Road texture analysis and anomaly segmentation

Project Title

Road texture analysis and anomaly segmentation

Project Area of Specialization Artificial IntelligenceProject Summary

Our Project aims to propose road texture analysis for less developed countries such as Pakistan. This project will analyze different conditions of the road by applying Computer Vision techniques in a real time and smartly predict the car’s velocity and gear change decisions. Efficient Segmentation of road surface is the supreme purpose of our project.

Project Objectives

There are more than 1.74 million cars on the roads of Pakistan and many people have been killed in car accident and many cars are being damaged because of the poor road conditions. The drivers and passengers travelling on such roads have high risk of being damaged. As a result, driver assistance systems and even unmanned vehicles have been researched for many years to help drivers drive safely and comfortably.

Road Texture Analysis is based on the idea of detecting the conditions of street roads, analyzing its anomalies and based on them, taking the controlling and gear shifting decisions.

Project Implementation Method

We will be using following Methodology and Tools:

• Convolutional Neural Network (CNN)
• Open CV
• Google Colab
• Deep Learning
• Keras
• Python
• Simulation in Carla

A convolutional neural network (CNN) is a type of artificial neural network used in image recognition and processing that is specifically designed to process pixel data.

CNNs are powerful image processing, artificial intelligence (AI) that use deep learning to perform both generative and descriptive tasks, often using machine vision that includes image and video recognition.

OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning software library. OpenCV was built to provide a common infrastructure for computer vision applications and to accelerate the use of machine perception in the commercial products. Being a BSD-licensed product, OpenCV makes it easy for businesses to utilize and modify the code.

Google Colab is a free cloud service and now it supports free GPU. The most important  feature that distinguishes Colab from other free cloud services is: Colab provides GPU and is totally free.

Deep learning is an artificial intelligence function that imitates the workings of the human brain in processing data and creating patterns for use in decision making. Deep learning is a subset of machine learning in artificial intelligence (AI) that has networks capable of supervised learning from data that is structured or labeled. Also known as deep neural learning or deep neural network.

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.

Use Keras if you need a deep learning library that:

• Allows for easy and fast prototyping (through user friendliness, modularity, and extensibility).
• Supports both convolutional networks and recurrent networks, as well as combinations of the two.
• Runs seamlessly on CPU and GPU.

Python is one of the most popular programming languages used by developers today. It is a High-level programming language and can be used for complicated scenarios. High-level languages deal with variables, arrays, objects, complex arithmetic or Boolean expressions, and other abstract computer science concepts to make it more comprehensive thereby exponentially increasing its usability.

Benefits of the Project

Autonomous driving is no longer a dream. The automotive industry is evolving the vehicle to take more responsibility over maneuvers.

Convincing drivers to hand over control requires significant trust in the vehicle’s ability to plan the right maneuvers and strategies. 

Self-driving technology has the potential to reduce crashes, but some high-profile accidents have raised questions about risks posed by poorly functioning autonomous-driving systems.  

There are millions of cars roaming on the roads of this metropolitan city and with the growing demand of cars, this number is only expected to increase. As a consequence, the number of road accidents are also expected to increase and this is where this project comes handy. With a highly efficient model, the number of these accidents will reduce drastically. This will solve all sorts of problems like traffic delays and traffic collisions caused by driver error. Research shows that 94% accidents are caused by driver behavior or error and self-driving cars can help reduce driver error which will result in a sharp plunge in the number of road accidents. This project will analyze the road texture and make decisions accordingly. These decisions include whether to apply brakes, whether to reduce the speed or not, how much speed needs to be reduced, whether to change gear etc

Technical Details of Final Deliverable

. This project will analyze the road texture and make decisions accordingly. These decisions include whether to apply brakes, whether to reduce the speed or not, how much speed needs to be reduced, whether to change gear etc. It will take images from the cameras and segment the road surface and if the road has any lines or marks or potholes, it has to recognize it and make appropriate decisions. The most important requirement is that the system should be real-time, which means that it should process enough frames per second.

Final Deliverable of the Project Software SystemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	5600
Mobile holder	Equipment	2	500	1000
Printouts	Miscellaneous	3	100	300
Datasets	Miscellaneous	4	1000	4000
tapes for car holder	Miscellaneous	2	150	300