Machine learning based house registry system using remote sensing data
The current global trend for information capturing, storage, processing, and retrieving is electronic. Using a manual system is wastes of time for information keeping and management lands records. Also, large space is occupied for storage and documents are prone to permanent damage and loss. The pro
2025-06-28 16:28:31 - Adil Khan
Machine learning based house registry system using remote sensing data
Project Area of Specialization Artificial IntelligenceProject SummaryThe current global trend for information capturing, storage, processing, and retrieving is electronic. Using a manual system is wastes of time for information keeping and management lands records. Also, large space is occupied for storage and documents are prone to permanent damage and loss. The problems associated with the manual recordkeeping system often prompt elective alternatives. This project developed Artificial Intelligence Based House Registry System Using Remote Sensing Data. Which currently works in a particular region. In this platform, all the detail of a house is recorded online by the authorities (owner/government) which can prevent land mafias to capture or transfer lands illegally. Through this, authorities could have better records regarding every individual’s house. Information like house owner name, CNIC, contact no. numbers of individuals living in a house etc.
By this platform, authorities could also analyze the growth of population in a specific region through the database of owner’s house (Number of individuals living in a house) which can also be helpful for the government in census data Digitalize In parallel to this if in case of any disaster occurs, disaster management provides resources and responsibilities for dealing with all humanitarian aspects of emergencies. Precautions could be made through census data of areas (Determining the number of people living there.) By using that census data, one can determine the resources & time is needed to evacuate that specific area
Project Objectives- To avoid fraud registration & illegal transfer of lands
- Help Digitize Census Data
- Applicable for Disaster Management
Download satellite image
Collect Large Dataset(Satellite Image) To Train The Model (other countries dataset is used pakistan dataset is not avaliable)
Pre-Processing cropping the image, resizing the image, removal of noise using filter filters like Gaussian filter
Import libraries for python code
Apply deep learning algorithm that is convolutional neural network
Train the model
Testing of the model for input images
Detect the buildings in satellite image
After detection of building then using SQL to show data of owner
Benefits of the Projectbuildings data will be digitized.
illegal land frauds will be minimized.
Disaster managements can count no of peoples in natural disaster.
Technical Details of Final DeliverableThere is no dataset avaliable for pakistan so other countires data sets are used to train model and detect buildings. we are working on dummy data for database we will replcae dummy data with real data in furture and also we will use drones to capture images so that we can have our own pakistan dataset of buildings.
Final Deliverable of the Project Software SystemCore Industry ITOther Industries Others Core Technology Artificial Intelligence(AI)Other Technologies OthersSustainable Development Goals Industry, Innovation and InfrastructureRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 61000 | |||
| MSI GeForce GT 1030 2GD4 LP OC 2GB Graphics Card | Equipment | 1 | 25000 | 25000 |
| 4 RAM | Equipment | 1 | 6000 | 6000 |
| 4k GPS Drone | Equipment | 1 | 30000 | 30000 |