CFAI-YOLO: an enhanced pedestrian and vehicle detection algorithm based on YOLOv11s

Abstract

A pedestrian and vehicle detection algorithm CFAI-YOLO based on you only look once v11 small (YOLOv11s) is proposed to process the issues of insufficient accuracy, high false detection and missed detection rates in existing pedestrian and vehicle detection algorithms. Firstly, the introduction of context and spatial feature calibration network (CSFCN) effectively solves the problems of pixel context mismatch and spatial feature misalignment. Secondly, an adaptive fine-grained channel attention (FCA) mechanism is added to the backbone network to achieve more effective feature weight allocation. Finally, using the ADown downsampling module preserves the target feature information and reduces the number of model parameters. The experimental results of the improved model on the KITTI dataset achieved 88.1% mean average precision (mAP), which is 2.4% higher than the original model.

Keywords

A

References

[1] Wu D, Fang C, Zheng X, et al. AMW-YOLOv8n: road scene object detection based on an improved YOLOv8. Electronics, 2024, 13204121. J]

[2] Shen L, Tao H, Ni Y, et al. Improved YOLOv3 model with feature map cropping for multi-scale road object detection. Measurement science and technology, 2023, 344045406. J]

[3] Zhang Z, Wang X, Huang D, et al. MRPT: millimeterwave radar-based pedestrian trajectory tracking for autonomous urban driving. IEEE transactions on instrumentation and measurement, 2021, 71: 1-17[J]

[4] Mao Z H, Zhu J L, Wu X, et al. Review of YOLO based target detection for autonomous driving. Computer engineering and applications, 2022, 58156877[J]

[5] Song M, Kim C, Kim M, et al. Robust lane tracking algorithm for forward target detection of automated driving vehicles. Proceedings of the institution of mechanical engineers, 2019, 233719301949. J]

[6] Wang L, Chen F L, Yin H M. Detecting and tracking vehicles in traffic by unmanned aerial vehicles. Automation in construction, 2016, 723: 294-308. J]

[7] Ren S Q, He K M, Ross G, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence, 2017, 39: 1137-1149. J]

[8] Wang W K, Xu X Y, Yang H. Intelligent detection of tunnel leakage based on improved mask R-CNN. Symmetry, 2024, 166709. J]

[9] Zhang Y, Gong Z Y, Wei W W. Traffic sign detection based on improved faster R-CNN model. Laser & optoelectronics progress, 2020, 57: 181015. J]

[10] He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence, 2015, 37: 1904-1916. J]

[11] Dai S S, Liu K S, Yu Z. A road crack detection method combining visual transformer and CNN. Semiconductor optoelectronics, 2024, 45: 252-260[J]

[12] Luo Y, Wang B Y, Chen X. A review of research on deep learning based object detection techniques. Semiconductor optoelectronics, 2020, 41: 1-10[J]

[13] Tan X P, Gao Z H, Han H D, et al. Research on intelligent detection of fluorescence image cells based on improved YOLOv5. Semiconductor optoelectronics, 2023, 44: 709-716[J]

[14] Jing F K, Ren H G, Li S. Small target traffic sign detection based on multi-scale feature fusion. Progress in laser and optoelectronics, 2024, 61: 372-380[J]

[15] Zhong Y J, Li K, Mo S, et al. Research on ground penetrating radar echo image recognition based on GSR-YOLOv7. Semiconductor optoelectronics, 2023, 44: 767-774[J]

[16] Chen Y. YOLOv3-MSSA based hot spot defect detection for photovoltaic power stations. Journal of measurements in engineering, 2024, 1212339. J]

[17] QIANG J, LIU W J, LI X X, et al. Detection of citrus pests in double backbone network based on single shot multibox detector[J]. Computers and electronics in agriculture, 2023, 212.

[18] Lou H T, Duan X H, Guo J M, et al. DC-YOLOv8: small-size object detection algorithm based on camera sensor. Electronics, 2023, 12: 2323. J]

[19] YANG W J, WU J C, GAO J L, et al. Deformable convolution and coordinate attention for fast cattle detection[J]. Computers and electronics in agriculture, 2023, 211.

[20] WANG G, CHEN Y F, AN P, et al. UAV-YOLOv8: a small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios[J]. Sensors, 2023, 23(16).

[21] Zhou Y, Wen S J, Wang D L, et al. Mobile YOLO: real-time object detection algorithm in autonomous driving scenarios. Sensors, 2022, 22: 3349. J]

[22] Singh N, Maurya P C, Mahaur B, et al. Improved YOLOv11 with weights pruning for road object detection in rainy environment. Signal, image and video processing, 2025, 196473. J]

[23] LI K G, GENG Q C, WAN M X, et al. Context and spatial feature calibration for real-time semantic segmentation[J]. IEEE transactions on image processing, 2023.

[24] Sun H, Wen Y, Feng H, et al. Unsupervised bidirectional contrastive reconstruction and adaptive fine-grained channel attention networks for image dehazing. Neural networks, 2024, 176: 106314. J]

[25] Ponduri V, Mohan L, Basheera S, et al. Highly efficient YOLOV9 model for detecting extremely small-scale objects. Engineering research express, 2025, 71015287. J]

[26] ZHANG H, XU C, ZHANG S J. Inner-IoU: more effective intersection over union loss with auxiliary bounding box[EB/OL]. (2023-11-06) [2025-12-23]. https://arxiv.org/abs/2311.02877.

[27] Andreas G, Philip L, Christoph S, et al. Vision meets robotics: the KITTI dataset. The international journal of robotics research, 2013, 32: 1231-1237. J]

Rights & permissions

Tianjin University of Technology