计算机视觉

R2026b

利用计算机视觉应用扩展深度学习工作流

通过将 Computer Vision Toolbox™ 与 Deep Learning Toolbox™ 结合使用，将深度学习应用于计算机视觉应用。

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
目标检测器分析器	Interactively visualize and evaluate object detection results against ground truth (自 R2026a 起)

函数

全部展开

视觉语言模型

`clipNetwork`	Create pretrained CLIP deep learning neural network for vision-language tasks (自 R2026a 起)
`moondream`	Create pretrained Moondream vision-language model (VLM) (自 R2026a 起)
`groundingDinoObjectDetector`	Detect and localize objects using Grounding DINO object detector (自 R2026a 起)

ViT（视觉变换器）

`visionTransformer`	Pretrained vision transformer (ViT) neural network (自 R2023b 起)
`patchEmbeddingLayer`	Patch embedding layer (自 R2023b 起)

语义分割

`bisenetv2`	Create BiSeNet v2 convolutional neural network for semantic segmentation (自 R2025a 起)
`semanticseg`	Semantic image segmentation using deep learning
`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)

目标检测

`rtmdetObjectDetector`	Detect objects using RTMDet object detector (自 R2024b 起)
`yolov4ObjectDetector`	Detect objects using YOLO v4 object detector (自 R2022a 起)
`yolov2ObjectDetector`	Detect objects using YOLO v2 object detector
`yolov3ObjectDetector`	Detect objects using YOLO v3 object detector
`hrnetObjectKeypointDetector`	Create object keypoint detector using HRNet deep learning network (自 R2023b 起)
`ssdObjectDetector`	Detect objects using SSD deep learning detector

实例分割和位姿估计

`solov2`	Segment objects using SOLOv2 instance segmentation network (自 R2023b 起)
`maskrcnn`	Detect objects using Mask R-CNN instance segmentation
`posemaskrcnn`	Predict object pose using Pose Mask R-CNN pose estimation (自 R2024a 起)

目标跟踪和重新识别

reidentificationNetwork Re-identification deep learning network for re-identifying and tracking objects (自 R2024a 起)

文本检测和识别

`detectTextCRAFT`	Detect texts in images by using CRAFT deep learning model (自 R2022a 起)
`ocr`	Recognize text using optical character recognition

主题

目标检测和实例分割

Get Started with Object Detection Using Deep Learning (Computer Vision Toolbox)
Perform object detection using deep learning neural networks such as YOLOX, YOLO v4, RTMDet, and SSD.
Get Started with Instance Segmentation Using Deep Learning (Computer Vision Toolbox)
Segment objects using an instance segmentation model such as SOLOv2 or Mask R-CNN.
Choose an Object Detector (Computer Vision Toolbox)
Compare object detection deep learning models, such as YOLOX, YOLO v4, RTMDet, and SSD.
Augment Bounding Boxes for Object Detection (Computer Vision Toolbox)
This example shows how to perform common kinds of image and bounding box augmentation as part of object detection workflows.
Import Pretrained ONNX YOLO v2 Object Detector
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 the network to detect objects.
Export YOLO v2 Object Detector to ONNX
This example shows how to export a YOLO v2 object detection network to ONNX™ (Open Neural Network Exchange) model format.
Multiclass Object Detection Using YOLO v2 Deep Learning (Computer Vision Toolbox)
Train a YOLO v2 multiclass object detector and evaluate object detector performance across selected classes and overlap thresholds. (自 R2024b 起)
将目标检测模型部署为微服务 (MATLAB Compiler SDK)
此示例说明如何从 MATLAB^® 目标检测模型创建微服务 Docker^® 镜像。

语义分割

Get Started with Semantic Segmentation Using Deep Learning (Computer Vision Toolbox)
Segment objects by class using deep learning networks such as U-Net and DeepLab v3+.
Augment Pixel Labels for Semantic Segmentation (Computer Vision Toolbox)
This example shows how to perform common kinds of image and pixel label augmentation as part of semantic segmentation workflows.
使用扩张卷积进行语义分割
此示例说明如何使用扩张卷积训练语义分割网络。
使用深度学习对多光谱图像进行语义分割 (Computer Vision Toolbox)
此示例说明如何使用 U-Net 对包含七个通道的多光谱图像执行语义分割。
Explore Semantic Segmentation Network Using Grad-CAM
This example shows how to explore the predictions of a pretrained semantic segmentation network using Grad-CAM.
Generate Adversarial Examples for Semantic Segmentation (Computer Vision Toolbox)
Generate adversarial examples for a semantic segmentation network using the basic iterative method (BIM).
Prune and Quantize Semantic Segmentation Network
Reduce the memory footprint of a semantic segmentation network and speed-up inference by compressing the network using pruning and quantization.
Automatically Label Ground Truth Using Segment Anything Model (Computer Vision Toolbox)
Label pixels using the Segment Anything Model (SAM) in the Image Labeler app. (自 R2024b 起)

图像和视频分类

Train Vision Transformer Network for Image Classification
This example shows how to fine-tune a pretrained vision transformer (ViT) neural network to perform classification on a new collection of images.
Human Activity Recognition Using R(2+1)D Video Classification (Computer Vision Toolbox)
Train an R(2+1)D video classifier for activity recognition.
Gesture Recognition using Videos and Deep Learning (Computer Vision Toolbox)
Train a SlowFast convolutional neural network for gesture recognition using RGB data from videos.

精选示例

全新

CBRS Band Radar Detection in 5G Signals and Noise Using YOLOX

Detect rectangular and linear-FM radar pulse waveforms embedded in a 5G+noise environment using a combination of time-frequency maps and a deep learning object detector.

(Signal Processing Toolbox)

自 R2026b 起

Automatically Label Ground Truth Using Vision-Language Model

Automatically label ground truth images for object detection using the Grounding DINO vision-language model (VLM).

(Computer Vision Toolbox)

自 R2026a 起

Perform 6-DoF Pose Estimation for Bin Picking Using Deep Learning

Perform six degrees-of-freedom (6-DoF) pose estimation by estimating the 3-D position and orientation of machine parts in a bin using RGB-D images and a deep learning network.

(Computer Vision Toolbox)