Pub Date : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065976
Ziqing Wang, Zhumu Fu
Vehicle path planning and tracking control are the key to achieving autonomous driving. In this paper, a combined algorithm based on artificial potential field algorithm and genetic algorithm is proposed. Based on information about the vehicle's driving environment, establishing potential field functions in different environments. And the initialized populations in the genetic algorithm are optimized using the established artificial potential fields. Planning a reliable driving path. Using model predictive control algorithms. Tracking control of the planned path. Unified modeling was achieved. Experimental results show that the improved path planning algorithm and tracking control method are able to plan and track the path well.
{"title":"Unified Modeling of Path Planning and Tracking Control Based on Improved Genetic Algorithm","authors":"Ziqing Wang, Zhumu Fu","doi":"10.1109/ICCC56324.2022.10065976","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065976","url":null,"abstract":"Vehicle path planning and tracking control are the key to achieving autonomous driving. In this paper, a combined algorithm based on artificial potential field algorithm and genetic algorithm is proposed. Based on information about the vehicle's driving environment, establishing potential field functions in different environments. And the initialized populations in the genetic algorithm are optimized using the established artificial potential fields. Planning a reliable driving path. Using model predictive control algorithms. Tracking control of the planned path. Unified modeling was achieved. Experimental results show that the improved path planning algorithm and tracking control method are able to plan and track the path well.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"26 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132708414","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065658
Jingwen Zhu, Jie Wang, Ming Chen, Zhaohui Tao, Xiangyuan Tang, Qingsheng Xue
The physical layer of satellite return link is studied in this work based on the latest version of the second generation return channel satellite for digital video broadcasting (DVB-RCS2). The satellite return link with linear modulation is designed and the experimental simulation of the burst error rate (BER) performance is carried out in this work. Based on the built satellite return link, the waveform performance that is not given in the specification is further simulated and complemented. Then, the link with direct-sequence spread as specified in the standard is simulated. The BER performance of the link with spread spectrum is compared with that of the original link The results proposes that the performance is related to the spreading factor: each time the spreading factor is doubled, the BER performance is improved by 3dB. Furthermore, experiments based on typical Rice channel are also carried out. The Rice factor is set to be 17dB referring to the specification, and the simulation results reveal narrow difference of 0.05dB compared with additional white gaussian noise (AWGN) channel. The research content of this paper will complement the waveform performance not given in the specification, fill the performance deficiency of spreading and verify the consistency of the satellite channel and the specification, which will lay a good foundation for the further research and application of the specification.
{"title":"Simulation Research on the Designed Physical Layer of Satellite Return Link Based on DVB-RCS2","authors":"Jingwen Zhu, Jie Wang, Ming Chen, Zhaohui Tao, Xiangyuan Tang, Qingsheng Xue","doi":"10.1109/ICCC56324.2022.10065658","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065658","url":null,"abstract":"The physical layer of satellite return link is studied in this work based on the latest version of the second generation return channel satellite for digital video broadcasting (DVB-RCS2). The satellite return link with linear modulation is designed and the experimental simulation of the burst error rate (BER) performance is carried out in this work. Based on the built satellite return link, the waveform performance that is not given in the specification is further simulated and complemented. Then, the link with direct-sequence spread as specified in the standard is simulated. The BER performance of the link with spread spectrum is compared with that of the original link The results proposes that the performance is related to the spreading factor: each time the spreading factor is doubled, the BER performance is improved by 3dB. Furthermore, experiments based on typical Rice channel are also carried out. The Rice factor is set to be 17dB referring to the specification, and the simulation results reveal narrow difference of 0.05dB compared with additional white gaussian noise (AWGN) channel. The research content of this paper will complement the waveform performance not given in the specification, fill the performance deficiency of spreading and verify the consistency of the satellite channel and the specification, which will lay a good foundation for the further research and application of the specification.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128909400","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065842
Wufei Yuan, Weiguang Li, Xingzhong Xiong, Xiaoli Cao
This paper proposes an anti-occlusion target tracking algorithm that integrates deep convolutional features with handcrafted features and adds Average Peak Correlation Energy(APCE). The performance of traditional handcrafted features, such as Histogram of Oriented Gradient(HOG) feature, is unsatisfactory in complex environments. This paper uses deep convolutional features with HOG feature and Color Naming(CN) feature, Fully consider the characteristics of deep convolutional feature with strong representation ability and the characteristics of handcrafted feature extraction is simple. For the target occlusion problem, the APCE is introduced to evaluate the reliability of the tracking target. Once the target is occluded, the filter stops updating the target model and searches the target again. The results tested on OTB-100 video sequence set demonstrates that the improved algorithm has better performance accuracy and success rate than Kernel Correlation Filter(KCF) algorithm in occlusion and motion blur scene.
{"title":"Anti-Occlusion Target Tracking Algorithm Based on Fusion of Deep Features and Handcrafted Features","authors":"Wufei Yuan, Weiguang Li, Xingzhong Xiong, Xiaoli Cao","doi":"10.1109/ICCC56324.2022.10065842","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065842","url":null,"abstract":"This paper proposes an anti-occlusion target tracking algorithm that integrates deep convolutional features with handcrafted features and adds Average Peak Correlation Energy(APCE). The performance of traditional handcrafted features, such as Histogram of Oriented Gradient(HOG) feature, is unsatisfactory in complex environments. This paper uses deep convolutional features with HOG feature and Color Naming(CN) feature, Fully consider the characteristics of deep convolutional feature with strong representation ability and the characteristics of handcrafted feature extraction is simple. For the target occlusion problem, the APCE is introduced to evaluate the reliability of the tracking target. Once the target is occluded, the filter stops updating the target model and searches the target again. The results tested on OTB-100 video sequence set demonstrates that the improved algorithm has better performance accuracy and success rate than Kernel Correlation Filter(KCF) algorithm in occlusion and motion blur scene.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131662437","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065942
Zerui Tian, Fan Yang
Time Sensitive Networking (TSN) is a recently proposed technology claiming to be capable of transmitting both best effort and real-time traffic simultaneously. TSN achieves real-time communications by per-queue Time-Division Multiplexing and takes no notice of the details of incoming frames. Therefore, the forwarding in TSN suffers from packet reordering because the practical forward sequences may differ from the window schedules, i.e., frame disordering errors. To enhance the robustness of TSN, in this paper, we propose a shaping mechanism, FOS, for frame ordering. FOS is able to sort incoming frames into expected sequences, therefore, providing the capacity of frame ordering configuration. To evaluate its performance, we conduct simulations for FOS based on a complete switch model under various conditions. The results prove the functional correctness of FOS and demonstrate that the FOS residence time is 15% to 34% of the total residence time. Therefore, FOS is able to guarantee the frame sequences without requiring unreasonable extra time.
{"title":"FOS: A Shaping Mechanism for Frame Ordering in Time Sensitive Networking","authors":"Zerui Tian, Fan Yang","doi":"10.1109/ICCC56324.2022.10065942","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065942","url":null,"abstract":"Time Sensitive Networking (TSN) is a recently proposed technology claiming to be capable of transmitting both best effort and real-time traffic simultaneously. TSN achieves real-time communications by per-queue Time-Division Multiplexing and takes no notice of the details of incoming frames. Therefore, the forwarding in TSN suffers from packet reordering because the practical forward sequences may differ from the window schedules, i.e., frame disordering errors. To enhance the robustness of TSN, in this paper, we propose a shaping mechanism, FOS, for frame ordering. FOS is able to sort incoming frames into expected sequences, therefore, providing the capacity of frame ordering configuration. To evaluate its performance, we conduct simulations for FOS based on a complete switch model under various conditions. The results prove the functional correctness of FOS and demonstrate that the FOS residence time is 15% to 34% of the total residence time. Therefore, FOS is able to guarantee the frame sequences without requiring unreasonable extra time.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131672806","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065774
Chenghong Zhang, Bo-quan Yu, Wei Wang
The defect detection of steel is an important process to ensure the quality of steel. The traditional detection methods have low efficiency and poor accuracy. With the development of deep learning and computer vision technologies, this paper proposes an improved Mask RCNN model for steel defect detection. The feature extraction network of Mask RCNN is replaced by a more robust EfficientNet, the improved BiFPN structure is combined with EfficientNet to extract features of different scales, and a CBAM module is added to the mask branch to improve the quality of mask prediction. Experiments on the Severstal steel surface defect dataset show that the improved method not only significantly improves the accuracy of the model, but also greatly reduces the model parameters.
{"title":"Steel Surface Defect Detection Based on Improved MASK RCNN","authors":"Chenghong Zhang, Bo-quan Yu, Wei Wang","doi":"10.1109/ICCC56324.2022.10065774","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065774","url":null,"abstract":"The defect detection of steel is an important process to ensure the quality of steel. The traditional detection methods have low efficiency and poor accuracy. With the development of deep learning and computer vision technologies, this paper proposes an improved Mask RCNN model for steel defect detection. The feature extraction network of Mask RCNN is replaced by a more robust EfficientNet, the improved BiFPN structure is combined with EfficientNet to extract features of different scales, and a CBAM module is added to the mask branch to improve the quality of mask prediction. Experiments on the Severstal steel surface defect dataset show that the improved method not only significantly improves the accuracy of the model, but also greatly reduces the model parameters.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115430758","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065853
Man Xu, C. Lam, Yuanhui Liang, B. Ng, S. Im
Deep joint source-channel coding (DJSCC) has received extensive attention in the communications community. However, the high computational costs and storage requirements prevent the DJSCC model from being effectively deployed on embedded systems and mobile devices. Recently, convolutional neural network (CNN) compression via low-rank decomposition has achieved remarkable performance. In this paper, we conduct a comparative study of low-rank decomposition for lowering the computational complexity and storage requirement for Rate-Adaptive DJSCC, including CANDECOMP/PARAFAC (CP) de-composition, Tucker (TK) decomposition, and Tensor-train (TT) decomposition. We evaluate the compression ratio, speedup ratio, and Peak Signal-to-Noise Ratio (PSNR) performance loss for the CP, TK, and TT decomposition with fine-tuning and pruning. From the experimental results, we found that compared with the TT decomposition, CP decomposition with fine-tuning lowers the PSNR performance degradation at the expense of higher compression and speedup ratio.
{"title":"Low-Rank Decomposition for Rate-Adaptive Deep Joint Source-Channel Coding","authors":"Man Xu, C. Lam, Yuanhui Liang, B. Ng, S. Im","doi":"10.1109/ICCC56324.2022.10065853","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065853","url":null,"abstract":"Deep joint source-channel coding (DJSCC) has received extensive attention in the communications community. However, the high computational costs and storage requirements prevent the DJSCC model from being effectively deployed on embedded systems and mobile devices. Recently, convolutional neural network (CNN) compression via low-rank decomposition has achieved remarkable performance. In this paper, we conduct a comparative study of low-rank decomposition for lowering the computational complexity and storage requirement for Rate-Adaptive DJSCC, including CANDECOMP/PARAFAC (CP) de-composition, Tucker (TK) decomposition, and Tensor-train (TT) decomposition. We evaluate the compression ratio, speedup ratio, and Peak Signal-to-Noise Ratio (PSNR) performance loss for the CP, TK, and TT decomposition with fine-tuning and pruning. From the experimental results, we found that compared with the TT decomposition, CP decomposition with fine-tuning lowers the PSNR performance degradation at the expense of higher compression and speedup ratio.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115605357","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065933
Yukun Zhao, Xinyun Zhang, Shuang Ren
Recently, 3D deep neural networks have been fully developed and applied to many high-safety tasks. However, due to the uninterpretability of deep learning networks, adversarial examples can easily prompt a normally trained deep learning model to make wrong predictions. In this paper, we propose a new point cloud defense network named DDR-Defense, a framework for defending neural network classifiers against adversarial examples. DDR-Defense neither modifies the number of the points in the input samples nor the protected classifiers so that it can protect most classification models. DDR-Defense first distinguishes adversarial examples from normal examples through a reconstruction-based detector. The detector can prevent errors caused by processing the entire input samples, thereby improving the security of the defense network. For adversarial examples, we first use the statistical outlier removal (SOR) method for denoising, then use a reformer to rebuild them. In this paper, We design a new reformer based on FoldingNet and variational autoencoder, named Folding-VAE. We test DDR-Defense on the ModelNet40 dataset and find that it has a better defense effect than other existing 3D defense networks, especially in saliency maps attack and LG-GAN attack. The lightweight detector, denoiser, and reformer framework ensures the security and efficiency of 3D defense for most application scenarios. Our research will provide a basis for improving the robustness of deep learning models on 3D point clouds.
{"title":"DDR-Defense: 3D Defense Network with a Detector, a Denoiser, and a Reformer","authors":"Yukun Zhao, Xinyun Zhang, Shuang Ren","doi":"10.1109/ICCC56324.2022.10065933","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065933","url":null,"abstract":"Recently, 3D deep neural networks have been fully developed and applied to many high-safety tasks. However, due to the uninterpretability of deep learning networks, adversarial examples can easily prompt a normally trained deep learning model to make wrong predictions. In this paper, we propose a new point cloud defense network named DDR-Defense, a framework for defending neural network classifiers against adversarial examples. DDR-Defense neither modifies the number of the points in the input samples nor the protected classifiers so that it can protect most classification models. DDR-Defense first distinguishes adversarial examples from normal examples through a reconstruction-based detector. The detector can prevent errors caused by processing the entire input samples, thereby improving the security of the defense network. For adversarial examples, we first use the statistical outlier removal (SOR) method for denoising, then use a reformer to rebuild them. In this paper, We design a new reformer based on FoldingNet and variational autoencoder, named Folding-VAE. We test DDR-Defense on the ModelNet40 dataset and find that it has a better defense effect than other existing 3D defense networks, especially in saliency maps attack and LG-GAN attack. The lightweight detector, denoiser, and reformer framework ensures the security and efficiency of 3D defense for most application scenarios. Our research will provide a basis for improving the robustness of deep learning models on 3D point clouds.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124209643","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065854
Zhiping Lu, Ruxin Zhi, Weiguo Ma
Low earth orbit satellite communication systems are attractive for provisioning global, high-speed and low latency Internet access services. In order to achieve global continuous multiple coverage, the number of satellites is tremendous. But Low earth orbit satellite networks are prone to instability due to unpredictable link failures and frequent topology changes. Therefore, in this paper, a novel routing schemes with quick response to link failures is first proposed. Based on Dijkstra algorithm, a scalable routing algorithm is proposed to minimize the end-to-end transmission delay. It takes advantage of the predictable constellation trajectory, and changes dynamically according to the changes of network topology. It provides the shortest routing path and an alternative path simultaneously. When a link failure is detected by one satellite, notification packets will be sent to its neighbors for adjustment to the alternative routing path. Notification packets also will be sent to the head node for the recalculation of routing table. Finally, extensive simulations have been conducted, and the results show that the proposed scheme is able to produce desired performance.
{"title":"Quick Routing Response to Link Failure in Low-Earth Orbit Satellite Networks","authors":"Zhiping Lu, Ruxin Zhi, Weiguo Ma","doi":"10.1109/ICCC56324.2022.10065854","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065854","url":null,"abstract":"Low earth orbit satellite communication systems are attractive for provisioning global, high-speed and low latency Internet access services. In order to achieve global continuous multiple coverage, the number of satellites is tremendous. But Low earth orbit satellite networks are prone to instability due to unpredictable link failures and frequent topology changes. Therefore, in this paper, a novel routing schemes with quick response to link failures is first proposed. Based on Dijkstra algorithm, a scalable routing algorithm is proposed to minimize the end-to-end transmission delay. It takes advantage of the predictable constellation trajectory, and changes dynamically according to the changes of network topology. It provides the shortest routing path and an alternative path simultaneously. When a link failure is detected by one satellite, notification packets will be sent to its neighbors for adjustment to the alternative routing path. Notification packets also will be sent to the head node for the recalculation of routing table. Finally, extensive simulations have been conducted, and the results show that the proposed scheme is able to produce desired performance.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"10 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114339607","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065697
R. Guo, Guangyuan Xu, Zhenyu Yin, Jiong Li, Feiqing Zhang
To solve the problem of low accuracy of rolling bearing fault diagnosis under complex noise and variable load conditions, this paper proposes a neural network based solution SSRNet. First, the rolling bearing signal is preprocessed by short-time Fourier transform, and the model structure and residual structure of the neural network are adjusted, and LeakyReLU function is integrated into it. The accuracy of rolling bearing fault diagnosis is improved under the condition of complex noise and variable load. At the same time, the data set of Case Western Reserve University is used for experimental verification. In the SNR of - 4dB, the SSRNet model proposed in this paper can achieve 97.11% accuracy and has better performance than the existing methods.
{"title":"A Neural Network Method for Bearing Fault Diagnosis","authors":"R. Guo, Guangyuan Xu, Zhenyu Yin, Jiong Li, Feiqing Zhang","doi":"10.1109/ICCC56324.2022.10065697","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065697","url":null,"abstract":"To solve the problem of low accuracy of rolling bearing fault diagnosis under complex noise and variable load conditions, this paper proposes a neural network based solution SSRNet. First, the rolling bearing signal is preprocessed by short-time Fourier transform, and the model structure and residual structure of the neural network are adjusted, and LeakyReLU function is integrated into it. The accuracy of rolling bearing fault diagnosis is improved under the condition of complex noise and variable load. At the same time, the data set of Case Western Reserve University is used for experimental verification. In the SNR of - 4dB, the SSRNet model proposed in this paper can achieve 97.11% accuracy and has better performance than the existing methods.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114524640","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 : 2022-12-09DOI: 10.1109/ICCC56324.2022.10065654
Zhecheng Wang, Shuai Wan, Lei Wei
The Point cloud is a popular representation format of 3D objects and scenes. For efficient transmission and storage of point clouds in practice, point cloud compression becomes an attractive research topic for academia and industry. Octree coding is one of the main features for coding the geometry in point clouds, as employed in the latest international standard of Geometry-based Point Cloud Compression (G-PCC). This paper aims to improve the performance of the octree coding in G-PCC with reduced complexity. For this purpose, we employ the neighboring nodes to model contexts for the entropy coding directly. As to neighboring sub-nodes, intermedia states are observed first during the coding process, with a memory channel employed for each state to record the occupancy bits of the already coded sub-nodes with the same state. Then the correlation of the sub-nodes recorded in the same memory channel can be utilized to reduce the spatial redundancy further. Compared to the state-of-the-art GPCC codec, the proposed entropy coding method provides about 1.0% bpp (bit per input point) and 3.5% BD-Rate (Bj⊘ntegaard Delta Rate) reduction under lossless and lossy geometry compression, respectively. Moreover, the proposed method also reduces the complexity.
{"title":"Entropy Coding of Point Cloud Geometry Using Memory Channel","authors":"Zhecheng Wang, Shuai Wan, Lei Wei","doi":"10.1109/ICCC56324.2022.10065654","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065654","url":null,"abstract":"The Point cloud is a popular representation format of 3D objects and scenes. For efficient transmission and storage of point clouds in practice, point cloud compression becomes an attractive research topic for academia and industry. Octree coding is one of the main features for coding the geometry in point clouds, as employed in the latest international standard of Geometry-based Point Cloud Compression (G-PCC). This paper aims to improve the performance of the octree coding in G-PCC with reduced complexity. For this purpose, we employ the neighboring nodes to model contexts for the entropy coding directly. As to neighboring sub-nodes, intermedia states are observed first during the coding process, with a memory channel employed for each state to record the occupancy bits of the already coded sub-nodes with the same state. Then the correlation of the sub-nodes recorded in the same memory channel can be utilized to reduce the spatial redundancy further. Compared to the state-of-the-art GPCC codec, the proposed entropy coding method provides about 1.0% bpp (bit per input point) and 3.5% BD-Rate (Bj⊘ntegaard Delta Rate) reduction under lossless and lossy geometry compression, respectively. Moreover, the proposed method also reduces the complexity.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"124 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120824263","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：