Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020

The easiest way to count pedestrians, cyclists, and vehicles on edge computing devices or live video feeds.

PyTorch code for ICPR 2020 paper "DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting"

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.

Python tools for working with PedX dataset.

The Arrogance of Space Mapping Tool

Yet Another attempt to build a traffic system in Unity.

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

A geospatial dataset focusing on walkability and pedestrian access

A Lightweight Residual Graph CNN for Pedestrians Trajectory Prediction

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

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

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

AI car & pedestrian tracking in python utilizing computer vision

Haar cascade for detecting vehicles and pedestrians in videos using Python

Матричное моделирование пассажиропотоков для оптимизации планировки здания.

deployableFiles from the simulation

Social Distancing Alert System

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.