The smart city reference pipeline shows how to integrate various media building blocks, with analytics powered by the OpenVINO™ Toolkit, for traffic or stadium sensing, analytics and management tasks.

the large-scale data set for people counting (LOI counting)

A Python 3 and Keras 2 implementation of MSCNN for people counting.

This repository presents a method for people counting using a CNN trained with IR-UWB radar samples, in the COVID-19 and GDPR context. The purpose is the monitoring of the number of people inside a room, sending e-mail notifications every 10 minutes with the status of the room.

A real-time bidirectional people counting and foot-traffic analytics system powered by YOLOv11 and OpenCV. Features multi-object tracking (MOT), dual-polygon region-of-interest (ROI) logic for entry/exit detection, and automated video reporting. Perfect for retail analytics and smart occupancy monitoring.

Application on Door counter using the mmWave FMCW IWR1642

people counting

Liblab, kütüphane doluluk oranı hakkında çalışmalar yapan IoT tabanlı bir görüntü işleme projesidir.

Multi-sensor RealSense + YOLO Top-View People Counting System, developed within the MEI (Museo Egizio Immersive) project. The solution enables real-time detection and counting of people in defined spatial areas, driving immersive scene logic, lighting systems, and audience analytics for interactive museum installations in Unreal Engine 5.

The OpenCV project is dedicated to tracking and counting people present in both images and videos. With two distinct folders, this project performs people tracking and counting and also includes the ability to predict the distance from the camera and determine their direction.

Tensorflow implementation of a lightweight people counting CNN

Crowd Counting: A view around state-of-the-art

A simple Python web application with API to count people.

This repository contains a crowd counting model using the CSRNet architecture to estimate the number of people in crowded scenes. The model is trained on the Shanghaitech dataset and aims to provide accurate crowd density maps and count predictions. Data augmentation techniques are employed to enhance the model's performance.

Real-time people counting and crowd monitoring using YOLO11 | AI-powered bidirectional tracking | Perfect for schools, retail, exhibitions | Raspberry Pi ready

Real-time head detection and tracking using YOLOv5 + DeepSORT/IoU.

Real-time people counting & tracking system for pharmacies using YOLOv5/YOLOv8 + DeepSORT with heatmaps and GDPR-compliant privacy