mlsanityData to 14 Oct 2026

Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark

arXiv 2105.02440 ↗First posted 6 May 2021cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33,600 HD frames in various scenarios. Notably, we annotate 20,800 people trajectories with 4.8 million heads and several video-level attributes. Meanwhile, we design the Space-Time Neighbor-Aware Network (STNNet) as a strong baseline to solve object detection, tracking and counting jointly in dense crowds. STNNet is formed by the feature extraction module, followed by the density map estimation heads, and localization and association subnets. To exploit the context information of neighboring objects, we design the neighboring context loss to guide the association subnet training, which enforces consistent relative position of nearby objects in temporal domain. Extensive experiments on our DroneCrowd dataset demonstrate that STNNet performs favorably against the state-of-the-arts.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

26 of 45 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  6. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  7. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  8. 2018CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenescited by 267
  9. 2018Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowdscited by 186
  10. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 156
  11. 2020NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localizationcited by 151
  12. 2018Context-Aware Crowd Countingcited by 150
14 more
  1. 2020Distribution Matching for Crowd Countingcited by 143
  2. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  3. 2017Switching Convolutional Neural Network for Crowd Countingcited by 93
  4. 2018Where are the Blobs: Counting by Localization with Point Supervisioncited by 54
  5. 2017CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Countingcited by 41
  6. 2019Locality-constrained Spatial Transformer Network for Video Crowd Countingcited by 30
  7. 2017Spatiotemporal Modeling for Crowd Counting in Videoscited by 27
  8. 2017FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Camerascited by 27
  9. 2017Multi-scale Convolutional Neural Networks for Crowd Countingcited by 26
  10. 2017Crowd counting via scale-adaptive convolutional neural networkcited by 23
  11. 2020Hybrid Graph Neural Networks for Crowd Countingcited by 21
  12. 2019Estimating People Flows to Better Count Them in Crowded Scenescited by 12
  13. 2018An Aggregated Multicolumn Dilated Convolution Network for Perspective-Free Countingcited by 5
  14. 2018Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariancecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 5; 2024: 4; 2025: 6; 2026: 9.

31 papers.

Sort:

By area:

  1. 2022An End-to-End Transformer Model for Crowd Localizationcited by 74
  2. 2023CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Modelcited by 47
  3. 2025UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spacescited by 36
  4. 2022The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Countingcited by 24
  5. 2022The State of Aerial Surveillance: A Surveycited by 20
  6. 2023Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?cited by 18
  7. 2024RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learningcited by 15
  8. 2024NWPU-MOC: A Benchmark for Fine-grained Multi-category Object Counting in Aerial Imagescited by 14
  9. 2025Open-World Object Counting in Videoscited by 11
  10. 2022Backdoor Attacks on Crowd Countingcited by 10
  11. 2023RGB-D Indiscernible Object Counting in Underwater Scenescited by 9
  12. 2023Oriented object detection in optical remote sensing images using deep learning: a surveycited by 8
19 more
  1. 2024FGENet: Fine-Grained Extraction Network for Congested Crowd Countingcited by 7
  2. 2024Open-World Drone Active Tracking with Goal-Centered Rewardscited by 6
  3. 2025Single Domain Generalization for Few-Shot Counting via Universal Representation Matchingcited by 6
  4. 2025Video Individual Counting for Moving Dronescited by 4
  5. 2026Instance-level Visual Active Tracking with Occlusion-Aware Planningcited by 3
  6. 2022RefCrowd: Grounding the Target in Crowd with Referring Expressionscited by 2
  7. 2025RIS-LAD: A Benchmark and Model for Referring Low-Altitude Drone Image Segmentationcited by 1
  8. 2026Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methodscited by 1
  9. 2026SENTRY: SAM2-Enhanced Neighbor-Aware and Temporally Reasoned Memory for Visual Trackingcited by 1
  10. 2022Self-Aligning Depth-regularized Radiance Fields for Asynchronous RGB-D Sequencescited by 0
  11. 2022Cattle Detection Occlusion Problemcited by 0
  12. 2023Density-based clustering with fully-convolutional networks for crowd flow detection from dronescited by 0
  13. 2025Improving trajectory continuity in drone-based crowd monitoring using a set of minimal-cost techniques and deep discriminative correlation filterscited by 0
  14. 2026One-Shot Crowd Counting With Density Guidance For Scene Adaptationcited by 0
  15. 2026A High-Level Survey of Optical Remote Sensingcited by 0
  16. 2026Count Anythingcited by 0
  17. 2026UAV-OVVIS: Unmanned Aerial Vehicles Also Need Open-Vocabulary Video Instance Segmentationcited by 0
  18. 2026Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challengescited by 0
  19. 2026The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understandingcited by 0