Portfolio

13 Aug 25

Real-Time Crowd Counting Using Computer Vision

Project at a Glance Domain: Computer Vision, Public Safety, Smart Cities, Event Ops What we built: A privacy-first, real-time crowd counting system that turns live CCTV/IP camera feeds into accurate counts and density heatmaps to help operators spot congestion early and act fast. Runs on: Edge devices (Jetson-class) or cloud…

13 Aug 25

License Plate Recognition using Image Processing

Project at a Glance Client/Team: Thesis Nest Domain: Intelligent Transportation, Smart Parking, Security Automation What we built: A fast, privacy-aware License Plate Recognition (LPR/ANPR) system that ingests live RTSP/ONVIF camera streams, detects vehicles, localizes plates, and extracts plate text in real time—complete with whitelists/blacklists, alerts, and searchable logs. Runs on:…

13 Aug 25

Traffic Sign Recognition using Deep Learning and Image Processing

Thesis Nest built a real-time TSR system that detects, classifies, and tracks road signs from dashcams/CCTV to power driver-assist alerts and infrastructure analytics. Optimized for small, distant signs, it handles night, rain, glare, and regional icon sets. Highlights: Multi-stage DL pipeline (detector → classifier/OCR → tracker) Edge-first deployment (Jetson/IPC) or…

13 Aug 25

Leaf disease detection using CNN-Deep learning

Thesis Nest built a real-time plant leaf disease detector that uses CNN-based deep learning to identify common diseases from field or greenhouse images and flag issues early—before yield drops. Highlights: Robust CNN pipeline with multi-class diagnosis (e.g., blight, rust, mildew) Works from phone, drone, or CCTV; offline edge inference available…

13 Aug 25

Human Action Recognition Using Image Processing

Thesis Nest built a real-time action recognition system that analyzes video streams to detect activities like walking, running, fighting, falling, loitering, and unsafe behaviors—powering safety alerts and analytics for campuses, factories, hospitals, and smart cities. Highlights: Spatiotemporal deep models (RGB + optional pose) for robust recognition Works with RTSP/ONVIF cameras;…

Real-Time Crowd Counting Using Computer Vision

License Plate Recognition using Image Processing

Traffic Sign Recognition using Deep Learning and Image Processing

Leaf disease detection using CNN-Deep learning

Human Action Recognition Using Image Processing

Links

Archives

Categories

RytSi - AI Assistant