本文来自于csdn,本文章主要运用了多个图片介绍了如何基于深度学习的动作进行识别,希望对您的学习有所帮助。
1
基于matlab人体异常行为检测。可以检测如跌倒,奔跑,打架等异常行为,从而预警。
1
手势动作识别 微调预训练的CNN模型(AlexNet,VGG,ResNet),然后微调LSTM。 该网络应用于手势控制无人机。 训练: 下载直升机编组数据集: : usp 将数据集放在/data文件夹下 运行培训代码并指定数据文件夹的路径 python basic_lstm.py ../data 测试: 使用具有指定型号的网络摄像头运行在线测试代码: cd testing python lstm_test.py ../weights/model_best_865.pth.tar 依存关系: pyTorch-0.3.xx Opencv的3.3.1 PIL-5.0.0 Numpy-1.13.1
2021-10-06 15:47:51 35.82MB Python
1
关于 基于Kinect骨架信息的人体动作识别的论文
2021-10-06 15:41:15 14.09MB Kinect 骨架信息 人体动作
1
用opencv进行姿态识别,人体姿态检测和动作识别
3-D convolutional neural networks (3-D-convNets) have been very recently proposed for action recognition in videos, and promising results are achieved. However, existing 3- D-convNets has two “artificial” requirements that may reduce the quality of video analysis: 1) It requires a fixed-sized (e.g., 112×112) input video; and 2)most of the 3-D-convNets require a fixed-length input (i.e., video shots with fixed number of frames). To tackle these issues, we propose an end-to-end pipeline named Two-stream 3-D-convNet Fusion, which can recognize human actions in videos of arbitrary size and length using multiple features. Specifically, we decompose a video into spatial and temporal shots. By taking a sequence of shots as input, each stream is implemented using a spatial temporal pyramid pooling (STPP) convNet with a long short-term memory (LSTM) or CNN-E model, softmax scores of which are combined by a late fusion.We devise the STPP convNet to extract equal-dimensional descriptions for each variable-size shot, andwe adopt theLSTM/CNN-Emodel to learn a global description for the input video using these time-varying descriptions. With these advantages, our method should improve all 3-D CNN-based video analysis methods. We empirically evaluate our method for action recognition in videos and the experimental results show that our method outperforms the state-of-the-art methods (both 2-D and 3-D based) on three standard benchmark datasets (UCF101, HMDB51 and ACT datasets).
2021-09-25 11:29:08 983KB Action recog 3D convoluti
1
Keras中的两流CNN工具 在的基于骨架的动作识别中,提出了两流CNN,用于基于骨架的动作识别。 它将骨架序列映射到图像(坐标x,y,z到图像R,G,B)。 他们专门设计了骨架变压器模块,以自动重新排列和选择重要的骨架关节。 要求 Python3 凯拉斯 h5py matplotlib 麻木 网络架构 该网络主要由Skeleton Transformer , ConvNet , Feature Fusion和Classification四个模块组成。 两个流的输入分别是原始数据(x,y,z)和帧差。 如下图所示: 用法 function / data_generator.py :生成两个流的输入numpy数组 layer / transformer :Keras中的Skeleton Transformer工具层 网络/ :褶皱有四只苍蝇,具有不同的特征融合方式 结果 模型 准确度(
2021-09-25 10:54:30 115KB keras action-recognition skeleton-data Python
1
为视频中的动作识别建立一个简单的模型 只是为了展示如何在Keras中使用Conv3d。 在视频动作识别中使用KTH数据集。 如何建立更好的模型和调整参数取决于您。
2021-09-20 10:07:34 44.7MB Python
1
毕业设计_ZHUKE 2016毕业设计,基于SVM分类器的动作识别系统
2021-09-16 17:31:24 75.77MB 系统开源
1