La traduction de cette page n'est pas à jour. Cliquez ici pour voir la dernière version en anglais.

Computer Vision

R2024b

Enrichir des workflows de Deep Learning avec des applications de Computer Vision

Appliquez le Deep Learning à des applications de Computer Vision en utilisant Deep Learning Toolbox™ avec Computer Vision Toolbox™.

Applications

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

Fonctions

développer tout

Datastores de données d’apprentissage

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

ViT (Vision Transformer)

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

Segmentation sémantique

`unet`	Create U-Net convolutional neural network for semantic segmentation (depuis R2024a)
`unet3d`	Create 3-D U-Net convolutional neural network for semantic segmentation of volumetric images (depuis R2024a)
`deeplabv3plus`	Create DeepLab v3+ convolutional neural network for semantic image segmentation (depuis R2024a)

Détection d’objets et segmentation d’instances

`rtmdetObjectDetector`	Detect objects using RTMDet object detector (depuis R2024b)
`yolov4ObjectDetector`	Detect objects using YOLO v4 object detector (depuis R2022a)
`yolov2ObjectDetector`	Detect objects using YOLO v2 object detector
`yolov3ObjectDetector`	Detect objects using YOLO v3 object detector
`ssdObjectDetector`	Detect objects using SSD deep learning detector

Segmentation d’instances

`solov2`	Segment objects using SOLOv2 instance segmentation network (depuis R2023b)
`maskrcnn`	Detect objects using Mask R-CNN instance segmentation

Estimation de la pose

posemaskrcnn Predict object pose using Pose Mask R-CNN pose estimation (depuis R2024a)

Pistage et réidentification d’objets

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

Inspection visuelle automatisée

yoloxObjectDetector

efficientADAnomalyDetector

patchCoreAnomalyDetector

fcddAnomalyDetector

fastFlowAnomalyDetector

Détection et reconnaissance de texte

detectTextCRAFT Detect texts in images by using CRAFT deep learning model (depuis R2022a)

Rubriques

Classification d’images

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.

Détection d’objets et segmentation d’instances

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.
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.

Inspection visuelle automatisée

Segmentation sémantique

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+.
Semantic Segmentation Using Dilated Convolutions
This example shows how to train a semantic segmentation network using dilated convolutions.
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.

Classification de vidéos

Sélection d՚exemples

Automatically Label Ground Truth Using Segment Anything Model

Label pixels using the Segment Anything Model (SAM) in the Image Labeler app.

(Computer Vision Toolbox)

Depuis R2024b

Perform Instance Segmentation Using SOLOv2

Segment object instances of randomly rotated machine parts in a bin using a deep learning SOLOv2 network.

(Computer Vision Toolbox)

Object Detection Using SSD Deep Learning

Train a Single Shot Detector (SSD).

Ouvrir le live script