NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization
arXiv:2001.03360 · doi:10.1109/TPAMI.2020.3013269
Abstract
In the last decade, crowd counting and localization attract much attention of researchers due to its wide-spread applications, including crowd monitoring, public safety, space design, etc. Many Convolutional Neural Networks (CNN) are designed for tackling this task. However, currently released datasets are so small-scale that they can not meet the needs of the supervised CNN-based algorithms. To remedy this problem, we construct a large-scale congested crowd counting and localization dataset, NWPU-Crowd, consisting of 5,109 images, in a total of 2,133,375 annotated heads with points and boxes. Compared with other real-world datasets, it contains various illumination scenes and has the largest density range (0~20,033). Besides, a benchmark website is developed for impartially evaluating the different methods, which allows researchers to submit the results of the test set. Based on the proposed dataset, we further describe the data characteristics, evaluate the performance of some mainstream state-of-the-art (SOTA) methods, and analyze the new problems that arise on the new data. What's more, the benchmark is deployed at \url{https://www.crowdbenchmark.com/}, and the dataset/code/models/results are available at \url{https://gjy3035.github.io/NWPU-Crowd-Sample-Code/}.
Accepted by T-PAMI
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- SCAR: Spatial-/Channel-wise Attention Regression Networks for Crowd Counting
- Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
- Switching Convolutional Neural Network for Crowd Counting
- C^3 Framework: An Open-source PyTorch Code for Crowd Counting
- Drone-based Joint Density Map Estimation, Localization and Tracking with Space-Time Multi-Scale Attention Network
- MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery
- A Deeply-Recursive Convolutional Network for Crowd Counting
Cited by in corpus (44)
- Towards Large-Scale Small Object Detection: Survey and Benchmarks
- TransCrowd: weakly-supervised crowd counting with transformers
- Distribution Matching for Crowd Counting
- Focal Inverse Distance Transform Maps for Crowd Localization
- CNN-based Density Estimation and Crowd Counting: A Survey
- A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds
- Redesigning Multi-Scale Neural Network for Crowd Counting
- Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
- CCTrans: Simplifying and Improving Crowd Counting with Transformer
- NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Images
- Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
- Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation
- Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting
- TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image
- Fine-Grained Crowd Counting
- DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting
- Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark
- Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
- Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher
- A Unified Multi-Task Learning Framework of Real-Time Drone Supervision for Crowd Counting
- Learning Discriminative Features for Crowd Counting
- SSR-HEF: Crowd Counting with Multi-Scale Semantic Refining and Hard Example Focusing
- An Improved Normed-Deformable Convolution for Crowd Counting
- Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting
- Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting
- Rethinking Global Context in Crowd Counting
- CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise Classification
- Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
- AdaTreeFormer: Few Shot Domain Adaptation for Tree Counting from a Single High-Resolution Image
- The Effectiveness of a Simplified Model Structure for Crowd Counting
- RGB-D Railway Platform Monitoring and Scene Understanding for Enhanced Passenger Safety
- LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds
- Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction
- AutoScale: Learning to Scale for Crowd Counting and Localization
- HDNet: A Hierarchically Decoupled Network for Crowd Counting
- Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods
- RPEE-HEADS: A Novel Benchmark for Pedestrian Head Detection in Crowd Videos
- AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
- Counting People by Estimating People Flows
- Multi-channel Deep Supervision for Crowd Counting
- Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting
- Harnessing Perceptual Adversarial Patches for Crowd Counting
- RepSFNet : A Single Fusion Network with Structural Reparameterization for Crowd Counting
- Region-Aware Network: Model Human's Top-Down Visual Perception Mechanism for Crowd Counting