Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26011Strong pickacceptance 4/5

3D ULPIN Generation and vertical Property Mapping SYstem

Ministry of Rural Development · Space Technology · Software

One of the few land-records statements not already answered by a deployed government system, and the standards work exists to ground it — just settle your 3D ULPIN encoding scheme in week one, because that decision is the actual deliverable.

What it actually is

India's land records identify flat pieces of ground, which breaks down in cities where the same footprint holds twenty apartments, a basement car park and a metro tunnel underneath. The ask is a system that gives every one of those volumes its own unique identity code and maps who owns what at which height. It should build those volumes automatically from drone and LiDAR data rather than by hand.

What to build

A 3D cadastre pipeline that ingests LiDAR point clouds and drone-derived DSM/DEM with GIS parcel polygons, automatically extracts building envelopes from the point cloud, segments each envelope into floors by detecting horizontal planar breaks, delineates each floor into volumetric sub-parcels using imported floor plans, generates a structured 3D ULPIN string per volume that encodes its parent surface parcel plus its vertical position including negative levels for basements and subsurface utilities, runs topology validation for overlapping or floating volumes, and presents the result in a 3D web viewer where clicking any floor or basement volume returns its identifier and ownership attributes.

Smallest thing that wins the room

Load a point cloud of a real multi-storey building, watch it split into floors automatically, then click the fourth floor in the 3D viewer and show a generated 3D ULPIN that traces cleanly back to the surface parcel ID.

How crowded this one gets

A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.

Moderate95–220 teams expectedroughly 1 in 80–186 wins it

Quieter than 68% of the 226 · #74 of 226 by expected field

A normal-sized field. Your idea has to be good, not miraculous.

Why: central ministry statements sat below the average.

This is a guess, not a fact

Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.

The scores

The number is the shorthand. The line under it is the reason.

What you will be writing

  • PDAL / Open3D point cloud segmentation
  • PointNet++ or RANSAC plane fitting for floor detection
  • CityGML / LADM 3D cadastre data model
  • PostGIS 3D geometry with SFCGAL
  • CesiumJS or deck.gl 3D web viewer
  • Open3D building envelope extraction
  • Land administration
  • 3D geospatial modelling
  • Urban property governance

Prior art to read before you start

3D cadastre and volumetric parcels · LiDAR building extraction · vertical property rights mapping

Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.