使用深度学习的计算机视觉

使用计算机视觉应用程序扩展深度学习工作流程

Apply deep learning to computer vision applications by using Deep Learning Toolbox™ together with the Computer Vision Toolbox™.

Apps

Image Labeler	计算机视觉应用的标签图像
Video Labeler	计算机视觉应用的标签视频

Functions

展开全部

培训数据的数据存储

`boxLabelDatastore`	Datastore for bounding box label data
`Pixellabeldatastore`	Datastore for pixel label data

语义细分

`deeplabv3plusLayers`	Create DeepLab v3+ convolutional neural network for semantic image segmentation
`segnetlayers`	Create SegNet layers for semantic segmentation
`unetLayers`	Create U-Net layers for semantic segmentation
`UNET3Dlayers`	Create 3-D U-Net layers for semantic segmentation of volumetric images

Object Detection

`rcnnObjectDetector`	使用R-CNN深度学习检测器检测对象
`fastRCNNObjectDetector`	Detect objects using Fast R-CNN deep learning detector
`fasterRCNNObjectDetector`	使用更快的R-CNN深度学习检测器检测对象
`ssdObjectDetector`	Detect objects using SSD deep learning detector
`yolov2ObjectDetector`	使用Yolo V2对象检测器检测对象
`Yolov3ObjectDetector`	使用Yolo V3对象检测器检测对象
`Yolov4ObjectDetector`	Detect objects using YOLO v4 object detector
`maskrcnn`	使用蒙版R-CNN实例分段检测对象

Text Detection and Recognition

检测文本 使用工艺深度学习模型检测图像中的文本

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
此示例显示了如何作为对象检测工作流程的一部分执行常见的图像和边界框增强。
使用R-CNN深度学习训练对象探测器
此示例显示了如何使用深度学习和R-CNN（具有卷积神经网络的区域）训练对象探测器。
进口预估计的ONNX YOLO V2对象检测器
This example shows how to import a pretrained ONNX™ (Open Neural Network Exchange) you only look once (YOLO) v2 [1] object detection network and use it to detect objects.
导出Yolo V2对象检测器到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。
火车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
此示例显示了如何使用Grad-CAM探索语义分割网络的预测。
生成语义细分的对抗示例(Computer Vision Toolbox)
Generate adversarial examples for a semantic segmentation network using the basic iterative method (BIM).

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。

Featured Examples

Object Detection Using Faster R-CNN Deep Learning

火车a Faster R-CNN (regions with convolutional neural networks) object detector.

打开实时脚本

Object Detection Using YOLO v2 Deep Learning

火车a you only look once (YOLO) v2 object detector.

打开实时脚本

使用PointNet深度学习点云分类

火车a PointNet network for point cloud classification.

打开实时脚本

Object Detection Using SSD Deep Learning

火车a Single Shot Detector (SSD).

打开实时脚本

对象检测使用YOLO v3意思深入学习

火车a YOLO v3 object detector.

打开实时脚本

Object Detection Using YOLO v4 Deep Learning

使用您的图像中检测对象，只有一次版本4（YOLO V4）深度学习网络。在此示例中，您将

打开实时脚本

Perform Instance Segmentation Using Mask R-CNN

Segment individual instances of people and cars using a multiclass Mask region-based convolutional neural network (R-CNN).

语义细分Using Deep Learning

火车a semantic segmentation network using deep learning.

打开实时脚本

使用深度学习从细分图生成图像

从语义分割图生成场景的合成图像。

打开实时脚本

Estimate Body Pose Using Deep Learning

Estimate the body pose of one or more people using the OpenPose algorithm.

打开实时脚本

Activity Recognition from Video and Optical Flow Data Using Deep Learning

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].

打开实时脚本

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。

打开实时脚本