vehicleDetectorYOLOv2

Detect vehicles using YOLO v2 Network

Since R2020a

Syntax

detector = vehicleDetectorYOLOv2

Description

detector = vehicleDetectorYOLOv2 returns a trained you only look once (YOLO) v2 object detector for detecting vehicles. YOLO v2 is a deep learning object detection framework that uses a convolutional neural network (CNN) for detection.

The detector is trained using unoccluded RGB images of the front, rear, left, and right sides of cars on a highway scene. The CNN used with the vehicle detector uses a modified version of the MobileNet-v2 network architecture. You can also fine tune the vehicle detector with additional training data by using the trainYOLOv2ObjectDetector.

For information about creating a YOLO v2 object detector, see Create Custom YOLO v2 Object Detection Network. Use of this function requires Deep Learning Toolbox™.

Examples

Detect Vehicles Using YOLO v2 Detector

This example shows how to detect cars in an image and annotate the image with the detection scores. To detect the cars, use a YOLO v2 detector that is trained to detect vehicles in an image.

Load the pretrained detector.

detector = vehicleDetectorYOLOv2();

Read a test image into the workspace.

I = imread('highway.png');

Detect vehicles in the test image by using the trained YOLO v2 detector. Pass the test image and the detector as input to the detect function. The detect function returns the bounding boxes and the detection scores.

[bboxes,scores] = detect(detector,I);

Annotate the image with the bounding boxes and the detection scores. Display the detection results. The bounding boxes localize vehicles in the test image.

I = insertObjectAnnotation(I,'rectangle',bboxes,scores);
figure
imshow(I)
title('Detected vehicles and detection scores');

Output Arguments

detector — Trained YOLO v2 network for vehicle detection

yolov2ObjectDetector

Trained YOLO v2 network for vehicle detection, returned as an yolov2ObjectDetector object. To detect vehicles in a test image, pass the YOLO v2 vehicle detector as input to the detect function.

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

For code generation, you can load the network by using the syntax detectorNet = vehicleDetectorYOLOv2() or by passing the vehicleDetectorYOLOv2 function to coder.loadDeepLearningNetwork (MATLAB Coder). For example: detectorNet = coder.loadDeepLearningNetwork('vehicleDetectorYOLOv2')

For more information, see Load Pretrained Networks for Code Generation (MATLAB Coder).

GPU Code Generation

Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Usage notes and limitations:

For code generation, you can load the network by using the syntax detectorNet = vehicleDetectorYOLOv2() or by passing the vehicleDetectorYOLOv2 function to coder.loadDeepLearningNetwork (GPU Coder). For example: detectorNet = coder.loadDeepLearningNetwork('vehicleDetectorYOLOv2')

For more information, see Load Pretrained Networks for Code Generation (GPU Coder).

Version History

Introduced in R2020a