This repository contains a real-time pedestrian detection and tracking system implemented using deep learning techniques, specifically leveraging the YOLO (You Only Look Once) V8 architecture. The system is designed to detect and track pedestrians in low-light conditions, making it suitable for applications such as night-time driving scenarios.

deployableFiles from the simulation

This repository provides the implementation of our paper "Exploring the Potential of Synthetic Data for Pedestrian Analysis" delivered for the "Computer Vision and Cognitive System" course @Unimore

Smart IoT system for managing people congestion in delimited spaces.

Pre-print version of "Assessment of Reward Functions in Reinforcement Learning for Multi-Modal Urban Traffic Control under Real-World limitations"

An AI based system that do detects the cars and the pedestrians from a captured video.

Results from 2014 Newport pedestrian safety survey conducted by the Bicycle and Pedestrian Advisory Commission

Haar cascade for detecting vehicles and pedestrians in videos using Python

Матричное моделирование пассажиропотоков для оптимизации планировки здания.

Social Distancing Alert System

safety-data - react client

Analysis of when and where New York City (NYC) vehicle collisions occur with a focus on collisions involving pedestrians and cyclists.

A Lightweight Residual Graph CNN for Pedestrians Trajectory Prediction

A geospatial dataset focusing on walkability and pedestrian access

AI car & pedestrian tracking in python utilizing computer vision

The Arrogance of Space Mapping Tool

This project uses Histogram of Oriented Gradients for pedestrian detection and Kalman Filter for tracking and prediction

Yet Another attempt to build a traffic system in Unity.

MonoLoco++ and MonStereo for 3D localization, orientation, bounding box dimensions and social distancing from monocular and / or stereo images. PyTorch Official Implementation.

Hungarian algorithm + Kalman filter multitarget (multi-object) tracker implementation.