Drone guide line recognition model based on deep learning

doi:10.11772/j.issn.1001-9081.2024010056

Abstract

Abstract:

Drone guide line recognition is an automatic path finding method based on ground guide lines. To address the issues of slow recognition speed and low recognition accuracy of ground guide lines， a multi-task lightweight model with data fusion called Mobile-FuUnet based on U-shaped Network （U-Net） was proposed. Firstly， on the structure of U-Net， MobileNet-V3 was introduced for feature extraction， and Depthwise Separable Convolution （DSC） was introduced to reduce the number of model parameters， so as to establish a multi-task lightweight model. Finally， based on attention mechanism for data fusion， the polynomial feature matrix of the pre-image was introduced to solve the computational problem caused by the large area missing at the edge of the guide line， in order to improve the operational accuracy of the model. Multiple comparisons were carried out on Tusimple dataset and the drone guide line dataset. Experimental results show that on the drone guide line dataset， Mobile-FuUnet model can achieve guide line recognition task with the frame rate of 109 frame/s， the Mean Intersection over Union （MIoU） of 98.71%， the F1 score of 99.64 %， and the curve model R2 score of 95.03%. Compared with models such as U-Net， ENet， and DeepLab v3， the proposed model improves both running speed and computational accuracy.

Key words: guide line recognition, deep learning, semantic segmentation, self-attention, data fusion

摘要：

无人机引导线识别是一种无人机基于地面引导线进行自动寻径的方法。针对地面引导线识别速度慢、识别准确率低等问题，提出一种多任务的基于U型网络（U-Net）的轻量化数据融合模型——Mobile-FuUnet。首先，在U-Net的结构上引入MobileNet-V3进行特征提取，并引入深度可分卷积（DSC）减少模型参数量，从而建立多任务轻量化模型；其次，引入前置图像的多项式特征矩阵，并基于注意力机制进行数据融合，从而解决引导线边缘部分大面积缺失所带来的计算问题，进而提高模型的识别准确率。在Tusimple数据集与无人机引导线数据集上展开多次对比验证，实验结果表明，在引导线数据集上，Mobile-FuUnet模型可以实现帧率为109 frame/s，平均交并比（MIoU）为98.71%，F1得分为99.64%，曲线模型R2评分95.03%的引导线识别任务，相较于U-Net、ENet、DeepLab v3等模型在运行速率与计算精度上均有提升。

关键词: 引导线识别, 深度学习, 语义分割, 注意力机制, 数据融合

CLC Number:

TP391

Duo CUI, Qiusheng WANG. Drone guide line recognition model based on deep learning[J]. Journal of Computer Applications, 0, (): 262-266.

崔多, 王秋生. 基于深度学习的无人机引导线识别模型[J]. 《计算机应用》唯一官方网站, 0, (): 262-266.

Figures/Tables 10

References 20

1	OTSU N. A threshold selection method from gray-level histograms ［J］. IEEE Transactions on Systems， Man， and Cybernetics， 1979， 9（1）： 62-66.
2	RAMÍREZ D， VÍA J， SANTAMARÍA I， et al. Entropy and Kullback-Leibler divergence estimation based on Szegö's theorem［C］// Proceedings of the 17th European Signal Processing Conference. Piscataway： IEEE， 2009： 2470-2474.
3	LONG J， ZHANG J， XIANG N， et al. An iterative maximum entropy thresholding algorithm ［C］// Proceedings of the 2016 International Conference on Cyberworlds. Piscataway： IEEE， 2016： 171-174.
4	DUDA R O， HART P E. Use of the Hough transformation to detect lines and curves in pictures ［J］. Communications of the ACM， 1972， 15（1）： 11-15.
5	胡斌，何克忠.基于分段直线模型和ATN的车道识别方法［J］.清华大学学报（自然科学版）， 2006， 46（10）： 1762-1766.
6	周发华，陈继清，杨蓉.基于改进Hough变换和斜率特征的车道线识别［J］.现代电子技术， 2023， 46（7）： 180-186.
7	LONG J， SHELHAMER E， DARRELL T. Fully convolutional networks for semantic segmentation ［C］// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2015： 3431-3440.
8	RONNEBERGER O， FISCHER P， BROX T， et al. U-Net： convolutional networks for biomedical image segmentation ［C］// Proceedings of the 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention， LNCS 9351. Cham： Springer， 2015： 234-241.
9	LIU D， ZHANG H， ZHAO M， et al. Brain tumor segmentation based on dilated convolution refine networks ［C］// Proceedings of the IEEE 16th International Conference on Software Engineering Research， Management and Applications. Piscataway： IEEE， 2018： 113-120.
10	PASZKE A， CHAURASIA A， KIM S， et al. ENet： a deep neural network architecture for real-time semantic segmentation ［EB/OL］. ［2024-03-23］. .
11	PAN X， SHI J， LUO P， et al. Spatial as deep： spatial CNN for traffic scene understanding ［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2018： 7276-7283.
12	HOWARD A G， ZHU M， CHEN B， et al. MobileNets： efficient convolutional neural networks for mobile vision applications ［EB/OL］. ［2024-03-23］. .
13	SANDLER M， HOWARD A， ZHU M， et al. MobileNetV2： inverted residuals and linear bottlenecks ［C］// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 4510-4520.
14	NEVEN D， DE BRABANDERE B， GEORGOULIS S， et al. Towards end-to-end lane detection： an instance segmentation approach ［C］// Proceedings of the 2018 IEEE Intelligent Vehicles Symposium. Piscataway： IEEE， 2018： 286-291.
15	HOWARD A， SANDLER M， CHEN B， et al. Searching for MobileNetV3 ［C］// Proceedings of the2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 1314-1324.
16	MNIH V， HEESS N， GRAVES A， et al. Recurrent models of visual attention ［C］// Proceedings of the 27th International Conference on Neural Information Processing Systems — Volume 2. Cambridge： MIT Press， 2014： 2204-2212.
17	徐泽，帅仁俊，刘开凯，等.基于特征融合的文本到图像的生成［J］.计算机科学， 2021， 48（6）： 125-130.
18	CHEN L C， PAPANDREOU G， SCHROFF F， et al. Rethinking atrous convolution for semantic image segmentation ［EB/OL］. ［2024-03-23］. .
19	SIMONYAN K， ZISSERMAN A. Very deep convolutional networks for large-scale image recognition ［EB/OL］. ［2024-03-23］. .
20	QIN Z， ZHANG P， LI X. Ultra fast deep lane detection with hybrid anchor driven ordinal classification ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2024， 46（5）： 2555-2568.

模型	F1 Score/%	MIoU/%	帧率/（frame·s^-1）
U-Net^［8］	99.20	97.64	12
ENet^［10］	91.02	90.05	112
LaneNet^［14］	97.85	96.71	53
DeepLab v3^［18］	98.82	98.03	11
Mobile-Unet	98.95	96.52	117

模型	F1 Score/%	MIoU/%	帧率/（frame·s^-1）
U-Net^［8］	99.20	97.64	12
ENet^［10］	91.02	90.05	112
LaneNet^［14］	97.85	96.71	53
DeepLab v3^［18］	98.82	98.03	11
Mobile-Unet	98.95	96.52	117

模型	F1 Score/%	MIoU/%	帧率/（frame·s^-1）	R2 Score/%
U-Net^［8］	99.70	98.51	12	—
ENet^［10］	91.02	90.05	113	—
LaneNet^［14］	97.85	96.71	53	—
DeepLab v3^［18］	99.32	98.77	9	—
LaneNetATT （ResNet-18）^［19］	97.32	95.33	146	—
SCNN^［20］	99.79	99.32	7	—
Mobile-Unet	99.76	98.72	115	89.52
Mobile-FuUnet	99.64	98.71	109	95.03

模型	F1 Score/%	MIoU/%	帧率/（frame·s^-1）	R2 Score/%
U-Net^［8］	99.70	98.51	12	—
ENet^［10］	91.02	90.05	113	—
LaneNet^［14］	97.85	96.71	53	—
DeepLab v3^［18］	99.32	98.77	9	—
LaneNetATT （ResNet-18）^［19］	97.32	95.33	146	—
SCNN^［20］	99.79	99.32	7	—
Mobile-Unet	99.76	98.72	115	89.52
Mobile-FuUnet	99.64	98.71	109	95.03

[1]	Chuandong QIN, Zhiqiang SUO. Skin cancer classification integrating improved ResNet50 with ensemble classifier [J]. Journal of Computer Applications, 2026, 46(4): 1354-1362.
[2]	Haoxuan CHEN, Peichang YE, Lei LIU, Chengming LIU, Wenhua HU. Survey of automated code edit suggestion [J]. Journal of Computer Applications, 2026, 46(4): 1227-1237.
[3]	Huanxian LIU, Hongtao WANG, Xian’ao WANG, Hongmei WANG, Weifeng XU. Multimodal fact verification with cross-modal semantic association [J]. Journal of Computer Applications, 2026, 46(4): 1069-1076.
[4]	Xiang BAI, Juchuan LI, Huimin WANG, Chao JING, Jian NIU, Xingzhong ZHANG, Yongqiang CHENG. Power image retrieval method based on improved Swin Transformer [J]. Journal of Computer Applications, 2026, 46(4): 1334-1343.
[5]	Xumeng DOU, Bin XIE, Zhaohui ZHANG, Zhengang ZHAO, Hanyu DUAN, Aolei GUO. Drug-target interaction prediction based on structure-network collaborative features and grid-attention enhanced Kolmogorov-Arnold network [J]. Journal of Computer Applications, 2026, 46(4): 1344-1353.
[6]	Songsen YU, Huang HE, Guopeng XUE, Hengtuo CUI. Quantitation and grading method for ceramic tile chromatic aberration based on improved fractal encoding network [J]. Journal of Computer Applications, 2026, 46(3): 959-968.
[7]	Peirong SHAO, Suzhen LIN, Yanbo WANG. Human-centric detail-enhanced virtual try-on method [J]. Journal of Computer Applications, 2026, 46(3): 915-923.
[8]	Jian ZHANG, Jianbo YU, Jian TANG. Municipal solid waste incineration state recognition method based on multilayer preprocessing [J]. Journal of Computer Applications, 2026, 46(3): 940-949.
[9]	Yongwei JIANG, Xiaoqing CHEN, Linjie FU. Elastic medical image registration model with high-frequency preservation based on spectrum decomposition [J]. Journal of Computer Applications, 2026, 46(3): 924-932.
[10]	Zuxi ZHANG, Zhancheng ZHANG, Fuyuan HU. Local and long-range temporal complementary modeling for video action recognition [J]. Journal of Computer Applications, 2026, 46(3): 758-766.
[11]	Min CHEN, Xiaolin QIN, Shaohan LI, Hao YANG, Taohong LI. Review of deep learning applications in severe convective weather prediction [J]. Journal of Computer Applications, 2026, 46(3): 980-992.
[12]	Haoqian JIANG, Dong ZHANG, Guanyu LI, Heng CHEN. SetaCRS： Conversational recommender system with structure-enhanced hierarchical task-oriented prompting strategy [J]. Journal of Computer Applications, 2026, 46(2): 368-377.
[13]	Jincheng FU, Shiyou YANG. Short-term wind power prediction using hybrid model based on Bayesian optimization and feature fusion [J]. Journal of Computer Applications, 2026, 46(2): 652-658.
[14]	Hu LUO, Mingshu ZHANG. Rumor detection method based on cross-modal attention mechanism and contrastive learning [J]. Journal of Computer Applications, 2026, 46(2): 361-367.
[15]	Feng HAN, Yongfeng BU, Haoxiang LIANG, Shuwen HUANG, Zhaoyang ZHANG, Shijie SUN. Vehicle trajectory anomaly detection based on multi-level spatio-temporal interaction dependency [J]. Journal of Computer Applications, 2026, 46(2): 604-612.