检索结果-内蒙古大学图书馆

IEEE Southwest Symposium on Image Analysis and Interpretation

作者： Adrian Kretz Rudolf Mester Visual Sensorics and Information Processing Goethe University Frankfurt am Main Germany Norwegian Open AI Lab NTNU Trondheim Norway

ISBN: (数字)9781728157450

ISBN: (纸本)9781728157467

Recently, Siamese neural networks have been employed to build several high performance object trackers capable of operating in real time. To further improve the tracking performance, one can train one network on the tracking task and another network on the task of object classification. One can then use the feature representations of both networks to obtain a tracker which performs better than each network on its own. This approach, however, has the downside that two networks have to be evaluated instead of one, resulting in runtime degradation. We demonstrate that it is feasible to train one Siamese network on the tracking and the classifications tasks simultaneously. Specifically, we achieve a tracking performance similar to the performance of two networks trained on tracking and classification separately. Since our approach does not depend on two separate networks though, it allows one to improve the performance of a Siamese network tracker without any runtime penalty.

关键词： Feature extraction Task analysis Training Target tracking Network architecture Object tracking Runtime

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Depth Interpolation (STDI)

Spatio-Temporal Depth Interpolation (STDI)

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Ochs, Matthias Bradler, Henry Mester, Rudolf Visual Sensorics and Information Processing Lab Goethe University Frankfurt am Main Germany Computer Vision Laboratory ISY Linköping University Sweden

ISBN: (纸本)9781538644522

In the area of autonomous driving, sensing the environment is most important for self-localization and egomotion estimation. visual odometry/SLAM methods have proven capable to achieve good results, even in real-time applications by operating in a sparse mode. Running on a sequence, these methods need to continuously incorporate new features well distributed over the image. Therefore, the performance of these methods can be further improved, if they are supplied with coarse but dense initial depth information, that can be utilized at arbitrary sparse image positions. Previously triangulated depths and even high quality depth measurements of a LIDAR sensor are not suitable for this task, since they only provide a sparse depth map. To solve this issue, we introduce a novel interpolation method called Spatio-Temporal Depth Interpolation (STDI), which exploits spatial and temporal correlations of the data (e.g. sequences of sparse depth maps) to give a consistent dense output including associated uncertainties. STDI is a fused approach, which makes use of the most important components of a principal component analysis (PCA) (spatial information) and additionally is capable to re-use information of previously interpolated depth maps in a regression based approach (temporal information). We evaluate the quality of STDI on the KITTI visual odometry benchmark, where a sequence of extremely sparsely sampled depth maps (≈40 depth values) is densified and on the KITTI depth completion benchmark. The latter deals with the densification of sparse LIDAR input. Of course, our method is not limited to these applications and can be used for any densification of sparse sequential data which is expected to contain spatial and/or temporal correlations (e.g. initialization for dense optical flow methods based on a sparse measurement). © 2018 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

CNN-based multi-frame IMO detection from a monocular camera

CNN-based multi-frame IMO detection from a monocular camera

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Fanani, Nolang Ochs, Matthias Stürck, Alina Mester, Rudolf Visual Sensorics and Information Processing Lab Goethe University Frankfurt Am Main Germany Computer Vision Laboratory ISY Linköping University Sweden

ISBN: (纸本)9781538644522

This paper presents a method for detecting independently moving objects (IMOs) from a monocular camera mounted on a moving car. A CNN-based classifier is employed to generate IMO candidate patches;independent motion is detected by geometric criteria on keypoint trajectories in these patches. Instead of looking only at two consecutive frames, we analyze keypoints inside the IMO candidate patches through multi-frame epipolar consistency checks. The obtained motion labels (IMO/static) are then propagated over time using the combination of motion cues and appearance-based information of the IMO candidate patches. We evaluate the performance of our method on the KITTI dataset, focusing on sub-sequences containing IMOs. © 2018 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

CNN-based multi-frame IMO detection from a monocular camera

CNN-based multi-frame IMO detection from a monocular camera

引用

IEEE Intelligent Vehicles Symposium

作者： Nolang Fanani Matthias Ochs Alina Sturck Rudolf Mester Visual Sensorics & Information Processing Lab Goethe University

ISBN: (纸本)9781538644539

关键词： monocular camera International Maritime Organisation multiframe

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Depth Interpolation (STDI)

Spatio-Temporal Depth Interpolation (STDI)

引用

IEEE Intelligent Vehicles Symposium

作者： Matthias Ochs Henry Bradler Rudolf Mester Visual Sensorics & Information Processing Lab Goethe University Frankfurt am Main

ISBN: (纸本)9781538644539

In the area of autonomous driving, sensing the environment is most important for self-localization and egomotion estimation. visual odometry/SLAM methods have proven capable to achieve good results, even in real-time applications by operating in a sparse mode. Running on a sequence, these methods need to continuously incorporate new features well distributed over the image. Therefore, the performance of these methods can be further improved, if they are supplied with coarse but dense initial depth information, that can be utilized at arbitrary sparse image positions. Previously triangulated depths and even high quality depth measurements of a LIDAR sensor are not suitable for this task, since they only provide a sparse depth map. To solve this issue, we introduce a novel interpolation method called Spatio-Temporal Depth Interpolation (STDI), which exploits spatial and temporal correlations of the data (e.g. sequences of sparse depth maps) to give a consistent dense output including associated uncertainties. STDI is a fused approach, which makes use of the most important components of a principal component analysis (PCA) (spatial information) and additionally is capable to re-use information of previously interpolated depth maps in a regression based approach (temporal information). We evaluate the quality of STDI on the KITTI visual odometry benchmark, where a sequence of extremely sparsely sampled depth maps (≈ 40 depth values) is densified and on the KITTI depth completion benchmark. The latter deals with the densification of sparse LIDAR input. Of course, our method is not limited to these applications and can be used for any densification of sparse sequential data which is expected to contain spatial and/or temporal correlations (e.g. initialization for dense optical flow methods based on a sparse measurement).

关键词： STRUCTURE MAP Densification Interpolation time information real-time application program initialization Lidar Dense

来源：评论

学校读者我要写书评

暂无评论

Simulated autonomous driving in a realistic driving environment using deep reinforcement learning and a deterministic finite state machine

arXiv

引用

arXiv 2018年

作者： Klose, Patrick Mester, Rudolf Visual Sensorics & Information Processing Lab CS Dept. Goethe University Frankfurt Germany Norwegian University of Science and Technology Trondheim Norway

In the field of Autonomous Driving, the system controlling the vehicle can be seen as an agent acting in a complex environment and thus naturally fits into the modern framework of Reinforcement Learning. However, learning to drive can be a challenging task and current results are often restricted to simplified driving environments. To advance the field, we present a method to adaptively restrict the action space of the agent according to its current driving situation and show that it can be used to swiftly learn to drive in a realistic environment based on the Deep Q-Network algorithm. Copyright © 2018, The Authors. All rights reserved.

关键词： Automobile drivers

来源：评论

学校读者我要写书评

暂无评论

The precision of triangulation in monocular visual odometry

The precision of triangulation in monocular visual odometry

引用

IEEE Southwest Symposium on Image Analysis and Interpretation

作者： Nolang Fanani Rudolf Mester Visual Sensorics & Information Processing Lab Goethe University Frankfurt/M. Germany Computer Vision Laboratory ISY Linköping University Sweden

We analyze the depth reconstruction precision and sensitivity of two-frame triangulation for the case of general motion, and focus on the case of monocular visual odometry, that is: a single camera looking mostly in the direction of motion. The results confirm intuitive assumptions about the limited triangulation precision close to the focus of expansion.

关键词： Cameras Three-dimensional displays Two dimensional displays Sensitivity Meters visual odometry Geometry

来源：评论

学校读者我要写书评

暂无评论

Multimodal Scale Estimation for Monocular visual Odometry

Multimodal Scale Estimation for Monocular Visual Odometry

引用

IEEE Intelligent Vehicles Symposium

作者： Nolang Fanani Alina Sturck Marc Barnada Rudolf Mester Visual Sensorics & Information Processing Lab Goethe University Frankfurt am Main Germany

ISBN: (纸本)9781509048052

Monocular visual odometry/SLAM requires the ability to deal with the scale ambiguity problem, or equivalently to transform the estimated unscaled poses into correctly scaled poses. While propagating the scale from frame to frame is possible, it is very prone to the scale drift effect. We address the problem of monocular scale estimation by proposing a multimodal mechanism of prediction, classification, and correction. Our scale correction scheme combines cues from both dense and sparse ground plane estimation;this makes the proposed method robust towards varying availability and distribution of trackable ground structure. Instead of optimizing the parameters of the ground plane related homography, we parametrize and optimize the underlying motion parameters directly. Furthermore, we employ classifiers to detect scale outliers based on various features (e.g. moments on residuals). We test our method on the challenging KITTI dataset and show that the proposed method is capable to provide scale estimates that are on par with current state-of-the-art monocular methods without using bundle adjustment or RANSAC.

关键词： Estimation Cameras Sparse matrices visualization Matrix decomposition Transmission line matrix methods Automobiles

来源：评论

学校读者我要写书评

暂无评论

Joint Epipolar Tracking (JET): Simultaneous optimization of epipolar geometry and feature correspondences

arXiv

引用

arXiv 2017年

作者： Bradler, Henry Ochs, Matthias Fanani, Nolang Mester, Rudolf Visual Sensorics & Information Processing Lab Goethe University Frankfurt Germany Computer Vision Laboratory ISY Linköping University Sweden

Traditionally, pose estimation is considered as a two step problem. First, feature correspondences are determined by direct comparison of image patches, or by associating feature descriptors. In a second step, the relative pose and the coordinates of corresponding points are estimated, most often by minimizing the reprojection error (RPE). RPE optimization is based on a loss function that is merely aware of the feature pixel positions but not of the underlying image intensities. In this paper, we propose a sparse direct method which introduces a loss function that allows to simultaneously optimize the unscaled relative pose, as well as the set of feature correspondences directly considering the image intensity values. Furthermore, we show how to integrate statistical prior information on the motion into the optimization process. This constructive inclusion of a Bayesian bias term is particularly efficient in application cases with a strongly predictable (short term) dynamic, e.g. in a driving scenario. In our experiments, we demonstrate that the ‘JET‘algorithm we propose outperforms the classical reprojection error optimization on two synthetic datasets and on the KITTI dataset. The JET algorithm runs in real-time on a single CPU thread. Copyright © 2017, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Learning rank reduced interpolation with principal component analysis

arXiv

引用

arXiv 2017年

作者： Ochs, Matthias Bradler, Henry Mester, Rudolf Visual Sensorics & Information Processing Lab Goethe University Frankfurt am Main Germany Computer Vision Laboratory ISY Linköping University Sweden

— In computer vision most iterative optimization algorithms, both sparse and dense, rely on a coarse and reliable dense initialization to bootstrap their optimization procedure. For example, dense optical flow algorithms profit massively in speed and robustness if they are initialized well in the basin of convergence of the used loss function. The same holds true for methods as sparse feature tracking when initial flow or depth information for new features at arbitrary positions is needed. This makes it extremely important to have techniques at hand that allow to obtain from only very few available measurements a dense but still approximative’sketch’ of a desired 2D structure (e.g. depth maps, optical flow, disparity maps, etc.). The 2D map is regarded as sample from a 2D random process. The method presented here exploits the complete information given by the principal component analysis (PCA) of that process, the principal basis and its prior distribution. The method is able to determine a dense reconstruction from sparse measurement. When facing situations with only very sparse measurements, typically the number of principal components is further reduced which results in a loss of expressiveness of the basis. We overcome this problem and inject prior knowledge in a maximum a posterior (MAP) approach. We test our approach on the KITTI and the virtual KITTI datasets and focus on the interpolation of depth maps for driving scenes. The evaluation of the results show good agreement to the ground truth and are clearly better than results of interpolation by the nearest neighbor method which disregards statistical information. Copyright © 2017, The Authors. All rights reserved.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：