发布求助
文献互助 智能选刊 最新文献

2016 IEEE International Conference on Digital Signal Processing (DSP)最新文献

筛选
英文 中文
Fast head-shoulder proposal for deformable part model based pedestrian detection 基于可变形零件模型的行人检测快速头肩算法
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868599
Tian-Rui Liu, T. Stathaki
{"title":"Fast head-shoulder proposal for deformable part model based pedestrian detection","authors":"Tian-Rui Liu, T. Stathaki","doi":"10.1109/ICDSP.2016.7868599","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868599","url":null,"abstract":"In this paper we propose a fast head-shoulder detector as a means to facilitating faster pedestrian detection. The proposed approach is based on the observation that human head-shoulder regions share relatively robust features. The purpose is to address the problem of high computational speed of the deformable part model (DPM) detector by selecting candidate regions with higher likelihood to contain pedestrians. The proposed head-shoulder detector is based on the simple, yet effective normed gradient features. Head-shoulder detector outputs regions which are strong candidates for the presence of pedestrians and therefore, pedestrian detection processes are performed only within these regions, avoiding exhaustive sliding window search across the entire test image. Additionally, a two-pedestrian detector is applied to reinforce the detection accuracy especially in scenarios where pedestrians are close to each other. Our experiments on the INRIA dataset indicate that the proposed pedestrian detection method achieves comparable detection rate to the DPM detector, with improved speed of implementation.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125170557","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: 7
Accurate mouth state estimation via convolutional neural networks 基于卷积神经网络的口部状态准确估计
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868531
Jie Cao, Haiqing Li, Zhenan Sun, R. He
{"title":"Accurate mouth state estimation via convolutional neural networks","authors":"Jie Cao, Haiqing Li, Zhenan Sun, R. He","doi":"10.1109/ICDSP.2016.7868531","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868531","url":null,"abstract":"Human mouth is very flexible such that its status (closed or open) is often used as a judgment in the liveness detection of face recognition. However, due to large head pose and illumination variations, accurate mouth status estimation is still challenging in real-world scenarios. In this paper, we propose a deep convolutional neural networks (CNNs) method for mouth status estimation under unconstrained conditions and different types of attacks. Different from previous methods that extract hand-crafted features and then treat the estimation problem as a binary classification task, our method automatically extracts discriminative features via learned convolutional and the pooling layers. To demonstrate the effectiveness of our method and the challenge of mouth status estimation in real-world, we also propose a mouth status estimation dataset that contains 10,714 images in the wild. Experimental results with two types of liveness attacks show that our proposed method outperforms the other traditional methods, especially in the wild condition.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127467628","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: 2
Throughput/area efficient FPGA implementation of QR decomposition for MIMO systems MIMO系统QR分解的吞吐量/面积高效FPGA实现
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868612
Wei Zhao, Jianqiang Lin, S. Chan
{"title":"Throughput/area efficient FPGA implementation of QR decomposition for MIMO systems","authors":"Wei Zhao, Jianqiang Lin, S. Chan","doi":"10.1109/ICDSP.2016.7868612","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868612","url":null,"abstract":"QR Decomposition (QRD) plays an important role in emerging multiple-input multiple-output (MIMO) systems. This paper proposes a basic master-slave-pair element for complex-valued QRD by exploring the CORDIC-based Three Angle Complex Rotation (TACR) method. Based on this basic element, a new low-complexity high-throughput structure is proposed. The proposed structure demonstrates its scalability for other matrix sizes. The computational error analysis and the resource utilization are evaluated with various wordlengths. We also study its fixed-point implementation on field-programming gate array (FPGA). Our structure can achieve 0.934MMatrices/sec throughput at the maximum working frequency 128MHz and show more efficient throughput/area than other works.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121864737","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: 4
Cooperative target searching and tracking via UCT with probability distribution model 基于概率分布模型的UCT协同目标搜索与跟踪
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868620
Ruoxi Qin, Tian Wang, Haotian Jiang, Qianhong Yan, Weikang Wang, H. Snoussi
{"title":"Cooperative target searching and tracking via UCT with probability distribution model","authors":"Ruoxi Qin, Tian Wang, Haotian Jiang, Qianhong Yan, Weikang Wang, H. Snoussi","doi":"10.1109/ICDSP.2016.7868620","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868620","url":null,"abstract":"As Unmanned Aerial Vehicle's (UAV) battery life and stability develop, multiple UAVs are having more and more applications in the uninterrupted patrol and security. Thus UAV's searching, tracking and trajectory planning become important issues. This paper proposes an online distributed algorithm used in UAV's tracking and searching, with the consideration of UAV's practical need to recharge under limited power. We propose a Quantum Probability Model to describe the partially observable target positions, and we use Upper Confidence Tree (UCT) algorithm to find out the best searching and tracking route based on this model. We also introduce the Teammate Learning Model to handle the nonstationary problems in distributed reinforcement learning.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133440347","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
An improved approach for face detection using superpixels, moment-based matching, and isosceles triangle matching 一种改进的基于超像素、矩基匹配和等腰三角形匹配的人脸检测方法
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868528
Cho-Hsin Tsai, Jian-Jiun Ding, Ko-Jie Liao
{"title":"An improved approach for face detection using superpixels, moment-based matching, and isosceles triangle matching","authors":"Cho-Hsin Tsai, Jian-Jiun Ding, Ko-Jie Liao","doi":"10.1109/ICDSP.2016.7868528","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868528","url":null,"abstract":"Face detection serves as a crucial step for a wide range of applications in computer vision. In this paper, we delve into the task of face detection. An algorithm is proposed for colour images to be robust to varied illumination, background setting, head pose and skin colour. Taking advantage of the superpixel segmentation followed by our trained SVM classifier, we are able to identify different skin-tone faces and generate face candidates. The moment-based elliptic shape matching is performed to remove invalid facial regions. Based on chroma and luma components, our scheme establishes the Eyemap and the Mouthmap to yield a pool of candidates for facial features. A delicate examination procedure considering the texture, colour and spatial relations with respect to the eyes-mouth pair is employed to verify each face candidate. Experimental results demonstrate better detection on the Caltech database in terms of F-measure. Results also show that our proposed algorithm more effectively rules out non-human faces than state-of-the-art algorithms.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131644757","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
Mitigation of the multiple RFIs in radio astronomy based on the subspace tracking 基于子空间跟踪的射电天文学多重射频干扰的缓解
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868516
Shiyu Zhu, Zhuang Wang, Mengnan Wang, Z. Cheng
{"title":"Mitigation of the multiple RFIs in radio astronomy based on the subspace tracking","authors":"Shiyu Zhu, Zhuang Wang, Mengnan Wang, Z. Cheng","doi":"10.1109/ICDSP.2016.7868516","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868516","url":null,"abstract":"Radio astronomical data is increasingly corrupted by human telecommunication activities. It is becoming particularly difficult to work at frequencies between 1100–1300 MHz that are rapidly filling up with satellite navigation signals. Therefore, Radio Frequency Interference (RFI) mitigation becomes an important step in the data processing flow. As to the telescopes based on Antenna array, RFI mitigation can be conducted in spatial domain using the sampled covariance matrix. In this paper, a subspace tracking RFI approach has been proposed based on the power method. The RFI spatial signature estimations provided by the reference antenna are used to initialize the power method to support a faster convergence and more accurate estimation. In addition, the reference antenna sequentially steers at the multiple interferences, thereby acquires new updates of each RFI spatial signature successively. Then, the Interference can be mitigated individually by applying the orthogonal projection. The simulation results validate the effectiveness of the proposed algorithm.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134297106","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 non-negative tensor factorization approach to feature extraction for image analysis 一种用于图像分析的非负张量分解特征提取方法
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868538
A. Ang, Y. Hung, Zhiguo Zhang
{"title":"A non-negative tensor factorization approach to feature extraction for image analysis","authors":"A. Ang, Y. Hung, Zhiguo Zhang","doi":"10.1109/ICDSP.2016.7868538","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868538","url":null,"abstract":"In this paper, a decomposition method is proposed for Separable Non-negative Tensor Factorization (SNTF), which yields a structure similar to the PARATUCK2 model for the decomposition of non-negative tensors. Among many different possibilities for performing tensor factorization, we develop a specific procedure for SNTF with an aim to decompose multi-way dataset expressed in the form of a tensor into low-rank components that extract dominant features in the data. The SNTF method is evaluated using real image data and the results show that the proposed SNTF is superior to other NTF methods in terms of error performance and computational efficiency.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129997325","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
Low-rank approximation based abnormal detection in the video sequence 基于低秩近似的视频序列异常检测
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868530
B. Yu, Yazhou Liu, Quansen Sun
{"title":"Low-rank approximation based abnormal detection in the video sequence","authors":"B. Yu, Yazhou Liu, Quansen Sun","doi":"10.1109/ICDSP.2016.7868530","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868530","url":null,"abstract":"This article presents a new method for abnormal events detection from video sequences by combing the low-rank approximation and sparse combination learning. Motivated by the structured sparsity of video data, the low-rank approximation is introduced to capture a set of normal dictionaries. With the captured dictionaries, the sparse combination learning is utilized to fit training samples and measure the abnormality of testing samples. Multi-scale 3D gradient features, which encode the spatiotemporal information, are adopted to detect abnormal events. The benefits of the proposed method are three-fold: firstly, the low-rank property is utilized to learn the underlying normal dictionaries, which can represent groups of similar normal features effectively; Secondly, the sparsity based algorithm can adaptively determine the number of dictionary bases, which makes it a preferable choice for interpreting the corresponding dynamic scene semantics; Thirdly, the proposed method is efficient and real time detection can be accomplished. Experimental results on public datasets have shown that the proposed method yields competitive performance comparing with the state-of-the-art methods.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133177950","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
Graph-based reconstruction of time-varying spatial signals 时变空间信号的基于图的重构
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868578
Kai Qiu, Xiaohan Wang, Tiejian Li, Yuantao Gu
{"title":"Graph-based reconstruction of time-varying spatial signals","authors":"Kai Qiu, Xiaohan Wang, Tiejian Li, Yuantao Gu","doi":"10.1109/ICDSP.2016.7868578","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868578","url":null,"abstract":"Signal processing on graphs is an emerging field studying signals in irregular domains, and has been applied to many applications such as sensor networks and recommendation systems. In this paper, a novel method for the recovery of time-varying spatial signal based on graph is proposed. A graph is established according to the spatial position of the signal. Unlike the previous works, the smoothness of the temporal differential signal on the graph rather than the smoothness of the signal itself is used to help reconstruction. Two experiments of real-world are conducted. The first experiment of sea surface temperature data shows that the proposed algorithm achieves less reconstruction error than other algorithms, and the second experiment of sensor network data demonstrates the rationality and superiority of the proposed algorithms from intuition.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132520816","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
Excavation devices classification using enhanced acoustics by MVDR beamforming with a cross microphone array 利用交叉麦克风阵列MVDR波束形成增强声学的挖掘设备分类
2016 IEEE International Conference on Digital Signal Processing (DSP) Pub Date : 2016-10-01 DOI: 10.1109/ICDSP.2016.7868585
Tianlei Wang, Jiuwen Cao, Jianzhong Wang, Xiaoping Lai, Zhiping Lin
{"title":"Excavation devices classification using enhanced acoustics by MVDR beamforming with a cross microphone array","authors":"Tianlei Wang, Jiuwen Cao, Jianzhong Wang, Xiaoping Lai, Zhiping Lin","doi":"10.1109/ICDSP.2016.7868585","DOIUrl":"https://doi.org/10.1109/ICDSP.2016.7868585","url":null,"abstract":"Acoustic signal based recognition for excavation devices has been investigated in the past due to its significance in preventing the underground cables from being destroyed during the ground excavation. However, existing excavation devices classification algorithms have paid little attention to the reduction of background noises which usually severely degrade the recognition performance. This paper utilizes a cross microphone array to record the acoustic signals of excavation devices, which are then filtered by the minimum variance distortionless response (MVDR) beamforming algorithm to reduce the environment noises and enhance the desired signals. The filtered signals are then fed into the feature extraction and classifier learning. To show the effectiveness of the proposed method, we collected the real acoustics of two representative devices in a construction site to make the performance testing. Experiments show that, compared with conventional recognition methods the performance of the proposed method is significantly improved.","PeriodicalId":206199,"journal":{"name":"2016 IEEE International Conference on Digital Signal Processing (DSP)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123770668","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: 3
首页 上一页 下一页 尾页
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
现在去查看 取消
×
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