多任务学习以及摄像机定位和物体检测之间的联合改进

IF 17.3 3区 计算机科学 Q1 COMPUTER SCIENCE, SOFTWARE ENGINEERING
Junyi Wang, Yue Qi
{"title":"多任务学习以及摄像机定位和物体检测之间的联合改进","authors":"Junyi Wang, Yue Qi","doi":"10.1007/s41095-022-0319-z","DOIUrl":null,"url":null,"abstract":"<p>Visual localization and object detection both play important roles in various tasks. In many indoor application scenarios where some detected objects have fixed positions, the two techniques work closely together. However, few researchers consider these two tasks simultaneously, because of a lack of datasets and the little attention paid to such environments. In this paper, we explore multi-task network design and joint refinement of detection and localization. To address the dataset problem, we construct a medium indoor scene of an aviation exhibition hall through a semi-automatic process. The dataset provides localization and detection information, and is publicly available at https://drive.google.com/drive/folders/1U28zkuN4_I0dbzkqyIAKlAl5k9oUK0jI?usp=sharing for benchmarking localization and object detection tasks. Targeting this dataset, we have designed a multi-task network, JLDNet, based on YOLO v3, that outputs a target point cloud and object bounding boxes. For dynamic environments, the detection branch also promotes the perception of dynamics. JLDNet includes image feature learning, point feature learning, feature fusion, detection construction, and point cloud regression. Moreover, object-level bundle adjustment is used to further improve localization and detection accuracy. To test JLDNet and compare it to other methods, we have conducted experiments on 7 static scenes, our constructed dataset, and the dynamic TUM RGB-D and Bonn datasets. Our results show state-of-the-art accuracy for both tasks, and the benefit of jointly working on both tasks is demonstrated.\n</p>","PeriodicalId":37301,"journal":{"name":"Computational Visual Media","volume":"4 1","pages":""},"PeriodicalIF":17.3000,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-task learning and joint refinement between camera localization and object detection\",\"authors\":\"Junyi Wang, Yue Qi\",\"doi\":\"10.1007/s41095-022-0319-z\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Visual localization and object detection both play important roles in various tasks. In many indoor application scenarios where some detected objects have fixed positions, the two techniques work closely together. However, few researchers consider these two tasks simultaneously, because of a lack of datasets and the little attention paid to such environments. In this paper, we explore multi-task network design and joint refinement of detection and localization. To address the dataset problem, we construct a medium indoor scene of an aviation exhibition hall through a semi-automatic process. The dataset provides localization and detection information, and is publicly available at https://drive.google.com/drive/folders/1U28zkuN4_I0dbzkqyIAKlAl5k9oUK0jI?usp=sharing for benchmarking localization and object detection tasks. Targeting this dataset, we have designed a multi-task network, JLDNet, based on YOLO v3, that outputs a target point cloud and object bounding boxes. For dynamic environments, the detection branch also promotes the perception of dynamics. JLDNet includes image feature learning, point feature learning, feature fusion, detection construction, and point cloud regression. Moreover, object-level bundle adjustment is used to further improve localization and detection accuracy. To test JLDNet and compare it to other methods, we have conducted experiments on 7 static scenes, our constructed dataset, and the dynamic TUM RGB-D and Bonn datasets. Our results show state-of-the-art accuracy for both tasks, and the benefit of jointly working on both tasks is demonstrated.\\n</p>\",\"PeriodicalId\":37301,\"journal\":{\"name\":\"Computational Visual Media\",\"volume\":\"4 1\",\"pages\":\"\"},\"PeriodicalIF\":17.3000,\"publicationDate\":\"2024-02-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computational Visual Media\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1007/s41095-022-0319-z\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computational Visual Media","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s41095-022-0319-z","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0

摘要

视觉定位和物体检测在各种任务中都发挥着重要作用。在许多室内应用场景中,一些被检测物体的位置是固定的,因此这两种技术可以密切配合。然而,由于缺乏数据集和对此类环境的关注度不高,很少有研究人员同时考虑这两项任务。在本文中,我们探讨了多任务网络设计以及检测和定位的联合改进。为了解决数据集问题,我们通过半自动流程构建了一个航空展览馆的中等室内场景。该数据集提供了定位和检测信息,可通过 https://drive.google.com/drive/folders/1U28zkuN4_I0dbzkqyIAKlAl5k9oUK0jI?usp=sharing 公开获取,用于定位和物体检测任务的基准测试。针对该数据集,我们设计了基于 YOLO v3 的多任务网络 JLDNet,该网络可输出目标点云和物体边界框。对于动态环境,检测分支还能促进动态感知。JLDNet 包括图像特征学习、点特征学习、特征融合、检测构建和点云回归。此外,还使用了对象级束调整来进一步提高定位和检测精度。为了测试 JLDNet 并将其与其他方法进行比较,我们在 7 个静态场景、我们构建的数据集以及动态 TUM RGB-D 和波恩数据集上进行了实验。我们的结果表明,这两项任务都达到了最先进的精度,同时也证明了联合完成这两项任务的优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Multi-task learning and joint refinement between camera localization and object detection

Multi-task learning and joint refinement between camera localization and object detection

Visual localization and object detection both play important roles in various tasks. In many indoor application scenarios where some detected objects have fixed positions, the two techniques work closely together. However, few researchers consider these two tasks simultaneously, because of a lack of datasets and the little attention paid to such environments. In this paper, we explore multi-task network design and joint refinement of detection and localization. To address the dataset problem, we construct a medium indoor scene of an aviation exhibition hall through a semi-automatic process. The dataset provides localization and detection information, and is publicly available at https://drive.google.com/drive/folders/1U28zkuN4_I0dbzkqyIAKlAl5k9oUK0jI?usp=sharing for benchmarking localization and object detection tasks. Targeting this dataset, we have designed a multi-task network, JLDNet, based on YOLO v3, that outputs a target point cloud and object bounding boxes. For dynamic environments, the detection branch also promotes the perception of dynamics. JLDNet includes image feature learning, point feature learning, feature fusion, detection construction, and point cloud regression. Moreover, object-level bundle adjustment is used to further improve localization and detection accuracy. To test JLDNet and compare it to other methods, we have conducted experiments on 7 static scenes, our constructed dataset, and the dynamic TUM RGB-D and Bonn datasets. Our results show state-of-the-art accuracy for both tasks, and the benefit of jointly working on both tasks is demonstrated.

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
Computational Visual Media
Computational Visual Media Computer Science-Computer Graphics and Computer-Aided Design
CiteScore
16.90
自引率
5.80%
发文量
243
审稿时长
6 weeks
期刊介绍: Computational Visual Media is a peer-reviewed open access journal. It publishes original high-quality research papers and significant review articles on novel ideas, methods, and systems relevant to visual media. Computational Visual Media publishes articles that focus on, but are not limited to, the following areas: • Editing and composition of visual media • Geometric computing for images and video • Geometry modeling and processing • Machine learning for visual media • Physically based animation • Realistic rendering • Recognition and understanding of visual media • Visual computing for robotics • Visualization and visual analytics Other interdisciplinary research into visual media that combines aspects of computer graphics, computer vision, image and video processing, geometric computing, and machine learning is also within the journal''s scope. This is an open access journal, published quarterly by Tsinghua University Press and Springer. The open access fees (article-processing charges) are fully sponsored by Tsinghua University, China. Authors can publish in the journal without any additional charges.
×
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:481959085
Book学术官方微信