Main Content

Instance Segmentation

Perform instance segmentation using pretrained deep learning networks and train networks using transfer learning on custom data

Instance segmentation is a computer vision technique that plays a crucial role in tasks requiring precise object localization and the identification of individual object instances, such as in medical imaging and autonomous driving. By combining the principles of object detection and semantic segmentation, instance segmentation provides a more refined understanding of visual data by identifying individual object instances and delineating their boundaries pixel-by-pixel. Use instance segmentation to precisely identify, classify, and separate individual objects within an image.

You can run inference on an image using a pretrained deep learning network, or perform transfer learning, an approach that enables you to start with a pretrained network and then train it on custom data set for your application. To generate ground truth data for training, you can use the Image Labeler, Video Labeler, or Ground Truth Labeler (Automated Driving Toolbox) app to interactively label pixels and export label data. Instance segmentation requires Deep Learning Toolbox™. Training and inference support CUDA®-enabled GPU. Use of a GPU is recommended, and requires Parallel Computing Toolbox™. For more information, see Parallel Computing Support in MathWorks Products (Parallel Computing Toolbox).

Instance segmentation using SOLOv2: Left — segmented and labeled road scenario using a sample modified RGB image from the CamVid data set, Right — segmented image of PVC pipe connectors

Funzioni

espandi tutto

Configure Instance Segmentation Network

solov2Segment objects using SOLOv2 instance segmentation network (Da R2023b)
maskrcnnDetect objects using Mask R-CNN instance segmentation (Da R2021b)

Perform Inference

segmentObjectsSegment objects using Mask R-CNN instance segmentation (Da R2021b)
segmentObjectsSegment objects using SOLOv2 instance segmentation (Da R2023b)

Load Training Data

boxLabelDatastoreDatastore for bounding box label data (Da R2019b)
groundTruthGround truth label data
imageDatastoreDatastore for image data
combineCombine data from multiple datastores

Train Instance Segmentation Networks

trainSOLOV2Train SOLOv2 network to perform instance segmentation (Da R2023b)
trainMaskRCNNTrain Mask R-CNN network to perform instance segmentation (Da R2022a)

Augment and Preprocess Training Data

poly2maskConvert region of interest (ROI) polygon to region mask
bwboundariesTrace object boundaries in binary image
balanceBoxLabelsBalance bounding box labels for object detection (Da R2020a)
bboxcropCrop bounding boxes (Da R2019b)
bboxeraseRemove bounding boxes (Da R2021a)
bboxresizeResize bounding boxes (Da R2019b)
bboxwarpApply geometric transformation to bounding boxes (Da R2019b)
bbox2pointsConvert rectangle to corner points list
imwarpApply geometric transformation to image
imcropCrop image
imresizeResize image
randomAffine2dCreate randomized 2-D affine transformation (Da R2019b)
centerCropWindow2dCreate rectangular center cropping window (Da R2019b)
randomWindow2dRandomly select rectangular region in image (Da R2021a)
posemaskrcnnPredict object pose using Pose Mask R-CNN pose estimation (Da R2024a)
predictPoseEstimate object pose using Pose Mask R-CNN deep learning network (Da R2024a)
trainPoseMaskRCNNTrain Pose Mask R-CNN network to perform pose estimation (Da R2024a)
insertObjectMask Insert masks in image or video stream (Da R2020b)
insertObjectAnnotationAnnotate truecolor or grayscale image or video
insertShapeInsert shapes in image or video
showShapeDisplay shapes on image, video, or point cloud (Da R2020b)
evaluateInstanceSegmentationEvaluate instance segmentation data set against ground truth (Da R2022b)
instanceSegmentationMetricsInstance segmentation quality metrics (Da R2022b)
metricsByAreaEvaluate instance segmentation across object mask size ranges (Da R2023b)

Argomenti

Get Started

Train Data for Instance Segmentation