语义分割

语义图像分割

语义分割将图像的每个像素与一个类标签相关联，例如花、人、道路、天空或汽车。使用图像标注器和视频标注器以交互方式标注像素，并导出标签数据以训练神经网络。

Input image of a seascape, then a series of cubes representing a deep learning network and a semantic segmented output image of the input.

App

图像标注器	为计算机视觉应用标注图像
视频标注器	Label video for computer vision applications

函数

全部展开

加载训练数据

`combine`	合并来自多个数据存储的数据
`countEachLabel`	Count occurrence of pixel or box labels
`groundTruth`	Ground truth label data
`imageDatastore`	图像数据的数据存储
`pixelLabelDatastore`	Datastore for pixel label data
`pixelLabelTrainingData`	Create training data for semantic segmentation from ground truth

增强和预处理训练数据

`balancePixelLabels`	Balance pixel labels by oversampling block locations in large images
`imwarp`	对图像应用几何变换
`imcrop`	裁剪图像
`imresize`	调整图像大小
`transform`	变换数据存储
`randomAffine2d`	Create randomized 2-D affine transformation
`randomWindow2d`	Randomly select rectangular region in image (自 R2021a 起)
`centerCropWindow2d`	Create rectangular center cropping window

配置语义分割深度学习网络

`bisenetv2`	Create BiSeNet v2 convolutional neural network for semantic segmentation (自 R2025a 起)
`unet`	Create U-Net convolutional neural network for semantic segmentation (自 R2024a 起)
`unet3d`	Create 3-D U-Net convolutional neural network for semantic segmentation of volumetric images (自 R2024a 起)
`deeplabv3plus`	Create DeepLab v3+ convolutional neural network for semantic image segmentation (自 R2024a 起)
`focalCrossEntropy`	Compute focal cross-entropy loss

使用深度学习分割图像

`semanticseg`	Semantic image segmentation using deep learning
`imsegsam`	Perform automatic full image segmentation using Segment Anything Model (SAM) (自 R2024b 起)
`segmentAnythingModel`	Pretrained Segment Anything Model (SAM) for semantic segmentation (自 R2024a 起)

可视化分割

`labeloverlay`	Overlay label matrix regions on 2-D image
`volshow`	Display volume
`insertObjectMask`	Insert masks in image or video stream

评估分割结果

`evaluateSemanticSegmentation`	Evaluate semantic segmentation data set against ground truth
`bfscore`	Contour matching score for image segmentation
`dice`	Sørensen-Dice similarity coefficient for image segmentation
`generalizedDice`	Generalized Sørensen-Dice similarity coefficient for image segmentation (自 R2021a 起)
`jaccard`	Jaccard similarity coefficient for image segmentation
`segmentationConfusionMatrix`	Confusion matrix of multi-class pixel-level image segmentation
`semanticSegmentationMetrics`	Semantic segmentation quality metrics

主题

快速入门

Get Started with Semantic Segmentation Using Deep Learning
Segment objects by class using deep learning networks such as U-Net and DeepLab v3+.
Choose Function to Visualize Detected Objects
Compare visualization functions.

为语义分割创建真实值数据

Label Pixels for Semantic Segmentation
Label pixels for training a semantic segmentation network by using a labeling app.
How Labeler Apps Store Exported Pixel Labels
Learn how the labeling apps store pixel label data.

为语义分割创建训练数据

Training Data for Object Detection and Semantic Segmentation
Create training data for object detection or semantic segmentation using the Image Labeler or Video Labeler.
Datastores for Deep Learning (Deep Learning Toolbox)
Learn how to use datastores in deep learning applications.
Get Started with Image Preprocessing and Augmentation for Deep Learning
Preprocess data for deep learning applications with deterministic operations such as resizing, or augment training data with randomized operations such as random cropping.

精选示例

Automatically Label Ground Truth Using Segment Anything Model

Produce pixel labels for semantic segmentation using the Segment Anything Model (SAM) in the 图像标注器 app. The SAM is an automatic segmentation technique that you can use to segment object regions to label with just a few clicks, or automatically segment the entire image and instantaneously create labels for selected regions. In this example, you interactively label pixels for semantic segmentation in two ways.