SIH26158/Robotics and Drones

Single-pass drone video 3D model generator

Build an AI-enabled system that takes a single drone video with GPS and metadata to generate a georeferenced, metrically accurate textured 3D model.

National Technical Research Organisation (NTRO) · Software

Teams already in: Not read yet
Buildable in 36 hours: LowOur estimate, from their wording
Hard blockers: NoneNothing you must source first
Submissions close: 15 Sept9 days left

Make this one of our two Compare with others

Signing in saves it for your whole team — everyone on your invite link sees the same two entries. Anything you shortlisted while signed out comes with you.

Submit on sih.gov.in Dataset

Whether this suits your team

Why this fits you

This organisation declared winners on 13 problem statement(s) in SIH 2025 and on 13 in SIH 2024. It has awarded 4 joint winner(s), so it sometimes splits a prize between two teams.

What you would have to build

Decomposed from what the description asks for. Nothing added.

01
Video Ingestion Module
Takes the mandatory 1080p or 4K drone video, GPS coordinates, and flight metadata as inputs.
02
Frame Processing Engine
Handles motion blur, video compression artifacts, and variable illumination across video frames.
03
3D Reconstruction Pipeline
Reconstructs terrain, structures, building facades, roads, vegetation, and dynamic objects from limited viewing angles.
04
Georeferencing and Metric Scaling
Applies GPS data and sensor inputs to ensure the final model maintains metric accuracy without extensive ground control points.
05
3D Model Export
Outputs textured 3D meshes or point clouds suitable for visualization, measurement, and analysis.

What they ask for, and what they leave open

Both columns are read off the brief's own wording. Nothing here is inferred from the ministry's name.

They state

The evaluators will check if the system can successfully generate a georeferenced, metrically accurate 3D model using only a single drone pass video while handling challenges like motion blur, dynamic objects, and limited viewing angles.

They never say

exact metric accuracy tolerance thresholds
maximum processing time limit for near real-time
specific output file format requirements

A jury can still ask about these. Decide them deliberately rather than by accident.

What they'll ask you

Generated from the brief's own wording and the competition's published rules — never from a guess about what this ministry prefers.

Exact metric accuracy tolerance thresholds?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Maximum processing time limit for near real-time?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.
Specific output file format requirements?
The brief never answers this, so a panel will. Whatever you decide, say it the same way twice.

9 more— the ones a panel gets to if there is time

Has any part of this been shown at a previous event, hackathon or college project?
The guidelines are explicit: your solution must not have appeared in any previous event or programme, of any sort. A recycled project is what a team under time pressure reaches for.

Before you commit

Each one is quoted from a gap in the brief, not a guess about your team.

No measurable target
The description asks for metrically accurate 3D models but never defines a specific numerical error margin or tolerance threshold for success.

The data

What the organisers attached, and what the brief assumes you can get.

Dataset from the organisers: Provided — open it
Does the brief need data?: Yes, and they gave it to you.

Also from National Technical Research Organisation (NTRO)

Same organisation, same year. Reading two of theirs tells you more about what they care about than reading one.

Take this to an AI

Pick what you are about to do and copy the prompt. It carries the organisers' own wording, the constraints they never spell out, and an instruction not to invent requirements they never set.

Who has this problem, what already exists, and what you would have to find out.

# Context: India's Smart India Hackathon 2026

I am on a student team entering SIH 2026. Problem statement SIH26158, set by National Technical Research Organisation (NTRO).
Its official title, word for word: "Single-Pass Drone Video to Accurate 3D Model Generation System"
Theme: Robotics and Drones. Category: software.

In plain terms: Build an AI-enabled system that takes a single drone video with GPS and metadata to generate a georeferenced, metrically accurate textured 3D model.

## The organisers' full description, verbatim

• Background: Generation of accurate 3D models of buildings, infrastructure, terrain, and objects typically requires multiple drone passes, extensive image overlap, specialized flight planning, and significant post-processing time. In operational scenarios such as disaster response, surveillance, infrastructure inspection, military reconnaissance, and rapid mapping, there is often only a single opportunity to capture data over the target area. A solution capable of generating an accurate and textured 3D model from a single drone pass video would significantly reduce mission time, operator effort, data acquisition requirements, and processing complexity while enabling near real-time situational awareness. • Description: Design and develop an AI-enabled system capable of generating a georeferenced and metrically accurate 3D model of a scene using only a single-pass drone video stream captured from a moving UAV. The system should process video frames captured during one flight path and reconstruct: (i) 3D terrain and structures (ii) Building facades and rooftops (iii) Roads and infrastructure (iv) Vegetation and obstacles (v) Textured 3D meshes or point clouds • Expected Solution/Deliverables: The generated model should be suitable for visualization, measurement, and analysis purposes. • Key Challenges (i) Limited viewing angles due to single flight path. (ii) Motion blur and video compression artifacts. (iii) Variable illumination and shadows. (iv) Dynamic objects (vehicles,humans, animals). (v) GPS inaccuracies and sensor noise. (vi) Real-time or near-real-time processing requirements. (vii) Reconstruction of occluded surfaces. (viii) Maintaining metric accuracy without extensive Ground Control Points (GCPs). • Input Data : • Mandatory (i) Drone video (1080p/4K) (ii) GPS coordinates (iii) Flight metadata • Optional (i) IMU data (ii) Barometric altitude (iii) Camera intrinsic parameters (iv) RTK/PPK corrections Add 'Desired Output' and 'Evaluation Criteria' table here • Potential Applications : (i) Border and strategic area mapping (ii) Disaster damage assessment (iii) Urban planning and smart cities (iv) Infrastructure inspection (v) Construction progress monitoring (vi) Archaeological documentation (vii) Digital twin generation (viii) Military reconnaissance and mission planning

## What the brief never says

- exact metric accuracy tolerance thresholds
- maximum processing time limit for near real-time
- specific output file format requirements
## Constraints that are not negotiable

- The judged build is a prototype demonstrated in roughly 36 hours by students, not a product.
- A jury evaluates it against this problem statement's own wording, not against general merit.
- We submit on sih.gov.in; the problem statement number and title above must match exactly.
- Your solution must not have appeared in any previous event or programme, of any sort.
- The organisers attached a dataset, so build against theirs rather than inventing one.
- Known obstacles in the brief: No target.

## What I want from you

1. Who actually has this problem in India, and what they do about it today.
2. What already exists — government systems, open-source projects, published research — that we should not rebuild.
3. For each item under 'what the brief never says', what the realistic answer is likely to be and how I could verify it.
4. The two or three things about this domain that a student team would get wrong without local knowledge.
## How to answer

- Everything above between quotation marks is the organisers' own wording. Treat it as the requirement.
- Do NOT invent requirements the brief does not state. If something matters and is not stated, say so and ask me, rather than assuming.
- Where you are inferring rather than reading, mark it as your inference.
- Do not guess what this ministry wants from its name. Its wording above is the only evidence.

---
Problem statement facts assembled by Wynit from National Technical Research Organisation (NTRO)'s published brief for SIH 2026.
The plain-English summary, the list of parts and the evaluator read are our interpretation of that text; the quoted title and the full description are theirs.

The government's original description (314 words)

• Background: Generation of accurate 3D models of buildings, infrastructure, terrain, and objects typically requires multiple drone passes, extensive image overlap, specialized flight planning, and significant post-processing time. In operational scenarios such as disaster response, surveillance, infrastructure inspection, military reconnaissance, and rapid mapping, there is often only a single opportunity to capture data over the target area. A solution capable of generating an accurate and textured 3D model from a single drone pass video would significantly reduce mission time, operator effort, data acquisition requirements, and processing complexity while enabling near real-time situational awareness. • Description: Design and develop an AI-enabled system capable of generating a georeferenced and metrically accurate 3D model of a scene using only a single-pass drone video stream captured from a moving UAV. The system should process video frames captured during one flight path and reconstruct: (i) 3D terrain and structures (ii) Building facades and rooftops (iii) Roads and infrastructure (iv) Vegetation and obstacles (v) Textured 3D meshes or point clouds • Expected Solution/Deliverables: The generated model should be suitable for visualization, measurement, and analysis purposes. • Key Challenges (i) Limited viewing angles due to single flight path. (ii) Motion blur and video compression artifacts. (iii) Variable illumination and shadows. (iv) Dynamic objects (vehicles,humans, animals). (v) GPS inaccuracies and sensor noise. (vi) Real-time or near-real-time processing requirements. (vii) Reconstruction of occluded surfaces. (viii) Maintaining metric accuracy without extensive Ground Control Points (GCPs). • Input Data : • Mandatory (i) Drone video (1080p/4K) (ii) GPS coordinates (iii) Flight metadata • Optional (i) IMU data (ii) Barometric altitude (iii) Camera intrinsic parameters (iv) RTK/PPK corrections Add 'Desired Output' and 'Evaluation Criteria' table here • Potential Applications : (i) Border and strategic area mapping (ii) Disaster damage assessment (iii) Urban planning and smart cities (iv) Infrastructure inspection (v) Construction progress monitoring (vi) Archaeological documentation (vii) Digital twin generation (viii) Military reconnaissance and mission planning