Semantische Segmentierung
Semantische Bildsegmentierung
Die semantische Segmentierung weist jedem Pixel eines Bildes eine Klassenkennzeichnung zu, wie „Blume“, „Person“, „Straße“, „Himmel“ oder „Fahrzeug“. Mit der Image Labeler App und der Video Labeler App können Sie Pixel interaktiv kennzeichnen und die Kennzeichnungsdaten zum Trainieren eines neuronalen Netzwerks exportieren.
![Input image of a seascape, then a series of cubes representing a deep learning network and a semantic segmented output image of the input.](semanticsegmentation_transferlearning.png)
Apps
Image Labeler | Label images for computer vision applications |
Video Labeler | Label video for computer vision applications |
Funktionen
Themen
Erste Schritte
- 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. - Choose Function to Visualize Detected Objects
Compare visualization functions. - Getting Started with Semantic Segmentation Using Deep Learning
Segment objects by class using deep learning. - Getting Started with Point Clouds Using Deep Learning
Understand how to use point clouds for deep learning.
Erstellen von Trainingsdaten für die semantische Segmentierung
- Datastores for Deep Learning (Deep Learning Toolbox)
Learn how to use datastores in deep learning applications. - Training Data for Object Detection and Semantic Segmentation
Create training data for object detection or semantic segmentation using the Image Labeler or Video Labeler. - 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.