人群计数最全代码、数据、论文合集

https://mp.weixin.qq.com/s?__biz=MzI5MDUyMDIxNA==&mid=2247487704&idx=1&sn=e0ea4c28c51cd153aaf388edaadb4d86&chksm=ec1ffd21db687437251a48a0047f991a0c5cae1700322591c69a0da2ee9f01f0bead2fd30bc2&mpshare=1&scene=1&srcid=&key=14af0718ac9cde956bb14c0e937a8d1c8fca66b7905339896c32e4c11e178761cb4ca8181fa3e3103c733648d619dd3d155bee86fe2c054442cb065d6a244eecb307d34e46ba7445c1d8cb569defa978&ascene=1&uin=MjIzODAyMTI0MA%3D%3D&devicetype=Windows+10&version=62060728&lang=zh_CN&pass_ticket=YRoP416NSvSChnrkrq9d7i1udjPebK7b3KEOt14hp8uSHLt6xVudHAMgD8VB2juM

人群计数最全代码、数据、论文合集（含最新CVPR2019论文）

 

人群计数最全代码、数据、论文合集

前言

之前极市曾分享了几个GitHub上的awesome系列项目，反响都很好（点击文末阅读原文即可获取以下资源）。

• 【资源】手势估计最全资源

• 【资源】多目标追踪资源列表

• 【资源】OCR 文本检测干货汇总

• 【资源】语义分割 paper 以及 code 汇总

• 【资源】视频研究常用方法、数据集和任务汇总

 

今日分享一个人群计数超全资源。近年来，由于拥挤人群引发的踩踏事故频发，人群计数在视频监控、公共安全方面的作用越发突出，以下是作者整理的人群计数资源，包含代码、工具、数据集、论文、leaderboard等。

 

作者：gjy3035

来源：https://github.com/gjy3035/Awesome-Crowd-Counting

 

 

注：本文涉及较多超链接，请点击文末阅读原文，以获得更好的阅读体验。

 

Contents

• Code

• Tools

• Datasets

• Papers

• Leaderboard

   

 

 

Code

Crowd Counting Code Framework (C^3 Framework)

[C^3 Framework] An open-source PyTorch code for crowd counting, which is under development.

 

Tools

• Density Map Generation from Key Points [Matlab Code] [Python Code] [Fast Python Code]

 

 

Datasets

• GCC Dataset [Link] (a large-scale, synthetic and diverse dataset)

• UCF-QNRF Dataset [Link]

• ShanghaiTech Dataset [Link: Dropbox / BaiduNetdisk]

• WorldExpo'10 Dataset [Link]

• UCF CC 50 Dataset [Link]

• Mall Dataset [Link]

• UCSD Dataset [Link]

• SmartCity Dataset [Link: GoogleDrive / BaiduNetdisk]

• AHU-Crowd Dataset [Link]

 

 

Papers

arXiv papers

This section only includes the last ten papers since 2018 in arXiv.org. Previous papers will be hidden using . If you want to view them, please open the raw file to read the source code. Note that all unpublished arXiv papers are not included into the leaderboard of performance.

 

• Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks [paper]

• Generalizing semi-supervised generative adversarial networks to regression using feature contrasting [paper]

• Improving Dense Crowd Counting Convolutional Neural Networks using Inverse k-Nearest Neighbor Maps and Multiscale Upsampling [paper]

• Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting [paper]

• Scale-Aware Attention Network for Crowd Counting [paper]

• Mask-aware networks for crowd counting [paper]

• ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding [paper]

• Context-Aware Crowd Counting [paper]

• PaDNet: Pan-Density Crowd Counting [paper]

 

Methods dealing with the lack of labelled data

• [CCWld] Learning from Synthetic Data for Crowd Counting in the Wild (CVPR2019) [paper] [Project] [arxiv]) 本文解读请关注极市今日推送二条

• [SL2R] Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank (T-PAMI) [paper](extension of L2R)

• [GWTA-CCNN] Almost Unsupervised Learning for Dense Crowd Counting (AAAI2019) [paper]

• [CAC] Class-Agnostic Counting (ACCV2018) [paper code]

• [L2R] Leveraging Unlabeled Data for Crowd Counting by Learning to Rank (CVPR2018) [paper] [code]

 

2019

• [CCWld] Learning from Synthetic Data for Crowd Counting in the Wild (CVPR2019) [paper] [Project] [arxiv])

• [SL2R] Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank (T-PAMI) [paper](extension of L2R)

• [ASD] Adaptive Scenario Discovery for Crowd Counting (ICASSP2019) [paper]

• Crowd Counting Using Scale-Aware Attention Networks (WACV2019) [paper]

• [GWTA-CCNN] Almost Unsupervised Learning for Dense Crowd Counting (AAAI2019) [paper]

 

2018

• [LCFCN] Where are the Blobs: Counting by Localization with Point Supervision (ECCV2018) [paper] [code]

• [CAC] Class-Agnostic Counting (ACCV2018) [paper code]

• [AFP] Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid (BMVC2018) [paper]

• [DRSAN] Crowd Counting using Deep Recurrent Spatial-Aware Network (IJCAI2018) [paper]

• [TDF-CNN] Top-Down Feedback for Crowd Counting Convolutional Neural Network (AAAI2018) [paper]

• [SANet] Scale Aggregation Network for Accurate and Efficient Crowd Counting (ECCV2018) [paper]

• [ic-CNN] Iterative Crowd Counting (ECCV2018) [paper]

• [CL] Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds (ECCV2018) [paper]

• [D-ConvNet] Crowd Counting with Deep Negative Correlation Learning (CVPR2018) [paper] [code]

• [IG-CNN] Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN (CVPR2018) [paper]

• [BSAD] Body Structure Aware Deep Crowd Counting (TIP2018) [paper]

• [CSR] CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (CVPR2018) [paper] [code]

• [L2R] Leveraging Unlabeled Data for Crowd Counting by Learning to Rank (CVPR2018) [paper] [code]

• [ACSCP] Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (CVPR2018) [paper]

• [DecideNet] DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density (CVPR2018) [paper]

• [AMDCN] An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Counting (CVPR2018) [paper] [code]

• [A-CCNN] A-CCNN: Adaptive CCNN for Density Estimation and Crowd Counting (ICIP2018) [paper]

• [DR-ResNet] A Deeply-Recursive Convolutional Network for Crowd Counting (ICASSP2018) [paper]

• [SaCNN] Crowd counting via scale-adaptive convolutional neural network (WACV2018) [paper] [code]

• [GAN-MTR] Crowd Counting With Minimal Data Using Generative Adversarial Networks For Multiple Target Regression (WACV2018) [paper]

• [NetVLAD] Multiscale Multitask Deep NetVLAD for Crowd Counting (TII2018) [paper] [code]

• [W-VLAD] Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps (CSVT2018) [paper]

 

2017

• [CP-CNN] Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs (ICCV2017) [paper]

• [ConvLSTM] Spatiotemporal Modeling for Crowd Counting in Videos (ICCV2017) [paper]

• [CMTL] CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting (AVSS2017) [paper] [code]

• [ResnetCrowd] ResnetCrowd: A Residual Deep Learning Architecture for Crowd Counting, Violent Behaviour Detection and Crowd Density Level Classification (AVSS2017) [paper]

• [Switching CNN] Switching Convolutional Neural Network for Crowd Counting (CVPR2017) [paper] [code]

• A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (PR Letters) [paper]

• [MSCNN] Multi-scale Convolution Neural Networks for Crowd Counting (ICIP2017) [paper] [code]

• [FCNCC] Fully Convolutional Crowd Counting On Highly Congested Scenes (VISAPP2017) [paper]

 

2016

• [Hydra-CNN] Towards perspective-free object counting with deep learning (ECCV2016) [paper] [code]

• [CNN-Boosting] Learning to Count with CNN Boosting (ECCV2016) [paper]

• [Crossing-line] Crossing-line Crowd Counting with Two-phase Deep Neural Networks (ECCV2016) [paper]

• [CrowdNet] CrowdNet: A Deep Convolutional Network for Dense Crowd Counting (ACMMM2016) [paper] [code]

• [MCNN] Single-Image Crowd Counting via Multi-Column Convolutional Neural Network (CVPR2016) [paper] [unofficial code: TensorFlow PyTorch]

• [Shang 2016] End-to-end crowd counting via joint learning local and global count (ICIP2016) [paper]

• [RPF] Crowd Density Estimation based on Rich Features and Random Projection Forest (WACV2016) [paper]

• [CS-SLR] Cost-sensitive sparse linear regression for crowd counting with imbalanced training data (ICME2016) [paper]

• [Faster-OHEM-KCF] Deep People Counting with Faster R-CNN and Correlation Tracking (ICME2016) [paper]

 

2015

• [COUNT Forest] COUNT Forest: CO-voting Uncertain Number of Targets using Random Forest for Crowd Density Estimation (ICCV2015) [paper]

• [Bayesian] Bayesian Model Adaptation for Crowd Counts (ICCV2015) [paper]

• [Zhang 2015] Cross-scene Crowd Counting via Deep Convolutional Neural Networks (CVPR2015) [paper] [code]

• [Wang 2015] Deep People Counting in Extremely Dense Crowds (ACMMM2015) [paper]

• [Fu 2015] Fast crowd density estimation with convolutional neural networks (AI2015) [paper]

 

2013

• [Idrees 2013] Multi-Source Multi-Scale Counting in Extremely Dense Crowd Images (CVPR2013) [paper]

• [Ma 2013] Crossing the Line: Crowd Counting by Integer Programming with Local Features (CVPR2013) [paper]

 

2012

• [Chen 2013] Feature mining for localised crowd counting (BMVC2012) [paper]

 

2010

• [Lempitsky 2010] Learning To Count Objects in Images (NIPS2010) [paper]

 

2008

• [Chan 2008] Privacy preserving crowd monitoring: Counting people without people models or tracking (CVPR 2008) [paper]

 

 

Leaderboard

阅读原文查看完整Leaderboard