Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26187Worth consideringacceptance 3/5

AI-Based Intelligent Video Analytics Platform for Border Surveillance using existing CCTV Infrastructure.

Ministry of Home Affairs · Smart Automation · Software

The no-extra-hardware value is real and border-relevant, but this is a saturated category with a long feature list — build the intrusion-detection and ANPR core well on real CCTV footage and be honest about the vague suspicious-activity part rather than claiming the whole list.

What it actually is

Border forces have lots of ordinary CCTV cameras but they only record and need constant human watching, while smart features like face recognition, plate reading and intrusion detection usually need expensive proprietary hardware. The ask is a software platform that turns existing standard CCTV into an intelligent surveillance network — running detection, tracking, ANPR, intrusion alerts and more purely in software.

What to build

A software-defined video-analytics platform that ingests live streams from standard IP CCTV cameras and runs, in software, human detection and tracking, vehicle detection and classification, face detection, automatic number-plate recognition, virtual-fence intrusion detection, suspicious-activity and night-time-movement detection, with real-time alert generation and event logging, so existing border CCTV becomes an intelligent network without dedicated FRS, ANPR or smart-camera hardware.

Smallest thing that wins the room

Point the platform at a standard CCTV stream and show it drawing a virtual fence, detecting and tracking a person crossing it at night, classifying a vehicle and reading its plate, and firing a real-time intrusion alert with the event logged.

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.

Moderate110–260 teams expectedroughly 1 in 94–217 wins it

Quieter than 61% of the 226 · #88 of 226 by expected field

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

Why: defence, intelligence and space bodies drew small fields.

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

  • YOLO detection + DeepSORT tracking on RTSP streams
  • ANPR (plate detection + OCR)
  • Face detection (RetinaFace)
  • Virtual-fence intrusion logic
  • Real-time alerting + event logging
  • Night-time / low-light enhancement
  • Video surveillance analytics
  • Border security
  • Computer vision

Prior art to read before you start

CCTV-to-smart-surveillance software · virtual-fence intrusion detection · multi-capability video analytics

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.