帮助 关于我们

返回检索结果

平行点云: 虚实互动的点云生成与三维模型进化方法
Parallel Point Clouds: Point Clouds Generation and 3D Model Evolution via Virtual-real Interaction

查看参考文献54篇

田永林 1,2   沈宇 2,3   李强 2,3   王飞跃 2,4 *  
文摘 三维信息的提取在自动驾驶等智能交通场景中正发挥着越来越重要的作用,为了解决以激光雷达为主的深度传感器在数据采集方面面临的成本高、样本覆盖不全面等问题,本文提出了平行点云的框架.利用人工定义场景获取虚拟点云数据,通过计算实验训练三维模型,借助平行执行对模型性能进行测试,并将结果反馈至数据生成和模型训练过程.通过不断地迭代,使三维模型得到充分评估并不断进化.在平行点云的框架下,我们以三维目标检测为例,通过闭环迭代,构建了虚实结合的点云数据集,在无需人工标注的情况下,可达到标注数据训练模型精度的72%.
其他语种文摘 The extraction of 3D information is playing an increasingly important role in intelligent traffic scenes such as autonomous driving. In order to solve the problems faced by LiDAR sensor such as the high cost and incomplete coverage of possible scenarios, this paper proposes parallel point clouds and its framework. For parallel point clouds, virtual point clouds are obtained by building artiflcial scenes. Then 3D models are trained through computational experiments and tested by parallel execution. The evaluation results are fed back to the data generation and the training process of 3D models. Through continuous iteration, 3D models can be fully evaluated and updated. Under the framework of Parallel Point Clouds, we take the 3D object detection as an example and build a point clouds dataset in a closed-loop manner. Without human annotation, it can be used to effectively train the detection model which can achieve the 72% of the performance of model trained with annotated data.
来源 自动化学报 ,2020,46(12):2572-2582 【核心库】
DOI 10.16383/j.aas.c200800
关键词 平行点云 ; 虚实互动 ; 三维视觉模型 ; 三维目标检测
地址

1. 中国科学技术大学自动化系, 合肥, 230027  

2. 中国科学院自动化研究所, 复杂系统管理与控制国家重点实验室, 北京, 100190  

3. 中国科学院大学人工智能学院, 北京, 100049  

4. 青岛智能产业技术研究院, 青岛, 266000

语种 中文
文献类型 研究性论文
ISSN 0254-4156
学科 电子技术、通信技术;公路运输
基金 国家自然科学基金重点项目 ;  英特尔智能网联汽车大学合作研究中心项目(ICRI-IACV) ;  国家自然科学基金项目联合基金 ;  广州市智能网联汽车重大科技专项
文献收藏号 CSCD:6876131

参考文献 共 54 共3页

1.  He K M. Residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2016:770-778 CSCD被引 56 次    
2.  Huang G. Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017:2261-2269 CSCD被引 16 次    
3.  Ren S Q. Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the 2015 Annual Conference on Neural Information Processing Systems,2015:91-99 CSCD被引 1 次    
4.  Zhu Z. End-to-end flow correlation tracking with spatial-temporal attention. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018:548-557 CSCD被引 2 次    
5.  Shen T Y. Hierarchical fused model with deep learning and type-2 fuzzy learning for breast cancer diagnosis. IEEE Transactions on Fuzzy Systems,2020 CSCD被引 1 次    
6.  Shen T Y. Learning from adversarial medical images for X-ray breast mass segmentation. Computer Methods and Programs in Biomedicine,2019,180:105012 CSCD被引 5 次    
7.  Chen X Z. Multi-view 3D object detection network for autonomous driving. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017:6526-6534 CSCD被引 1 次    
8.  Wang C. Densefusion: 6D object pose estimation by iterative dense fusion. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2019:3343-3352 CSCD被引 1 次    
9.  Geiger A. Are we ready for autonomous driving? The KITTI vision benchmark suite. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition,2012:3354-3361 CSCD被引 33 次    
10.  Sun P. Scalability in perception for autonomous driving: Waymo open dataset. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2020:2443-2451 CSCD被引 2 次    
11.  Huang X Y. The apolloscape open dataset for autonomous driving and its application. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(10):2702-2719 CSCD被引 25 次    
12.  Wang Y. Pseudo-LiDAR from visual depth estimation: Bridging the gap in 3D object detection for autonomous driving. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2019:8437-8445 CSCD被引 1 次    
13.  Qian R. End-to-end pseudo-LiDAR for image-based 3D object detection. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2020:5880-5889 CSCD被引 1 次    
14.  Elmadawi K. End-to-end sensor modeling for LiDAR Point Cloud. Proceedings of the 2019 IEEE Intelligent Transportation Systems Conference (ITSC),2019:1619-1624 CSCD被引 1 次    
15.  Fang J. Augmented LiDAR simulator for autonomous driving. IEEE Robotics and Automation Letters,2020,5(2):1931-1938 CSCD被引 7 次    
16.  王飞跃. 平行系统方法与复杂系统的管理和控制. 控制与决策,2004,19(5):485-489,514 CSCD被引 157 次    
17.  Wang F Y. Parallel control and management for intelligent transportation systems: Concepts, architectures, and applications. IEEE Transactions on Intelligent Transportation Systems,2010,11(3):630-638 CSCD被引 122 次    
18.  王飞跃. 平行控制: 数据驱动的计算控制方法. 自动化学报,2013,39(4):293-302 CSCD被引 76 次    
19.  Guo Y L. Deep learning for 3D point clouds: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence,2020 CSCD被引 5 次    
20.  Su H. Multi-view convolutional neural networks for 3D shape recognition. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV),2015:945-953 CSCD被引 2 次    
引证文献 7 篇

1 王亚东 基于卷积神经网络的三维目标检测研究综述 模式识别与人工智能,2021,34(12):1103-1119
CSCD被引 8 次

2 李悄 采用稀疏3D卷积的单阶段点云三维目标检测方法 西安交通大学学报,2022,56(9):112-122
CSCD被引 5 次

显示所有7篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号