In order to high reality and efficiency, the technique computer animation. With the development of motion capture, a of motion capture （MoCap） has been widely used in the field of large amount of motion capture data...In order to high reality and efficiency, the technique computer animation. With the development of motion capture, a of motion capture （MoCap） has been widely used in the field of large amount of motion capture databases are available and this is significant for the reuse of motion data. But due to the high degree of freedoms and high capture frequency, the dimension of the mo- tion capture data is usually very high and this will lead to a low efficiency in data processing. So how to process the high dimension data and design an efficient and effective retrieval approach has become a challenge which we can＇t ignore. In this paper, first we lay out some problems about the key techniques in motion capture data processing. Then the existing approaches are analyzed and sum- marized. At last, some future work is proposed.展开更多
This article addresses the problem of reference picture optimization in video communication over error prone networks. A novel estimation model for transmission distortion is proposed. This model is capable of recursi...This article addresses the problem of reference picture optimization in video communication over error prone networks. A novel estimation model for transmission distortion is proposed. This model is capable of recursively estimating the overall end-to-end distortion caused by quantization, error propagation, and error concealment. Simulation results show that this model can accurately estimate channel distortion. Then, based on the distortion estimation model, a new non-feedback key-frame reference picture selection （KRPS） algorithm is developed. The optimum reference picture minimizes the transmission distortion under the rate-distortion optimization framework. Extensive experiment results demonstrate that the proposed KRPS algorithm substantially achieves more peak signal to noise ratio （PSNR） gain over traditional prediction, especially in low bit-rate transmission.展开更多
Recognizing scene information in images or has attracted much attention in computer vision or videos, such as locating the objects and answering ＂Where am research field. Many existing scene recognition methods focus...Recognizing scene information in images or has attracted much attention in computer vision or videos, such as locating the objects and answering ＂Where am research field. Many existing scene recognition methods focus on static images, and cannot achieve satisfactory results on videos which contain more complex scenes features than images. In this paper, we propose a robust movie scene recognition approach based on panoramic frame and representative feature patch. More specifically, the movie is first efficiently segmented into video shots and scenes. Secondly, we introduce a novel key-frame extraction method using panoramic frame and also a local feature extraction process is applied to get the representative feature patches （RFPs） in each video shot. Thirdly, a Latent Dirichlet Allocation （LDA） based recognition model is trained to recognize the scene within each individual video scene clip. The correlations between video clips are considered to enhance the recognition performance. When our proposed approach is implemented to recognize the scene in realistic movies, the experimental results shows that it can achieve satisfactory performance.展开更多
激光实时定位与地图构建(simultaneous localization and mapping,SLAM)是创建地图和实时导航的重要手段之一,也是无人驾驶不可缺少的一环。针对目前激光SLAM算法对特征匹配可靠性不足、配准误差较大等问题,基于平面拟合算法,提出一种...激光实时定位与地图构建(simultaneous localization and mapping,SLAM)是创建地图和实时导航的重要手段之一,也是无人驾驶不可缺少的一环。针对目前激光SLAM算法对特征匹配可靠性不足、配准误差较大等问题,基于平面拟合算法,提出一种局部地图改进和关键帧估计的方案。具体包括以下3个方面:①局部地图匹配规则和平面表示方法;②局部地图更新方案;③关键帧筛选机制。该方法解决了目前激光定位方案中缺乏关键帧估计,以及局部地图中平面多向性问题,实验表明该方法使得局部地图能够保留更具多样性的激光雷达帧,同时平面表示和匹配也更为可靠。展开更多
基金Supported by the National Natural Science Foundation of China(No.60875046)by Program for Changjiang Scholars and Innovative Research Team in University(No.IRT1109)+5 种基金the Key Project of Chinese Ministry of Education(No.209029)the Program for Liaoning Excellent Talents in University(No.LR201003)the Program for Liaoning Science and Technology Research in University(No.LS2010008,2009S008,2009S009,LS2010179)the Program for Liaoning Innovative Research Team in University(Nos.2009T005,LT2010005,LT2011018)Natural Science Foundation of Liaoning Province(201102008)by"Liaoning BaiQianWan Talents Program(2010921010,2011921009)"
文摘In order to high reality and efficiency, the technique computer animation. With the development of motion capture, a of motion capture （MoCap） has been widely used in the field of large amount of motion capture databases are available and this is significant for the reuse of motion data. But due to the high degree of freedoms and high capture frequency, the dimension of the mo- tion capture data is usually very high and this will lead to a low efficiency in data processing. So how to process the high dimension data and design an efficient and effective retrieval approach has become a challenge which we can＇t ignore. In this paper, first we lay out some problems about the key techniques in motion capture data processing. Then the existing approaches are analyzed and sum- marized. At last, some future work is proposed.
基金supported by the National Natural Science Foundation of China (60672099)
文摘This article addresses the problem of reference picture optimization in video communication over error prone networks. A novel estimation model for transmission distortion is proposed. This model is capable of recursively estimating the overall end-to-end distortion caused by quantization, error propagation, and error concealment. Simulation results show that this model can accurately estimate channel distortion. Then, based on the distortion estimation model, a new non-feedback key-frame reference picture selection （KRPS） algorithm is developed. The optimum reference picture minimizes the transmission distortion under the rate-distortion optimization framework. Extensive experiment results demonstrate that the proposed KRPS algorithm substantially achieves more peak signal to noise ratio （PSNR） gain over traditional prediction, especially in low bit-rate transmission.
基金supported by the National Funds for Distinguished Young Scientists of China under Grant No.60925010the Specialized Research Fund for the Doctoral Program of Higher Education of China under Grant No.20120005130002+1 种基金the Cosponsored Project of Beijing Committee of Education,the Funds for Creative Research Groups of China under Grant No.61121001the Program for Changjiang Scholars and Innovative Research Team in University of China under Grant No.IRT1049
文摘Recognizing scene information in images or has attracted much attention in computer vision or videos, such as locating the objects and answering ＂Where am research field. Many existing scene recognition methods focus on static images, and cannot achieve satisfactory results on videos which contain more complex scenes features than images. In this paper, we propose a robust movie scene recognition approach based on panoramic frame and representative feature patch. More specifically, the movie is first efficiently segmented into video shots and scenes. Secondly, we introduce a novel key-frame extraction method using panoramic frame and also a local feature extraction process is applied to get the representative feature patches （RFPs） in each video shot. Thirdly, a Latent Dirichlet Allocation （LDA） based recognition model is trained to recognize the scene within each individual video scene clip. The correlations between video clips are considered to enhance the recognition performance. When our proposed approach is implemented to recognize the scene in realistic movies, the experimental results shows that it can achieve satisfactory performance.
文摘激光实时定位与地图构建(simultaneous localization and mapping,SLAM)是创建地图和实时导航的重要手段之一,也是无人驾驶不可缺少的一环。针对目前激光SLAM算法对特征匹配可靠性不足、配准误差较大等问题,基于平面拟合算法,提出一种局部地图改进和关键帧估计的方案。具体包括以下3个方面:①局部地图匹配规则和平面表示方法;②局部地图更新方案;③关键帧筛选机制。该方法解决了目前激光定位方案中缺乏关键帧估计,以及局部地图中平面多向性问题,实验表明该方法使得局部地图能够保留更具多样性的激光雷达帧,同时平面表示和匹配也更为可靠。
