Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance (2405.10589v1)

Published 17 May 2024 in cs.CV, cs.AI, and eess.IV

Abstract: Crowd counting and localization have become increasingly important in computer vision due to their wide-ranging applications. While point-based strategies have been widely used in crowd counting methods, they face a significant challenge, i.e., the lack of an effective learning strategy to guide the matching process. This deficiency leads to instability in matching point proposals to target points, adversely affecting overall performance. To address this issue, we introduce an effective approach to stabilize the proposal-target matching in point-based methods. We propose Auxiliary Point Guidance (APG) to provide clear and effective guidance for proposal selection and optimization, addressing the core issue of matching uncertainty. Additionally, we develop Implicit Feature Interpolation (IFI) to enable adaptive feature extraction in diverse crowd scenarios, further enhancing the model's robustness and accuracy. Extensive experiments demonstrate the effectiveness of our approach, showing significant improvements in crowd counting and localization performance, particularly under challenging conditions. The source codes and trained models will be made publicly available.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Localization in the crowd with topological constraints. In AAAI, 2021.
  2. Adaptive dilated network with self-correction supervision for counting. In CVPR, 2020.
  3. Frequency bias in neural networks for input of non-uniform density. In ICML, 2020.
  4. All snow removed: Single image desnowing algorithm using hierarchical dual-tree complex wavelet representation and contradict channel loss. In ICCV, 2021.
  5. Learning continuous image representation with local implicit image function. In CVPR, 2021.
  6. Rethinking spatial invariance of convolutional networks for object counting. In CVPR, 2022.
  7. Redesigning multi-scale neural network for crowd counting. TIP, 2023.
  8. Rethinking atrous convolution for semantic image segmentation. In CVPR, 2017.
  9. Domain-adaptive crowd counting via inter-domain features segregation and gaussian-prior reconstruction. arXiv preprint arXiv:1912.03677, 2019.
  10. Learning independent instance maps for crowd localization. arXiv preprint arXiv:2012.04164, 2020.
  11. Finding tiny faces. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 951–959, 2017.
  12. Nas-count: Counting-by-density with neural architecture search. In ECCV, 2020.
  13. Counting crowds in bad weather. arXiv preprint arXiv:2306.01209, 2023.
  14. Multi-source multi-scale counting in extremely dense crowd images. In CVPR, 2013.
  15. Composition loss for counting, density map estimation and localization in dense crowds. In ECCV, 2018.
  16. Attention scaling for crowd counting. In CVPR, 2020.
  17. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  18. Harold W Kuhn. The hungarian method for the assignment problem. NRL, 1955.
  19. Where are the blobs: Counting by localization with point supervision. In ECCV, 2018.
  20. Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. In CVPR, 2018.
  21. Density map regression guided detection network for rgb-d crowd counting and localization. In CVPR, 2019.
  22. An end-to-end transformer model for crowd localization. In ECCV, 2022.
  23. Focal inverse distance transform maps for crowd localization. TMM, 2022.
  24. Boosting crowd counting via multifaceted attention. In CVPR, 2022.
  25. Point-query quadtree for crowd counting, localization, and more. In ICCV, pages 1676–1685, 2023.
  26. Recurrent attentive zooming for joint crowd counting and precise localization. In CVPR, 2019.
  27. Counting objects by blockwise classification. TCSVT, 2019.
  28. Weighing counts: Sequential crowd counting by reinforcement learning. In ECCV, 2020.
  29. Leveraging self-supervision for cross-domain crowd counting. In CVPR, 2022.
  30. Adaptive mixture regression network with local counting map for crowd counting. In ECCV, 2020.
  31. Point in, box out: Beyond counting persons in crowds. In CVPR, 2019.
  32. Towards a universal model for cross-dataset crowd counting. In ICCV, 2021.
  33. Bayesian loss for crowd count estimation with point supervision. In ICCV, 2019.
  34. Learning to count via unbalanced optimal transport. In AAAI, 2021.
  35. Shallow feature based dense attention network for crowd counting. In AAAI, 2020.
  36. Nerf: Representing scenes as neural radiance fields for view synthesis. ACM, 2021.
  37. Deepsdf: Learning continuous signed distance functions for shape representation. In CVPR, 2019.
  38. On the spectral bias of neural networks. In ICML, pages 5301–5310. PMLR, 2019.
  39. Faster r-cnn: Towards real-time object detection with region proposal networks. NeurIPS, 2015.
  40. Locating objects without bounding boxes. In CVPR, 2019.
  41. Locate, size, and count: accurately resolving people in dense crowds via detection. TPAMI, 2020.
  42. Crowd counting in the frequency domain. In CVPR, 2022.
  43. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  44. Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method. TPAMI, 2020.
  45. Rethinking counting and localization in crowds: A purely point-based framework. In ICCV, 2021.
  46. Fourier features let networks learn high frequency functions in low dimensional domains. NeurIPS, 2020.
  47. Modeling noisy annotations for crowd counting. NeurIPS, 2020.
  48. A generalized loss function for crowd counting and localization. In CVPR, 2021.
  49. Nwpu-crowd: A large-scale benchmark for crowd counting and localization. TPAMI, 2020.
  50. A self-training approach for point-supervised object detection and counting in crowds. TIP, 2021.
  51. From open set to closed set: Counting objects by spatial divide-and-conquer. In ICCV, 2019.
  52. Discrete-constrained regression for local counting models. In ECCV, 2022.
  53. Autoscale: learning to scale for crowd counting. IJCV, 2022.
  54. Ultrasr: Spatial encoding is a missing key for implicit image function-based arbitrary-scale super-resolution. arXiv preprint arXiv:2103.12716, 2021.
  55. Single-image crowd counting via multi-column convolutional neural network. In CVPR, 2016.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets