Adaptive Mix-Gated Multi-Attention Fusion in YOLOv11s for Dense Person Detection: A Systematic Evaluation of Dual and Triple Attention Configurations

Aya Ahmed, Karam Abdullah

Abstract


Person detection in a crowded environment is very challenging due to excessive occlusion, scale variation, and heavy overlap between individuals. This paper proposes a lightweight Mix-Gated attention framework to enhance the feature representation capacity of YOLOv11s for dense person detection. The proposed framework incorporates two complementary channel-wise and spatial attention mechanisms under a flexible channel-wise gating strategy, while preserving the original YOLOv11s architecture and real-time inference ability. Unlike previous studies, which primarily employed either a single attention mechanism or fixed combinations of multiple attention modules, the proposed framework introduces an adaptive Mix-Gated feature selection mechanism that dynamically learns the contribution of complementary attention modules through trainable channel-wise gating. Furthermore, this study systematically evaluates ten dual and triple attention configurations under identical training and evaluation conditions, providing a comprehensive and fair comparison of their effectiveness. this study evaluated the performance on four popular benchmark datasets - CrowdHuman, WiderPerson, MOT17Det and MOT20Det - using Precision, Recall, F1-score, mAP@50 and mAP@50-95 as evaluation metrics. The experimental results show that all proposed Mix-Gated configurations outperform the baseline YOLOv11s model. Mix-Gated-CBAM+SE+SA has the best detection accuracy and efficient inference performance among Mix-Gated configurations. These results indicate that adaptive fusion of complementary attention mechanisms can improve the feature representation and person detection performance in crowded scenes while not sacrificing computational efficiency.

Keywords


Dense person detection, YOLOv11s, Mix-Gated attention, CBAM, SE, ECA, Spatial Attention, Crowd analysis.

Full Text:

PDF

References


S. Abba, A. M. Bizi, J.-A. Lee, S. Bakouri, and M. L. Crespo, ‘Real-Time Object Detection, Tracking, and Monitoring Framework for Security Surveillance Systems’, Heliyon, Vol. 10, No. 15, p. e34922, Aug. 2024, DOI: 10.1016/j.heliyon.2024.e34922.

P. Raja, D. B K, R. T, V. Ravi, and N. S. Alghamdi, ‘A Context-Aware Multi-Modal Generative Adversarial Network for Real-Time Anomaly Detection in Video Surveillance’, Peer-to-Peer Netw. Appl., Vol. 19, No. 1, p. 29, Jan. 2026, DOI: 10.1007/s12083-025-02134-1.

Y. Chen, J. Li, E. Blasch, and Q. Qu, ‘Future Outdoor Safety Monitoring: Integrating Human Activity Recognition with the Internet of Physical–Virtual Things’, Applied Sciences, Vol. 15, No. 7, p. 3434, Mar. 2025, DOI: 10.3390/app15073434.

M. Contreras, A. Jain, N. P. Bhatt, A. Banerjee, and E. Hashemi, ‘A Survey on 3D Object Detection in Real Time for Autonomous Driving’, Front. Robot. AI, Vol. 11, p. 1212070, Mar. 2024, DOI: 10.3389/frobt.2024.1212070.

A. M. Alasmari, N. S. Farooqi, and Y. A. Alotaibi, ‘Recent Trends in Crowd Management using Deep Learning Techniques: A Systematic Literature Review’, J. Umm Al-Qura Univ. Eng.Archit., Vol. 15, No. 4, pp. 355–383, Dec. 2024, DOI: 10.1007/s43995-024-00071-3.

S. Essahraui et al., ‘Human Behavior Analysis: A Comprehensive Survey on Techniques, Applications, Challenges, and Future Directions’, IEEE Access, Vol. 13, pp. 128379–128419, 2025, DOI: 10.1109/ACCESS.2025.3589938.

E. A. Rodríguez-Martínez, W. Flores-Fuentes, F. Achakir, O. Sergiyenko, and F. N. Murrieta-Rico, ‘Vision-based Navigation and Perception for Autonomous Robots: Sensors, SLAM, Control Strategies, and Cross-Domain Applications—A Review’, Eng, Vol. 6, No. 7, p. 153, Jul. 2025, DOI: 10.3390/eng6070153.

C. Chen, J. Li, Z. Shuai, Y. Wang, and Y. Wang, ‘A Lightweight Optimization Framework for Real-Time Pedestrian Detection in Dense and Occluded Scenes’, Mech. SCI., Vol. 16, No. 2, pp. 877–886, Nov. 2025, DOI: 10.5194/ms-16-877-2025.

S. Xing, F. Wang, and H. Wang, ‘A Pedestrian Detection Model based on YOLO for Dense Scenes’, Optoelectron. Lett., Vol. 22, No. 4, pp. 229–235, Apr. 2026, DOI: 10.1007/s11801-026-4274-2.

Z. Hu, W. Niu, and S. Mo, ‘CRD-YOLO: A High-Accuracy Real-Time Crowded Pedestrian Detection Algorithm’, SIViP, Vol. 20, No. 3, p. 159, Mar. 2026, DOI: 10.1007/s11760-026-05220-w.

W. Sheng, M. Liu, X. Li, and M. Zhang, ‘OLODN: An Efficient Lightweight People Detection Method for Occlusion and Crowding Scenarios’, IET Image Processing, Vol. 19, No. 1, p. e13325, Jan. 2025, DOI: 10.1049/ipr2.13325.

N. Dalal and B. Triggs, ‘Histograms of Oriented Gradients for Human Detection’, in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA: IEEE, 2005, pp. 886–893. DOI: 10.1109/CVPR.2005.177.

D. G. Lowe, ‘Distinctive Image Features from Scale-Invariant Keypoints’, International Journal of Computer Vision, Vol. 60, No. 2, pp. 91–110, Nov. 2004, DOI: 10.1023/B:VISI.0000029664.99615.94.

E. Edozie, A. N. Shuaibu, U. K. John, and B. O. Sadiq, ‘Comprehensive Review of Recent Developments in Visual Object Detection based on Deep Learning’, Artif Intell Rev, Vol. 58, No. 9, p. 277, Jun. 2025, DOI: 10.1007/s10462-025-11284-w.

V. Pagire, M. Chavali, and A. Kale, ‘A Comprehensive Review of Object Detection with Traditional and Deep Learning Methods’, Signal Processing, Vol. 237, p. 110075, Dec. 2025, DOI: 10.1016/j.sigpro.2025.110075.

A. A. Murat and M. S. Kiran, ‘A Comprehensive Review on YOLO Versions for Object Detection’, Engineering Science and Technology, an International Journal, Vol. 70, p. 102161, Oct. 2025, DOI: 10.1016/j.jestch.2025.102161.

R. Sapkota et al., ‘YOLO Advances to its Genesis: A Decadal and Comprehensive Review of the You Only Look Once (YOLO) series’, Artif Intell Rev, Vol. 58, No. 9, p. 274, Jun. 2025, DOI: 10.1007/s10462-025-11253-3.

M.-H. Guo et al., ‘Attention Mechanisms in Computer Vision: A Survey’, Comp. Visual. Med., Vol. 8, No. 3, pp. 331–368, Sep. 2022, DOI: 10.1007/s41095-022-0271-y.

S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, ‘CBAM: Convolutional Block Attention Module’, in Computer Vision – ECCV 2018, Vol. 11211, V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, Eds, in Lecture Notes in Computer Science, Vol. 11211. , Cham: Springer International Publishing, 2018, pp. 3–19. DOI: 10.1007/978-3-030-01234-2_1.

J. Hu, L. Shen, and G. Sun, ‘Squeeze-and-Excitation Networks’, 2018.

Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, ‘ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks’, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA: IEEE, Jun. 2020, pp. 11531–11539. DOI: 10.1109/CVPR42600.2020.01155.

X. Zhu, D. Cheng, Z. Zhang, S. Lin, and J. Dai, ‘An Empirical Study of Spatial Attention Mechanisms in Deep Networks’, in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South): IEEE, Oct. 2019, pp. 6687–6696. DOI: 10.1109/ICCV.2019.00679.

M.-H. Bae, S.-W. Park, J. Park, S.-H. Jung, and C.-B. Sim, ‘YOLO-RACE: Reassembly and Convolutional Block Attention for Enhanced Dense Object Detection’, Pattern Anal Applic, Vol. 28, No. 2, p. 90, Jun. 2025, DOI: 10.1007/s10044-025-01471-4.

X. Chen, J. Li, H. Zhang, J. Gong, H. Wu, and O. Postolache, ‘Vehicle Navigation-Oriented Object Distance Estimation via a Squeeze and Excitation Channel Attention Mechanism-Enhanced YOLO Module’, 2026, SSRN. DOI: 10.2139/ssrn.6143995.

Z. Chen, S. Tian, L. Yu, L. Zhang, and X. Zhang, ‘An Object Detection Network based on YOLOv4 and Improved Spatial Attention Mechanism’, IFS, Vol. 42, No. 3, pp. 2359–2368, Feb. 2022, DOI: 10.3233/JIFS-211648.

C.-T. Chien, R.-Y. Ju, K.-Y. Chou, E. Xieerke, and J.-S. Chiang, ‘YOLOv8-AM: YOLOv8 based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection’, IEEE Access, Vol. 13, pp. 52461–52477, 2025, DOI: 10.1109/ACCESS.2025.3549839.

Z. Tang, J. Lu, Z. Chen, F. Qi, and L. Zhang, ‘Improved Pest-YOLO: Real-Time Pest Detection based on Efficient Channel Attention Mechanism and Transformer Encoder’, Ecological Informatics, Vol. 78, p. 102340, Dec. 2023, DOI: 10.1016/j.ecoinf.2023.102340.

L. Wu, X. Li, P. Ma, and Y. Cai, ‘Research on a Dense Pedestrian-Detection Algorithm based on an Improved YOLO11’, Future Internet, Vol. 17, No. 10, p. 438, Sep. 2025, DOI: 10.3390/fi17100438.

D. Chavan and A. Purohit, ‘Machine Learning Techniques for Crowd Counting: A Survey’, IJCA, Vol. 185, No. 37, pp. 1–8, Oct. 2023, DOI: 10.5120/ijca2023923176.

I. Beqqali Hassani, S. Benhida, N. Lamii, K. Oqaidi, A. Ouiddad, and S. Ghiadi, ‘From YOLO V1 to YOLO V11: Comparative Analysis of YOLO Algorithm (Review)’, IJECE, Vol. 16, No. 1, p. 450, Feb. 2026, DOI: 10.11591/ijece.v16i1.pp450-462.

M. A. A. Adam and J. R. Tapamo, ‘Enhancing YOLOv5 for Autonomous Driving: Efficient Attention-based Object Detection on Edge Devices’, J. Imaging, Vol. 11, No. 8, p. 263, Aug. 2025, DOI: 10.3390/jimaging11080263.

S. Potharaju, S. N. Tambe, K. Dasari, N. Srikanth, R. Venkatarao, and S. Tambe, ‘Enhanced X-Ray Image Classification for Pneumonia Detection using Deep Learning based CBAM and SE Mechanisms’, Intelligence-Based Medicine, Vol. 12, p. 100299, 2025, DOI: 10.1016/j.ibmed.2025.100299.

Z. Kang, Y. Liao, S. Du, H. Li, and Z. Li, ‘SE-CBAM-YOLOv7: An Improved Lightweight Attention Mechanism-Based YOLOv7 for Real-Time Detection of Small Aircraft Targets in Microsatellite Remote Sensing Imaging’, Aerospace, Vol. 11, No. 8, p. 605, Jul. 2024, DOI: 10.3390/aerospace11080605.

T. M. M. Aung and A. A. Khan, ‘Enhanced U-Net with Attention Mechanisms for Improved Feature Representation in Lung Nodule Segmentation’, CMIR, Vol. 21, p. e15734056386382, Oct. 2025, DOI: 10.2174/0115734056386382250902064757.

N. Chandra, H. Vaidya, S. Sawant, S. Gite, and B. Pradhan, ‘Attention Driven YOLOv5 Network for Enhanced Landslide Detection using Satellite Imagery of Complex Terrain’, CMES, Vol. 143, No. 3, pp. 3351–3375, 2025, DOI: 10.32604/cmes.2025.064395.

Y. Mao and S. Pan, ‘Steel Surface Defect Detection Method based on MAA_YOLOv8’.

S. Yang, J. Xing, Z. Liu, and X. Zheng, ‘HCA-YOLOv8: A Pedestrian Detection Model that Integrates Multi-Source Context-Aware Mechanisms’, IEEE Access, Vol. 14, pp. 48487–48503, 2026, DOI: 10.1109/ACCESS.2026.3673396.

S. Shao et al., ‘CrowdHuman: A Benchmark for Detecting Human in a Crowd’, Apr. 30, 2018, arXiv: arXiv:1805.00123. DOI: 10.48550/arXiv.1805.00123.

S. Zhang, Y. Xie, J. Wan, H. Xia, S. Z. Li, and G. Guo, ‘WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild’, Sep. 25, 2019, arXiv: arXiv:1909.12118. DOI: 10.48550/arXiv.1909.12118.

A. Milan, L. Leal-Taixe, I. Reid, S. Roth, and K. Schindler, ‘MOT16: A Benchmark for Multi-Object Tracking’, May 03, 2016, arXiv: arXiv:1603.00831. DOI: 10.48550/arXiv.1603.00831.

P. Dendorfer et al., ‘MOT20: A Benchmark for Multi Object Tracking in Crowded Scenes’, Mar. 19, 2020, arXiv: arXiv:2003.09003. DOI: 10.48550/arXiv.2003.09003.




DOI: https://doi.org/10.32520/stmsi.v15i8.6733

Article Metrics

Abstract view : 1 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.