A system for the capture and synthesis of insect motion

We present an integrated system that enables the capture and synthesis of 3D motions of small scale dynamic creatures, typically insects and arachnids, in order to drive computer generated models. The system consists of a number of stages, initially, the acquisition of a multi-view calibration scene and synchronised video footage of a subject performing some action is carried out. A user guided labelling process, that can be semi-automated using tracking techniques and a 3D point generating algorithm, then enables a full metric calibration and captures the motions of specific points on the subject. The 3D motions extracted, which often come from a limited number of frames of the original footage, are then extended to generate potentially infinitely long, characteristic motion sequences for multiple similar subjects. Finally a novel path following algorithm is used to find optimal path along with coherent motion for synthetic subjects.     

The model-based human body motion analysis system

In this paper, we propose a model-based method to analyze the human walking motion. This system consists of three phases: the preprocessing phase, the model construction phase, and the motion analysis phase. In the experimental results, we show that our system not only analyzes the motion characteristics of the human body, but also recognizes the motion type of the input image sequences. Finally, the synthesized motion sequences are illustrated for verification. The major contributions of this research are: (1) developing a skeleton-based method to analyze the human motion; (2) using Hidden Markov Model (HMM) and posture patterns to describe the motion type.     

Constrained synthesis of textural motion for articulated characters

Obtaining high-quality, realistic motions of articulated characters is both time consuming and expensive, necessitating the development of easy-to-use and effective tools for motion editing and reuse. We propose a new simple technique for generating constrained variations of different lengths from an existing captured or otherwise animated motion. Our technique is applicable to textural motions, such as walking or dancing, where the motion sequence can be decomposed into shorter motion segments without an obvious temporal ordering among them. Inspired by previous work on texture synthesis and video textures, our method essentially produces a reordering of these shorter segments. Discontinuities are eliminated by carefully choosing the transition points and applying local adaptive smoothing in their vicinity, if necessary. The user is able to control the synthesis process by specifying a small number of simple constraints.     

Photo-consistent synthesis of motion blur and depth-of-field effects with a real camera model

Depth-of-field (DOF) and motion blur are important visual cues used for computer graphics and photography to illustrate focus of attention and object motion. In this work, we present a method for photo-realistic DOF and motion blur generation based on the characteristics of a real camera system. Both the depth–blur relation for different camera focus settings and the nonlinear intensity response of image sensors are modeled. The camera parameters are calibrated and used for defocus and motion blur synthesis. For a well-focused real scene image, DOF and motion blur effects are generated by post-processing techniques. Experiments have shown that the proposed method generates more photo-consistent results than the commonly used graphical models.     

在字符权图中挖掘关联规则

为了提高关联规则挖掘效率,在挖掘频繁项目集的同时,挖掘出包含频繁项目集的事务集,提出了基于字符权图的关联规则挖掘算法。首先,提出了字符权图的概念,发现和证明了它的一些性质。基于此,提出了挖掘频繁项目集及包含频繁项目集的事务集的算法。时间和空间复杂性的分析表明,该算法是合理和高效的。     

基于参数化运动合成的运动图构建及其应用

虚拟人运动的可控性和逼真性是虚拟现实应用中追求的重要目标,为了实现对虚拟人的灵活控制,合成出逼真的运动序列,提出了基于参数化运动合成的运动图方法.运动图的结点中存储了具有明确含义的控制参数,通过改变控制参数合成不同的运动片段,可以实现对虚拟人的灵活控制;提出了一种改进的运动融合方法,运动图的边将不同运动片段进行融合,有效的避免了脚步滑动和根关节朝向抖动的产生.根据用户对交互控制和路径轨迹的不同应用需求设计实验,实验结果表明,方法不仅具有较高的控制精度,而且合成的运动序列逼真自然.     

Enriching a motion database by analogous combination of partial human motions

We have synthesized new human body motions from existing motion data, by dividing the body of an animated character into several parts, such as upper and lower body, and partitioning the motion of the character into corresponding partial motions. By combining different partial motions, we can generate new motion sequences. We select the most natural-looking combinations by analyzing the similarity of partial motions, using techniques such as motion segmentation, dimensionality reduction, and clustering. These new combinations can dramatically increase the size of a motion database, allowing more score in selecting motions to meet constraints, such as collision avoidance. We verify the naturalness and physical plausibility of the new motions using an SVM learning model and by analysis of static and dynamic balance.     

A Comparative analysis of Green’s functions of 1D matching equations for motion synthesis

When filtering an input image, the Green’s functions of matching equations are capable of inducing a broad class of motions, a property that has led to their use in several computer graphics and computer vision applications. In all such applications, the Green’s functions of second-order differential equations have been considered, even though no justification has been given for their preference over simpler, first-order equations. Here we present a study of first-order one-dimensional matching equations, both in the uniform and in the affine motion models. Comparing their Green’s functions with those of the corresponding second-order cases, we find evidence for the latter’s superiority in motion synthesis. We also propose and discuss a general discretization scheme for Green’s functions of one-dimensional matching equations, showing that the affine motion model is particularly sensitive to the sampling frequency. In this case, we advocate the use of area sampling, for allowing realistic motion simulations.     

基于变迁图编辑距离的流程相似性算法

为了提高从企业模型库中查询检索模型的效率,提出一种基于变迁图编辑距离的流程相似性算法。首先,给出了变迁图的概念及其生成方法;其次,提出边的长度概念,且删除和插入边的代价由该边的长度决定,基于此定义出图编辑操作及其代价,并用节点匹配算法计算最小图编辑距离;然后,给出两个过程模型的相似性概念和计算方法;最后,通过实验验证了算法的正确性且满足七条相似性性质,并验证了变迁图编辑距离满足四条距离性质。     

Video motion analysis for the synthesis of dynamic cues and Futurist art

This paper presents new methods for stylising video to produce cartoon motion emphasis cues and modern art. Specifically, we introduce “dynamic cues” as a class of motion emphasis cue, encompassing traditional animation techniques such as anticipation and motion exaggeration. We describe methods for automatically synthesising such cues within video premised upon the recovery of articulated figures, and the subsequent manipulation of the recovered pose trajectories. Additionally, we show how our motion emphasis framework may be applied to emulate artwork in the Futurist style, popularised by Duchamp.     

模板化的人体运动合成

为解决现有运动合成方法中控制方式过于复杂的问题,提出一种模板化的运动合成模型,旨在降低运动合成技术的应用门槛.利用稀疏主成分分析(Sparse principal component analysis, SPCA)、Group lasso和Exclusive group lasso对人体运动进行建模,使其对应的每一个低维参数只依赖于少数几个人体关节,构成人体运动的一个内在自由度(Degree of freedom, DOF),并具有直观语义;同时,每个关节被尽量少的低维参数所控制,以减少低维参数对彼此所控制的自由度的交叉影响.实验表明,通过直观地修改低维参数,就能够实时地控制每个参数对应的摆臂幅度、踢腿高度、跳跃距离等运动属性.这种模板学习、模板定制的两步方法,有效地降低了运动合成控制的复杂度,即便非专业人员也可以用其进行艺术创作.     

面向图相似性搜索的高效图编辑距离算法

在图相似性搜索问题中,图编辑距离是较为普遍的度量方法,其计算性能很大程度上决定了图相似性搜索算法的性能。针对传统图编辑距离算法中存在的因大量冗余映射和较大搜索空间导致的性能低下问题,提出了一种改进的图编辑距离算法。该算法首先对图中顶点进行等价划分,以此计算映射编码来判断等价映射;然后定义映射完整性更新等价映射优先级,选出主映射参与扩展;其次,设计高效的启发式函数,提出基于映射编码的下界计算方法,快速得到最优映射。最后,将改进的图编辑距离算法扩展应用于图相似性搜索。在不同数据集上的实验结果表明,该算法具有更好的搜索性能,在搜索空间上最大可降低49%,速度提升了约29%。     

Orderly algorithms for graph generation

The existence of orderly analogues of graph generators proposed by Heap and Farrell is established. The modifications to these algorithms supply practical methods enabling one to generate exhaustive lists of graphs and locally restricted graphs; moreover, the difficulty involved in ensuring that no duplications occur in the list is greatly reduced.     

融合时空图卷积网络与非自回归模型的三维人体运动预测

当前人体运动预测的方法大多采用基于图卷积网络的自回归模型,没有充分考虑关节间的特有关系和自回归网络性能的限制,从而产生平均姿态和误差累积等问题。为解决以上问题,提出融合时空图卷积网络和非自回归的模型对人体运动进行预测。一方面利用时空图卷积的网络提取人体运动序列的局部特征,可以有效减少三维人体运动预测场景中的平均姿态问题和过度堆叠图卷积层引起的过平滑问题的发生;另一方面将非自回归模型与时空图卷积网络进行结合,减少误差累计问题的发生。利用Human3.6M的数据集进行80 ms、160 ms、320 ms和400 ms的人体运动预测实验。结果表明,NAS-GCN模型与现有方法相比,能预测出更精确的结果。     

Path planning directed motion control of virtual humans in complex environments

Natural motion synthesis of virtual humans have been studied extensively, however, motion control of virtual characters actively responding to complex dynamic environments is still a challenging task in computer animation. It is a labor and cost intensive animator-driven work to create realistic human motions of character animations in a dynamically varying environment in movies, television and video games. To solve this problem, in this paper we propose a novel approach of motion synthesis that applies the optimal path planning to direct motion synthesis for generating realistic character motions in response to complex dynamic environment. In our framework, SIPP (Safe Interval Path Planning) search is implemented to plan a globally optimal path in complex dynamic environments. Three types of control anchors to motion synthesis are for the first time defined and extracted on the obtained planning path, including turning anchors, height anchors and time anchors. Directed by these control anchors, highly interactive motions of virtual character are synthesized by motion field which produces a wide variety of natural motions and has high control agility to handle complex dynamic environments. Experimental results have proven that our framework is capable of synthesizing motions of virtual humans naturally adapted to the complex dynamic environments which guarantee both the optimal path and the realistic motion simultaneously.     

一种基于状态转换图的Ajax爬行算法

传统Web爬虫无法解决爬行Ajax应用所面临的JavaScript执行、状态识别与切换、重复状态检测等问题。为此,首先定义Ajax应用的状态转换图,并设计了一种基于状态转换图的Ajax爬行算法,通过该算法可以获取Ajax应用状态信息和后台Deep Web资源。为了提高Ajax爬行的准确性、减少待爬行的状态数目,使用Ajax指纹识别、DOM结构过滤等方法改进上述算法。实验结果表明了算法的有效性和性能。     

A real-time system for motion retrieval and interpretation

This paper proposes a new examplar-based method for real-time human motion recognition using Motion Capture (MoCap) data. We have formalized streamed recognizable actions, coming from an online MoCap engine, into a motion graph that is similar to an animation motion graph. This graph is used as an automaton to recognize known actions as well as to add new ones. We have defined and used a spatio-temporal metric for similarity measurements to achieve more accurate feedbacks on classification. The proposed method has the advantage of being linear and incremental, making the recognition process very fast and the addition of a new action straightforward. Furthermore, actions can be recognized with a score even before they are fully completed. Thanks to the use of a skeleton-centric coordinate system, our recognition method has become view-invariant. We have successfully tested our action recognition method on both synthetic and real data. We have also compared our results with four state-of-the-art methods using three well known datasets for human action recognition. In particular, the comparisons have clearly shown the advantage of our method through better recognition rates.     

Automatic motion detection for surveillance

Automatic motion detection features are able to enhance surveillance efficiency and quality. The aim of this research is to recognize and detect motion automatically around a robot's environment in order to equip a mobile robot for a surveillance task. The required information is based on the input obtained from a charge coupled device (CCD) camera mounted on the mobile robot. As the first step toward achieving the goal, it is necessary to have a stationary mobile robot and moving objects. Experiments in a different environment, such as different movements, size of moving objects, and lighting conditions, have also been conducted. The “adjacent pixels comparison” is the proposed method to detect motion in this experiment. The results have verified that the motion detection experiments operate as expected. This work was presented in part at the 11^th International Symposium on Artificial Life and Robotics, Oita, Japan, January 23–25, 2006