Pub Date : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310009
I. S. M. Hashim, A. Al-Hourani, Wayne S. T. Rowe
Utilizing machine learning methods for radio localization is gaining popularity in recent years. This is because of the current technology trends in better connectivity, cloud database, and cheaper processing power. Received signal strength (RSS) fingerprinting is one of the common localization methods because of its relative simplicity and ability to produce well-distinct patterns at different locations. In this paper, we compare the performance of different machine learning algorithms in terms of their mean localization error using RSS fingerprinting. The comparison is based on two key parameters, namely; (i) the correlation distance of the radio shadowing, and (ii) the standard deviation of the shadowing. The studied machine learning methods are the linear regression (LR), k-nearest neighbour regression (kNR), decision tree regression (DTR) and random forest regression (RFR), where extensive simulation demonstrates the performance of these methods under the correlated shadowing scenarios.
{"title":"Machine Learning Performance for Radio Localization under Correlated Shadowing","authors":"I. S. M. Hashim, A. Al-Hourani, Wayne S. T. Rowe","doi":"10.1109/ICSPCS50536.2020.9310009","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310009","url":null,"abstract":"Utilizing machine learning methods for radio localization is gaining popularity in recent years. This is because of the current technology trends in better connectivity, cloud database, and cheaper processing power. Received signal strength (RSS) fingerprinting is one of the common localization methods because of its relative simplicity and ability to produce well-distinct patterns at different locations. In this paper, we compare the performance of different machine learning algorithms in terms of their mean localization error using RSS fingerprinting. The comparison is based on two key parameters, namely; (i) the correlation distance of the radio shadowing, and (ii) the standard deviation of the shadowing. The studied machine learning methods are the linear regression (LR), k-nearest neighbour regression (kNR), decision tree regression (DTR) and random forest regression (RFR), where extensive simulation demonstrates the performance of these methods under the correlated shadowing scenarios.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116658979","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9309999
T. Laadung, Sander Ulp, M. Alam, Y. Moullec
This paper proposes a generalized approach combining two-way ranging (TWR) and passive ranging methods, called active-passive two-way ranging (AP-TWR). The proposed approach offers a generalized solution for a wide range of anchor configurations in positioning systems. The possibility to define active-passive and passive-only anchor roles allows scaling the system to improve the root-mean-square-error (RMSE) of the ranging estimations and the air time occupancy. Practical experiments show that with the proposed method consisting of 5 active-passive anchors and a single passive anchor, the RMSE is improved by 7.4% and the air time occupancy by 12.5% as compared to the single-sided TWR method with a 6 anchor configuration. Moreover, simulation results show that a maximum theoretical RMSE improvement of 31.7% can be achieved with the proposed setup.
{"title":"Active-Passive Two-Way Ranging Using UWB","authors":"T. Laadung, Sander Ulp, M. Alam, Y. Moullec","doi":"10.1109/ICSPCS50536.2020.9309999","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9309999","url":null,"abstract":"This paper proposes a generalized approach combining two-way ranging (TWR) and passive ranging methods, called active-passive two-way ranging (AP-TWR). The proposed approach offers a generalized solution for a wide range of anchor configurations in positioning systems. The possibility to define active-passive and passive-only anchor roles allows scaling the system to improve the root-mean-square-error (RMSE) of the ranging estimations and the air time occupancy. Practical experiments show that with the proposed method consisting of 5 active-passive anchors and a single passive anchor, the RMSE is improved by 7.4% and the air time occupancy by 12.5% as compared to the single-sided TWR method with a 6 anchor configuration. Moreover, simulation results show that a maximum theoretical RMSE improvement of 31.7% can be achieved with the proposed setup.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117066034","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310026
Raghad Yaseen Lazim Al-Taai, Wu Xiaojun, Y. Zhu
In many hearing-aids systems, background noise degrades the speech quality and intelligibility. In this paper, we propose a hybrid system for hearing-aids application, which works to separates the target voice from the noisy signal and then enhance the speech based on the user’s hearing loss. We achieve this by using two stages: (1) A bandpass filter to filter out the unwanted noise which is followed by (2) composite of two-level of multi-layers deep denoising autoencoder, each which specialized for specific enhancement task of a complete set of tasks. We evaluated the improvement of the speech quality using two typical hearing loss audiograms. For evaluation, hearing-aid speech perception index (HASPI), hearing-aid sound quality index (HASQI), and perceptual evaluation of speech quality (PESQ) used in two types audiograms of high-frequency hearing loss (HFHL). The results for the experiments show that the proposed method achieved significant results compared with the individual deep denoising autoencoder.
{"title":"Targeted Voice Enhancement by Bandpass Filter and Composite Deep Denoising Autoencoder","authors":"Raghad Yaseen Lazim Al-Taai, Wu Xiaojun, Y. Zhu","doi":"10.1109/ICSPCS50536.2020.9310026","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310026","url":null,"abstract":"In many hearing-aids systems, background noise degrades the speech quality and intelligibility. In this paper, we propose a hybrid system for hearing-aids application, which works to separates the target voice from the noisy signal and then enhance the speech based on the user’s hearing loss. We achieve this by using two stages: (1) A bandpass filter to filter out the unwanted noise which is followed by (2) composite of two-level of multi-layers deep denoising autoencoder, each which specialized for specific enhancement task of a complete set of tasks. We evaluated the improvement of the speech quality using two typical hearing loss audiograms. For evaluation, hearing-aid speech perception index (HASPI), hearing-aid sound quality index (HASQI), and perceptual evaluation of speech quality (PESQ) used in two types audiograms of high-frequency hearing loss (HFHL). The results for the experiments show that the proposed method achieved significant results compared with the individual deep denoising autoencoder.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123769240","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310031
F. Farahnakian, J. Heikkonen
We present an early fusion framework for robust object detection in autonomous vehicles. This framework firstly employs Monodepth as a self-supervised learning method to automatically infer a dense depth image from a single color input image. Then, the RGB image and its corresponding depth image are processed by a deep Convolutional Neural Networks (CNNs) to predict multiple 2D bounding boxes. We conduct experiments on the challenging KITTI benchmark dataset. The experimental results show that the features learnt from our fusion framework, when fused with the features learnt from depth-only and RGB-only architectures, outperform the state of the art on RGB-depth category recognition. We also investigated on performance of our fusion framework when it utilizes various sources (such as monocular and stereo imagery or both imageries) for generating the depth image.
{"title":"RGB-depth Fusion Framework for Object Detection in Autonomous Vehicles","authors":"F. Farahnakian, J. Heikkonen","doi":"10.1109/ICSPCS50536.2020.9310031","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310031","url":null,"abstract":"We present an early fusion framework for robust object detection in autonomous vehicles. This framework firstly employs Monodepth as a self-supervised learning method to automatically infer a dense depth image from a single color input image. Then, the RGB image and its corresponding depth image are processed by a deep Convolutional Neural Networks (CNNs) to predict multiple 2D bounding boxes. We conduct experiments on the challenging KITTI benchmark dataset. The experimental results show that the features learnt from our fusion framework, when fused with the features learnt from depth-only and RGB-only architectures, outperform the state of the art on RGB-depth category recognition. We also investigated on performance of our fusion framework when it utilizes various sources (such as monocular and stereo imagery or both imageries) for generating the depth image.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122592372","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310036
J. Leis
Synchronous detection is an approach used to detect very low level signals within noise when the excitation signal is precisely known or generated locally. In the instrumentation and measurement field, this is generally termed lockin detection and the instrument is a lockin amplifier. A direct implementation samples the measured signal to the required precision, and then applies the lockin algorithm to the data in order to recover an estimate of the measured parameter. The mixing inherent in the lockin requires multiplication as well as filtering. In this paper, we propose dispensing with the full analog to digital conversion prior to analysis. The proposed method operates directly in the digital domain, with both filtering and synchronous averaging performed using oversampled bilevel signals. It is further shown that the required computation can be performed recursively and without the requirement for multiplication. The recursive calculation is exact, and no approximations are involved. This enables lower-complexity hardware and permits operation in resource-constrained devices where arithmetic, especially floating-point, is unavailable.
{"title":"Computationally Efficient Synchronous Demodulation using Sigma-Delta Approach","authors":"J. Leis","doi":"10.1109/ICSPCS50536.2020.9310036","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310036","url":null,"abstract":"Synchronous detection is an approach used to detect very low level signals within noise when the excitation signal is precisely known or generated locally. In the instrumentation and measurement field, this is generally termed lockin detection and the instrument is a lockin amplifier. A direct implementation samples the measured signal to the required precision, and then applies the lockin algorithm to the data in order to recover an estimate of the measured parameter. The mixing inherent in the lockin requires multiplication as well as filtering. In this paper, we propose dispensing with the full analog to digital conversion prior to analysis. The proposed method operates directly in the digital domain, with both filtering and synchronous averaging performed using oversampled bilevel signals. It is further shown that the required computation can be performed recursively and without the requirement for multiplication. The recursive calculation is exact, and no approximations are involved. This enables lower-complexity hardware and permits operation in resource-constrained devices where arithmetic, especially floating-point, is unavailable.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122970646","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310001
Yamen Alsaba, Michel Saideh, I. Dayoub, M. Berbineau
In this paper, we report on the performance of different Multi-Carrier Modulation (MCM) techniques combined with both Non-Orthogonal Multiple Access (NOMA) and the conventional Orthogonal Multiple Access (OMA) systems. MCM-NOMA and MCM-OMA systems are analyzed in terms of efficient sum rate in mobility channel. In order to perform a fair comparison, we take into consideration all the different parameters among the MCM techniques, in addition to the distinct resource allocation in both NOMA and OMA systems. In addition, the performance of both MCM-NOMA and MCM-OMA systems is analyzed at different terminals speeds. The comparisons illustrate that all MCM techniques performs better when combined with NOMA systems comparing to OMA based systems. Furthermore, numerical simulations prove that Filter Bank Multi-Carrier (FBMC)-NOMA combination provides the best performance when compared to other MCM techniques in both NOMA and OMA systems.
{"title":"On the Sum Rate of MCM-Based NOMA and MCM-Based OMA Systems","authors":"Yamen Alsaba, Michel Saideh, I. Dayoub, M. Berbineau","doi":"10.1109/ICSPCS50536.2020.9310001","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310001","url":null,"abstract":"In this paper, we report on the performance of different Multi-Carrier Modulation (MCM) techniques combined with both Non-Orthogonal Multiple Access (NOMA) and the conventional Orthogonal Multiple Access (OMA) systems. MCM-NOMA and MCM-OMA systems are analyzed in terms of efficient sum rate in mobility channel. In order to perform a fair comparison, we take into consideration all the different parameters among the MCM techniques, in addition to the distinct resource allocation in both NOMA and OMA systems. In addition, the performance of both MCM-NOMA and MCM-OMA systems is analyzed at different terminals speeds. The comparisons illustrate that all MCM techniques performs better when combined with NOMA systems comparing to OMA based systems. Furthermore, numerical simulations prove that Filter Bank Multi-Carrier (FBMC)-NOMA combination provides the best performance when compared to other MCM techniques in both NOMA and OMA systems.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128731363","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310055
J. A. Zhang, L. Hoang, Diep N. Nguyen, Xiaojing Huang, Asanka Kekirigoda, Kin-Ping Hui
In this paper, we present a technique for realizing reliable multi-user MIMO communications in the presence of interference in time-varying channels. The null space of interfering channels is estimated and exploited for interference mitigation. We first introduce an improved superframe structure to enable frequent tracking of user channels and the null space of interfering channels. The different natures of the received user signals and interference require different processing methods. We improve and compare several adaptive equalizers to deal with time-varying user channels, and propose to use a subspace-based tracking algorithm to handle time-varying interfering channels. We simulate the proposed tracking algorithms in various settings, including when the interference signals are correlated. Simulation results are provided and validate the effectiveness of the proposed technique.
{"title":"Multi-user MIMO Communications with Interference Mitigation in Time-varying Channels","authors":"J. A. Zhang, L. Hoang, Diep N. Nguyen, Xiaojing Huang, Asanka Kekirigoda, Kin-Ping Hui","doi":"10.1109/ICSPCS50536.2020.9310055","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310055","url":null,"abstract":"In this paper, we present a technique for realizing reliable multi-user MIMO communications in the presence of interference in time-varying channels. The null space of interfering channels is estimated and exploited for interference mitigation. We first introduce an improved superframe structure to enable frequent tracking of user channels and the null space of interfering channels. The different natures of the received user signals and interference require different processing methods. We improve and compare several adaptive equalizers to deal with time-varying user channels, and propose to use a subspace-based tracking algorithm to handle time-varying interfering channels. We simulate the proposed tracking algorithms in various settings, including when the interference signals are correlated. Simulation results are provided and validate the effectiveness of the proposed technique.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129126762","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310047
Michel Saideh, E. Simon, J. Farah, Jonathan Villain, A. Fleury, V. Deniau, C. Gransart
Extreme Learning Machine (ELM) technology has started gaining interest in the channel estimation and equalization aspects of wireless communications systems. This is due to its fast training and global optimization capabilities that might allow the ELM-based receivers to be deployed in an online mode while facing the channel scenario at hand. However, ELM still needs a relatively large amount of training samples, thus causing important losses in spectral resources. In this work, we make use of the ensemble learning theory to propose different ensemble learning-based ELM equalizers that need much less spectral resources, while achieving better performance accuracy. Also, we verify the robustness of our proposed equalizers within different communication settings and channel scenarios by conducting different Monte Carlo simulations.
{"title":"Ensemble Extreme Learning Machine Based Equalizers for OFDM Systems","authors":"Michel Saideh, E. Simon, J. Farah, Jonathan Villain, A. Fleury, V. Deniau, C. Gransart","doi":"10.1109/ICSPCS50536.2020.9310047","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310047","url":null,"abstract":"Extreme Learning Machine (ELM) technology has started gaining interest in the channel estimation and equalization aspects of wireless communications systems. This is due to its fast training and global optimization capabilities that might allow the ELM-based receivers to be deployed in an online mode while facing the channel scenario at hand. However, ELM still needs a relatively large amount of training samples, thus causing important losses in spectral resources. In this work, we make use of the ensemble learning theory to propose different ensemble learning-based ELM equalizers that need much less spectral resources, while achieving better performance accuracy. Also, we verify the robustness of our proposed equalizers within different communication settings and channel scenarios by conducting different Monte Carlo simulations.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129349684","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310033
Pousali Chakraborty, M. Corici, T. Magedanz
5G has a very flexible network architecture due to virtualization and will come with various customisations based on different use cases. 5G also promises to provide intelligent networks with high bandwidth and low latency. One of the tradeoffs for this is the complexity of network monitoring and resource management of 5G; making availability, reliability and performance a challenge. The adoption of Software Defined Networking (SDN) and Network Function Virtualization (NFV) concepts ensure availability of network data and flexibility in architectural decisions for 5G. Because of the availability of data and advanced computing capabilities usage of ML (Machine Learning)/Artificial Intelligence (AI) can be envisaged in the control and management of 5G networks by predicting the load on the network. This article proposes a solution to integrate time-series based predictive analytics with 5G Core and shows a comparative study between two Time Series Forecasting Models-AutoRegressive Integrated Moving Average (ARIMA) and Face-book Prophet. Fraunhofer FOKUS Open5GCore is used as the reference 5G testbed toolkit for validating the proposal.
{"title":"A comparative study for Time Series Forecasting within software 5G networks","authors":"Pousali Chakraborty, M. Corici, T. Magedanz","doi":"10.1109/ICSPCS50536.2020.9310033","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310033","url":null,"abstract":"5G has a very flexible network architecture due to virtualization and will come with various customisations based on different use cases. 5G also promises to provide intelligent networks with high bandwidth and low latency. One of the tradeoffs for this is the complexity of network monitoring and resource management of 5G; making availability, reliability and performance a challenge. The adoption of Software Defined Networking (SDN) and Network Function Virtualization (NFV) concepts ensure availability of network data and flexibility in architectural decisions for 5G. Because of the availability of data and advanced computing capabilities usage of ML (Machine Learning)/Artificial Intelligence (AI) can be envisaged in the control and management of 5G networks by predicting the load on the network. This article proposes a solution to integrate time-series based predictive analytics with 5G Core and shows a comparative study between two Time Series Forecasting Models-AutoRegressive Integrated Moving Average (ARIMA) and Face-book Prophet. Fraunhofer FOKUS Open5GCore is used as the reference 5G testbed toolkit for validating the proposal.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129065596","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 : 2020-12-14DOI: 10.1109/ICSPCS50536.2020.9310051
D. Tran, H. Zepernick, T. Chu
In this paper, we propose a visual attention based least significant bit (LSB) data hiding method for 360° videos. In particular, information about the relative frequency of pixel access is used to control the amount of secret data to be hidden at the different latitudes of 360° videos. In this way, the typical behavior of users paying more attention to the equator region compared to the north and south poles when viewing 360° videos on a head-mounted display is taken into account. An analytical expression for capacity offered by this method to hide secret data in 360° cover videos is derived. A performance assessment of the visual attention based LSB data hiding method is conducted in terms of the peak signal-to-noise ratio (PSNR) and weighted-to-spherically-uniform PSNR (WS-PSNR) which both quantify the fidelity of a 360° stego-video with reference to the related 360° cover video.
{"title":"Visual Attention Based LSB Data Hiding in 360° Videos","authors":"D. Tran, H. Zepernick, T. Chu","doi":"10.1109/ICSPCS50536.2020.9310051","DOIUrl":"https://doi.org/10.1109/ICSPCS50536.2020.9310051","url":null,"abstract":"In this paper, we propose a visual attention based least significant bit (LSB) data hiding method for 360° videos. In particular, information about the relative frequency of pixel access is used to control the amount of secret data to be hidden at the different latitudes of 360° videos. In this way, the typical behavior of users paying more attention to the equator region compared to the north and south poles when viewing 360° videos on a head-mounted display is taken into account. An analytical expression for capacity offered by this method to hide secret data in 360° cover videos is derived. A performance assessment of the visual attention based LSB data hiding method is conducted in terms of the peak signal-to-noise ratio (PSNR) and weighted-to-spherically-uniform PSNR (WS-PSNR) which both quantify the fidelity of a 360° stego-video with reference to the related 360° cover video.","PeriodicalId":427362,"journal":{"name":"2020 14th International Conference on Signal Processing and Communication Systems (ICSPCS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121175592","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：