使用深度学习的计算机视觉

Extend deep learning workflows with computer vision applications

通过将深度学习Toolbox™与计算机视觉Toolbox™一起使用深度学习将其应用于计算机视觉应用程序。

Apps

Image Labeler	Label images for computer vision applications
Video Labeler	Label video for computer vision applications

Functions

`boxLabelDatastore`	Datastore for bounding box label data
`Pixellabeldatastore`	Datastore for pixel label data
`pixelLabelImageDatastore`	语义分割网络的数据存储

Topics

Object Detection

Getting Started with Object Detection Using Deep Learning(Computer Vision Toolbox)

Object detection using deep learning neural networks.

Augment Bounding Boxes for Object Detection

This example shows how to perform common kinds of image and bounding box augmentation as part of object detection workflows.

使用R-CNN深度学习训练对象探测器

This example shows how to train an object detector using deep learning and R-CNN (Regions with Convolutional Neural Networks).

进口预估计的ONNX YOLO V2对象检测器

此示例显示了如何导入预处理的ONNX™（开放神经网络交换），您只看一次（YOLO）v2 [1]对象检测网络并使用它来检测对象。

Export YOLO v2 Object Detector to ONNX

此示例显示了如何将Yolo V2对象检测网络导出到ONNX™（开放神经网络交换）模型格式。

语义细分

使用深度学习开始使用语义细分(Computer Vision Toolbox)

使用深度学习通过课程进行细分对象。

Train Simple Semantic Segmentation Network in Deep Network Designer

This example shows how to create and train a simple semantic segmentation network using Deep Network Designer.

增强语义细分的像素标签

This example shows how to perform common kinds of image and pixel label augmentation as part of semantic segmentation workflows.

使用扩张卷积的语义分割

使用扩张的卷积训练语义分割网络。

语义细分of Multispectral Images Using Deep Learning

This example shows how to perform semantic segmentation of a multispectral image with seven channels using a U-Net.

3-D Brain Tumor Segmentation Using Deep Learning

This example shows how to train a 3-D U-Net neural network and perform semantic segmentation of brain tumors from 3-D medical images.

Define Custom Pixel Classification Layer with Tversky Loss

This example shows how to define and create a custom pixel classification layer that uses Tversky loss.

使用Grad-CAM探索语义分割网络

This example shows how to explore the predictions of a semantic segmentation network using Grad-CAM.

视频分类

Activity Recognition from Video and Optical Flow Data Using Deep Learning

This example first shows how to perform activity recognition using a pretrained Inflated 3-D (I3D) two-stream convolutional neural network based video classifier and then shows how to use transfer learning to train such a video classifier using RGB and optical flow data from videos [1].

使用视频和深度学习的手势识别

使用验证的慢速视频分类器执行手势识别。