With the continuous development of modern information society, all kinds of high-speed wireless communication application are emerging, while the traditional spectrum resources are becoming scarce.The terahertz (THz) band is an enabler for wireless communication (Beyond 5G) since the excellent characteristics of terahertz communication. It is extremely challenging to design the modulator for THz communications.In this paper, an electrically controlled THz metasurface was designed and fabricated based on the phase transition characteristic of Vanadium Dioxide (VO2). It can switch between two resonant states with a large difference in transmittance. The experimental results show that the transmittance of perpendicular incident THz wave reaches to the highest at 0.31 THz. When the applied voltage is increased from 0 V to 8 V, the transmittance significantly decreases to the lowest value at 0.41 THz. The modulation depth can be up to 59% in the entire band of 0.2-0.6 THz. This work is of great significance for the research and development of THz modulators.
{"title":"Modulator Design for THz Communication Based on Vanadium Dioxide Metasurface","authors":"Yaojia Chi, Ningyuan Kuang, Yahua Tang, Wenjie Chen, Xinying Ma, Zhuoxun Li, Q. Wen, Zhi Chen","doi":"10.1109/ICCChinaW.2019.8849947","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849947","url":null,"abstract":"With the continuous development of modern information society, all kinds of high-speed wireless communication application are emerging, while the traditional spectrum resources are becoming scarce.The terahertz (THz) band is an enabler for wireless communication (Beyond 5G) since the excellent characteristics of terahertz communication. It is extremely challenging to design the modulator for THz communications.In this paper, an electrically controlled THz metasurface was designed and fabricated based on the phase transition characteristic of Vanadium Dioxide (VO2). It can switch between two resonant states with a large difference in transmittance. The experimental results show that the transmittance of perpendicular incident THz wave reaches to the highest at 0.31 THz. When the applied voltage is increased from 0 V to 8 V, the transmittance significantly decreases to the lowest value at 0.41 THz. The modulation depth can be up to 59% in the entire band of 0.2-0.6 THz. This work is of great significance for the research and development of THz modulators.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"52 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120817022","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849935
Peng He, Bowen Pi, Qiang Liu
This paper investigates the switching functionality for molecular communication networks. In particular, we design channel switches for molecular communication among biological cells through calcium signaling. We adopt stochastic noisy channels to design the channel switching with a stochastic process. First, a basic design of channel switches is presented considering variational gating of gap junction channels and noise. Then, we propose the decision-making problem of channel switches. After that, we propose a strategy using the support vector machine tool for the channel switching. The simulation results show that decision-making problem of channel switches could be properly solved with an accepted performance. The results also indicate that complex molecular communication networks may be designed using channel switches.
{"title":"Decision-making Strategy of Channel Switching in Molecular Communication Networks","authors":"Peng He, Bowen Pi, Qiang Liu","doi":"10.1109/ICCChinaW.2019.8849935","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849935","url":null,"abstract":"This paper investigates the switching functionality for molecular communication networks. In particular, we design channel switches for molecular communication among biological cells through calcium signaling. We adopt stochastic noisy channels to design the channel switching with a stochastic process. First, a basic design of channel switches is presented considering variational gating of gap junction channels and noise. Then, we propose the decision-making problem of channel switches. After that, we propose a strategy using the support vector machine tool for the channel switching. The simulation results show that decision-making problem of channel switches could be properly solved with an accepted performance. The results also indicate that complex molecular communication networks may be designed using channel switches.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131288068","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849971
Zhiqun Zou, Rui Yin, Xianfu Chen, Celimuge Wu
In this paper, a reinforcement learning based approach is proposed to realize the distributed power and spectrum allocation for the Device-to-Device (D2D) communications in unlicensed bands, named as D2D-U. To guarantee the harmonious coexistence with the WiFi networks, the conventional duty-cycle muting (DCM) is employed by the D2D-U links. With the proposed learning approach, D2D-U links can optimally select the time fraction on unlicensed channels without knowing the accurate WiFi traffic in a dynamic WiFi working environment. To address the state space explosion during the learning process, the Deep Q-learning network (DQN) is adopted by combining a deep neural network (DNN) with the traditional Q-learning mechanism. After obtaining the available time fraction on unlicensed channels, the spectrum and power allocation on licensed and unlicensed bands can be optimized jointly via the classic convex optimization methods at each D2D-U link. Numerical results are demonstrated to verify the effectiveness of the proposed approach.
{"title":"Deep Reinforcement Learning for D2D transmission in unlicensed bands","authors":"Zhiqun Zou, Rui Yin, Xianfu Chen, Celimuge Wu","doi":"10.1109/ICCChinaW.2019.8849971","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849971","url":null,"abstract":"In this paper, a reinforcement learning based approach is proposed to realize the distributed power and spectrum allocation for the Device-to-Device (D2D) communications in unlicensed bands, named as D2D-U. To guarantee the harmonious coexistence with the WiFi networks, the conventional duty-cycle muting (DCM) is employed by the D2D-U links. With the proposed learning approach, D2D-U links can optimally select the time fraction on unlicensed channels without knowing the accurate WiFi traffic in a dynamic WiFi working environment. To address the state space explosion during the learning process, the Deep Q-learning network (DQN) is adopted by combining a deep neural network (DNN) with the traditional Q-learning mechanism. After obtaining the available time fraction on unlicensed channels, the spectrum and power allocation on licensed and unlicensed bands can be optimized jointly via the classic convex optimization methods at each D2D-U link. Numerical results are demonstrated to verify the effectiveness of the proposed approach.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123929131","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849940
Zhuoxun Li, Xinying Ma, Wenjie Chen, Ningyuan Kuang, Bo Zhang
With the rapidly increasing demand for communication, terahertz wave communication has gradually stands out with its higher rate, lower power consumption, and secure communication. Furthermore, to reduce the use of radio frequency chains, hybrid beamforming for MIMO system is proposed. In conventional method, in order to optimal the uplink sum rate, exhaustive search algorithms are commonly used to select the best codeword for analog beamforming. However, exhaustive search algorithms also cause too much complexity to be implemented in engineering. In this paper, an iterative sub-optimal algorithm is firstly proposed to avoid the computation of matrix inversion. Moreover, we propose a data-driven method based on RBF-NN of analog beam codebook selection to further reduce the complexity. Specifically, with training data coming from samples of the terahertz channel, the analog beam codebook selection problem is considered as a multiclass-classification problem. Using the dataset, we built a statistical classification model via RBF-NN method which can select suitable analog beams for each user, with low complexity and near optimal sum rate. Analysis and simulation results reveal that, compared with the conventional method, as long as the training data are sufficient, the proposed method reduce complexity by several orders, with near-optimal performance.
{"title":"Neural Network Enhanced Analog Beam Selection Scheme for Terahertz Systems","authors":"Zhuoxun Li, Xinying Ma, Wenjie Chen, Ningyuan Kuang, Bo Zhang","doi":"10.1109/ICCChinaW.2019.8849940","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849940","url":null,"abstract":"With the rapidly increasing demand for communication, terahertz wave communication has gradually stands out with its higher rate, lower power consumption, and secure communication. Furthermore, to reduce the use of radio frequency chains, hybrid beamforming for MIMO system is proposed. In conventional method, in order to optimal the uplink sum rate, exhaustive search algorithms are commonly used to select the best codeword for analog beamforming. However, exhaustive search algorithms also cause too much complexity to be implemented in engineering. In this paper, an iterative sub-optimal algorithm is firstly proposed to avoid the computation of matrix inversion. Moreover, we propose a data-driven method based on RBF-NN of analog beam codebook selection to further reduce the complexity. Specifically, with training data coming from samples of the terahertz channel, the analog beam codebook selection problem is considered as a multiclass-classification problem. Using the dataset, we built a statistical classification model via RBF-NN method which can select suitable analog beams for each user, with low complexity and near optimal sum rate. Analysis and simulation results reveal that, compared with the conventional method, as long as the training data are sufficient, the proposed method reduce complexity by several orders, with near-optimal performance.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123978564","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849973
Xinwei Yao, Fang-Zhou Ni, Chao-Chao Wang
Terahertz (THz) communication is envisioned as one of the key technologies to achieve Terabit-per-second (Tbps) wireless data transmission speed. However, the communication distance in THz networks is constrained by the severe path loss in THz frequencies and the limited transmission power, which results in the network deployment issue. In recent years, researchers have shown a growing interest in the utilization of adaptive transmission power as well as multi-connectivity THz communication. In this paper, a multi-beam on-demand power allocation medium access control (MAC) protocol for Multiple-Input Multiple-Output (MIMO) THz communication in distributed wireless networks is presented. The proposed dual-band protocol relies on a multi-beam antenna structure, which utilizes the limited transmission power to achieve multiple concurrent THz connections by applying the proposed distance-aware power allocation scheme and redesigning the frame formats. The simulation results demonstrate the relationship between the number of beams with SNR threshold and average node distance. The results concluded by comparing the total throughput of the proposed multi-beam network with classical single-beam network show that the proposed protocol maximize the THz channel utilization and achievable throughput.
{"title":"Multi-Beam On-Demand Power Allocation MAC Protocol for MIMO Terahertz Communication Networks","authors":"Xinwei Yao, Fang-Zhou Ni, Chao-Chao Wang","doi":"10.1109/ICCChinaW.2019.8849973","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849973","url":null,"abstract":"Terahertz (THz) communication is envisioned as one of the key technologies to achieve Terabit-per-second (Tbps) wireless data transmission speed. However, the communication distance in THz networks is constrained by the severe path loss in THz frequencies and the limited transmission power, which results in the network deployment issue. In recent years, researchers have shown a growing interest in the utilization of adaptive transmission power as well as multi-connectivity THz communication. In this paper, a multi-beam on-demand power allocation medium access control (MAC) protocol for Multiple-Input Multiple-Output (MIMO) THz communication in distributed wireless networks is presented. The proposed dual-band protocol relies on a multi-beam antenna structure, which utilizes the limited transmission power to achieve multiple concurrent THz connections by applying the proposed distance-aware power allocation scheme and redesigning the frame formats. The simulation results demonstrate the relationship between the number of beams with SNR threshold and average node distance. The results concluded by comparing the total throughput of the proposed multi-beam network with classical single-beam network show that the proposed protocol maximize the THz channel utilization and achievable throughput.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124466171","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849946
Peng Yuan, Min Su, Yue Li, Qinyu Zhang
Recently, small satellites have been playing important roles in numerous military and civil applications, such as remote sensing and communication support, befitting from the coverage performance. However, restricted by the fixed orbits and on-board equipments, the long revisiting period and undesired blind stripe become the bottleneck for timely and full coverage, especially for the wide-range region area. Therefore, in this paper, the coverage-enhanced system comprising small satellites in constellation and Unmanned Aerial Vehicles (UAV) in formation is demonstrated. Based on the coverage system, the region decomposition and cooperative mechanism algorithm is designed to allocate coverage task to appropriate passing satellites and flying UAVs. Moreover, the design criterion for the satellite constellation in the UAV s-assisted system is proposed, achieving higher full-coverage ratio. The experimental results verify the enhancement of coverage performance for the proposed coverage system.
{"title":"Timely and Full Coverage Algorithm for Region Area with UAVs-assisted Small Satellite Constellation","authors":"Peng Yuan, Min Su, Yue Li, Qinyu Zhang","doi":"10.1109/ICCChinaW.2019.8849946","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849946","url":null,"abstract":"Recently, small satellites have been playing important roles in numerous military and civil applications, such as remote sensing and communication support, befitting from the coverage performance. However, restricted by the fixed orbits and on-board equipments, the long revisiting period and undesired blind stripe become the bottleneck for timely and full coverage, especially for the wide-range region area. Therefore, in this paper, the coverage-enhanced system comprising small satellites in constellation and Unmanned Aerial Vehicles (UAV) in formation is demonstrated. Based on the coverage system, the region decomposition and cooperative mechanism algorithm is designed to allocate coverage task to appropriate passing satellites and flying UAVs. Moreover, the design criterion for the satellite constellation in the UAV s-assisted system is proposed, achieving higher full-coverage ratio. The experimental results verify the enhancement of coverage performance for the proposed coverage system.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127250449","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849975
Bowen Pi, Peng He, Kun Yang, Qiang Liu
Molecular communication (MC) is a kind of communication technology using biochemical molecules as information carrier. Compared with traditional electromagnetic signal, the signal attenuation of biochemical molecules in the transmission process is very serious. However, in the body area nano-networks, in order to ensure the normal life activities of cells, there is a limit to the concentration of the signal molecules. Communication distance cannot be increased by increasing the concentration of information molecules, simply. Channel aggregation can reduce the concentration constraint and effectively solve the communication distance problem caused by signal attenuation. This paper introduces the molecular communication network about channel aggregation using calcium signal. According to the attenuation regulation of calcium signal, a scheme of channel aggregation is proposed.
{"title":"Channel Aggregation in Molecular Communication Network Based on Calcium Signal","authors":"Bowen Pi, Peng He, Kun Yang, Qiang Liu","doi":"10.1109/ICCChinaW.2019.8849975","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849975","url":null,"abstract":"Molecular communication (MC) is a kind of communication technology using biochemical molecules as information carrier. Compared with traditional electromagnetic signal, the signal attenuation of biochemical molecules in the transmission process is very serious. However, in the body area nano-networks, in order to ensure the normal life activities of cells, there is a limit to the concentration of the signal molecules. Communication distance cannot be increased by increasing the concentration of information molecules, simply. Channel aggregation can reduce the concentration constraint and effectively solve the communication distance problem caused by signal attenuation. This paper introduces the molecular communication network about channel aggregation using calcium signal. According to the attenuation regulation of calcium signal, a scheme of channel aggregation is proposed.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124149422","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849962
Hang Kong, Kai Feng, Jie Wu, Nan Jin, Shuaibiao He, Jiagui Tao
In the conventional structure of simultaneous wireless information and power transfer (SWIPT) system, the information channel depends on power transmission, which means if there is no power transfer, then all switches in the inverter are turned off, it is impossible to transfer information anymore. Therefore, an improved structure of SWIPT system with independent information channel is proposed in this paper. This paper establishes the model of the structure and analyzes the power and information channel of the system to verify the feasibility of the structure. Theoretical analysis and simulation results validate the proposed conception of information transmission with an independent channel.
{"title":"A Novel Conception of SWIPT System Considering Information Independent Transmission","authors":"Hang Kong, Kai Feng, Jie Wu, Nan Jin, Shuaibiao He, Jiagui Tao","doi":"10.1109/ICCChinaW.2019.8849962","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849962","url":null,"abstract":"In the conventional structure of simultaneous wireless information and power transfer (SWIPT) system, the information channel depends on power transmission, which means if there is no power transfer, then all switches in the inverter are turned off, it is impossible to transfer information anymore. Therefore, an improved structure of SWIPT system with independent information channel is proposed in this paper. This paper establishes the model of the structure and analyzes the power and information channel of the system to verify the feasibility of the structure. Theoretical analysis and simulation results validate the proposed conception of information transmission with an independent channel.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115948223","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}
Network slicing has emerged as a key technology to support the coexistence of multi-service in the the 5G/B5G networks. However, due to the resource scarcity and the diversity of slice requests, how to allocate resources efficiently to maximize the long-term reward of the infrastructure network is a challenging issue. In this paper, we model the resource allocation problem as a semi-Markov decision process (SMDP), which is defined by state space, action space, reward and transition probability distribution. The reward function jointly considers the total income, the cost of available resource and the utilization of the total resource for the infrastructure network. Not focusing on one step decisions reward, we apply the Bellman equation to obtain long-term reward by accumulating. Then we exploit value iteration algorithm to determine the resource allocation scheme according to a certain state in such a way that the long-term reward can be maximized. Extensive simulation results show that the proposed SMDP can achieve a superior performance compared with the existing heuristic methods.
{"title":"SMDP-Based Resource Allocation for Slice Requests with Long-term Reward Maximization","authors":"Xin-lian Zhou, X. Wen, Luhan Wang, Zhaoming Lu, Wanqing Guan","doi":"10.1109/ICCChinaW.2019.8849933","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849933","url":null,"abstract":"Network slicing has emerged as a key technology to support the coexistence of multi-service in the the 5G/B5G networks. However, due to the resource scarcity and the diversity of slice requests, how to allocate resources efficiently to maximize the long-term reward of the infrastructure network is a challenging issue. In this paper, we model the resource allocation problem as a semi-Markov decision process (SMDP), which is defined by state space, action space, reward and transition probability distribution. The reward function jointly considers the total income, the cost of available resource and the utilization of the total resource for the infrastructure network. Not focusing on one step decisions reward, we apply the Bellman equation to obtain long-term reward by accumulating. Then we exploit value iteration algorithm to determine the resource allocation scheme according to a certain state in such a way that the long-term reward can be maximized. Extensive simulation results show that the proposed SMDP can achieve a superior performance compared with the existing heuristic methods.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123716876","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 : 2019-08-01DOI: 10.1109/ICCChinaW.2019.8849954
Shuo Chang, Fan Zhang, Sai Huang, Yuanyuan Yao, Xiaotong Zhao, Z. Feng
Visual tracking is an important technology of robot-assisted surgery in 5G-health. Recently, discriminative correlation filter (DCF) methods utilizing in-network feature hierarchy in convolutional neural networks (CNNs) have made state-of-art results in visual tracking. However, their models are complex, which can not run in real-time. Different from DCF methods, SiamFC (Siamese Fully Convolutional) can operate at 86 frames-per-second, while it doesn't leverage the in-network feature hierarchy. Inspired by the high speed of SiamFC and in-network feature hierarchy in CNNs, a Siamese model based on feature pyramid network is proposed to improve tracking performance. The proposed tracking algorithm can not only benefit from fine-grained spatial details in low level features, but also the semantic information in high level features. Besides, a group of ablation experiments are conducted. Without the bells and whistles, the performance improvements are visible compared to SiamFC.
{"title":"Siamese Feature Pyramid Network for Visual Tracking","authors":"Shuo Chang, Fan Zhang, Sai Huang, Yuanyuan Yao, Xiaotong Zhao, Z. Feng","doi":"10.1109/ICCChinaW.2019.8849954","DOIUrl":"https://doi.org/10.1109/ICCChinaW.2019.8849954","url":null,"abstract":"Visual tracking is an important technology of robot-assisted surgery in 5G-health. Recently, discriminative correlation filter (DCF) methods utilizing in-network feature hierarchy in convolutional neural networks (CNNs) have made state-of-art results in visual tracking. However, their models are complex, which can not run in real-time. Different from DCF methods, SiamFC (Siamese Fully Convolutional) can operate at 86 frames-per-second, while it doesn't leverage the in-network feature hierarchy. Inspired by the high speed of SiamFC and in-network feature hierarchy in CNNs, a Siamese model based on feature pyramid network is proposed to improve tracking performance. The proposed tracking algorithm can not only benefit from fine-grained spatial details in low level features, but also the semantic information in high level features. Besides, a group of ablation experiments are conducted. Without the bells and whistles, the performance improvements are visible compared to SiamFC.","PeriodicalId":252172,"journal":{"name":"2019 IEEE/CIC International Conference on Communications Workshops in China (ICCC Workshops)","volume":"362 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121648041","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：