Recently, 3D display technology, and content creation tools have been undergone rigorous development and as a result they have been widely adopted by home and professional users. 3D digital repositories are increasing...Recently, 3D display technology, and content creation tools have been undergone rigorous development and as a result they have been widely adopted by home and professional users. 3D digital repositories are increasing and becoming available ubiquitously. However, searching and visualizing 3D content remains a great challenge. In this paper, we propose and present the development of a novel approach for creating hypervideos, which ease the 3D content search and retrieval. It is called the dynamic hyperlinker for 3D content search and retrieval process. It advances 3D multimedia navigability and searchability by creating dynamic links for selectable and clickable objects in the video scene whilst the user consumes the 3D video clip. The proposed system involves 3D video processing, such as detecting/tracking clickable objects, annotating objects, and metadata engineering including 3D content descriptive protocol. Such system attracts the attention from both home and professional users and more specifically broadcasters and digital content providers. The experiment is conducted on full parallax holoscopic 3D videos “also known as integral images”.展开更多
A new faster block-matching algorithm （BMA） by using both search candidate and pixd sulzsamplings is proposed. Firstly a pixd-subsampling approach used in adjustable partial distortion search （APDS） is adjusted to...A new faster block-matching algorithm （BMA） by using both search candidate and pixd sulzsamplings is proposed. Firstly a pixd-subsampling approach used in adjustable partial distortion search （APDS） is adjusted to visit about half points of all search candidates by subsampling them, using a spiral-scanning path with one skip. Two sdected candidates that have minimal and second minimal block distortion measures are obtained. Then a fine-tune step is taken around them to find the best one. Some analyses are given to approve the rationality of the approach of this paper. Experimental results show that, as compared to APDS, the proposed algorithm can enhance the block-matching speed by about 30% while maintaining its MSE performance very close to that of it. And it performs much better than many other BMAs such as TSS, NTSS, UCDBS and NPDS.展开更多
A minimum distortion direction prediction-based novel fast half-pixel motion vector search algorithm is proposed, which can reduce considerably the computation load of half-pixel search. Based on the single valley cha...A minimum distortion direction prediction-based novel fast half-pixel motion vector search algorithm is proposed, which can reduce considerably the computation load of half-pixel search. Based on the single valley characteristic of half-pixel error matching function inside search grid, the minimum distortion direction is predicted with the help of comparative results of sum of absolute difference(SAD) values of four integer-pixel points around integer-pixel motion vector. The experimental results reveal that, to all kinds of video sequences, the proposed algorithm can obtain almost the same video quality as that of the half-pixel full search algorithm with a decrease of computation cost by more than 66%.展开更多
人体目标检测对社会治理和城市安全具有很重要的现实意义,监控数据是数据安全的重要来源。小目标检测是目前受到广泛关注的安全检测问题中一项具有挑战性的任务,其检测对象为大型图像中少于20个像素的目标。小目标的特征难以表征,其中...人体目标检测对社会治理和城市安全具有很重要的现实意义,监控数据是数据安全的重要来源。小目标检测是目前受到广泛关注的安全检测问题中一项具有挑战性的任务,其检测对象为大型图像中少于20个像素的目标。小目标的特征难以表征,其中一个主要挑战是,用于预训练/共同训练检测器的数据集(如COCO)与用于微调检测器的数据集(如TinyPerson)之间存在尺度不匹配的情况,这给小目标检测器的性能带来了负面影响。为了解决这个问题,文中提出了一种优化策略,用于匹配不同数据集的尺度,称其为尺度分布搜索(Scale Distribution Search,SDS),同时平衡图片的信息收益(数据集之间的尺度相近)和信息损失(信噪比(SNR)的降低)。该策略使用高斯模型对数据集中目标的尺度分布进行建模,通过迭代的方式寻找最优分布参数;并对比数据集中目标的特征分布和检测器的性能,以找到最佳的尺度分布。通过SDS策略,主流目标检测方法在TinyPerson上实现了更好的性能,证明了SDS策略在提升预训练/共同训练效率上的有效性。展开更多
文摘Recently, 3D display technology, and content creation tools have been undergone rigorous development and as a result they have been widely adopted by home and professional users. 3D digital repositories are increasing and becoming available ubiquitously. However, searching and visualizing 3D content remains a great challenge. In this paper, we propose and present the development of a novel approach for creating hypervideos, which ease the 3D content search and retrieval. It is called the dynamic hyperlinker for 3D content search and retrieval process. It advances 3D multimedia navigability and searchability by creating dynamic links for selectable and clickable objects in the video scene whilst the user consumes the 3D video clip. The proposed system involves 3D video processing, such as detecting/tracking clickable objects, annotating objects, and metadata engineering including 3D content descriptive protocol. Such system attracts the attention from both home and professional users and more specifically broadcasters and digital content providers. The experiment is conducted on full parallax holoscopic 3D videos “also known as integral images”.
基金This project was supported by the National Natural Science Foundation of China (60272099) .
文摘A new faster block-matching algorithm （BMA） by using both search candidate and pixd sulzsamplings is proposed. Firstly a pixd-subsampling approach used in adjustable partial distortion search （APDS） is adjusted to visit about half points of all search candidates by subsampling them, using a spiral-scanning path with one skip. Two sdected candidates that have minimal and second minimal block distortion measures are obtained. Then a fine-tune step is taken around them to find the best one. Some analyses are given to approve the rationality of the approach of this paper. Experimental results show that, as compared to APDS, the proposed algorithm can enhance the block-matching speed by about 30% while maintaining its MSE performance very close to that of it. And it performs much better than many other BMAs such as TSS, NTSS, UCDBS and NPDS.
文摘A minimum distortion direction prediction-based novel fast half-pixel motion vector search algorithm is proposed, which can reduce considerably the computation load of half-pixel search. Based on the single valley characteristic of half-pixel error matching function inside search grid, the minimum distortion direction is predicted with the help of comparative results of sum of absolute difference(SAD) values of four integer-pixel points around integer-pixel motion vector. The experimental results reveal that, to all kinds of video sequences, the proposed algorithm can obtain almost the same video quality as that of the half-pixel full search algorithm with a decrease of computation cost by more than 66%.
文摘人体目标检测对社会治理和城市安全具有很重要的现实意义,监控数据是数据安全的重要来源。小目标检测是目前受到广泛关注的安全检测问题中一项具有挑战性的任务,其检测对象为大型图像中少于20个像素的目标。小目标的特征难以表征,其中一个主要挑战是,用于预训练/共同训练检测器的数据集(如COCO)与用于微调检测器的数据集(如TinyPerson)之间存在尺度不匹配的情况,这给小目标检测器的性能带来了负面影响。为了解决这个问题,文中提出了一种优化策略,用于匹配不同数据集的尺度,称其为尺度分布搜索(Scale Distribution Search,SDS),同时平衡图片的信息收益(数据集之间的尺度相近)和信息损失(信噪比(SNR)的降低)。该策略使用高斯模型对数据集中目标的尺度分布进行建模,通过迭代的方式寻找最优分布参数;并对比数据集中目标的特征分布和检测器的性能,以找到最佳的尺度分布。通过SDS策略,主流目标检测方法在TinyPerson上实现了更好的性能,证明了SDS策略在提升预训练/共同训练效率上的有效性。
