DecodeX
Home/Problem Statements/SIH26187
All 226 Statements
SIH26187SoftwareBlockchain & Cybersecurity
₹1,50,000 Prize (₹75k Joint)
•
Deadline: 20 September 2026
•
Submitted Ideas: 0/500

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

Ministry / Organization: Ministry of Home Affairs
Department: Sashastra Seema Bal (SSB), Police II Division
SIH Official Portal
Technical Complexity
8/10
Dataset Accessibility
8/10
36h Hackathon Viability
9/10
Step 0 • Zero-Jargon Layman Summary

“Border security forces currently use standard CCTV cameras that need humans to constantly watch screens to spot intruders. This project builds a smart software platform that connects to these existing cameras and uses artificial intelligence to automatically detect people, vehicles, faces, license plates, and boundary breaches in real-time.”

The DecodeX PS Decoder™

Deconstructed Problem Blueprint

Step 1

WHAT TO BUILD?

An AI-powered software-defined video analytics platform that ingests standard RTSP/IP CCTV camera feeds and performs real-time computer vision tasks without requiring expensive specialized smart cameras.

Step 2

WHO IS IT FOR?

Problem owners: Sashastra Seema Bal (SSB), Ministry of Home Affairs, and border security forces. Users: Control room operators, field commanders, and patrolling guards.

Step 3

WHY DOES IT EXIST?

Upgrading thousands of remote border CCTV cameras to smart hardware is financially impossible. Relying on human monitors leads to fatigue, missed intrusions, and delayed responses.

Step 4

INPUT → PROCESS → OUTPUT ARCHITECTURE PIPELINE

01 • Inputs & Telemetry

Live RTSP/HTTP video streams from standard IP CCTV cameras, pre-recorded security footage, PTZ camera controls, and manual configuration zones (virtual fences).

02 • Processing & AI Core

Frame extraction, lightweight object detection (YOLO), face embedding generation, Optical Character Recognition for number plates (ANPR), and spatial-temporal tracking across frames with edge-optimized inference.

03 • Actionable Deliverables

Real-time visual and audio alerts on a centralized web dashboard, SMS/Push notifications for high-priority intrusions, annotated video clips of incidents, and forensic event logs.

Step 5

CONSTRAINTS

  • Must operate efficiently on standard commodity hardware or edge devices with limited GPU capacity.
  • Bandwidth constraints in remote border outposts requiring edge-computing capabilities.
  • High accuracy needed in low-light, night-time, fog, or adverse weather conditions.
  • Integration compatibility with existing Command and Control systems.
Step 6

JURY METRICS

  • Inference latency (FPS per camera stream)
  • False Alarm Rate (FAR) under environmental changes (shadows, swaying trees, animals)
  • Object detection and ANPR recognition accuracy (mAP and character error rate)
  • Dashboard UI responsiveness and alert delivery time
Step 7

CORE BOTTLENECK

Balancing high-accuracy AI model inference (like heavy face recognition or vehicle tracking models) with low-latency processing across multiple concurrent live video streams on limited hardware.

Why You Should Choose This PS (Pros)

  • Extremely high national security and social impact.
  • Clear, modular feature set allowing rapid incremental development during a 36-hour hackathon.
  • Direct cost-saving value proposition by leveraging legacy hardware.

Challenges & Risks to Watch (Cons)

  • Heavy reliance on video processing pipelines can easily break if hardware acceleration (CUDA/OpenVINO) isn't configured right.
  • Crowded domain if teams only submit a basic YOLO wrapper without specialized border security logic.
Hackathon Blueprint

Recommended Tech Stack & Grand Finale Features

Frontend & Mobile
React.jsTailwind CSSLucide Icons
Backend & APIs
FastAPI (Python)OpenCVWebSockets for real-time alerts
AI / ML & Models
YOLOv11 for human and vehicle detectionDeepSORT for object trackingEasyOCR / PaddleOCR for ANPR
Database & Cloud
SQLite / PostgreSQLRedis for real-time alert cachingLocal file system / MinIO for incident clips

Killer Features to Impress the SIH Jury

Bandwidth-adaptive streaming that reduces frame rate dynamically when network connectivity drops.
Custom polygon 'Virtual Fence' builder directly on the UI dashboard for easy zone intrusion setup.
Multi-camera stitching or map-based tracking view showing the path of an intruder across cameras.
Offline-first queuing system that stores alerts locally and syncs when connectivity is restored.
View Official SIH 2026 Portal Raw Text
▼
•Background Border security forces deploy CCTV cameras at Border Out Posts(BOPs), check posts, border roads, and other strategic locations for surveillance and monitoring. However, conventional CCTV systems primarily provide video recording and live monitoring capabilities,requiring continuous human observation. Advanced surveillance functionalities such as Facial Recognition Systems (FRS), Automatic Number Plate Recognition (ANPR), intrusion detection, and object tracking often require specialized hardware and proprietary solutions,making large-scale deployment costly and difficult, particularly in remote border areas.
•Description The proposed solution aims to develop an AI-driven software platform capable of transforming existing CCTV infrastructure into an intelligent surveillance network without requiring dedicated FRS, ANPR, or smart-camera hardware. The platform shall ingest live video streams from standard IP-based CCTV cameras and perform real-time video analytics using Artificial Intelligence and Computer Vision techniques.

The solution should provide capabilities such as:

•Human detection and tracking
•Vehicle detection and classification
•Face detection
•Automatic Number Plate Recognition (ANPR)
•Virtual fence intrusion detection
•Suspicious activity detection
•Night-time movement detection
•Real-time alert generation and event logging
•Expected Solution The proposed system should leverage Artificial Intelligence, Machine Learning, Computer Vision, and Video Analytics to create a software-defined surveillance platform capable of extracting actionable intelligence from existing CCTV infrastructure.

The solution should:

•Eliminate dependence on expensive dedicated surveillance hardware.
•Enable intelligent monitoring through AI-powered video analytics.
•Provide real-time alerts for security incidents and border intrusions.
•Support facial recognition, vehicle identification, and behavioral analytics through software.
•Improve situational awareness and response time for border security forces.
•Support integration with existing command and control systems.
•The final solution should be cost-effective, scalable, and suitable for deployment across remote border locations and strategic installations.
•Possible Project Name IBVAP – Intelligent Border Video Analytics Platform