检索结果-内蒙古大学图书馆

An innovational GNN-based Urban Traffic-flow measuring approach using dynamic vision sensor

MEASUREMENT 2025年 252卷

作者： Qian, Cheng Tang, Chengkang Li, Chuang Zhao, Wenjun Tang, Rongnian Hainan Univ 58 Remin St Haikou 57000 Hainan Peoples R China

Smart urban mobility is an important approach for meeting the rapid increasing demanding of the urban populations. Urban mobility problems could be more effectively resolved by artificial intelligent techniques. Traditional visual sensors and visual algorithms suffer from low dynamic response and high computational cost. This paper proposes an Event-camera Traffic-flow Measuring Graph Neural Network (ETM-GNN) method for traffic flow detection, which features low sampling latency and sparse data sampling characteristics. An optimized proximity search strategy is firstly developed for event-data preprocessing to construct an event graph, which is then fed into the proposed graph-based neural network for traffic detection. An innovational graph convolution block is developed by applying layer normalization instead of batch normalization for sequential event-data. The overall detection accuracy of the proposed approach reached as high as 85.62%, with equivalent event frame rate of 40 frames per second on average. The proposed method can be further applied to other areas where high dynamical object detection is required.

关键词： Traffic flow measurement dynamic vision sensor Smart city

来源：评论

学校读者我要写书评

暂无评论

dynamic vision sensor for Low Power Applications

Dynamic Vision Sensor for Low Power Applications

引用

18th IEEE International Symposium on Consumer Electronics (ISCE)

作者： Berner, R. Lichtsteiner, P. Delbruck, T. Kim, J. Lee, K. Lee, J. Park, K. Kim, T. Ryu, H. Univ Zurich Inst Neuroinformat Zurich Switzerland Swiss Fed Inst Technol Zurich Switzerland Samsung Elect SAIT Suwon South Korea Samsung Elect SLSI Suwon South Korea

ISBN: (纸本)9781479945917

This paper presents the design of a dynamic vision sensor for mobile applications. The sensor features a standby mode with less than 250uW of power dissipation. The sensor changes operation mode between standby and normal operation itself depending on input activity. The power consumption in normal operation mode is typically 500uW and activity dependent. The sensor design is implemented in a 90nm backside illumination process with a pixel-array size of 1.44mm by 1.44mm.

关键词： dynamic vision sensor gesture tracking mobile low power

来源：评论

学校读者我要写书评

暂无评论

dynamic vision sensor datasets in the maritime domain 3

Dynamic vision sensor datasets in the maritime domain

引用

Conference on Artificial Intelligence and Machine Learning in Defense Applications III Held as Part of SPIE Security+Defence Conference

作者： Rodriguez, Jacob A. Mauger, Justin Parameswaran, Shibin Zeller-Townson, Riley Cauble, Galen Naval Informat Warfare Ctr Pacific 53560 Hull St San Diego CA 92152 USA

ISBN: (数字)9781510645851

ISBN: (纸本)9781510645851;9781510645844

Event cameras utilize novel imaging sensors patterned after visual pathways in the brain that are responsive to low contrast, transient events. The pixels of dynamic vision sensors (DVS) react independently and asynchronously to changes in light intensity, creating a stream of time-stamped events encoding the pixels' (x, y) location in the sensor array and the sign of the brightness change. In contrast with conventional cameras that sample pixels at a fixed rate, DVS pixels output only when the change in intensity has surpassed a set threshold, leading to reduced power consumption in scenes with little motion. Compared to conventional CMOS imaging pixels, DVS pixels have high dynamic range, low latency, and low motion blur;these characteristics make event cameras uniquely qualified for surveillance applications in maritime environments. Such an application of DVS presents the need for automated object recognition and tracking algorithms that process event data. Due to the fundamentally different nature of the output relative to conventional cameras, traditional methods of machine learning for computer vision cannot be directly applied. Anticipating this need, this work details collection of a maritime event dataset capturing moving objects including sail boats, motorboats, and large ships to develop detection and tracking algorithms. The data was collected with multiple lenses and captured in various states of movement to understand how such modifications and environments can affect the algorithms developed for ship detection and tracking. We will describe the dataset, effects of hardware settings and lighting conditions, and how sensor movement contributed to the quality of the event data recorded.

关键词： dynamic vision sensor event camera sensor dataset port surveillance maritime vessel

来源：评论

学校读者我要写书评

暂无评论

Denoising for dynamic vision sensor Based on Augmented Spatiotemporal Correlation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2023年第9期33卷 4812-4824页

作者： Xu, Ninghui Wang, Lihui Zhao, Jiajia Yao, Zhiting Southeast Univ Sch Instrument Sci & Engn Key Lab Microinertial Instrument & Adv Nav Technol Minist Educ Nanjing 210096 Peoples R China Sci & Technol Complex Syst Control & Intelligent A Beijing 100074 Peoples R China

To effectively denoise the output events of dynamic vision sensor (DVS) in real-time, a denoising method based on augmented spatiotemporal correlation is proposed. In addition, this paper also presents a novel method to evaluate the performance of event denoising. By classifying the events and noise based on their spatiotemporal properties, we use the dynamic response characteristics of DVS under different cases to augment the spatiotemporal correlation, and construct two event filters to process different kinds of events. To benchmark event denoising, we exploit the low-latency of DVS to temporally synchronize raw event stream through motion compensation and obtain the ideal response probability of DVS to quantify the plausibility of events and measure the denoising accuracy. Experiments in various scenes validate that the denoising method is effective at reducing noise with high accuracy and little computational cost, which significantly outperforms the state-of-the-art methods. Moreover, the evaluation method can quantify the denoising accuracy and benchmark different denoising methods objectively and comprehensively.

关键词： Voltage control Noise reduction Spatiotemporal phenomena Correlation Transient analysis Real-time systems Low latency communication Denoising denoising evaluation dynamic vision sensor event stream noise filter neuromorphic sensor

来源：评论

学校读者我要写书评

暂无评论

Analysis of Input-Dependent Noise in Self-Timed Reset dynamic vision sensor and Its Impact on Data Quality

引用

IEEE sensorS JOURNAL 2019年第15期19卷 6240-6250页

作者： Xu, Jiangtao Zou, Jiawei Gao, Zhiyuan Ma, Jianguo Tianjin Univ Sch Microelect Tianjin Key Lab Imaging & Sensing Microelect Technol Tianjin 300072 Peoples R China Guangdong Univ Technol Sch Comp Guangzhou 510006 Guangdong Peoples R China

Threshold temporal contrast (TTC), as a key feature of event-based signal encoding scheme, always fluctuates due to the various noise sources in circuit implementation. This fluctuation (or noise) distorts the information that each event contains, leading to the data quality degeneration. To avoid the errors that may appear in the subsequent signal processing, the degeneration needs to be within the limit demanded by the algorithm. Therefore, modeling the relationship between noise and data quality is important for the event-based hardware application. This paper focuses on analyzing the input-dependent noise on TTC caused by dark current and charge injection, which are labeled as delta Theta(dc) and delta Theta(ci) respectively, in self-timed reset dynamic vision sensors (STR-DVS), and evaluates the corresponding impacts on data quality. As for the theoretical derivation part, delta Theta(dc) is calculated using a logarithmic photocurrent-to-voltage model with dark current taken into account, and delta Theta(ci) is figured out with a three-phase on-to-off-transient switch model applied in differencing circuit. The data quality evaluation is implemented with event clusters generated from the nonideality-contained model, and the signal-to-distortion ratio (SDR) of the signal reconstructed by a perfect nonlinear recovery algorithm is taken as the metric. The analysis and simulation results are expected to offer a reference on assessing the applicability of STR-DVS for a specific application, or system parameter settings to make the data quality satisfy the requirement while using the sensor.

关键词： Data quality degeneration dynamic vision sensor input-dependent noise nonidealities self-timed reset

来源：评论

学校读者我要写书评

暂无评论

HashHeat: A hashing-based spatiotemporal filter for dynamic vision sensor

引用

INTEGRATION-THE VLSI JOURNAL 2021年 81卷 99-107页

作者： Guo, Shasha Kang, Ziyang Wang, Lei Zhang, Limeng Chen, Xiaofan Li, Shiming Xu, Weixia Natl Univ Def Technol Coll Comp Sci & Technol Changsha Peoples R China

Neuromorphic event-based dynamic vision sensors (DVS) have much faster sampling rates and a higher dynamic range than frame-based imagers. However, they are sensitive to background activity (BA) events that are unwanted. We propose HashHeat, a hashing-based spatiotemporal BA filter for DVS. It is the first spatiotemporal filter that doesn't scale with the DVS output size and doesn't store the 32-bits timestamps. We not only give the visual denoising effect of the filter but also use two metrics for quantitatively analyzing the filter's global performance and local performance respectively, where we introduce a novel metric for evaluating global performance. The experimental results show that HashHeat achieves similar global performance as baseline filters, but increases the signal to noise ratio by about 1.5x to nearly 5x compared with other baseline filters concerning the local performance. The hardware implementation enables HashHeat to output a labeled event every 10ns and meets the real-time requirement. And it can reduce the storage cost by 128x to 256x compared with baseline filters.

关键词： dynamic vision sensor Spatiotemporal filter Background activity noise Hash Memory reduction

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Undirected Graph Based Denoising Method for dynamic vision sensor

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2021年 23卷 1148-1159页

作者： Wu, Jinjian Ma, Chuanwei Li, Leida Dong, Weisheng Shi, Guangming Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China

dynamic vision sensor (DVS) is a new type of neuromorphic event-based sensor, which has an innate advantage in capturing fast-moving objects. Due to the interference of DVS hardware itself and many external factors, noise is unavoidable in the output of DVS. Different from frame/image with structural data, the output of DVS is in the form of address-event representation (AER), which means that the traditional denoising methods cannot be used for the output (i.e., event stream) of the DVS. In this paper, we propose a novel event stream denoising method based on probabilistic undirected graph model (PUGM). The motion of objects always shows a certain regularity/trajectory in space and time, which reflects the spatio-temporal correlation between effective events in the stream. Meanwhile, the event stream of DVS is composed by the effective events and random noise. Thus, a probabilistic undirected graph model is constructed to describe such priori knowledge (i.e., spatio-temporal correlation). The undirected graph model is factorized into the product of the cliques energy function, and the energy function is defined to obtain the complete expression of the joint probability distribution. Better denoising effect means a higher probability (lower energy), which means the denoising problem can be transfered into energy optimization problem. Thus, the iterated conditional modes (ICM) algorithm is used to optimize the model to remove the noise. Experimental results on denoising show that the proposed algorithm can effectively remove noise events. Moreover, with the preprocessing of the proposed algorithm, the recognition accuracy on AER data can be remarkably promoted. The source code of the proposed method is available at https://***/wjj/***.

关键词： Voltage control Noise reduction Streaming media Correlation Probabilistic logic Adaptation models Hardware dynamic vision sensor Event Stream Denoising Probabilistic Undirected Graph Model

来源：评论

学校读者我要写书评

暂无评论

A dual threshold adaptation method to dynamic vision sensor pixel

引用

MICROELECTRONICS JOURNAL 2024年 149卷

作者： He, Yanghao Shi, Xiaopei Nie, Kaiming Xu, Jiangtao Tianjin Univ Sch Microelect 92 Weijin Rd Tianjin 300072 Peoples R China Tianjin Key Lab Imaging & Sensing Microelect Techn 92 Weijin Rd Tianjin 300072 Peoples R China

This paper introduces a method for the dynamic vision sensor (DVS) pixel that achieves dual -threshold adaptation based on the interval between adjacent event spikes. The Time -to -Amplitude Converter (TAC) measures the adjacent spike interval per pixel. Based on the output of the TAC and two predefined time limits, the threshold selection circuit automatically chooses between the low threshold (R) L and the high threshold (R) H . The proposed pixel pitch is 33 . 2 mu m x 34 . 2 mu m with 8.1% fill factor in a 0 . 11 mu m 1P4M CMOS process. Compared to the traditional pixel with fixed threshold temporal contrast (R) = 15%, the behavior model indicates that the proposed structure maintains almost equivalent detection ability while reducing event output by 30% when (R) H = 45% and (R) L = 15%. Compared to the traditional pixel with fixed (R) = 45%, the behavior model indicates that the average gradient of the proposed structure is improved by at least 3 times with (R) H = 45% and (R) L = 15%. This enables the detection of low temporal contrast signals while minimizing the quantity of output events.

关键词： dynamic vision sensor Event spike interval Dual-threshold adaptation Threshold temporal contrast

来源：评论

学校读者我要写书评

暂无评论

A Spatial Localization and Attitude Estimation System for Unmanned Aerial Vehicles Using a Single dynamic vision sensor

引用

IEEE sensorS JOURNAL 2022年第15期22卷 15497-15507页

作者： Stuckey, Hunter Al-Radaideh, Amer Sun, Liang Tang, Wei New Mexico State Univ Klipsch Sch Elect & Comp Engn Las Cruces NM 88003 USA New Mexico State Univ Dept Mech & Aerosp Engn Las Cruces NM 88003 USA

This paper presents a three-dimensional (3D) localization and attitude estimation system to track a Unmanned Aerial Vehicle (UAV) using a single camera without prior knowledge of the environment. The hardware system consists of a dynamic vision Sensing (DVS) camera, a circle-shaped blinking marker made by Light-Emitting Diodes (LEDs), and a base station computer. The algorithm for spatial localization and attitude estimation includes a temporal video filter, triangulation-based location and attitude estimation, and 3D real-time plotting with a graphical user interface (GUI). The temporal video filter processes the image stream from the DVS camera to identify the frequency of the marker and removes the background image. The circle-shaped marker creates an ellipse in the image, whose diameter length and angles are utilized for calculating the location and attitude of the UAV, which offers a low-computing overhead. The proposed system has been evaluated in hardware flight testing. The results are compared with the benchmark data from both the infrared motion capturing system for localization and the on-board inertial measurement units of the UAV for attitude estimation. The accuracy and detection range surpasses similar state-of-the-art systems. The proposed method provides a simple yet accurate solution for tracking the location and attitude of a UAV.

关键词： Location awareness sensors Autonomous aerial vehicles Light emitting diodes Cameras Optical filters Testing Localization attitude estimation unmanned aerial vehicle dynamic vision sensor

来源：评论

学校读者我要写书评

暂无评论

Self-organisation of motion features with a temporal asynchronous dynamic vision sensor

引用

BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES 2013年 6卷 8-11页

作者： Koeth, F. Marques, H. G. Delbruck, T. Univ Zurich Al Lab Zurich Switzerland Univ Osnabruck Inst Cognit Sci Osnabruck Germany Univ Zurich Inst Neuroinformat Zurich Switzerland

Neural circuits closer to the periphery tend to be organised in a topological way, i.e. stimuli which are spatially close tend to be mapped onto neighbouring processing neurons. The goal of this study is to show how motion features (optic-flow), which have an inherent spatio-temporal profile, can be self-organised using correlations of precise spike intervals. The proposed framework is applied to the spiking output of an asynchronous dynamic vision sensor (DVS), which mimics the workings of the mammalian retina. Our results show that our framework is able to form a topologic organisation of optic-flow features similar to that observed in the human middle temporal lobe. (C) 2013 The Authors. Published by Elsevier B.V. All rights reserved.

关键词： Self-organisation Motion perception dynamic vision sensor Kohonen-network

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：