Proportional feature pyramid network based on weight fusion for lane detection

Author:

Hui Jiapeng12,Lian Guoyun1,Wu Jiansheng2,Ge Shuting12,Yang Jinfeng1

Affiliation:

1. Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen Polytechnic University, Shenzhen, Guangdong, China

2. School of Computer and Software Engineering, University of Science and Technology Liaoning, Anshan, Liaoning, China

Abstract

Lane detection under extreme conditions presents a highly challenging task that requires capturing each crucial pixel to predict the complex topology of lane lines and differentiate the various lane types. Existing methods predominantly rely on deep feature extraction networks with substantial parameters or the fusion of multiple prediction modules, resulting in large model sizes, embedding difficulties, and slow detection speeds. This article proposes a Proportional Feature Pyramid Network (P-FPN) through fusing the weights into the FPN for lane detection. For obtaining a more accurately detecting result, the cross refinement block is introduced in the P-FPN network. The cross refinement block takes the feature maps and anchors as inputs and gradually refines the anchors from high to low level feature maps. In our method, the high-level features are explored to predict lanes coarsely while local-detailed features are leveraged to improve localization accuracy. Extensive experiments on two widely used lane detection datasets, The Chinese Urban Scene Benchmark for Lane Detection (CULane) and the TuSimple Lane Detection Challenge (TuSimple) datasets, demonstrate that the proposed method achieves competitive results compared with several state-of-the-art approaches.

Funder

The Project of Educational Commission of Guangdong Province

China University Innovation Fund

Shenzhen Polytechnic Project

Opening Foundation of State Key Laboatory of Cognitive Intelligence, iFLYTEK

Science and Technology Innovation Project of University of Science and Technology Liaoning

Publisher

PeerJ

Reference43 articles.

1. Laneaf: robust multi-lane detection with affinity fields;Abualsaud;IEEE Robotics and Automation Letters,2021

2. Real time lane detection for autonomous vehicles;Assidiq,2008

3. Self-driving cars: a survey;Badue;Expert Systems with Applications,2021

4. Recent progress in road and lane detection: a survey;Bar Hillel;Machine Vision and Applications,2014

5. Ego-lane analysis system (elas): dataset and algorithms;Berriel;Image and Vision Computing,2017

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3