检索结果-内蒙古大学图书馆

22nd IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Abdelhamed, Abdelrahman Yim, Jonghwa Punnappurath, Abhijith Brown, Michael S. Choe, Jihwan Kim, Kihwan Samsung AI Ctr Toronto ON Canada Samsung Elect Suwon South Korea NCSOFT Seongnam Si South Korea

ISBN: (纸本)9781665409155

Most smartphones support the use of real-time camera filters to impart visual effects to captured images. Currently, such filters come preinstalled on-device or need to be downloaded and installed before use (e.g., Instagram filters). Recent work [24] proposed a method to extract a camera filter directly from an example photo that has already had a filter applied. The work in [24] focused only on the color and tonal aspects of the underlying filter. In this paper, we introduce a method to extract two spatially varying effects commonly used by on-device camera filters-namely, image vignetting and image grain. Specifically, we show how to extract the parameters for vignetting and image grain present in an example image and replicate these effects as an on-device filter. We use lightweight CNNs to estimate the filter parameters and employ efficient techniques-isotropic Gaussian filters and simplex noise-for regenerating the filters. Our design achieves a reasonable trade-off between efficiency and realism. We show that our method can extract vignetting and image grain filters from stylized photos and replicate the filters on captured images more faithfully, as compared to color and style transfer methods. Our method is significantly efficient and has been already deployed to millions of flagship smartphones.

关键词： Image color analysis Multimedia Web sites Neural networks filtering algorithms Cameras Information filters Visual effects

来源：评论

学校读者我要写书评

暂无评论

LiDAR-based Obstacle Detection and Avoidance for Autonomous Vehicles using Raspberry Pi 3B 13

LiDAR-based Obstacle Detection and Avoidance for Autonomous ...

引用

13th UK-Automatic-Control-Council (UKACC) International Conference on Control (CONTROL)

作者： Calcroft, Max Khan, Asiya Univ Plymouth Sch Engn Comp & Math SECaM Plymouth PL4 8AA Devon England Univ Plymouth SECaM Plymouth PL4 8AA Devon England

ISBN: (纸本)9781665452007

Autonomous vehicles are redefining the transport industry - obstacle detection and avoidance are key to their operation. A number of sensor technologies have been developed and trialled. This paper presents the implementation of a Hokuyo URG-04LX Light Detection And Ranging (LiDAR) sensor on an autonomous vehicle developed with a Raspberry Pi 3B microcontroller and demonstrates its effectiveness for object detection and avoidance in varying conditions. The LiDAR sensor was integrated with the Raspberry Pi 3B using Python on LUbuntu (lightweight version of Ubuntu) and Robot Operating System (ROS). Various scenarios with low light conditions, reflective surfaces at multiple angles, simple stopping tests and different motion paths at varying speeds were tested. All tests were run at 3.2 and 4mph speed. It was found that the LiDAR sensor performed well for basic object detection but did not respond well to reflective or dark surfaces. We further compared the LiDAR's performance with ultrasonic sensors and found that it outperformed ultrasonic sensors for stopping distances. Overall, the LiDAR acts as an effective sensor for the autonomous vehicle, showing its viability in detecting objects and acting as a small scale representation of autonomous technology.

关键词： Point cloud compression Industries Laser radar Microcontrollers Operating systems Object detection filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

On Phase Noise Compensation for OFDM Operation in 5G and Beyond

On Phase Noise Compensation for OFDM Operation in 5G and Bey...

引用

IEEE Wireless Communications and Networking Conference (IEEE WCNC)

作者： Afshang, Mehrnaz Hui, Dennis Cheng, Jung-Fu (Thomas) Grant, Stephen Ericsson Santa Clara CA 95054 USA

ISBN: (纸本)9781665442664

In OFDM transmission system, phase noise (PN) caused by non-ideal oscillator induces inter carrier interference (ICI), which is problematic for operation of high order modulation, especially in mm-wave frequency bands. This paper develops two low-complexity and effective ICI compensation algorithms: (i) Direct de-ICI filtering approach which is agnostic to the exact locations of phase tracking reference signal (PTRS), and hence it can readily operate with existing 3GPP Rel-15 PTRS and (ii) Circulant ICI filter approximation which exploits the circulant matrix constructed by a PTRS sequence with cyclic structure to reduce the complexity of ICI compensation algorithm. Our results reveal that both algorithms significantly reduce the negative impact of phase noise on the link performance.

关键词： Phase noise filtering Phase modulation OFDM Interference filtering algorithms Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Automatic Step Detection of Tandem Gait Test in Patients with Vestibular Hypofunction Using Wearable Sensors

Automatic Step Detection of Tandem Gait Test in Patients wit...

引用

14th Annual Summit and Conference of the Asia-Pacific-Signal-and-Information-Processing-Association (APSIPA ASC)

作者： Huang, Yi-Ju Liu, Chien-Pin Ting, Kuan-Chung Hsieh, Chia-Yeh Liu, Kai-Chun Chan, Chia-Tai Natl Yang Ming Chiao Tung Univ Dept Biomed Engn Hsinchu Taiwan Taipei Vet Gen Hosp Dept Otolaryngol Head & Neck Surg Taipei Taiwan Fu Jen Catholic Univ Bachelors Program Med Informat & Innovat Applica New Taipei Taiwan Acad Sinica Res Ctr Informat Technol Innovat Taipei Taiwan

ISBN: (数字)9786165904773

ISBN: (纸本)9786165904773

The tandem gait test is a common examination in testing individuals with possible neurologic diseases, such as motor neurons or cortex problems, and vestibular disorders. A reliable step detection method is essential to capture these step-based features to assess vestibular hypofunction. However, most studies still relied on manual labeling or a simple threshold-based peak detection approach to obtain step information. These methods often suffer issues in time consuming and reliability. This study proposes an automatic and accurate step detection algorithm for the tandem gait test using a dynamic threshold. This technique could filter noises and adapt to individual step patterns. The proposed algorithm was validated on a dataset including 15 healthy subjects and 62 patients with peripheral vestibular disorders. The results show that using the developed step detection approach with the shank-worn sensor has the best performance, which achieves 99.8%, 100%, 99.8% and 99.9% in accuracy, recall, precision and F1-score, respectively.

关键词： Heuristic algorithms Neurons Manuals filtering algorithms Information filters Reliability Labeling

来源：评论

学校读者我要写书评

暂无评论

引用

4th World Robot Conference (WRC) / Symposium on Advanced Robotics and Automation (SARA)

作者： Zhang, Xiaowen Yuan, Shuai Luan, Fangjun Lv, Jiaqi Liu, Guifu Shenyang Jianzhu Univ Sch Elect & Control Engn Shenyang 110168 Peoples R China Shenyang Jianzhu Univ Sch Comp Sci & Engn Shenyang 110168 Peoples R China

ISBN: (数字)9781665463690

ISBN: (纸本)9781665463690

Ship detection has always been an important and challenging task. Small ship targets and complex backgrounds in optical remote sensing images can both lead to false alarms and missed alarms in detection. The YOLO series algorithms have been widely used in optical remote sensing ship target detection, which has the advantage of fast detection speed. However, the YOLO series algorithms have poor detection performance when facing small targets. Therefore, we propose a new algorithm, SMMA-YOLOv5, which can improve the model detection accuracy without significantly increasing the model size. We first introduce a self-attention mechanism to replace some of the convolutional layers to capture the global information of the feature map. Second, we integrate an efficient channel attention (ECA) model to the self-attention mechanism to enable information interaction between channels without adding additional computational overhead. Furthermore, we propose a new similarity mask structure to filter out the invalid regions in the feature map based on the elements' similarity. The experiments on the public MASATI ship dataset indicate that SMMA-YOLOv5 improves Precision by 3.9%, Recall by 5.3%, and AP by 5.4%, and prove the effectiveness of the algorithm while maintaining real-time detection.

关键词： Optical filters Computational modeling Object detection filtering algorithms Optical imaging Information filters Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Multiobjective Optimization Approach for Air Traffic Flow Management for Airspace Safety Enhancement

A Multiobjective Optimization Approach for Air Traffic Flow ...

引用

IEEE Congress on Evolutionary Computation (CEC)

作者： Cai, Qing Ang, Haojie Alam, Sameer Nanyang Technol Univ Sch Mech & Aerosp Engn Air Traff Management Res Inst Singapore 639798 Singapore

ISBN: (数字)9781665467087

ISBN: (纸本)9781665467087

This work aims to enhance the safety of air traffic in a procedural airspace by air traffic flow management (ATFM) without compromizing air traffic demand. In civil aviation, collision risk is an important indicator for air traffic safety assessment. In this work, we propose a generic ATFM framework based on multiobjective optimization for reducing lateral collision risk of the traffic in a given procedural airspace. T he proposed framework aims to optimize the flight level assignment for a given set of flight plans such that the lateral collision risk can be reduced. To achieve this goal, we formulate an optimization problem containing two partially conflicting objective functions. We then adopt three well-known evolutionary algorithms, i.e., MODPSO, NSGA-II, and MOEA/D to solve the optimization problem. We specially design some of the operators of those algorithms to make them suitable for the optimization problem. We merge the solutions yielded by those three algorithms and filter out the final Pareto solutions. We carry out a case study on the procedural airspace of Singapore flight information region (FIR) with respect to twelve daily traffic data selected from t he real traffic data for December 2019. Experiment results demonstrates that the lateral occupancy which is the key contributor to lateral risk can be reduced by 10.65% to 93.05% at a strategic planning level. This research contribute to strategic flight p tanning by assigning flight levels that may reduce the risk of collision in procedural airspace.

关键词： Finite impulse response filters Atmospheric modeling Evolutionary computation Strategic planning filtering algorithms Search problems Information filters

来源：评论

学校读者我要写书评

暂无评论

SIMULTANEOUS SMOOTHING AND SHARPENING USING iWGIF 29

SIMULTANEOUS SMOOTHING AND SHARPENING USING iWGIF

引用

IEEE International Conference on Image Processing (ICIP)

作者： Li, Zhengguo Zheng, Jinghong Senthilnath, J. Inst Infocomm Res 1 Fusionopolis Way Singapore Singapore

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Smoothing and sharpening are two fundamental operations in image processing, and they are usually conducted separately. In this paper, an improved weighted guided image filter (iWGIF) is first proposed to enhance existing guided filters. A content adaptive smoothing and sharpening (CASS) algorithm is then presented by using coefficients of the iWGIF intelligently. A simple despeckling algorithm is finally introduced to simultaneously smoothen homogeneous regions and preserve heterogeneous regions of synthetic-aperture radar images. Experimental results validate all the proposed algorithms.

关键词： Smoothing methods Image processing Radar filtering algorithms Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Gravity Matching Algorithm Based on Backtracking for Small Range Adaptation Area

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Zhao, Shengwu Xiao, Xuan Pang, Xuan Wang, Yu Deng, Zhihong Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Beijing Inst Technol Natl Key Lab Intelligent Control & Decis Complex S Beijing 100081 Peoples R China

The existing gravity matching algorithms are affected either by gravity measurement error or by the initial position of inertial navigation system (INS). Filter algorithms can solve the problem under the condition of enough measurement data. However, the range of most adaptation areas is small. Due to the long matching period, the available measurement data may be not enough to make the filter converge. Aiming to obtain high-precision position information in the small range adaptation area, backtracking strategies that combine the filter algorithm are first proposed in this article. Next, the observability of gravity-aided navigation system is also analyzed based on graph analysis. Furthermore, the reverse error equations are obtained by analogy corresponding to the reverse solution, and the relationship between forward navigation and reverse navigation is also given. The results of simulation and marine experiment show that the proposed algorithm is superior to the existing gravity matching algorithms, and has a high positioning accuracy in the small range adaptation area.

关键词： Backtracking Navigation Gravity filtering algorithms Underwater vehicles Switches Estimation Backtracking navigation gravity-aided inertial navigation system (GAINS) reverse navigation underwater navigation

来源：评论

学校读者我要写书评

暂无评论

A Fusion Algorithm Based on a Constant Velocity Model for Improving the Measurement of Saccade Parameters with Electrooculography

引用

SENSORS 2024年第2期24卷 540页

作者： Gunawardane, Palpolage Don Shehan Hiroshan MacNeil, Raymond Robert Zhao, Leo Enns, James Theodore de Silva, Clarence Wilfred Chiao, Mu Univ British Columbia Dept Mech Engn Vancouver BC V6T 1Z4 Canada Univ British Columbia Dept Psychol Vancouver BC V6T 1Z4 Canada

Electrooculography (EOG) serves as a widely employed technique for tracking saccadic eye movements in a diverse array of applications. These encompass the identification of various medical conditions and the development of interfaces facilitating human-computer interaction. Nonetheless, EOG signals are often met with skepticism due to the presence of multiple sources of noise interference. These sources include electroencephalography, electromyography linked to facial and extraocular muscle activity, electrical noise, signal artifacts, skin-electrode drifts, impedance fluctuations over time, and a host of associated challenges. Traditional methods of addressing these issues, such as bandpass filtering, have been frequently utilized to overcome these challenges but have the associated drawback of altering the inherent characteristics of EOG signals, encompassing their shape, magnitude, peak velocity, and duration, all of which are pivotal parameters in research studies. In prior work, several model-based adaptive denoising strategies have been introduced, incorporating mechanical and electrical model-based state estimators. However, these approaches are really complex and rely on brain and neural control models that have difficulty processing EOG signals in real time. In this present investigation, we introduce a real-time denoising method grounded in a constant velocity model, adopting a physics-based model-oriented approach. This approach is underpinned by the assumption that there exists a consistent rate of change in the cornea-retinal potential during saccadic movements. Empirical findings reveal that this approach remarkably preserves EOG saccade signals, resulting in a substantial enhancement of up to 29% in signal preservation during the denoising process when compared to alternative techniques, such as bandpass filters, constant acceleration models, and model-based fusion methods.

关键词： biomedical signal processing corneo-retinal potential electrooculography filtering algorithms eye tracking Kalman filters saccades

来源：评论

学校读者我要写书评

暂无评论

Bamboo Filters: Make Resizing Smooth 38

Bamboo Filters: Make Resizing Smooth

引用

38th IEEE International Conference on Data Engineering (ICDE)

作者： Wang, Hancheng Dai, Haipeng Li, Meng Yu, Jun Gu, Rong Zheng, Jiaqi Chen, Guihai Nanjing Univ State Key Lab Novel Software Technol Nanjing 210023 Jiangsu Peoples R China

ISBN: (数字)9781665408837

ISBN: (纸本)9781665408837

The approximate membership query (AMQ) data structure is a kind of space-efficient probabilistic data structure. It can approximately indicate whether an element exists in a set. The AMQ data structure has been widely used in database indexing, network security, IoT applications, etc. Resizing is an extensively utilized operation of the AMQ data structure, but it can lead to system performance degradation. We summarize two main problems that lead to such degradation. Specifically, one of them is that the resizing operation can block other operations, while the other is that the performance of AMQ structures will deteriorate after multiple resizing operations. However, existing related work cannot alleviate both of them. Therefore, we propose a novel AMQ data structure called bamboo filter, which can alleviate the two problems simultaneously. Bamboo filters can insert, search and delete an element in constant time. Moreover, bamboo filters can dynamically resize in a fine-grained way according to the number of contained elements. Experimental results show that bamboo filters significantly outperform state-of-the-art resizable AMQ data structures in insertion, lookup, and deletion operations. For example, bamboo filters achieve 2.46x lookup throughput of the dynamic cuckoo filter, on average.

关键词： Degradation Maximum likelihood detection System performance Nonlinear filters filtering algorithms Fingerprint recognition Data structures

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：