Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820775
Tomohito Suzaki, Takatomi Kubo, T. Hiraoka, Yuto Nakagawa, T. Terada, T. Yoshioka, K. Ikeda
A driver is regarded as a system that receives visual information and that controls the steering wheel. To identify the system, we conducted experiments to get input-output data using a driving simulator and confirmed that the focus of expansion of optical flow has sufficient information to predict steering behaviors.
{"title":"Steering behavior model of drivers on driving simulator through visual information","authors":"Tomohito Suzaki, Takatomi Kubo, T. Hiraoka, Yuto Nakagawa, T. Terada, T. Yoshioka, K. Ikeda","doi":"10.1109/APSIPA.2016.7820775","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820775","url":null,"abstract":"A driver is regarded as a system that receives visual information and that controls the steering wheel. To identify the system, we conducted experiments to get input-output data using a driving simulator and confirmed that the focus of expansion of optical flow has sufficient information to predict steering behaviors.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134112027","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820805
Doyoung Kim, Sanghoon Lee, Sagar Jadhav, Sanghoon Lee
This paper proposes a fingerprint method for webtoon identification using frequency features. The proposed fingerprint method uses features of a webtoon extracted from frequency components of each row of the webtoon image. Applying the proposed fingerprint method, the perfect accuracy is achieved for webtoon identification with randomly selected webtoon patches for testing. We compared our proposed method with a global thresholding method in frequency domain. Simulation results show that our method gets 100% accuracy with distorted (JPEG compression) images while the global thresholding method gets 32% accuracy only.
{"title":"Content-based webtoon fingerprint method","authors":"Doyoung Kim, Sanghoon Lee, Sagar Jadhav, Sanghoon Lee","doi":"10.1109/APSIPA.2016.7820805","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820805","url":null,"abstract":"This paper proposes a fingerprint method for webtoon identification using frequency features. The proposed fingerprint method uses features of a webtoon extracted from frequency components of each row of the webtoon image. Applying the proposed fingerprint method, the perfect accuracy is achieved for webtoon identification with randomly selected webtoon patches for testing. We compared our proposed method with a global thresholding method in frequency domain. Simulation results show that our method gets 100% accuracy with distorted (JPEG compression) images while the global thresholding method gets 32% accuracy only.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134415857","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820825
Hitoshi Sawano, Y. Kajikawa
In this paper, we examine the effectiveness of an active noise control (ANC) system with period aware linear prediction (PALP) method and simplified PALP (SPALP) method for MR noise. The PALP method expanding ordinary linear prediction method using delayed signal has high prediction accuracy for periodic signal. We have attempted to apply the ANC system with the PALP method for reducing MR noise which has high periodicity. However PALP method requires two adaptive filters and delay device. Thus the PALP method requires large memory size and computational complexity. For this reason, we simplify the PALP method by removing one adaptive filter with undelayed signal. Simulation results demonstrate that the feedback ANC system with the SPALP method has the same noise reduction performance as the PALP method while saving the computational complexity.
{"title":"Active noise control systems with simplified period aware linear prediction method for MR noise","authors":"Hitoshi Sawano, Y. Kajikawa","doi":"10.1109/APSIPA.2016.7820825","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820825","url":null,"abstract":"In this paper, we examine the effectiveness of an active noise control (ANC) system with period aware linear prediction (PALP) method and simplified PALP (SPALP) method for MR noise. The PALP method expanding ordinary linear prediction method using delayed signal has high prediction accuracy for periodic signal. We have attempted to apply the ANC system with the PALP method for reducing MR noise which has high periodicity. However PALP method requires two adaptive filters and delay device. Thus the PALP method requires large memory size and computational complexity. For this reason, we simplify the PALP method by removing one adaptive filter with undelayed signal. Simulation results demonstrate that the feedback ANC system with the SPALP method has the same noise reduction performance as the PALP method while saving the computational complexity.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"50 13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131219888","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820676
Siang Thye Hang, Masaki Aono
In this paper, we propose several enhancements to the well-known VGG 16-layers Convolutional Neural Network (CNN) model towards open world image classification, by taking plant identification as an example. We first propose to replace the last pooling layer of the VGG 16-layers model with a Spatial Pyramid Pooling layer, enabling the model to accept arbitrary sized input images. Second, for the activation function, we replace Rectified Linear Unit (ReLU) with Parametric ReLU in order to increase the adaptability of parameter learning. In addition, we introduce the Unseen Category Query Identification algorithm to identify and omit images of unseen category, thus preventing false classification into predefined categories. Such algorithm is essential in real life, since there is no guarantee that a given image has to fall into a predefined category. We use the dataset from the LifeCLEF 2016 plant identification task. We compare our results with other participants and demonstrate that our enhanced model with proposed algorithm exhibits outstanding performance.
{"title":"Open world plant image identification based on convolutional neural network","authors":"Siang Thye Hang, Masaki Aono","doi":"10.1109/APSIPA.2016.7820676","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820676","url":null,"abstract":"In this paper, we propose several enhancements to the well-known VGG 16-layers Convolutional Neural Network (CNN) model towards open world image classification, by taking plant identification as an example. We first propose to replace the last pooling layer of the VGG 16-layers model with a Spatial Pyramid Pooling layer, enabling the model to accept arbitrary sized input images. Second, for the activation function, we replace Rectified Linear Unit (ReLU) with Parametric ReLU in order to increase the adaptability of parameter learning. In addition, we introduce the Unseen Category Query Identification algorithm to identify and omit images of unseen category, thus preventing false classification into predefined categories. Such algorithm is essential in real life, since there is no guarantee that a given image has to fall into a predefined category. We use the dataset from the LifeCLEF 2016 plant identification task. We compare our results with other participants and demonstrate that our enhanced model with proposed algorithm exhibits outstanding performance.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130953346","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820725
Euyoung Kim, Kyoung Mu Lee
Optical flow is one of the key components in computer vision research area. Since the seminal work proposed by Horn and Schunck [1], numerous advanced algorithms have been proposed. Many state-of-the-art optical flow estimation algorithms optimize the data and regularization terms to solve ill-posed problems. However, despite their major advances over last decade, conventional optical flow methods utilize a single or fixed data terms without concerning scale changes in two consecutive frames of images. In this paper, we propose scale-change aware block matching data terms fused with locally adaptive models to establish dense correspondence between frames containing objects in different scales. We observed that taking scale variations into account in matching has a positive effect on optical flow accuracy.
{"title":"Scale-change aware locally adaptive optical flow","authors":"Euyoung Kim, Kyoung Mu Lee","doi":"10.1109/APSIPA.2016.7820725","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820725","url":null,"abstract":"Optical flow is one of the key components in computer vision research area. Since the seminal work proposed by Horn and Schunck [1], numerous advanced algorithms have been proposed. Many state-of-the-art optical flow estimation algorithms optimize the data and regularization terms to solve ill-posed problems. However, despite their major advances over last decade, conventional optical flow methods utilize a single or fixed data terms without concerning scale changes in two consecutive frames of images. In this paper, we propose scale-change aware block matching data terms fused with locally adaptive models to establish dense correspondence between frames containing objects in different scales. We observed that taking scale variations into account in matching has a positive effect on optical flow accuracy.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115413335","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820798
Qi Chen, Yuchen Zhang, Xiaochun Cao, Yunfei Zhang, H. Xiong
We present a scene depth map generation method based on light field cameras. From the plenoptic function, the angular information about each image point under different sizes of aperture is extracted, which could be used for confocal stereo. Considering confocal constancy and gradient constancy, we take into account two constraints: (1) When a pixel is in focus, its relative intensities across aperture should match the variation predicted by the relative exitance of the lens; and (2) When a pixel is in focus, the gradient of the pixel should equal to that of the corresponding pixel in reference image. Based on these two constraints, we develop data term which measures the probability of each pixel in each depth. Considering the textureless area, we also develop smoothness term which helps to determine the depth of textureless area by its neighboring texture area. Finally, the depth map is estimated via multi-label optimization and weighted median filtering.
{"title":"Depth map estimation with 4D light fields using confocal stereo","authors":"Qi Chen, Yuchen Zhang, Xiaochun Cao, Yunfei Zhang, H. Xiong","doi":"10.1109/APSIPA.2016.7820798","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820798","url":null,"abstract":"We present a scene depth map generation method based on light field cameras. From the plenoptic function, the angular information about each image point under different sizes of aperture is extracted, which could be used for confocal stereo. Considering confocal constancy and gradient constancy, we take into account two constraints: (1) When a pixel is in focus, its relative intensities across aperture should match the variation predicted by the relative exitance of the lens; and (2) When a pixel is in focus, the gradient of the pixel should equal to that of the corresponding pixel in reference image. Based on these two constraints, we develop data term which measures the probability of each pixel in each depth. Considering the textureless area, we also develop smoothness term which helps to determine the depth of textureless area by its neighboring texture area. Finally, the depth map is estimated via multi-label optimization and weighted median filtering.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124360093","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820858
Julan Xie, Xue Yang, Huiyong Li, Jinfeng Hu
In order to avoid the multi-dimensional spectrum peak search for multiple parameters estimation, a hybrid algorithm with uniform circular array (UCA) of electromagnetic vector sensors based on the beamspace transformation is proposed. In the beamspace, the azimuth angle can be split from other parameters and can be estimated without using spectral peak search. Then, the elevation estimation can be obtained with the estimated azimuth angle via a one-dimensional spectrum peak search. Finally, the polarized parameters are obtained based on the estimated azimuth and elevation angle via the engine decomposition with the modulus constraint. Its computation complexity is superior to the one of the tradition MUSIC and the existing reduced-dimensional algorithm.
{"title":"A hybrid algorithm for multiple parameters estimation with UCA of electromagnetic vector sensors","authors":"Julan Xie, Xue Yang, Huiyong Li, Jinfeng Hu","doi":"10.1109/APSIPA.2016.7820858","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820858","url":null,"abstract":"In order to avoid the multi-dimensional spectrum peak search for multiple parameters estimation, a hybrid algorithm with uniform circular array (UCA) of electromagnetic vector sensors based on the beamspace transformation is proposed. In the beamspace, the azimuth angle can be split from other parameters and can be estimated without using spectral peak search. Then, the elevation estimation can be obtained with the estimated azimuth angle via a one-dimensional spectrum peak search. Finally, the polarized parameters are obtained based on the estimated azimuth and elevation angle via the engine decomposition with the modulus constraint. Its computation complexity is superior to the one of the tradition MUSIC and the existing reduced-dimensional algorithm.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"320 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124527619","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820695
Jingxiu Zong, Lili Meng, Yanyan Tan, Yuwei Ren
A novel perceptual multiple description coding with randomly offset quantizers (PMDROQ) is proposed. In the proposed PMDROQ method, the input image is partitioned into M subsets, and then obtaining M descriptions. In each description, one subset is directly encoded and decoded with different-small perceptual quantization stepsizes in DCT domain, while other subsets are predictively coded and decoded with a large quantization stepsize. The perceptual quantization stepsize of low frequency coefficient is smaller than that of the high frequency coefficient. The proposed PMDROQ is applied to two-description lapped transform-based image coding. The experimental results show that the developed scheme obtains better performance than other methods in this category.
{"title":"Perceptual multiple description coding with randomly offset quantizers","authors":"Jingxiu Zong, Lili Meng, Yanyan Tan, Yuwei Ren","doi":"10.1109/APSIPA.2016.7820695","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820695","url":null,"abstract":"A novel perceptual multiple description coding with randomly offset quantizers (PMDROQ) is proposed. In the proposed PMDROQ method, the input image is partitioned into M subsets, and then obtaining M descriptions. In each description, one subset is directly encoded and decoded with different-small perceptual quantization stepsizes in DCT domain, while other subsets are predictively coded and decoded with a large quantization stepsize. The perceptual quantization stepsize of low frequency coefficient is smaller than that of the high frequency coefficient. The proposed PMDROQ is applied to two-description lapped transform-based image coding. The experimental results show that the developed scheme obtains better performance than other methods in this category.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"391 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124541520","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820822
Yanbin Zou, Q. Wan
This paper considers the problem of moving target localization in noncoherent distributed multiple-input multiple-output (MIMO) radar systems by using the bistatic range and range rate measurements. We propose a weighted least squares (WLS) method to estimate the target position and velocity, and then use the semidefinite programming (SDP) method to improve the accuracy of the WLS estimation by relaxing the constraints that exist in the WLS solution. Simulation results are included to show the performance of the proposed algorithm. It is shown that the proposed method can reach the Cramer-Rao lower bound (CRLB) in a range of moderate measurements noise, and the proposed algorithm is robust to some special geometries, in which the two-step weighted least squares-based (2SWLS-based) methods will be failed.
{"title":"Moving target localization in noncoherent distributed MIMO radar systems using range and range rate measurements","authors":"Yanbin Zou, Q. Wan","doi":"10.1109/APSIPA.2016.7820822","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820822","url":null,"abstract":"This paper considers the problem of moving target localization in noncoherent distributed multiple-input multiple-output (MIMO) radar systems by using the bistatic range and range rate measurements. We propose a weighted least squares (WLS) method to estimate the target position and velocity, and then use the semidefinite programming (SDP) method to improve the accuracy of the WLS estimation by relaxing the constraints that exist in the WLS solution. Simulation results are included to show the performance of the proposed algorithm. It is shown that the proposed method can reach the Cramer-Rao lower bound (CRLB) in a range of moderate measurements noise, and the proposed algorithm is robust to some special geometries, in which the two-step weighted least squares-based (2SWLS-based) methods will be failed.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124546749","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}
Pub Date : 2016-12-01DOI: 10.1109/APSIPA.2016.7820826
Mashael M. AlSaleh, M. Arvaneh, H. Christensen, Roger K. Moore
This paper presents an overview of the studies that have been conducted with the purpose of understanding the use of brain signals as input to a speech recogniser. The studies have been categorised based on the type of the technology used with a summary of the methodologies used and achieved results. In addition, the paper gives an insight into some studies that examined the effect of the chosen stimuli on brain activities as an important factor in the recognition process. The remaining part of this paper lists the limitations of the available studies and the challenges for future work in this area.
{"title":"Brain-computer interface technology for speech recognition: A review","authors":"Mashael M. AlSaleh, M. Arvaneh, H. Christensen, Roger K. Moore","doi":"10.1109/APSIPA.2016.7820826","DOIUrl":"https://doi.org/10.1109/APSIPA.2016.7820826","url":null,"abstract":"This paper presents an overview of the studies that have been conducted with the purpose of understanding the use of brain signals as input to a speech recogniser. The studies have been categorised based on the type of the technology used with a summary of the methodologies used and achieved results. In addition, the paper gives an insight into some studies that examined the effect of the chosen stimuli on brain activities as an important factor in the recognition process. The remaining part of this paper lists the limitations of the available studies and the challenges for future work in this area.","PeriodicalId":409448,"journal":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115015253","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：