共查询到20条相似文献,搜索用时 15 毫秒
1.
针对基于人体骨架序列的动作识别存在的特征提取不充分、不全面及识别准确率不高的问题,本文提出了基于多分支特征和多尺度时空特征的动作识别模型。首先,利用多种算法的结合对原始数据进行了特征增强;其次,将多分支的特征输入形式改进为多分支的融合特征信息并分别输入到网络中,经过一定深度的网络模块后融合在一起;然后,构建多尺度的时空卷积模块作为网络的基本模块,用来提取多尺度的时空特征;最后,构建整体网络模型输出动作类别。实验结果表明,在NTURGB-D60数据集的两种划分标准Cross-subject和Cross-view上的识别准确率分别为89.6%和95.1%,在NTURGB-D120数据集的两种划分标准Cross-subject和Cross-setup上的识别准确率分别为84.1%和86.0%。与其他算法相对比,本文算法提取到了更为多样化、多尺度的动作特征,动作类别的识别准确率有一定的提升。 相似文献
2.
《Journal of Visual Communication and Image Representation》2014,25(6):1432-1445
In this paper we introduce a novel method for action/movement recognition in motion capture data. The joints orientation angles and the forward differences of these angles in different temporal scales are used to represent a motion capture sequence. Initially K-means is applied on training data to discover the most representative patterns on orientation angles and their forward differences. A novel K-means variant that takes into account the periodic nature of angular data is applied on the former. Each frame is then assigned to one or more of these patterns and histograms that describe the frequency of occurrence of these patterns for each movement are constructed. Nearest neighbour and SVM classification are used for action recognition on the test data. The effectiveness and robustness of this method is shown through extensive experimental results on four standard databases of motion capture data and various experimental setups. 相似文献
3.
4.
Romain Raveaux Jean-Christophe Burie Jean-Marc Ogier 《Journal of Visual Communication and Image Representation》2013,24(8):1252-1268
Here, we propose an automatic system to annotate and retrieve images. We assume that regions in an image can be described using a vocabulary of blobs. Blobs are generated from image features using clustering. Features are locally extracted on regions to capture Color, Texture and Shape information. Regions are processed by an efficient segmentation algorithm. Images are structured into a region adjacency graph to consider spatial relationships between regions. This representation is used to perform a similarity search into an image set. Hence, the user can express his need by giving a query image, and thereafter receiving as a result all similar images. Our graph based approach is benchmarked to conventional Bag of Words methods. Results tend to reveal a good behavior in classification of our graph based solution on two publicly available databases. Experiments illustrate that a structural approach requires a smaller vocabulary size to reach its best performance. 相似文献
6.
针对运动多目标识别与跟踪所必需的准备环节--运动目标检测,本文提出了的一种改进的自适应运动目标检测方法,检测运动目标是否存在,并利用试验证明,该方法确实不仅能有效抑制光照变化、人影、噪声等影响,进而对运动目标是否在跟踪区域徘徊进行判断,保证了对进出目标跟踪的准确跟踪,而且运算量小,容易软件实现,实际效果较好. 相似文献
7.
8.
As a challenging task of video classification, action recognition has become a significant topic of computer vision community. The most popular methods based on two-stream architecture up to now are still simply fusing the prediction scores of each stream. In that case, the complementary characteristics of two streams cannot be fully utilized and the effect of shallower features is often overlooked. In addition, the equal treatment to features may weaken the role of the feature contributing significantly to the classification. Accordingly, a novel network called Multiple Depth-levels Features Fusion Enhanced Network (MDFFEN) is proposed. It improves on two aspects of two-stream architecture. In terms of the two-stream interaction mechanism, multiple depth-levels features fusion (MDFF) is formed to aggregate spatial–temporal features extracted from several sub-modules of original two streams by spatial–temporal features fusion (STFF). And with respect to further refining the spatiotemporal features, we propose a group-wise spatial-channel enhance (GSCE) module to highlight the meaningful regions and expressive channels automatically by priority assignment. The competitive results are achieved after we validate MDFFEN on three public challenging action recognition datasets, HDMB51, UCF101 and ChaLearn LAP IsoGD. 相似文献
9.
10.
基于相关区域约束的SURF特征点匹配 总被引:1,自引:0,他引:1
针对特征向量匹配计算量较大的问题,提出了一种改进的基于区域相关约束的快速鲁棒局部特征(SURF,Speeded-Up Robust Feature)的视频帧间的特征匹配算法。相比于最近邻与次近邻之比,增加随机抽样一致性估计来去除误匹配,再结合连续帧间的像素相关性,进一步降低误匹配和加速匹配过程。在PETS数据库的仿真结果表明,该算法能够在凌乱和存在遮挡的背景下完成目标识别,去除误匹配更加有效,适用于对实时性要求较高的场合。 相似文献
11.
一种基于词袋模型的图像分类方法 总被引:1,自引:0,他引:1
采用词袋模型(BoW)对图像进行分类,并针对传统词袋模型存在的不足进行了改进,提出了一种特征软量化的方式。软赋值量化通过将局部显著特征量化(SIFT)为与其距离最近的若干个视觉单词,并对其进行加权,由此保存特征空间中的距离信息,从而解决硬赋值量化造成的特征空间信息损失问题。通过在Caltech 101数据库进行实验,验证了本文方法的有效性,实验结果表明,该方法能够大幅度提高图像分类的性能。 相似文献
12.
13.
14.
本文提出了一种新的针对细化指纹图像的修复方法,通过参照附近有效指纹线条的走向来还原或者修复断裂了的指纹线条,这样就突破了只有近距离近似方向才能修复的局限,并且很好地修补了本该连接的断裂指纹线条,有利于提高以后的指纹特征值提取的精确性。实验结果表明,不管两断裂点距离是近还是远,两断裂点所在指纹线条的方向相差多大,这种方法均能够很好地修复指纹图像。 相似文献
15.
Gait and static body measurement are important biometric technologies for passive human recognition. Many previous works argue that recognition performance based completely on the gait feature is limited. The reason for this limited performance remains unclear. This study focuses on human recognition with gait feature obtained by Kinect and shows that gait feature can effectively distinguish from different human beings through a novel representation – relative distance-based gait features. Experimental results show that the recognition accuracy with relative distance features reaches up to 85%, which is comparable with that of anthropometric features. The combination of relative distance features and anthropometric features can provide an accuracy of more than 95%. Results indicate that the relative distance feature is quite effective and worthy of further study in more general scenarios (e.g., without Kinect). 相似文献
16.
17.
18.
19.
针对现有通道注意力机制对各通道信息直接全局平均池化而忽略其局部空间信息的问题,该文结合人体行为识别研究提出了两种改进通道注意力模块,即矩阵操作的时空(ST)交互模块和深度可分离卷积(DS)模块。ST模块通过卷积和维度转换操作提取各通道时空加权信息数列,经卷积得到各通道的注意权重;DS模块首先利用深度可分离卷积获取各通道局部空间信息,然后压缩通道尺寸使其具有全局的感受野,接着通过卷积操作得到各通道注意权重,进而完成通道注意力机制下的特征重标定。将改进后的注意力模块插入基础网络并在常见的人体行为识别数据集UCF101和HDBM51上进行实验分析,实现了准确率的提升。 相似文献
20.