eMap

https://docs.google.com/presentation/d/1-0DbkGgFA9jykyIfkIwbLS_lR6d_3JuJ/edit?usp=sharing&ouid=113282978398416744323&rtpof=true&sd=true

https://github.com/amalatif/SpaceApps2021

As a pre-request for the solution to work, physical QR Code need to be generated and installed on top of the target area. The QR code will hold a link to geospatial data hosted in the internet and contain all the information about the target area. Once the QR Code is installed, the UAV will be able to take an aerial photo of the target area.

All the aerial photos then will be processed by the Image Extraction and Decoding software that will extract the data display it on Geospatial browsers such as Google Earth

The Process

1. Creation of geospatial data
2. This covers all the information that needs to be included in the final map. Such as the area boundaries, name, location, ets. http://Geojson.io web site was used to create the GeoJson file and was hosted in Google Docs
3. Utilizing the tiny URL to shorten the URL to Google Docs
4. Creating the QR Code holding the tiny URL
5. Printing the QR code and physically installing it on the target area
6. Utilizing the UAV to take an aerial images of the target area
7. Uploading all the UAV taken images into the image recognitions and extraction Notebook
8. Scan the Aerial Images via QR code detector and decoding module
9. Use the Decoded URL to fetch the GeoJson and Display the data on Google Earth

Components 

Hardware(Field) Components

• Physical QR Code 1m x1m to be mounted in the target area
• UAV with high-resolution camera

Software

• GIS Software for Data Creation
• Image Recognition for extracting and decoding the captured images
• Jupyter notebook
• Geospatial Browser 

Benefits

• Automate the map creation
• Easy dissemination of the data to all concerned parties
• More reliable information about the target areas
• Decentralization of the GIS data 
• Eliminate the pre and post processing of imagery after acquisition
• Can be integrated with IoT for real-time information about features
• Ease of Access to Information & Attributes for local stakeholders
• Quick Turnaround
• Encourage Crowd-sourcing

The team utilized google earth data to create that geospatial data that was created by the team.

Maxar Satellite Imagery was used to verify the quality of ML generated and decoded data from QR code

Imagery taken by the team

This hackathon gave the team an opportunity to sharpen their skills required to build the prototype of a granted patent in the domain of remote sensing , GIS and UAV. The approach used to distribute the main tasks based on the experience team has. The team is happy to participate in introducing a positive change for the future of the world.

• Granted Patent https://patents.google.com/patent/US10290137B2/en?oq=US10290137B2
• ML / AA
• http://Geojson.io
• https://earth.google.com
• https://Jupiter.org
• Hussain N., Finelli C. (2020) KP-YOLO: A Modification of YOLO Algorithm for the Keypoint-Based Detection of QR Codes. In: Schilling FP., Stadelmann T. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2020. Lecture Notes in Computer Science, vol 12294. Springer, Cham. https://doi.org/10.1007/978-3-030-58309-5_17 Python Libraries pyzbar PIL Opencv

#Remote Sensing, #GIS, #patent, #UAV, #drone, #reserve, #ML,

This project has been submitted for consideration during the Judging process.