Description: 本代码实现的是人体手势的实时识别。可以分析处理人的手势。是用visual c++开发。-the implementation of the code of human gesture recognition in real-time. Analysis can deal with the gestures. C is visual development. Platform: |
Size: 32539 |
Author:李童 |
Hits:
Description: 整理了现有的手势识别的重点，以及几个重要方法的特点，对每种方法都分析了优缺点，便于大家选择方法确定适合自己的方法。-collation of existing gesture recognition of the key and a number of important features, Each method of analysis of the advantages and help everyone to choose their own methods to determine the appropriate method. Platform: |
Size: 7107 |
Author:faithgod124 |
Hits:
Description: 本代码实现的是人体手势的实时识别。可以分析处理人的手势。是用visual c++开发。-the implementation of the code of human gesture recognition in real-time. Analysis can deal with the gestures. C is visual development. Platform: |
Size: 4781056 |
Author: |
Hits:
Description: 整理了现有的手势识别的重点，以及几个重要方法的特点，对每种方法都分析了优缺点，便于大家选择方法确定适合自己的方法。-collation of existing gesture recognition of the key and a number of important features, Each method of analysis of the advantages and help everyone to choose their own methods to determine the appropriate method. Platform: |
Size: 7168 |
Author:faithgod124 |
Hits:
Description: 在广泛研究前人工作的基础上，本文对运动人物的检测、跟踪与识别进行了综述。为
使分类清楚明了，本文将人物运动分析分为两大类：人体运动分析，人脸分析。人体运动分
析包括人的较大幅度的肢体运动，如手势识别、步态分析、整个人体的运动分析；人脸分析
包括人脸检测与识别、表情分析。在详细介绍了国内外研究现状后，提出了存在的问题及研
究前景。-Extensively studied in previous work on the basis of the figures in this article on the movement detection, tracking and recognition are reviewed. To enable a clear understanding of classification, motion analysis of figures in this article will be divided into two categories: human motion analysis, analysis of human faces. Analysis of human motion including the relatively large body movements, such as gesture recognition, gait analysis, motion analysis of the human body Facial analysis includes face detection and recognition, facial expression analysis. In the study described in detail the status quo at home and abroad, the proposed study of the problems and prospects. Platform: |
Size: 357376 |
Author:martin |
Hits:
Description: 粒子滤波的训练部分.理论部分参考michael isard的博士论文<Visual Motion Analysis by Probabilistic Propagation of Conditional Density>learn a dynamical matrix部分.训练集合和采集需要的图片都包含了(原用于手势跟踪,故图片均为手势图片).采集代码使用另外一个代码image_demo(已上传)-Particle filter part of the training. Michael isard theory some reference to the doctoral dissertation <Visual Motion Analysis by Probabilistic Propagation of Conditional Density> some learn a dynamical matrix. the training needs of the collection and gathering images are included (the original track for the gesture, so pictures are hand picture). collection code to use a different code image_demo (already uploaded) Platform: |
Size: 32040960 |
Author:Rongbin |
Hits:
Description: 本文对当今静态手势识别技术中的各种方法进行了详细的分析，并在此基础上，设计并实现了一套可以进行实时识别的静态手势识别系统。-In this paper a detailed analysis of the various methods of static gesture recognition technology today, and on this basis, the design and realization of a set of real-time identification of static gesture recognition system. Platform: |
Size: 40960 |
Author:史景利 |
Hits:
Description: 在广泛研究前人工作的基础上，本文对运动人物的检测、跟踪与识别进行了综述。为使分类清楚明了，本文将人物运动分析分为两大类：人体运动分析，人脸分析。人体运动分析包括括人的较大幅度的肢体运动，如手势识别、步态分析、整个人体的运动分析；人脸分析包括人脸检测与识别、表情分析。在详细介绍了国内外研究现状后，提出了存在的问题及研究前景。
-On the basis of previous work in the extensive research, detection, tracking and recognition of moving figures were reviewed. Clear classification, character movement analysis is divided into two major categories: human motion analysis, face. Human motion analysis including including more substantial limb movements, such as gesture recognition, gait analysis, motion analysis of the entire human body human face analysis including face detection and recognition, expression analysis. Detailed research status, Problems and research prospects. Platform: |
Size: 357376 |
Author:kommkk |
Hits:
Description: 手势识别非常重要的一个特点是要体验要好，即需要以用户为核心。而手势的定位一般在手势识别过程的前面，在上一篇博文Kinect+OpenNI学习笔记之8(Robert Walter手部提取代码的分析) 中已经介绍过怎样获取手势区域，且取得了不错的效果，但是那个手势部位的提取有一个大的缺点，即需要人站立起来，当站立起来后才能够分隔出手。而手势在人之间的交流时，并不一定要处于站立状态，所以这不是一个好的HCI。因此本文介绍的手势部位的提取并不需要人处于站立状态，同样取得了不错的效果。-A characteristic gesture recognition is very important to experience better, and that needs to be user core. Gestures positioning generally in front of the gesture recognition process on a blog Kinect+OpenNI learning notes (Robert Walter hands to extract the code analysis) has been described how to obtain the gesture area, and achieved good results, but that gestures parts extraction have a big drawback, namely the need to stand up, be able to stand up before separated shot. While the gesture when the exchanges between the people, not necessarily to be in a standing position, so this is not a good HCI. So part of the extract of the article describes the gesture does not need people in the standing position, also achieved good results. Platform: |
Size: 921600 |
Author:wuwei |
Hits:
Description: 通过在线PCA来识别手势，并能对新增手势做一定的增量，很好的实现了增量学习。算法具有效率高，识别率好，速度快等特点，同样适合其他模式识别方面的应用。-The learning method for hand gesture recognition system based on vision is commonly off-line，which results in repeated off-line learning when new hand gestures come． Its real-time performance，expansibility and robustness are poor． In this paper，a method named online principle component analysis ( PCA) with adaptive subspace is proposed for hand gesture recognition． The subspace is updated online by calculating PCA of sample coefficients． The subspace updating strategy is adjusted according to the degree of difference between new sample and learned sample． The algorithm is able to adapt to different situations and reduce the cost of calculation and storage． The incremental online learning and recognition of hand gestures are realized by the proposed algorithm． Experimental results show that the proposed method solves the unknown hand gesture problem，realizes online hand gesture accumulation and updating and improves the recognition performance of system． Platform: |
Size: 2154496 |
Author:张灿淋 |
Hits:
Description: 绍了一个微小型自主直升机试验平台的系统组成和工作原理。基于嵌入式计算机和MEMS传
感器技术，构建了一个小巧的低成本飞行控制系统；针对微小型直升机的姿态控制问题，提出
了一种基于多传感器测量的姿态数据融合方法和姿态控制算法，并进行了飞行试验研究，同时
探讨了初期试验阶段的实用安全装置和方法，给出了单自由度、三自由度和系留飞行姿态控制
试验的结果与分析。-Introduction of a miniature autonomous helicopter testbed system composition and working principle. MEMS-based embedded computer and sensor technology, to build a compact, low-cost flight control systems miniature helicopter for attitude control problem, we propose a gesture based on multi-sensor data fusion method and attitude control algorithms, and conducted flight test research, and discuss the initial pilot phase of the practical security apparatus and method, gives the single degree of freedom, three degrees of freedom and tethered flight attitude control test results and analysis. Platform: |
Size: 565248 |
Author:马国豪 |
Hits:
Description: 感知行为的影响因素包括单个关节的动作和不同关节的组态。因此提出一种新的基于关节的位置差异的特征类型，联合包括静态姿势、动作、位移在内的行为信息进行识别。采用关节在两个时间和空间区域的差异来明确地模拟个别关节动力学和不同关节的组态。然后应用主成分分析（PCA）来获得所需的特征。同时应用非参数的简捷的贝叶斯最近邻（NBNN）分类器进行多类行为的分类。这个NBNN分类器避免了帧描述符的量化，计算“图像到类别”的距离而不是“图像到图像”的距离。15到20帧的数据就足以实现手势以及动作的识别，无需应用整个视频序列，极大地缩短了延时，提高了识别效率。-Perceived behavioral factors, including single-joint movements and configure different joints. Therefore suggests a new location-based differences in the characteristics of the type of joint, the joint including a static posture, movement, displacement including behavioral information for identification. Differences in the use of the joint region both time and space explicitly configured to simulate individual joints kinetics and different joints. Then principal component analysis (PCA) to obtain the desired characteristics. At the same time a simple nonparametric Bayesian nearest neighbor (NBNN) classifier to classify many types of behavior. This avoids the frame NBNN classification descriptors to quantify computing " image to the category" distance rather than distance " image to the image" of. Data 15-20 is sufficient to achieve the gesture and action recognition, without application of the entire video sequence, which greatly reduces the latency and improve the ef Platform: |
Size: 38912 |
Author:杨杨 |
Hits:
Description: 属于机器学习的范畴，通过输入训练样本，通过分类或线性回归得到标签的假设性函数-The Gesture Recognition Toolkit (GRT) is a cross-platform, open-source, C++ machine learning library that has been specifically designed for real-time gesture recognition.
In addition to a comprehensive C++ API, the GRT now also includes an easy-to-use graphical user interface (GUI) which enables user s to stream real-time data into the GUI via the Open Sound Control network protocol. Using the GUI you can:
(1) Setup and configure a gesture recognition pipeline that can be used for classification, regression, or timeseries analysis.
(2) Stream real-time data into the GUI via Open Sound Control (OSC) another application (such as Processing, Max, Pure Data, Openframeworks, etc.).
(3) Record, label, save and load your training data.
(4) Train a model for classification or regression.
(5) Test the generalization abilities of the model (using another test dataset or cross validation).
(6) Perform real-time prediction on new data streamed into the GUI via OSC.
(7) Stre Platform: |
Size: 21445632 |
Author:王哲 |
Hits:
Description: Use kinect to extract joint coordinates can do gesture recognition gesture recognition, hope to be useful to you. Platform: |
Size: 9783296 |
Author:LWPHHXX
|
Hits:
Search - gesture analysis