mint-1

byDivya Rajput

1 Project Setup 2 React Dashboard 3 FastAPI Backend 4 GeoTIFF Validation 5 Planner Agent 6 AI Models 7 GeoReason Engine 8 Dashboard + PDF Phase 1 — Project Setup Ye sabse pehle banta hai. Languages Frontend: TypeScript Backend: Python AI Tools Work Tool Code ChatGPT UI Figma Git GitHub Deployment Docker Folder: satquery-x/ │ ├── frontend/ ├── backend/ ├── ai_models/ ├── database/ └── datasets/ Phase 2 — Dashboard (React) Sabse pehle UI banao. 6 Tech React Next.js Tailwind Pages Page Purpose Home Landing Upload Images Dashboard Results Report PDF Components: Navbar Upload Zone Image Preview Chat Box Map Confidence Card Phase 3 — Backend React directly AI se baat nahi karega. Beech me FastAPI hoga. APIs POST /upload POST /validate POST /analyze GET /report Language: Python Framework: FastAPI Phase 4 — GeoTIFF Validation User image upload karega. Python me Rasterio metadata read karega. Validation Flow Read GeoTIFF Read CRS Check Resolution Detect Sensor Libraries: Rasterio GDAL Output: CRS ✓ Resolution ✓ Sensor = Optical Phase 5 — Planner Agent (Required by ISRO) Planner sirf routing karta hai. Example: User Query Highlight flooded roads. Planner Output Task = SAR Flood Analysis Models = Grounding + SAR Fusion Input = Optical + SAR Pair Tech: Python Llama 3.1 Prompt Engineering Planner kuch train nahi karega. Phase 6 — AI Models Ye alag-alag specialist models hain. 6.1 VQA Question: Describe this image. Model: RemoteCLIP RSVQA Output: River Buildings Forest 6.2 Grounding Question: Highlight water body. Model: GroundingDINO Output: Blue polygon 6.3 Change Detection Input: 2023 + 2026 Model: ChangeCLIP Output: Urban growth Forest loss Roads 6.4 Optical + SAR Purpose: Flood detection Model: SEN12MS encoder Output: Verified flooded villages Phase 7 — GeoReason Engine (Innovation) Ye hamara original module hai. Ye verify karega: Optical SAR Metadata Temporal Final confidence generate karega. Language: Python Phase 8 — Database Store karega: Table Data Users Login Projects Analysis Images Metadata Reports PDF Database: PostgreSQL + PostGIS Phase 9 — Final Dashboard 6 User dekhega: Left Satellite map Highlighted objects Right AI answer Confidence Objects Bottom Execution summary Download report Phase 10 — PDF Report Python: ReportLab PDF pages: Cover User Query Images Highlighted Map Statistics Confidence Models Used Complete Tech Stack Module Language Library UI TypeScript React + Next.js Styling CSS Tailwind Backend Python FastAPI AI Python PyTorch VQA Python RSVQA Grounding Python GroundingDINO Change Python ChangeCLIP GIS Python Rasterio + GDAL Database SQL PostgreSQL PDF Python ReportLab AI Tools to Use Purpose AI Tool UI Code ChatGPT Backend Code ChatGPT Auto-complete GitHub Copilot UI Design Figma AI Testing Postman Version Control GitHub Team Division Member Work AI-1 VQA + Caption AI-2 Change Detection AI-3 Optical–SAR Fusion Backend FastAPI + Planner Frontend React Dashboard ML Ops Database + Docker 24-Hour SIH Execution Hours Task 0–2 Setup & Git clone 2–5 React UI 5–8 FastAPI APIs 8–12 AI model integration 12–16 Planner + Validation 16–20 GeoReason + Dashboard 20–24 Testing + PPT + Demo Final Innovation (Judges ko ye bolna) Planner Agent ISRO ka required feature hai. Hamari originality GeoReason Engine hai, jo Optical, SAR aur temporal outputs ko cross-verify karke explainable confidence score aur contradiction-free final answer generate karta hai. Ye hi SATQUERY X ki unique contribution hai.

HomeLogin
Home

Comments (0)

No comments yet. Be the first!

System Requirements

System Requirement Document
Page 1 of 8

System Requirements Document for mint-1

1. Introduction

The mint-1 project, also known as SATQUERY X, is a high-tech satellite image analysis and AI dashboard designed for ISRO and advanced users. It leverages cutting-edge technology and AI models to provide comprehensive satellite imagery analysis. The system is built using a React/Next.js frontend and a FastAPI backend, with a focus on providing a cinematic and futuristic user experience.

2. System Overview

The SATQUERY X system is designed to facilitate satellite image analysis through a user-friendly dashboard. It supports image uploads, GeoTIFF metadata validation, and advanced AI-driven analysis. The system includes a Planner Agent for task routing and a GeoReason Engine for cross-verifying analysis outputs. Users can generate detailed PDF reports of their analyses. The system is built with a focus on high-tech design and user experience, using a specified tech stack and adhering to a 24-hour execution plan.

Page 2 of 8

2a. Product Interpretation and Delivery Boundary

The system is delivered as a web application with a React/Next.js frontend and a FastAPI backend. It requires user authentication for accessing protected features such as image uploads and analysis dashboards. The system persists data using PostgreSQL/PostGIS and generates reports using ReportLab. The Planner Agent and GeoReason Engine are key components, with the former handling task routing and the latter providing verification and confidence scoring. The system's design is inspired by Gleb Kuznetsov's cinematic future tech style, emphasizing a high-tech and immersive user experience.

2b. Source Content Inventory

Not applicable as no content source directive was provided.

2c. Page Content and Component Coverage

Home

  • Purpose: Landing page introducing SATQUERY X.
  • Components: Overview of features, navigation to login or upload.
  • States: Loading, success.

Login

  • Purpose: User authentication.
  • Components: Username and password fields, login button.
  • States: Loading, success, error.
Page 3 of 8

Upload

  • Purpose: Image upload and GeoTIFF validation.
  • Components: Upload Zone, Image Preview, Validation Results.
  • States: Loading, success, error.

Dashboard

  • Purpose: Display analysis results and planning.
  • Components: Map, Chat Box, Confidence Card, Execution Summary.
  • States: Loading, success, error.

Report

  • Purpose: PDF report generation and download.
  • Components: Report preview, download button.
  • States: Loading, success, error.
Page 4 of 8

3. Functional Requirements

  • As an Analyst, I should be able to upload satellite images for analysis.

    • Provenance: Explicit
    • Lifecycle: Initiated on the Upload page, validated using Rasterio/GDAL, results displayed on the same page.
    • Observable Result: Successful upload and validation results.
  • As an Analyst, I should be able to view analysis results on a dashboard.

    • Provenance: Explicit
    • Lifecycle: Initiated on the Dashboard page after image upload and analysis.
    • Observable Result: Display of maps, AI answers, confidence scores, and execution summaries.
  • As an Analyst, I should be able to generate and download a PDF report of my analysis.

    • Provenance: Explicit
    • Lifecycle: Initiated on the Report page, uses ReportLab for generation.
    • Observable Result: Downloadable PDF report.
  • As an Analyst, I should be able to log in to access my projects and analyses.

    • Provenance: Required Inference
    • Lifecycle: Initiated on the Login page, required for accessing Upload, Dashboard, and Report pages.
    • Observable Result: Successful login grants access to protected features.
Page 5 of 8

4. User Personas

  • Analyst
    • Responsibilities: Upload satellite imagery, ask analysis questions, review maps and AI answers, download reports.
    • Outcomes: Successful image analysis, report generation, and data-driven decision-making.

5. Core User Flows

Analyst Flow

  1. Access Home Page: View introductory content and navigate to login.
  2. Login: Enter credentials to access the system.
  3. Upload Image: Navigate to the Upload page, upload a satellite image, and view validation results.
  4. View Dashboard: Access the Dashboard to view analysis results, including maps and confidence scores.
  5. Generate Report: Navigate to the Report page and generate a PDF report of the analysis.
  6. Download Report: Download the generated PDF for offline review.
Page 6 of 8

6. Visuals Colors and Theme

  • Muse: Gleb Kuznetsov
  • Palette:
    • Background: #000022
    • Surface: #1c1c3a
    • Text: #ffffff
    • Primary: #00ffff
    • Accent: #ff00ff
    • Muted: #444466
  • Typography:
    • Headings: Space Grotesk, Uppercase, wide spacing
    • Body: Orbitron
    • Scale: 1.5 modular, 64/42/28/18/14
  • Shape Language: Full-bleed 3D scene, floating glass panels, thin luminous strokes
  • Layout: Radial layouts with floating elements

7. Signature Design Concept

A full-bleed 3D scene dominates the viewport on the Home page, with floating glass panels displaying live data streams over a dark void. Electric cyan and magenta glows highlight important sections, creating an immersive and futuristic experience.

Page 7 of 8

8. Interaction Model & Motion Direction

  • Interaction Model: Animated
  • Motion Tempo: Cinematic
  • Hero Dimensionality: webgl
  • Landing Hero Motion Brief: A full-bleed 3D holographic object with floating data panels, using electric cyan and magenta highlights that animate on hover. The scene orbits slowly, creating a sense of depth and immersion.

9. Non-Functional Requirements

  • Performance: The system must handle concurrent user sessions efficiently.
  • Scalability: The architecture should support scaling to accommodate increased data and user load.
  • Security: User data must be protected with encryption and secure authentication mechanisms.
  • Usability: The interface should be intuitive and accessible to users with varying levels of technical expertise.

10. Tech Stack

  • Frontend: TypeScript, React, Next.js, Tailwind
  • Backend: Python, FastAPI
  • AI: PyTorch, RemoteCLIP, RSVQA, GroundingDINO, ChangeCLIP, SEN12MS encoder
  • GIS: Rasterio, GDAL
  • Database: PostgreSQL, PostGIS
  • PDF Generation: ReportLab
  • Tools: ChatGPT, Figma AI, GitHub, Docker, Postman
Page 8 of 8

11. Assumptions and Constraints

  • Assumption: Users have access to modern web browsers and stable internet connections.
  • Constraint: The system must use the specified tech stack and adhere to the 24-hour execution plan.

12. Glossary

  • GeoTIFF: A public domain metadata standard which allows georeferencing information to be embedded within a TIFF file.
  • CRS: Coordinate Reference System, a coordinate-based local, regional or global system used to locate geographical entities.
  • SAR: Synthetic Aperture Radar, a form of radar used to create two-dimensional images or three-dimensional reconstructions of objects.
  • ISRO: Indian Space Research Organisation, the space agency of the Government of India.
Home design preview
Home: View introduction
Login: Sign in
Upload: Upload satellite image
Upload: View validation results
Dashboard: Ask analysis question
Dashboard: View maps and answers
Dashboard: Review confidence scores
Report: Generate PDF report
Report: Download report
Home design preview
Home: View introduction
Login: Sign in
Upload: Upload satellite image
Upload: View validation results
Dashboard: Ask analysis question
Dashboard: View maps and answers
Dashboard: Review confidence scores
Report: Generate PDF report
Report: Download report