The Improved Deeplabv3plus Based Fast Lane Detection Method

被引：1

作者：

Wang, Zhong ^{[1
]}

Zhao, Yin ^{[1
]}

Tian, Yang ^{[2
,3
]}

Zhang, Yahui ^{[2
,3
]}

Gao, Landa ^{[4
]}

机构：

[1] Yanshan Univ, Sch Vehicle & Energy, Qinhuangdao 066004, Hebei, Peoples R China

[2] Yanshan Univ, Sch Mech Engn, Qinhuangdao 066004, Hebei, Peoples R China

[3] Hebei Innovat Ctr Equipment Lightweight Design &, Qinhuangdao 066004, Hebei, Peoples R China

[4] Minist Transport, Res Inst Highway, Beijing 100088, Peoples R China

来源：

ACTUATORS | 2022年 / 11卷 / 07期

关键词：

deep learning; attentional mechanisms; attention distillation; lane detection; deeplabv3plus; NETWORK;

D O I：

10.3390/act11070197

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

Lane detection is one of the most basic and essential tasks for autonomous vehicles. Therefore, the fast and accurate recognition of lanes has become a hot topic in industry and academia. Deep learning based on a neural network is also a common method for lane detection. However, due to the huge computational burden of the neural network, its real-time performance is often difficult to meet the requirements in the fast-changing actual driving scenes. A lightweight network combining the Squeeze-and-Excitation block and the Self-Attention Distillation module is proposed in this paper, which is based on the existing deeplabv3plus network and specifically improves its real-time performance. After experimental verification, the proposed network achieved 97.49% accuracy and 60.0% MIOU at a run time of 8.7 ms, so the network structure achieves a good trade-off between real-time performance and accuracy.

引用

页数：13

共 35 条

[1] A Novel Lane Detection System With Efficient Ground Truth Generation [J].

Borkar, Amol ;

Hayes, Monson ;

Smith, Mark T. .

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2012, 13 (01) :365-374

[2] CAN: Effective Cross Features by Global Attention Mechanism and Neural Network for Ad Click Prediction [J].

Cai, Wenjie ;

Wang, Yufeng ;

Ma, Jianhua ;

Jin, Qun .

TSINGHUA SCIENCE AND TECHNOLOGY, 2022, 27 (01) :186-195

[3] A Precise Information Extraction Algorithm for Lane Lines [J].

Chen, Jinyan ;

Ruan, Yaduan ;

Chen, Qimei .

CHINA COMMUNICATIONS, 2018, 15 (10) :210-219

[4] Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation [J].

Chen, Liang-Chieh ;

Zhu, Yukun ;

Papandreou, George ;

Schroff, Florian ;

Adam, Hartwig .

COMPUTER VISION - ECCV 2018, PT VII, 2018, 11211 :833-851

[5]

Chen LB, 2017, IEEE INT SYMP NANO, P1, DOI 10.1109/NANOARCH.2017.8053709

[6] Xception: Deep Learning with Depthwise Separable Convolutions [J].

Chollet, Francois .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1800-1807

[7] Combining Residual Attention Mechanisms and Generative Adversarial Networks for Hippocampus Segmentation [J].

Deng, Hongxia ;

Zhang, Yuefang ;

Li, Ran ;

Hu, Chunxiang ;

Feng, Zijian ;

Li, Haifang .

TSINGHUA SCIENCE AND TECHNOLOGY, 2022, 27 (01) :68-78

[8]

Guo J.-M., 2021, P 2021 INT S INTELLI, P1

[9] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[10] Learning Lightweight Lane Detection CNNs by Self Attention Distillation [J].

Hou, Yuenan ;

Ma, Zheng ;

Liu, Chunxiao ;

Loy, Chen Change .

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :1013-1021

← 1 2 3 4 →