2022 Sensor Signal Processing for Defence Conference (SSPD)最新文献

筛选
英文 中文
SSPD Conference 2022 - Welcome SSPD会议2022 -欢迎
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/sspd54131.2022.9896189
{"title":"SSPD Conference 2022 - Welcome","authors":"","doi":"10.1109/sspd54131.2022.9896189","DOIUrl":"https://doi.org/10.1109/sspd54131.2022.9896189","url":null,"abstract":"","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117297936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Learning Low-Rank Models From Compressive Measurements for Efficient Projection Design 从压缩测量中学习低秩模型用于高效投影设计
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896186
Fraser K. Coutts, John Thompson, B. Mulgrew
{"title":"Learning Low-Rank Models From Compressive Measurements for Efficient Projection Design","authors":"Fraser K. Coutts, John Thompson, B. Mulgrew","doi":"10.1109/SSPD54131.2022.9896186","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896186","url":null,"abstract":"Recent research has uncovered information-theoretic means to design projection matrices in scenarios where one information source is compressively sampled in the presence of a secondary source. Furthermore, if both sources can be approximated by Gaussian mixture (GM) models, it has been shown that it is possible to learn the characteristics of the secondary source from compressive measurements only. In this work, we investigate techniques that exploit low-rank GM approximations to the true distributions to reduce computational complexity and memory requirements during source learning and projection design. Two novel alternative projection design strategies are also introduced. These are tested against an existing strategy to determine which approach is superior for low size, weight, and power (SWAP) applications. Experimental results validate the benefits of the proposed low-rank strategies and reveal that all projection design algorithms offer similar levels of performance.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124694950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Non-Coherent Discrete Chirp Fourier Transform for Modulated LFM Parameter Estimation 调制LFM参数估计的非相干离散啁啾傅立叶变换
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896195
Kaiyu Zhang, Fraser K. Coutts, John Thompson
{"title":"Non-Coherent Discrete Chirp Fourier Transform for Modulated LFM Parameter Estimation","authors":"Kaiyu Zhang, Fraser K. Coutts, John Thompson","doi":"10.1109/SSPD54131.2022.9896195","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896195","url":null,"abstract":"Linear frequency modulated (LFM) waveforms play a significant role in both military and civilian detection and ranging applications. Based on LFM, researchers have designed a phase shift keying (PSK) modulated LFM waveform to enable both communication and radar functions simultaneously. Estimating the chirp rate and carrier frequency of data modulated LFM waveforms is therefore of interest in defence applications. In the previous research, the discrete chirp-Fourier transform (DCFT) was proposed to estimate the parameters for non-modulated waveforms. However, the DCFT method is limited with respect to the transform length and the estimation range. Thus, this paper proposes a generalised coherent DCFT that extends the previous DCFT method. We also introduce a novel non-coherent DCFT to improve parameter estimation for PSK modulated LFM waveforms. In the simulation section, this paper discusses the applicability of two modified DCFT methods and demonstrates their superior performance.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"42 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131680634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Fast Trajectory Forecasting With Automatic Identification System Broadcasts 基于自动识别系统广播的快速弹道预报
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896218
Yicheng Wang, Murat Üney
{"title":"Fast Trajectory Forecasting With Automatic Identification System Broadcasts","authors":"Yicheng Wang, Murat Üney","doi":"10.1109/SSPD54131.2022.9896218","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896218","url":null,"abstract":"This work proposes a fast trajectory forecasting algorithm to use with automatic identification system (AIS) broadcasts of vessels. The algorithm involves fast sub-optimal model parameter estimation from AIS messages and the computation of Gaussian location predictions for a series of future timestamps. The underlying trajectory model is a stochastic process that uses six parameters to generate near-constant velocity trajectories. These parameters include the desired cruise heading and speed of the vessel and velocity standard deviations along the heading direction and its perpendicular complement. We demonstrate the performance of our approach using a real AIS data set.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133642710","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Movement Classification and Segmentation Using Event-Based Sensing and Spiking Neural Networks 基于事件感知和脉冲神经网络的运动分类和分割
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896217
Paul Kirkland, G. Di Caterina
{"title":"Movement Classification and Segmentation Using Event-Based Sensing and Spiking Neural Networks","authors":"Paul Kirkland, G. Di Caterina","doi":"10.1109/SSPD54131.2022.9896217","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896217","url":null,"abstract":"The development of Spiking Neural Networks (SNN) and the discipline of Neuromorphic Engineering has resulted in a paradigm shift in how Machine Learning (ML) and Computer Vision (CV) problems are approached. At the heart of this shift is the adoption of event-based sensing and processing methods. The production of sparse and asynchronous events that are dynamically connected to the scene is possible with an event-based vision sensor, allowing for the acquisition of not just spatial data but also high-fidelity temporal data. In this work, we describe a novel method for performing instance segmentation of objects, only using their spatio-temporal movement patterns, by utilising the weights of an unsupervised Spiking Convolutional Neural Network that was originally trained for object recognition and extending it to instance segmentation. This takes advantage of the network’s spatial and temporal characteristics encoded within its internal feature representation, to offer this additional discriminative ability. We demonstrate this through a track path identification problem, where 6 identical blobs complete complex movement patterns within the same area at the same time. The network is able to successfully identify all 6 individual movements and segment the movement patterns belonging to each. The work then also explains how these methods map into the more complex Track before Detect problem. A complex track initiation problem, where detection can only be completed after an integration period, due to the low signal, high noise environment. These problem characteristics seem to complement the properties of event-based sensing and processing and initial test results are shown.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120989234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
OMASGAN: Out-of-distribution Minimum Anomaly Score GAN for Anomaly Detection OMASGAN:用于异常检测的分布外最小异常评分GAN
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896220
Nikolaos Dionelis, S. Tsaftaris, Mehrdad Yaghoobi
{"title":"OMASGAN: Out-of-distribution Minimum Anomaly Score GAN for Anomaly Detection","authors":"Nikolaos Dionelis, S. Tsaftaris, Mehrdad Yaghoobi","doi":"10.1109/SSPD54131.2022.9896220","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896220","url":null,"abstract":"Generative models trained in an unsupervised manner may set high likelihood and low reconstruction loss to Out-of-Distribution (OoD) samples. This leads to failures to detect anomalies, overall decreasing Anomaly Detection (AD) performance. In addition, AD models underperform due to the rarity of anomalies. To address these limitations, we develop the OoD Minimum Anomaly Score GAN (OMASGAN) which performs retraining by including the proposed minimum-anomaly-score OoD samples. These OoD samples are generated on the boundary of the support of the normal class data distribution in a proposed self-supervised learning manner. Our OMASGAN retraining algorithm leads to more accurate estimation of the underlying data distribution including multimodal supports and also disconnected modes. For inference, for AD, we devise a discriminator which is trained with negative and positive samples either generated (negative or positive) or real (only positive). The evaluation of OMASGAN on image data using the leave-one-out method shows that it achieves an improvement of at least 0.24 and 0.07 points in AUROC on average on the MNIST and CIFAR-10 datasets, respectively, over other benchmark models for AD.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123945507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Joint Undervolting and Overclocking Power Scaling Approximation on FPGAs fpga的联合欠压和超频功率缩放近似
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896229
Yun Wu, J. Mota, A. Wallace
{"title":"Joint Undervolting and Overclocking Power Scaling Approximation on FPGAs","authors":"Yun Wu, J. Mota, A. Wallace","doi":"10.1109/SSPD54131.2022.9896229","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896229","url":null,"abstract":"For applications in signal processing, Field Programmable Gate Arrays (FPGAs) are more flexible than Application Specific Integrated Circuits (ASICs), yet reconfigurable and still power and energy efficient to a degree. Undervolting and overclocking are approximate computing techniques that can further save power and energy, closing the efficiency gap by reducing the static/dynamic power and potentially speeding up the computation. However, these techniques may introduce bit level faults, which affect not only the computational correctness but also the security of the hardware. Understanding these fault behaviors provides necessary information for approximate implementation in low-power and secure design.In this work, we investigate joint undervolting and overclocking of AXI peripherals, specifically on-chip AXI memory access, using different commercial Xilinx Ultrascale+ heterogeneous MPSoCs with practical data movement between the ARM processor and the FPGA. Through experimental study we have observed fine-grained bit-flipping patterns when the voltage and clock are tuned beyond certain thresholds. By judging the probability of bit-flipping in terms of bit error rate, we propose a guideline for a balanced choice of voltage and frequency.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125985149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Image Quality SAR Refocus of Moving Targets undergoing Complicated Rolling Maneuvers 复杂滚动机动运动目标的图像质量SAR重聚焦
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896188
D. Garren
{"title":"Image Quality SAR Refocus of Moving Targets undergoing Complicated Rolling Maneuvers","authors":"D. Garren","doi":"10.1109/SSPD54131.2022.9896188","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896188","url":null,"abstract":"Moving targets typically appear smeared in synthetic aperture radar (SAR) imagery, often making the task of target recognition more difficult. Recently, research has yielded an ability to perform Arbitrary Rigid Object Motion Autofocus (AROMA) to generate automatically focused target images for cases of arbitrary target rotation and translation during the coherent processing interval of SAR collections. The current research analyzes the efficacy of AROMA processing for targets undergoing complicated rolling maneuvers against a background of measured Ku-band image clutter. The results of this analysis reveal that AROMA can yield focused target imagery that correlates well with the true structure of the target.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125048027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Polynomial Subspace Projection Approach for the Detection of Weak Voice Activity 微弱语音活动检测的多项式子空间投影方法
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896222
Vincent W. Neo, Stephan Weiss, P. Naylor
{"title":"A Polynomial Subspace Projection Approach for the Detection of Weak Voice Activity","authors":"Vincent W. Neo, Stephan Weiss, P. Naylor","doi":"10.1109/SSPD54131.2022.9896222","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896222","url":null,"abstract":"A voice activity detection (VAD) algorithm identifies whether or not time frames contain speech. It is essential for many military and commercial speech processing applications, including speech enhancement, speech coding, speaker identification, and automatic speech recognition. In this work, we adopt earlier work on detecting weak transient signals and propose a polynomial subspace projection pre-processor to improve an existing VAD algorithm. The proposed multi-channel pre-processor projects the microphone signals onto a lower dimensional subspace which attempts to remove the interferer components and thus eases the detection of the speech target. Compared to applying the same VAD to the microphone signal, the proposed approach almost always improves the F1 and balanced accuracy scores even in adverse environments, e.g. −30 dB SIR, which may be typical of operations involving noisy machinery and signal jamming scenarios.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129623265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
An extension to the Frenet-Serret and Bishop invariant extended Kalman filters for tracking accelerating targets 扩展了用于跟踪加速目标的Frenet-Serret和Bishop不变扩展卡尔曼滤波器
2022 Sensor Signal Processing for Defence Conference (SSPD) Pub Date : 2022-09-01 DOI: 10.1109/SSPD54131.2022.9896179
Joe Gibbs, David Anderson, M. Macdonald, John Russell
{"title":"An extension to the Frenet-Serret and Bishop invariant extended Kalman filters for tracking accelerating targets","authors":"Joe Gibbs, David Anderson, M. Macdonald, John Russell","doi":"10.1109/SSPD54131.2022.9896179","DOIUrl":"https://doi.org/10.1109/SSPD54131.2022.9896179","url":null,"abstract":"This paper presents an extension to the original Frenet-Serret and Bishop frame target models used in the invariant extended Kalman filter (IEKF) to account for tangential accelerations for highly-manoeuvrable targets. State error propagation matrices are derived for both IEKFs and used to build the accelerating Frenet-Serret (FSa-LIEKF) and Bishop (Ba-LIEKF) algorithms. The filters are compared to the original Frenet-Serret and Bishop algorithms in a tracking scenario featuring a target performing a series of complex manoeuvres. The accelerating forms of the LIEKF are shown to improve velocity estimation during non-constant velocity trajectory segments at the expense of increased noise during simpler manoeuvres.","PeriodicalId":439007,"journal":{"name":"2022 Sensor Signal Processing for Defence Conference (SSPD)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116739030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
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×
相关产品
×
本文献相关产品
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:604180095
Book学术官方微信
小红书