MtpNet:多任务全景驾驶感知网络

IF 8.4 1区 工程技术 Q1 ENGINEERING, CIVIL
Zheng Li;Xiaohui Yuan;Bifan Sun;Yuting Xia;Tingting Jiang;Chao Wang;Wentao Ma;Shuai Yang;Siyuan Liu;Lichuan Gu
{"title":"MtpNet:多任务全景驾驶感知网络","authors":"Zheng Li;Xiaohui Yuan;Bifan Sun;Yuting Xia;Tingting Jiang;Chao Wang;Wentao Ma;Shuai Yang;Siyuan Liu;Lichuan Gu","doi":"10.1109/TITS.2025.3558467","DOIUrl":null,"url":null,"abstract":"Panoramic driving systems are crucial for autonomous driving but face challenges in real-time performance and reliability. This paper proposes an end-to-end, multi-tasking MtpNet that reduces latency and enhances detection accuracy. The convolution was upgraded using the Efficient Layer Aggregation Network, and precise multi-task loss functions and more effective training strategies were devised. Our results demonstrate improved performance in small object detection, partial occlusion handling, and drivable area segmentation. The recall of the traffic object detection is 1.3% higher than that of the state-of-the-art model, reaching 94.1%, the mAP50 is 6.4% higher, reaching 89.8%, and the mIoU of the drivable area segmentation is 2.7% higher, reaching 95.9%. Additionally, the accuracy of lane detection reached 88.7%. The visual comparison using three datasets TuSimple, CityScapes, and CULane demonstrates that MtpNet has good detection segmentation and strong robustness under various conditions. Codes are available at <uri>https://github.com/ErLinErYi/mtpnet</uri>","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 6","pages":"7600-7609"},"PeriodicalIF":8.4000,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MtpNet: Multi-Task Panoptic Driving Perception Network\",\"authors\":\"Zheng Li;Xiaohui Yuan;Bifan Sun;Yuting Xia;Tingting Jiang;Chao Wang;Wentao Ma;Shuai Yang;Siyuan Liu;Lichuan Gu\",\"doi\":\"10.1109/TITS.2025.3558467\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Panoramic driving systems are crucial for autonomous driving but face challenges in real-time performance and reliability. This paper proposes an end-to-end, multi-tasking MtpNet that reduces latency and enhances detection accuracy. The convolution was upgraded using the Efficient Layer Aggregation Network, and precise multi-task loss functions and more effective training strategies were devised. Our results demonstrate improved performance in small object detection, partial occlusion handling, and drivable area segmentation. The recall of the traffic object detection is 1.3% higher than that of the state-of-the-art model, reaching 94.1%, the mAP50 is 6.4% higher, reaching 89.8%, and the mIoU of the drivable area segmentation is 2.7% higher, reaching 95.9%. Additionally, the accuracy of lane detection reached 88.7%. The visual comparison using three datasets TuSimple, CityScapes, and CULane demonstrates that MtpNet has good detection segmentation and strong robustness under various conditions. Codes are available at <uri>https://github.com/ErLinErYi/mtpnet</uri>\",\"PeriodicalId\":13416,\"journal\":{\"name\":\"IEEE Transactions on Intelligent Transportation Systems\",\"volume\":\"26 6\",\"pages\":\"7600-7609\"},\"PeriodicalIF\":8.4000,\"publicationDate\":\"2025-04-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Intelligent Transportation Systems\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10967017/\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Intelligent Transportation Systems","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10967017/","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0

摘要

全景驾驶系统对自动驾驶至关重要,但在实时性和可靠性方面面临挑战。本文提出了一个端到端、多任务的MtpNet,减少了延迟,提高了检测精度。利用高效层聚合网络对卷积进行升级,设计出精确的多任务损失函数和更有效的训练策略。我们的结果表明,在小目标检测、局部遮挡处理和可驾驶区域分割方面,性能得到了改善。交通目标检测的召回率比最先进模型提高1.3%,达到94.1%,mAP50提高6.4%,达到89.8%,可驾驶区域分割的mIoU提高2.7%,达到95.9%。车道检测准确率达到88.7%。通过对TuSimple、cityscape和CULane三个数据集的视觉对比表明,MtpNet在各种条件下都具有良好的检测分割和较强的鲁棒性。代码可在https://github.com/ErLinErYi/mtpnet上获得
本文章由计算机程序翻译,如有差异,请以英文原文为准。
MtpNet: Multi-Task Panoptic Driving Perception Network
Panoramic driving systems are crucial for autonomous driving but face challenges in real-time performance and reliability. This paper proposes an end-to-end, multi-tasking MtpNet that reduces latency and enhances detection accuracy. The convolution was upgraded using the Efficient Layer Aggregation Network, and precise multi-task loss functions and more effective training strategies were devised. Our results demonstrate improved performance in small object detection, partial occlusion handling, and drivable area segmentation. The recall of the traffic object detection is 1.3% higher than that of the state-of-the-art model, reaching 94.1%, the mAP50 is 6.4% higher, reaching 89.8%, and the mIoU of the drivable area segmentation is 2.7% higher, reaching 95.9%. Additionally, the accuracy of lane detection reached 88.7%. The visual comparison using three datasets TuSimple, CityScapes, and CULane demonstrates that MtpNet has good detection segmentation and strong robustness under various conditions. Codes are available at https://github.com/ErLinErYi/mtpnet
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Transactions on Intelligent Transportation Systems
IEEE Transactions on Intelligent Transportation Systems 工程技术-工程:电子与电气
CiteScore
14.80
自引率
12.90%
发文量
1872
审稿时长
7.5 months
期刊介绍: The theoretical, experimental and operational aspects of electrical and electronics engineering and information technologies as applied to Intelligent Transportation Systems (ITS). Intelligent Transportation Systems are defined as those systems utilizing synergistic technologies and systems engineering concepts to develop and improve transportation systems of all kinds. The scope of this interdisciplinary activity includes the promotion, consolidation and coordination of ITS technical activities among IEEE entities, and providing a focus for cooperative activities, both internally and externally.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信