Poor road conditions are causing a lot of discomfort to people, leading to vehicle damage and loss of precious lives. Moreover, potholes lead to the D-shaping of tyres, making them weak and in need of replacement sooner rather than later. It usually costs 4500-8500 pkr/tyre which is not so affordabl
Pothole detector
Poor road conditions are causing a lot of discomfort to people, leading to vehicle damage and loss of precious lives. Moreover, potholes lead to the D-shaping of tyres, making them weak and in need of replacement sooner rather than later. It usually costs 4500-8500 pkr/tyre which is not so affordable for everyone. Not changing the weak tyre can cause tyre burst leading to accidents and loss of precious life. Potholes also cause a great damage to the car’s suspension, bolts and shocks, causing them to be changed once in every six months, which is also not so affordable. Keeping in mind all these problems, our final year project aims to develop such an android application which will detect the potholes and pin the potholes’ current location on the map which will be updated to the server side. The application will use city map and current location of the driver as they turn on their phone’s GPS. Detection of potholes will be done using two techniques as proposed in the application. The two techniques can work independently as well as collectively to detect potholes. First technique is by using image processing, as the driver drives through the road with a windscreen mounted device. We will train our model to detect the potholes and then our application will pin the current location on the map indicating a pothole. The second technique is by using the gyroscope and accelerometer sensors in the phone.
The objectives of our application are as follows:
This application will provide ease to the public to have a better road experience and inform the civic authorities about the exact location on the road which they need to get repaired.
The frontend of the system will be developed on Java using the android SDK. The backend i.e. the server will be built using ROR (Ruby on Rails). Detection of potholes will be done using two techniques as proposed in the application. First technique is using image processing, as the driver drives through the road with a windscreen mounted device We will train our model to detect the potholes using tensorflow and then our application will pin the current location on the map indicating a pothole. The second technique is by using the gyroscope and accelerometer sensors in the phone. As the driver drives the car through the city, our trained model (using SVM classifying technique) detects the potholes and the application pins the location on the map. The user can decide if he wants to use the phone’s camera or the phone’s sensor or both. Our application can detect potholes on lower costs just by using phone’s camera or phone’s sensor or both. This application can provide ease to Pakistan National Highway Authority and other supporting authorities as currently they have to spend considerable time detecting potholes than fixing them. The information of the application can also be used by the public to be careful in case of damaged road providing them safety.
IMPACT ON SOCIETY and TECHNOLOGY
Potholes are a serious threat to the driver’s as well as the vehicles’ safety. Our application can detect potholes on lower costs just by using windscreen mounted device or phone’s gyroscope and accelerometer sensors or both. This application can provide ease to Pakistan National Highway Authority and other supporting authorities as currently they have to spend considerable time detecting potholes and then fixing them. The information of the application can also be used by the public to avoid potholes on the roads providing them safety.
The final product will be an android application that can run on supporting platforms. The application that will use city map and current location of the driver as they turn on their phone’s GPS. The application will detect the potholes and pin the current location that will be updated to the server side and available to other users as well.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| already used nvidia gtx 1070 | Equipment | 1 | 33000 | 33000 |
| Papago safe 220 dash camera | Equipment | 1 | 24999 | 24999 |
| Raspberry pi 3 starter kit | Equipment | 1 | 7000 | 7000 |
| Total in (Rs) | 64999 |
The purpose of this project to identify Mild Cognitive Impairment (MCI) an early stage &nb...
Along with the construction and development of smart grid, the power system has put forwar...
In the backdrop of soaring un-employment, financial challenges and lack of knowledge in cu...
This system can be proved beneficial for the farmers for early detection of Plant Diseases...