Using transfer learning on pretrained image models to learn density map generation and count the number of people in an image.

This repository performs crowd counting inference using a pre-trained ONNX model. Input an image to estimate head localization in crowded scenes.

This is the implementation of paper "A Multi-Scale and Multi-level Feature Aggregation Network for Crowd Counting"

A simple label tool for crowd counting.

unofficial keras port of LSC-CNN

Pytorch implementation of SGANet for crowd counting

[ICCV 2023] Point-Query Quadtree for Crowd Counting, Localization, and More

Multi-level Attention Refined UNet for crowd counting

Crowd counting on the ShanghaiTech dataset, using multi-column convolutional neural networks.

The code for our ECCV 2020 paper: Estimating People Flows to Better Count Them in Crowded Scenes

Single Image Crowd Counting (CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting)

Single Image Crowd Counting via MCNN (Unofficial Implementation)