Documentation

This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English verison of the page.

Note: This page has been translated by MathWorks. Please click here
To view all translated materals including this page, select Japan from the country navigator on the bottom of this page.

fasterRCNNObjectDetector class

Detect objects using Faster R-CNN deep learning detector

Description

The fasterRCNNObjectDetector object contains a Faster R-CNN (regions with convolution neural networks) object detector returned by the trainFasterRCNNObjectDetector function. Use of the fasterRCNNObjectDetector object requires the Neural Network Toolbox™.

When using the detect method, use of a CUDA®-enabled NVIDIA® GPU with compute capability 3.0 or higher is highly recommended. The GPU reduces computation time significantly. Usage of the GPU requires Parallel Computing Toolbox™.

Properties

expand all

Name of the trained object detector, specified as a character vector. By default, the trainFasterRCNNObjectDetector function sets the name. You can modify the name after training.

Trained Faster R-CNN object detection network, specified as a vision.cnn.FastRCNN object. The object stores the layers that define the convolutional neural network used within the R-CNN detector. This network classifies region proposals produced by RegionProposalFcn.

Trained region proposal network (RPN), specified as a vision.cnn.RegionProposalNetwork object. This object represents the RPN used in the R-CNN detector. The RPN shares weights with the network stored in Network property.

Names of the object classes that the Faster R-CNN detected was trained to find, specified as a cell array.

Minimum anchor box sizes used to build the anchor box pyramid of the region proposal network (RPN), specified as a matrix. Each row defines the [height width] of an anchor box.

Anchor box pyramid scale factor used to successively upscale anchor box sizes, specified as a scalar.

Number of levels in each anchor box pyramid, specified as a scalar.

Minimum object size supported by the R-CNN network, specified as a [height width] vector. The minimum size depends on the network architecture.

Methods

detectDetect objects using Faster R-CNN object detector

Introduced in R2017a