{"id":2109,"date":"2026-04-02T18:42:46","date_gmt":"2026-04-02T10:42:46","guid":{"rendered":"https:\/\/iweb20wp-b205b.url.tku.edu.tw\/jase\/?post_type=tkuisotope&p=2109"},"modified":"2026-05-11T22:31:15","modified_gmt":"2026-05-11T14:31:15","slug":"tourist-density-estimation-based-on-lightweight-swin-transformer","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=tourist-density-estimation-based-on-lightweight-swin-transformer","title":{"rendered":"Tourist density estimation based on lightweight Swin- Transformer"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 29, Issue 6<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Xuxiang Zhang<\/i><\/a><\/p>\n\n\n\n

School of Finance and Economics, Zhengzhou University of Science and Technology, Zhengzhou, China<\/p>\n<\/div>\n\n\n\n

\n

Received: August 24, 2025
Accepted: October 28, 2025
Publication Date: April 2, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

MFPP module<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:\u00a0 BibTeX <\/a>| https:\/\/doi.org\/10.6180\/jase.202606_29(6).0024<\/a>\u00a0\u00a0<\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

There are two problems in traditional population counting models. (1) The complex heavy-duty counting models have strong counting performance, but they have excessive model parameters and computational costs, thus lacking practicality. (2) The current lightweight models have reduced the complexity of the models, but their counting performance is poor. Therefore, this paper proposes a novel tourist density estimation based on lightweight Swin-Transformer. The proposed method takes advantage of the distinct encoding advantages of Swin-Transformer and convolutional neural network (CNN), effectively capturing the global semantic information and local details of image features, thereby enhancing the model\u2019s expressive power. To minimize the loss of feature details during down-sampling, a multi-scale resolution feature pyramid pooling (MFPP) module is designed. By combining features from different dimensions, it acquires more contextual information at different scales and enhances the expression of local details. Various advanced methods are compared on three population datasets. The experimental results show that all the indicators of the proposed framework perform exceptionally well, effectively alleviating the scale differences in tourist counting, generating high-fidelity density maps and enhancing the generalization ability of the model.<\/p>\n\n\n\n

Keywords: tourist density estimation, lightweight Swin-Transformer, CNN, multi-scale resolution feature pyramid pooling<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
\n
    \n
  1. [1] H. Meng, X. Hong, C. Wang, M. Shang, and W. Zuo, (2024) \u201cMulti-modal crowd counting via a broker modality\u201d: 231\u2013250. DOI: 10.1007\/978-3-031-72904-1_14.<\/li>\n
  2. [2] L. Deng, Q. Zhou, S. Wang, J. M. G\u00f3rriz, and Y. Zhang, (2024) \u201cDeep learning in crowd counting: A survey\u201d CAAI Transactions on Intelligence Technology 9(5): 1043\u20131077. DOI: 10.1049\/cit2.12241.<\/li>\n
  3. [3] W. Wang, Q. Liu, and W. Wang, (2022) \u201cPyramid-dilated deep convolutional neural network for crowd counting\u201d Applied Intelligence 52(2): 1825\u20131837. DOI: 10.1007\/s10489-021-02537-6.<\/li>\n
  4. [4] M.-h. Oh, P. Olsen, and K. N. Ramamurthy. \u201cCrowd counting with decomposed uncertainty\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 34. 07. 2020, 11799\u201311806. DOI: 10.1609\/aaai.v34i07.6852.<\/li>\n
  5. [5] S. Yin, L. Wang, T. Chen, H. Huang, J. Gao, J. Zhang, M. Liu, P. Li, and C. Xu, (2025) \u201cLKAFormer: A Lightweight Kolmogorov-Arnold Transformer Model for Image Semantic Segmentation\u201d ACM Transactions on Intelligent Systems and Technology: DOI: 10.1145\/3759254.<\/li>\n
  6. [6] Y. Li, X. Zhang, and D. Chen. \u201cCsrnet: Dilated convolutional neural networks for understanding the highly congested scenes\u201d. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, 1091\u20131100. DOI: 10.1109\/CVPR.2018.00120.<\/li>\n
  7. [7] W. Liu, M. Salzmann, and P. Fua. \u201cContext-aware crowd counting\u201d. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019, 5099\u20135108. DOI: 10.1109\/CVPR.2019.00524.<\/li>\n
  8. [8] Y. Meng, H. Zhang, Y. Zhao, X. Yang, X. Qian, X. Huang, and Y. Zheng. \u201cSpatial uncertainty-aware semi-supervised crowd counting\u201d. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2021, 15549\u201315559. DOI: 10.1109\/ICCV48922.2021.01526.<\/li>\n
  9. [9] M. Wang, H. Cai, X.-F. Han, J. Zhou, and M. Gong, (2022) \u201cSTNet: Scale tree network with multi-level auxiliator for crowd counting\u201d IEEE Transactions on Multimedia 25: 2074\u20132084. DOI: 10.1109 \/ TMM.2022.3142398.<\/li>\n
  10. [10] S. Yin, H. Li, A. A. Laghari, L. Teng, T. R. Gadekallu, and A. Almadhor, (2024) \u201cFLSN-MVO: edge computing and privacy protection based on federated learning Siamese network with multi-verse optimization algorithm for industry 5.0\u201d IEEE Open Journal of the Communications Society 6: 3443\u20133458. DOI: 10.1109\/OJCOMS.2024.3520562.<\/li>\n
  11. [11] H. Lin, Z. Ma, X. Hong, Q. Shangguan, and D. Meng. \u201cGramformer: Learning crowd counting via graph-modulated transformer\u201d. In: Proceedings of the AAAI Conference on Artificial Intelligence. 38. 4. 2024, 3395\u20133403. DOI: 10.1609\/aaai.v38i4.28126.<\/li>\n
  12. [12] D. B. Sam and R. V. Babu. \u201cTop-down feedback for crowd counting convolutional neural network\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 32. 1. 2018. DOI: 10.1609\/aaai.v32i1.12290.<\/li>\n
  13. [13] J. Gao, Q. Wang, and X. Li, (2019) \u201cPcc net: Perspective crowd counting via spatial convolutional network\u201d IEEE Transactions on Circuits and Systems for Video Technology 30(10): 3486\u20133498. DOI: 10.1109\/TCSVT.2019.2919139.<\/li>\n
  14. [14] X. Ma, S. Du, and Y. Liu. \u201cA lightweight neural network for crowd analysis of images with congested scenes\u201d. In: 2019 IEEE international conference on image processing (ICIP). IEEE. 2019, 979\u2013983. DOI: 10.1109\/ICIP.2019.8803062.<\/li>\n
  15. [15] L. Liang, H. Zhao, F. Zhou, M. Ma, F. Yao, and X. Ji, (2023) \u201cPDDNet: lightweight congested crowd counting via pyramid depth-wise dilated convolution\u201d Applied Intelligence 53(9): 10472\u201310484. DOI: 10.1007\/s10489-022-03967-6.<\/li>\n
  16. [16] J. Yi, Z. Shen, F. Chen, Y. Zhao, S. Xiao, and W. Zhou, (2023) \u201cA lightweight multiscale feature fusion network for remote sensing object counting\u201d IEEE Transactions on Geoscience and Remote Sensing 61: 1\u201313. DOI: 10.1109\/TGRS.2023.3238185.<\/li>\n
  17. [17] S. Yin, L. Wang, and L. Teng, (2024) \u201cThreshold segmentation based on information fusion for object shadow detection in remote sensing images\u201d Computer Science and Information Systems 21(4): 1221\u20131241. DOI: 10.2298\/CSIS231230023Y.<\/li>\n
  18. [18] A. Kumar, S. P. Yadav, and A. Kumar, (2025) \u201cAn improved feature extraction algorithm for robust Swin Transformer model in high-dimensional medical image analysis\u201d Computers in biology and medicine 188: 109822. DOI: 10.1016\/j.compbiomed.2025.109822.<\/li>\n
  19. [19] Z. Ma, X. Wu, A. Chu, L. Huang, and Z. Wei, (2024) \u201cSwinFG: A fine-grained recognition scheme based on swin transformer\u201d Expert Systems with Applications 244: 123021. DOI: 10.1016\/j.eswa.2023.123021.<\/li>\n
  20. [20] S. Yin, H. Li, A. A. Laghari, T. R. Gadekallu, G. A. Sampedro, and A. Almadhor, (2024) \u201cAn anomaly detection model based on deep auto-encoder and capsule graph convolution via sparrow search algorithm in 6G Internet of Everything\u201d IEEE Internet of Things Journal 11(18): 29402\u201329411. DOI: 10.1109\/JIOT.2024.3353337.<\/li>\n
  21. [21] M. A. Kizrak and B. Bolat, (2021) \u201cCrowd density estimation by using attention based capsule network and multi-column CNN\u201d IEEE Access 9: 75435\u201375445. DOI: 10.1109\/ACCESS.2021.3081529.<\/li>\n
  22. [22] J. Sang, W. Wu, H. Luo, H. Xiang, and X. Xia, (2019) \u201cImproved Crowd Counting Method Based on Scale-Adaptive Convolutional Neural Network\u201d IEEE Access 7(99): 24411\u201324419. DOI: 10.1109\/ACCESS.2019.2899939.<\/li>\n
  23. [23] Z. Chen, S. Zhang, X. Zheng, X. Zhao, and Y. Kong, (2023) “Crowd counting based on multiscale spatial guided perception aggregation network” IEEE Transactions on Neural Networks and Learning Systems: DOI: 10.1109\/TNNLS.2023.3304348.<\/li>\n
  24. [24] J.-a. Cheng, Q. Li, A. Souri, X. Lei, C. Zhang, and M. Gao, (2025) “Towards trustworthy crowd counting by distillation hierarchical mixture of experts for edge-based cluster computing” Cluster computing 28(7): 1\u201315. DOI: 10.1007\/s10586-025-05226-y.<\/li>\n
  25. [25] K.-H. Kim, T.-K. Ahn, and S. Kim, (2025) “Estimating Invisible Passenger Count Using CCTV Footage: An Approach Combining Object Detection Models and Machine Learning” IEEE Access: DOI: 0.1109\/ACCESS.2025.3597708.<\/li>\n
  26. [26] Z. Niu, H. Pi, G. Xiao, S. Yang, Z. Tang, and D. Liu, (2025) “Low-Light Domain Enhancement and Multi-Domain Progressive Fusion for RGB-T Day-Night Crowd Counting” IEEE Internet of Things Journal: DOI: 10.1109\/JIOT.2025.3594227.<\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,15,6,121],"tags":[262],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:\u00a0 BibTeX | https:\/\/doi.org\/10.6180\/jase.202606_29(6).0024\u00a0\u00a0 Download PDF There are two problems in traditional population counting models. (1) The…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/2109"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2109"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2109"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2109"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}