Detect objects using Faster R-CNN deep learning detector
fasterRCNNObjectDetector object contains
a Faster R-CNN (regions with convolution neural networks) object detector
returned by the
Use of the
fasterRCNNObjectDetector object requires
the Neural Network
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
ModelName— Name of the trained object detector
Name of the trained object detector, specified as a character
vector. By default, the
sets the name. You can modify the name after training.
Network— Trained Faster R-CNN object detection network
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
RegionProposalNetwork— Trained region proposal network
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
ClassNames— Object class names
Names of the object classes that the Faster R-CNN detected was trained to find, specified as a cell array.
MinBoxSizes— Minimum anchor box sizes
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.
BoxPyramidScale— Anchor box pyramid scale
Anchor box pyramid scale factor used to successively upscale anchor box sizes, specified as a scalar.
NumBoxPyramidLevels— Number of anchor box pyramid levels
Number of levels in each anchor box pyramid, specified as a scalar.
MinObjectSize— Minimum object size supported
Minimum object size supported by the R-CNN network, specified as a [height width] vector. The minimum size depends on the network architecture.
|detect||Detect objects using Faster R-CNN object detector|