Database system for AI-powered apps

Python framework that facilitates the quick development of complex video analysis applications and other series-processing based applications in a multiprocessing environment.

Fall Detection using OpenPifPaf's Human Pose Estimation model

Video and Image Analytics for Multiple Environments

Demo on how to compute soccer ball possession automatically using AI.

Securade.ai HUB - A generative AI based edge platform for computer vision that connects to existing CCTV cameras and makes them smart.

Optical Flow Dataset and Benchmark for Visual Crowd Analysis

Create a Video Membership app using FastAPI & NoSQL

Face recognition software to detect criminals in images and videos, noting their time of occurences.

Official Mux API wrapper for python projects, supporting both Mux Data and Mux Video.

VQPy: An object-oriented approach to modern video analytics

Entropy and Memorability Based Video Summarization

Python Script that performs search queries on YouTube, collects metadata, and exports to a CSV file for data analysis.

Securade.ai Sentinel - A monitoring and surveillance application that enables visual Q&A and video captioning for existing CCTV cameras.

🚀 Geo-trax is a comprehensive pipeline for extracting and analyzing high-accuracy georeferenced vehicle trajectories from quasi-stationary, bird’s-eye view drone footage. Using advanced computer vision and deep learning, it enables detailed urban traffic analysis and supports scalable, precise studies of vehicle dynamics.

ROS package for multi-object tracking using Norfair.

The repository contains a reference end-to-end pipeline for a real-time video analytics application. Realtime data is provided to an inference endpoint that executes single shot object detection. The metadata created during inference is then uploaded to a database for curation.

Code for paper "TLEE: Temporal-wise and Layer-wise Early Exiting Network for Efficient Video Recognition on Edge Devices"

Efficient edge video analytics platform via active continuous learning.

Code for paper "Joint Adaptive Resolution Selection and Conditional Early Exiting for Efficient Video Recognition on Edge Devices"