Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow

FastER RCNN built on tensorflow

Pedestrian simulator powered by the social force model

Simple model to Track and Re-identify individuals in different cameras/videos.(Yolov3 & Yolov4)

Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories with GANs (CVPR 2019)

Real-time Traffic and Pedestrian Counting (YOLOV3 in tensorflow2)

pedestrian detection in hazy weather

Caltech Pedestrian Dataset Converter

Analysis of pedestrian dynamics based on trajectory files.

Driver assistant - GTU Undergraduate Project II - 2016

Code for: "Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs", ICCV2021 Workshops

A crowd simulation and visualization demo implemented in Unity using Dijkstra Distance Field and simplified version of the Optimal Steps Model.

pedestriandynamics.org

The Safer Streets Priority Finder enables you to analyze the risk to bicyclists and pedestrians on your community’s roads.

Leveraging Neural Network Gradients within Trajectory Optimization for Proactive Human-Robot Interactions

People Live Tracking using YOLOv2 in MATLAB

A vehicle-pedestrian interaction framework for simulation.

Automatic classification of pedestrian trajectories using clustering techniques.