes and inform drivers and authorities. The methodology uses YOLO object detection to analyze images and detect potholes. APIs were developed to add, delete, display, and check pothole locations in a database. The results and discussion are presented, followed by conclusions that the alert application notifies drivers of potholes and shares locations with officials to facilitate repairs.

Uploaded by

Bharath
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

REAL TIME DETECTION OF

ROAD ANOMALIES

GROUP MEMBERS GUIDE


SAI ROHITH BALA - 1MS17EI010 DR A SARVANAN
JAYARAJ G - 1MS17EI015
RAJENDRA N - 1MS17EI031
SUSHANTH REDDY - 1MS17EI040
BHARATH CHANDRA - 1MS17EI055
TABLE OF CONTENTS

• INTRODUCTION
• LITERATURE REVIEW
• OBJECTIVES
• METHODOLOGY
• RESULTS AND DISCUSSION
• CONCLUSION
• REFERENCES
INTRODUCTION

• Poor road conditions like cracks and potholes can cause inconvenience to
passengers, damage to vehicles, and accidents. Detecting those obstacles has
become relevant due to the rise of the autonomous vehicle.

• Our project addresses this issue with the help of deep-learning based
techniques.

• The system we propose deals with the detection of potholes and prevention
of potholes by using a driver alert application that gives prior information
about the pothole to the driver so that the driver can avoid any kind of
accidents that might occur due to potholes
LITERATURE REVIEW

S No reference papers keywords


Danti, A., Kulkarni, J. & Hiremath, P., has developed a model based on Image Processing
2012. An Image Processing Approach to approach. In this paper Haugh Transformation is given
1 Detect Lanes, Potholes and Recognize for lane detection. Clustering based algorithm is used for
Road Signs in Indian Roads. detection of potholes. In this, experimental results are
International Journal of Modeling and tested using the real time image database.
Optimization, 2(6), pp. 658-662.

 J. Lin and Y. Liu, “Potholes detection  has proposed a method for pothole detection based on
based on SVM in the pavement distress SVM (Support Vector Machine). This method
2 image,” in Proc. 9th Int. Symp. Distrib. distinguishes potholes from other defects such as cracks.
Comput. Appl. Bus. Eng. Sci., Aug. The images are segmented by using partial differential
2010, pp. 544– 547. equations. In order to detect potholes, the method trains
the SVM with a set of pavement images. However, the
training model fails to detect the pavement defects if the
images are not properly illuminated.
He Youquan, Wang Jian, Qiu Hanxing,  have developed a model which employs optical imaging
Zhang Wei, Xie Jianfang, “A Research of principle of three dimensional projection transformation to
3 Pavement Potholes Detection Based on obtain pictorial information of pothole’s cross-section in
Three-Dimensional Project pothole detection. Multiple digital image processing
Transformation”, In Proceedings of technologies, including: binarization, image processing,
International Congress on Image and Signal thinning, three dimensional reconstruction, error analysis
Processing, pp.1805- 1808, 2011. & compensation are conducted in the series of image
analysis and processing. 

Kongyang Chen, Z. Wei,, “A research of proposed a system for detecting potholes using a GPS
pavement potholes detection based on three sensor & three-axis accelerometer. The outputs are taken
4 dimensional projection transformation,” in from the GPS sensor & three-axis accelerometer and fed
Proc. 4th Int. Congr. Image Signal Process into a data cleaning algorithm. In the second part of the
(CISP), Oct. 2011.   implementation the inputs to the algorithm are processed
for power spectra density (PSD) to calculate the roughness
of potholes. After analysing, roughness is classified into
different levels.
OBJECTIVES

• The goal of this project is to design and develop a prototype of an


intelligent data gathering system that can be fitted in any transportation
vehicle or car to detect the potholes.
• The prototype develops an information gathering system that informs the
driver and authorities about the road conditions. 
• With this information the authorities could take measures to repair the
roads which in turn help to avoid accidents caused due to bad roads and
hence lower the percentage of damaged roads and avoid road accidents. 
METHODOLOGY

YOLO Object Detection

Yolo reframes object detection as a single regression problem. YOLO looks at the input
image just once, and divides it into a grid of S x S cells. Each grid cell predicts B
bounding boxes, a confidence score representing the intersection over union (IOU) with
the ground truth bounding box, and the probability that the predicted bounding box
contains some objects.

We have written APIS for the addition, deletion, display and check functions. From UI,
api calls are made to the backend and respective functions are made
RESULTS AND DISCUSSION
CONCLUSION

•The project presented a good preliminary method for pothole detection using
deep learning techniques to extract information about the road and to
understand the environment surrounding the vehicle.

•Our  personally designed alert application helps in giving prior notification


alerts to the driver about the potholes. It is also used to share the pothole info
and location to the respective government officials to take preventive action to
get rid of them. We can also delete the location of the pothole from the
database after it is repaired by the government. 
REFERENCES

1.

01. Danti, A., Kulkarni, J. & Hiremath, P., 2012. An Image Processing Approach to Detect Lanes, Potholes and
Recognize Road Signs in Indian Roads. International Journal of Modeling and Optimization, 2(6), pp. 658-662.
•
02.       J. Lin and Y. Liu, “Potholes detection based on SVM in the pavement distress image,” in Proc. 9th Int.
Distrib. Comput. Appl. Bus. Eng. Sci., Aug. 2010, pp. 544– 547.
•
03.     He Youquan, Wang Jian, Qiu Hanxing, Zhang Wei, Xie Jianfang, “A Research of Pavement Potholes Detection
Based on Three-Dimensional Project Transformation”, In Proceedings of International Congress on Image and Signal
Processing, pp.1805- 1808, 2011. 
•
04.      Kongyang Chen, Z. Wei,, “A research of pavement potholes detection based on three dimensional projection
transformation,” in Proc. 4th Int. Congr. Image Signal Process (CISP), Oct. 2011.  
•
05.       Karuppuswamy, J., Selvaraj, V., Ganesh, M. & Hall, E., 2000. Detection and Avoidance of Simulated Potholes
in Autonomous Vehicle Navigation in an Unstructured Environment. Intelligent Robots and Computer Vision XIX:
Algorithms, Techniques, and Active Vision. Proc. SPIE 4197, pp. 70-80
THANK YOU

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy