Pub Date : 2020-10-01DOI: 10.1109/ICIP40778.2020.9190689
D. Graziosi, B. Kroon
New standards are emerging for the coding of volumetric 3D data such as immersive video and point clouds. Some of these volumetric encoders similarly utilize video codecs as the core of their compression approach, but apply different techniques to convert volumetric 3D data into 2D content for subsequent 2D video compression. Currently in MPEG there are two activities that follow this paradigm: ISO/IEC 23090-5 Video-based Point Cloud Compression (V-PCC) and ISO/IEC 23090-12 MPEG Immersive Video (MIV). In this article we propose for both standards to define 2D projection as common transmission format. We then describe a procedure based on camera projections that is applicable to both standards to convert 3D information into 2D images for efficient 2D compression. Results show that our approach successfully encodes both point clouds and immersive video content with the same performance as the current test models that MPEG experts developed separately for the respective standards. We conclude the article by discussing further integration steps and future directions.
{"title":"Video-Based Coding Of Volumetric Data","authors":"D. Graziosi, B. Kroon","doi":"10.1109/ICIP40778.2020.9190689","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9190689","url":null,"abstract":"New standards are emerging for the coding of volumetric 3D data such as immersive video and point clouds. Some of these volumetric encoders similarly utilize video codecs as the core of their compression approach, but apply different techniques to convert volumetric 3D data into 2D content for subsequent 2D video compression. Currently in MPEG there are two activities that follow this paradigm: ISO/IEC 23090-5 Video-based Point Cloud Compression (V-PCC) and ISO/IEC 23090-12 MPEG Immersive Video (MIV). In this article we propose for both standards to define 2D projection as common transmission format. We then describe a procedure based on camera projections that is applicable to both standards to convert 3D information into 2D images for efficient 2D compression. Results show that our approach successfully encodes both point clouds and immersive video content with the same performance as the current test models that MPEG experts developed separately for the respective standards. We conclude the article by discussing further integration steps and future directions.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114972387","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9191279
Liang Zhao, Xin Zhao, Shan Liu
A fixed set of intra prediction angles by using the reconstructed samples in adjacent reference line are employed in AV1 to remove the spatial redundancy of video signals. Two methods are proposed in this paper to further improve the intra coding performance of AV1. Firsly, to better signal the intra prediction modes, only a subset of the intra prediction modes (IPMs) are allowed and signaled for each block, which is adaptively selected according to the IPMs of neighboring blocks. Secondly, to reduce the prediction errors when there is a strong discontinuity between the samples in current block and its adjacent reference samples, an adaptive reference line selection method is proposed by enabling farther reference lines for intra prediction. Experimental results show that, the proposed methods achieve 2.2% luma BD-rate savings with around 150% encoding time for intra coding on top of the libaom implementation of AV1.
{"title":"Improved Intra Coding Beyond AV1 Using Adaptive Prediction Angles and Reference Lines","authors":"Liang Zhao, Xin Zhao, Shan Liu","doi":"10.1109/ICIP40778.2020.9191279","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191279","url":null,"abstract":"A fixed set of intra prediction angles by using the reconstructed samples in adjacent reference line are employed in AV1 to remove the spatial redundancy of video signals. Two methods are proposed in this paper to further improve the intra coding performance of AV1. Firsly, to better signal the intra prediction modes, only a subset of the intra prediction modes (IPMs) are allowed and signaled for each block, which is adaptively selected according to the IPMs of neighboring blocks. Secondly, to reduce the prediction errors when there is a strong discontinuity between the samples in current block and its adjacent reference samples, an adaptive reference line selection method is proposed by enabling farther reference lines for intra prediction. Experimental results show that, the proposed methods achieve 2.2% luma BD-rate savings with around 150% encoding time for intra coding on top of the libaom implementation of AV1.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116683439","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9190758
T. Theodoridis, V. Solachidis, K. Dimitropoulos, P. Daras
Food analysis resides at the core of modern nutrition recommender systems, providing the foundation for a high-level understanding of users’ eating habits. This paper focuses on the sub-task of ingredient recognition from food images using a variational framework. The framework consists of two variational encoder-decoder branches, aimed at processing information from different modalities (images and text), as well as a variational mapper branch, which accomplishes the task of aligning the distributions of the individual branches. Experimental results on the Yummly-28K data-set showcase that the proposed framework performs better than similar variational frameworks, while it surpasses current state-of-the-art approaches on the large-scale Recipe1M data-set.
{"title":"A Cross-Modal Variational Framework For Food Image Analysis","authors":"T. Theodoridis, V. Solachidis, K. Dimitropoulos, P. Daras","doi":"10.1109/ICIP40778.2020.9190758","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9190758","url":null,"abstract":"Food analysis resides at the core of modern nutrition recommender systems, providing the foundation for a high-level understanding of users’ eating habits. This paper focuses on the sub-task of ingredient recognition from food images using a variational framework. The framework consists of two variational encoder-decoder branches, aimed at processing information from different modalities (images and text), as well as a variational mapper branch, which accomplishes the task of aligning the distributions of the individual branches. Experimental results on the Yummly-28K data-set showcase that the proposed framework performs better than similar variational frameworks, while it surpasses current state-of-the-art approaches on the large-scale Recipe1M data-set.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116956258","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9190708
Xu Han, Shanshe Wang, Siwei Ma, Wen Gao
To achieve higher compression efficiency, the new developing video coding standard Versatile Video Coding(VVC) introduced a large amount of new coding technologies, which increases the computational complexity of the decoder significantly. Among these technologies, the inter prediction methods, including affine motion compensation and decoder side motion vector refinement(DMVR), make inter prediction become the most time consuming module and bring new challenges for real-time decoding. In this paper, we proposed an efficient GPU-based motion compensation scheme to speedup the decoding. Through re-partition of coding unit(CU) according to the data dependency and different thread organization methods for different situation, the computational resources of GPU are utilized efficiently. Experiments on NVIDIA GeForce RTX 2080Ti GPU showed the motion compensation can be done in 5ms for Ultra HD 4K, which means the decoding speed is accelerated by 16 times compared to the VVC reference software on CPU.
为了获得更高的压缩效率，新开发的视频编码标准VVC (Versatile video coding)引入了大量新的编码技术，这大大增加了解码器的计算复杂度。其中，仿射运动补偿和解码器侧运动矢量细化(DMVR)等互预测方法使得互预测成为耗时最多的模块，给实时解码带来了新的挑战。在本文中，我们提出了一种高效的基于gpu的运动补偿方案来加快解码速度。通过根据数据依赖性对编码单元(CU)进行重新划分，并针对不同情况采用不同的线程组织方法，有效地利用了GPU的计算资源。在NVIDIA GeForce RTX 2080Ti GPU上的实验表明，超高清4K的运动补偿可以在5ms内完成，这意味着与CPU上的VVC参考软件相比，解码速度提高了16倍。
{"title":"Optimization Of Motion Compensation Based On GPU And CPU For VVC Decoding","authors":"Xu Han, Shanshe Wang, Siwei Ma, Wen Gao","doi":"10.1109/ICIP40778.2020.9190708","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9190708","url":null,"abstract":"To achieve higher compression efficiency, the new developing video coding standard Versatile Video Coding(VVC) introduced a large amount of new coding technologies, which increases the computational complexity of the decoder significantly. Among these technologies, the inter prediction methods, including affine motion compensation and decoder side motion vector refinement(DMVR), make inter prediction become the most time consuming module and bring new challenges for real-time decoding. In this paper, we proposed an efficient GPU-based motion compensation scheme to speedup the decoding. Through re-partition of coding unit(CU) according to the data dependency and different thread organization methods for different situation, the computational resources of GPU are utilized efficiently. Experiments on NVIDIA GeForce RTX 2080Ti GPU showed the motion compensation can be done in 5ms for Ultra HD 4K, which means the decoding speed is accelerated by 16 times compared to the VVC reference software on CPU.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120973594","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9191111
Zohaib Amjad Khan, Azeddine Beghdadi, M. Kaaniche, F. A. Cheikh
Laparoscopic images and videos are often affected by different types of distortion like noise, smoke, blur and nonuniform illumination. Automatic detection of these distortions, followed generally by application of appropriate image quality enhancement methods, is critical to avoid errors during surgery. In this context, a crucial step involves an objective assessment of the image quality, which is a two-fold problem requiring both the classification of the distortion type affecting the image and the estimation of the severity level of that distortion. Unlike existing image quality measures which focus mainly on estimating a quality score, we propose in this paper to formulate the image quality assessment task as a multi-label classification problem taking into account both the type as well as the severity level (or rank) of distortions. Here, this problem is then solved by resorting to a deep neural networks based approach. The obtained results on a laparoscopic image dataset show the efficiency of the proposed approach.
{"title":"Residual Networks Based Distortion Classification and Ranking for Laparoscopic Image Quality Assessment","authors":"Zohaib Amjad Khan, Azeddine Beghdadi, M. Kaaniche, F. A. Cheikh","doi":"10.1109/ICIP40778.2020.9191111","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191111","url":null,"abstract":"Laparoscopic images and videos are often affected by different types of distortion like noise, smoke, blur and nonuniform illumination. Automatic detection of these distortions, followed generally by application of appropriate image quality enhancement methods, is critical to avoid errors during surgery. In this context, a crucial step involves an objective assessment of the image quality, which is a two-fold problem requiring both the classification of the distortion type affecting the image and the estimation of the severity level of that distortion. Unlike existing image quality measures which focus mainly on estimating a quality score, we propose in this paper to formulate the image quality assessment task as a multi-label classification problem taking into account both the type as well as the severity level (or rank) of distortions. Here, this problem is then solved by resorting to a deep neural networks based approach. The obtained results on a laparoscopic image dataset show the efficiency of the proposed approach.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127365903","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9191168
A. Pinto, Manuel Alberto Cordova Neira, L. G. L. Decker, J. L. Flores-Campana, M. R. Souza, A. Santos, Jhonatas S. Conceição, H. F. Gagliardi, D. Luvizon, R. Torres, H. Pedrini
Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as virtual and augmented reality applications. To enhance the user’s experience in three-dimensional virtual environments, the motion parallax estimation is a promising technique to achieve this objective. In this paper, we propose an algorithm for generating parallax motion effects from a single image, taking advantage of state-of-the-art instance segmentation and depth estimation approaches. This work also presents a comparison against such algorithms to investigate the trade-off between efficiency and quality of the parallax motion effects, taking into consideration a multi-task learning network capable of estimating instance segmentation and depth estimation at once. Experimental results and visual quality assessment indicate that the PyD-Net network (depth estimation) combined with Mask R-CNN or FBNet networks (instance segmentation) can produce parallax motion effects with good visual quality.
{"title":"Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation","authors":"A. Pinto, Manuel Alberto Cordova Neira, L. G. L. Decker, J. L. Flores-Campana, M. R. Souza, A. Santos, Jhonatas S. Conceição, H. F. Gagliardi, D. Luvizon, R. Torres, H. Pedrini","doi":"10.1109/ICIP40778.2020.9191168","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191168","url":null,"abstract":"Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as virtual and augmented reality applications. To enhance the user’s experience in three-dimensional virtual environments, the motion parallax estimation is a promising technique to achieve this objective. In this paper, we propose an algorithm for generating parallax motion effects from a single image, taking advantage of state-of-the-art instance segmentation and depth estimation approaches. This work also presents a comparison against such algorithms to investigate the trade-off between efficiency and quality of the parallax motion effects, taking into consideration a multi-task learning network capable of estimating instance segmentation and depth estimation at once. Experimental results and visual quality assessment indicate that the PyD-Net network (depth estimation) combined with Mask R-CNN or FBNet networks (instance segmentation) can produce parallax motion effects with good visual quality.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127434208","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9191144
Samr Ali, N. Bouguila
Challenges in realtime installation of surveillance systems is an active area of research, especially with the use of adaptable machine learning techniques. In this paper, we propose the use of variational learning of Beta-Liouville (BL) hidden Markov models (HMM) for AR in an online setup. This proposed incremental framework enables continuous adjustment of the system for better modelling. We evaluate the proposed model on the visible IOSB dataset to validate the framework.
{"title":"Online Learning for Beta-Liouville Hidden Markov Models: Incremental Variational Learning for Video Surveillance and Action Recognition","authors":"Samr Ali, N. Bouguila","doi":"10.1109/ICIP40778.2020.9191144","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191144","url":null,"abstract":"Challenges in realtime installation of surveillance systems is an active area of research, especially with the use of adaptable machine learning techniques. In this paper, we propose the use of variational learning of Beta-Liouville (BL) hidden Markov models (HMM) for AR in an online setup. This proposed incremental framework enables continuous adjustment of the system for better modelling. We evaluate the proposed model on the visible IOSB dataset to validate the framework.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124824291","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9191145
Yasheng Sun, Tao He, Ying-hong Peng, Jin Qi, Jie Hu
In this paper, we introduce an approach for visual tracking in videos that predicts the bounding box location of a target object at every frame. This tracking problem is formulated as a sequential decision-making process where both historical and current information are taken into account to decide the correct object location. We develop a deep reinforcement learning based strategy, via which the target object position is predicted and decided in a unified framework. Specifically, a RNN based prediction network is developed where local features and global features are fused together to predict object movement. Together with the predicted movement, some predefined possible offsets and detection results form into an action space. A decision network is trained in a reinforcement manner to learn to select the most reasonable tracking box from the action space, through which the target object is tracked at each frame. Experiments in an existing tracking benchmark demonstrate the effectiveness and robustness of our proposed strategy.
{"title":"Prediction-Decision Network For Video Object Tracking","authors":"Yasheng Sun, Tao He, Ying-hong Peng, Jin Qi, Jie Hu","doi":"10.1109/ICIP40778.2020.9191145","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191145","url":null,"abstract":"In this paper, we introduce an approach for visual tracking in videos that predicts the bounding box location of a target object at every frame. This tracking problem is formulated as a sequential decision-making process where both historical and current information are taken into account to decide the correct object location. We develop a deep reinforcement learning based strategy, via which the target object position is predicted and decided in a unified framework. Specifically, a RNN based prediction network is developed where local features and global features are fused together to predict object movement. Together with the predicted movement, some predefined possible offsets and detection results form into an action space. A decision network is trained in a reinforcement manner to learn to select the most reasonable tracking box from the action space, through which the target object is tracked at each frame. Experiments in an existing tracking benchmark demonstrate the effectiveness and robustness of our proposed strategy.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125075095","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9191118
Martin Alain, A. Smolic
Light fields are able to capture light rays from a scene arriving at different angles, effectively creating multiple perspective views of the same scene. Thus, one of the flagship applications of light fields is to estimate the captured scene geometry, which can notably be achieved by establishing correspondences between the perspective views, usually in the form of a disparity map. Such correspondence estimation has been a long standing research topic in computer vision, with application to stereo vision or optical flow. Research in this area has shown the importance of well designed descriptors to enable fast and accurate matching. We propose in this paper a binary descriptor exploiting the light field gradient over both the spatial and the angular dimensions in order to improve inter view matching. We demonstrate in a disparity estimation application that it can achieve comparable accuracy compared to existing descriptors while being faster to compute.
{"title":"A Spatio-Angular Binary Descriptor For Fast Light Field Inter View Matching","authors":"Martin Alain, A. Smolic","doi":"10.1109/ICIP40778.2020.9191118","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9191118","url":null,"abstract":"Light fields are able to capture light rays from a scene arriving at different angles, effectively creating multiple perspective views of the same scene. Thus, one of the flagship applications of light fields is to estimate the captured scene geometry, which can notably be achieved by establishing correspondences between the perspective views, usually in the form of a disparity map. Such correspondence estimation has been a long standing research topic in computer vision, with application to stereo vision or optical flow. Research in this area has shown the importance of well designed descriptors to enable fast and accurate matching. We propose in this paper a binary descriptor exploiting the light field gradient over both the spatial and the angular dimensions in order to improve inter view matching. We demonstrate in a disparity estimation application that it can achieve comparable accuracy compared to existing descriptors while being faster to compute.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126164837","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 : 2020-10-01DOI: 10.1109/ICIP40778.2020.9190735
Baohua Sun, Hao Sha, M. Rafie, Lin Yang
Intelligent transportation is a complex system that involves the interaction of connected technologies, including Smart Sensors, Intelligent and Autonomous Vehicles, High Precision Maps, and 5G. The coordination of all these machines mandates a common language that serves as a protocol for intelligent machines to communicate. International standards serves as the global protocol to satisfy industry needs at the product level. MPEG-CDVA is the official ISO standard for search and retrieval applications by providing Compact Descriptors for Video Analysis (CDVA). It is robust and enables efficient implementations on embedded systems. CDVA is the first generation language for images/videos. MPEG-VCM is developing advanced features beyond CDVA to the new generation as Video Coding for Machines (VCM). With the wide availability of low-power AI chips, CDVA and VCM are ready to deploy and serve as the language for intelligent and autonomous vehicles. In this paper, we demonstrate the use of the SuperCDVA and Closed Captioning CDVA algorithms for intelligent and autonomous vehicles. Concepts are borrowed from the Super Characters algorithm in Natural Language Processing. In order for intelligent and autonomous vehicles to understand events on the road, the CDVA vectors are organized into an image to represent the story of the video.
{"title":"CDVA/VCM: Language for Intelligent and Autonomous Vehicles","authors":"Baohua Sun, Hao Sha, M. Rafie, Lin Yang","doi":"10.1109/ICIP40778.2020.9190735","DOIUrl":"https://doi.org/10.1109/ICIP40778.2020.9190735","url":null,"abstract":"Intelligent transportation is a complex system that involves the interaction of connected technologies, including Smart Sensors, Intelligent and Autonomous Vehicles, High Precision Maps, and 5G. The coordination of all these machines mandates a common language that serves as a protocol for intelligent machines to communicate. International standards serves as the global protocol to satisfy industry needs at the product level. MPEG-CDVA is the official ISO standard for search and retrieval applications by providing Compact Descriptors for Video Analysis (CDVA). It is robust and enables efficient implementations on embedded systems. CDVA is the first generation language for images/videos. MPEG-VCM is developing advanced features beyond CDVA to the new generation as Video Coding for Machines (VCM). With the wide availability of low-power AI chips, CDVA and VCM are ready to deploy and serve as the language for intelligent and autonomous vehicles. In this paper, we demonstrate the use of the SuperCDVA and Closed Captioning CDVA algorithms for intelligent and autonomous vehicles. Concepts are borrowed from the Super Characters algorithm in Natural Language Processing. In order for intelligent and autonomous vehicles to understand events on the road, the CDVA vectors are organized into an image to represent the story of the video.","PeriodicalId":405734,"journal":{"name":"2020 IEEE International Conference on Image Processing (ICIP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123288000","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：