Detection< A > Struct Template Reference

The Detection structure provides object detection with using of HAAR and LBP cascade classifiers. More...

#include <SimdDetection.hpp>

Data Structures
struct	Object
	The Object structure describes detected object. More...

Public Types
typedef A< uint8_t >	Allocator
typedef Simd::View< A >	View
typedef Simd::Point< ptrdiff_t >	Size
typedef std::vector< Size >	Sizes
typedef Simd::Rectangle< ptrdiff_t >	Rect
typedef std::vector< Rect >	Rects
typedef int	Tag
typedef std::vector< Object >	Objects

Public Member Functions
	Detection ()
	~Detection ()
bool	LoadStringXml (const std::string &xml, Tag tag=UNDEFINED_OBJECT_TAG)
bool	Load (const std::string &path, Tag tag=UNDEFINED_OBJECT_TAG)
bool	Init (const Size &imageSize, double scaleFactor=1.1, const Size &sizeMin=Size(0, 0), const Size &sizeMax=Size(INT_MAX, INT_MAX), const View &roi=View(), ptrdiff_t threadNumber=-1)
bool	Detect (const View &src, Objects &objects, int groupSizeMin=3, double sizeDifferenceMax=0.2, bool motionMask=false, const Rects &motionRegions=Rects())

Static Public Attributes
static const Tag	UNDEFINED_OBJECT_TAG = -1

Detailed Description

template<template< class > class A>
struct Simd::Detection< A >

The Detection structure provides object detection with using of HAAR and LBP cascade classifiers.

Using example (face detection in the image):

#include "Simd/SimdDetection.hpp"
#include "Simd/SimdDrawing.hpp"
 
int main()
{
    typedef Simd::Detection<Simd::Allocator> Detection;
 
    Detection::View image;
    image.Load("../../data/image/face/lena.pgm");
 
    Detection detection;
 
    detection.Load("../../data/cascade/haar_face_0.xml");
 
    detection.Init(image.Size());
 
    Detection::Objects objects;
    detection.Detect(image, objects);
 
    for (size_t i = 0; i < objects.size(); ++i)
        Simd::DrawRectangle(image, objects[i].rect, uint8_t(255));
 
    image.Save("result.pgm");
 
    return 0;
}

Using example (face detection in the video captured by OpenCV):

#include <iostream>
#include <string>
 
#include "opencv2/opencv.hpp"
#include "opencv2/core/utils/logger.hpp"
#ifndef SIMD_OPENCV_ENABLE
#define SIMD_OPENCV_ENABLE
#endif
#include "Simd/SimdDetection.hpp"
#include "Simd/SimdDrawing.hpp"
 
int main(int argc, char * argv[])
{
    if (argc < 2)
    {
        std::cout << "You have to set video source! It can be 0 for camera or video file name." << std::endl;
        return 1;
    }
    std::string source = argv[1], output = argc > 2 ? argv[2] : "";
 
    cv::VideoCapture capture;
    cv::utils::logging::setLogLevel(cv::utils::logging::LOG_LEVEL_ERROR);
    if (source == "0")
        capture.open(0);
    else
        capture.open(source);
    if (!capture.isOpened())
    {
        std::cout << "Can't capture '" << source << "' !" << std::endl;
        return 1;
    }
    int W = (int)capture.get(cv::CAP_PROP_FRAME_WIDTH);
    int H = (int)capture.get(cv::CAP_PROP_FRAME_HEIGHT);
 
    cv::VideoWriter writer;
    if (output.size())
    {
        writer.open(output, cv::VideoWriter::fourcc('F', 'M', 'P', '4'), capture.get(cv::CAP_PROP_FPS), cv::Size(W, H));
        if (!writer.isOpened())
        {
            std::cout << "Can't open output file '" << output << "' !" << std::endl;
            return 1;
        }
    }
 
    typedef Simd::Detection<Simd::Allocator> Detection;
    Detection detection;
    detection.Load("../../data/cascade/haar_face_0.xml");
    detection.Init(Detection::Size(W, H), 1.2, Detection::Size(W, H) / 20);
 
    const char * WINDOW_NAME = "FaceDetection";
    cv::namedWindow(WINDOW_NAME, 1);
    for (;;)
    {
        cv::Mat frame;
        if (!capture.read(frame))
            break;
        Detection::View image = frame;
 
        Detection::Objects objects;
        detection.Detect(image, objects);
 
        for (size_t i = 0; i < objects.size(); ++i)
            Simd::DrawRectangle(image, objects[i].rect, Simd::Pixel::Bgr24(0, 255, 255));
 
        cv::imshow(WINDOW_NAME, frame);
        if (writer.isOpened())
            writer.write(frame);
        if (cv::waitKey(1) == 27)// "press 'Esc' to break video";
            break;
    }
    return 0;
}

Note

This is wrapper around low-level Object Detection API.

Member Typedef Documentation

Allocator

typedef A<uint8_t> Allocator

Allocator type definition.

View

typedef Simd::View<A> View

An image type definition.

Size

typedef Simd::Point<ptrdiff_t> Size

An image size type definition.

Sizes

typedef std::vector<Size> Sizes

A vector of image sizes type definition.

Rect

typedef Simd::Rectangle<ptrdiff_t> Rect

A rectangle type definition.

Rects

typedef std::vector<Rect> Rects

A vector of rectangles type definition.

Tag

typedef int Tag

A tag type definition.

Objects

typedef std::vector<Object> Objects

A vector of objects type defenition.

Constructor & Destructor Documentation

Detection()

Detection

(

)

Creates a new empty Detection structure.

~Detection()

~Detection

(

)

A Detection destructor.

Member Function Documentation

LoadStringXml()

bool LoadStringXml	(	const std::string &	xml,
		Tag	tag = UNDEFINED_OBJECT_TAG
	)

Loads from file classifier cascade. Supports OpenCV HAAR and LBP cascades type. You can call this function more than once if you want to use several object detectors at the same time.

Note

Tree based cascades and old cascade formats are not supported!

Parameters

[in]	xml	- a string containing XML with cascade.
[in]	tag	- an user defined tag. This tag will be inserted in output Object structure.

Returns

a result of this operation.

Load()

bool Load	(	const std::string &	path,
		Tag	tag = UNDEFINED_OBJECT_TAG
	)

Loads from file classifier cascade. Supports OpenCV HAAR and LBP cascades type. You can call this function more than once if you want to use several object detectors at the same time.

Note

Tree based cascades and old cascade formats are not supported!

Parameters

[in]	path	- a path to cascade.
[in]	tag	- an user defined tag. This tag will be inserted in output Object structure.

Returns

a result of this operation.

Init()

bool Init	(	const Size &	imageSize,
		double	scaleFactor = 1.1,
		const Size &	sizeMin = Size(0, 0),
		const Size &	sizeMax = Size(INT_MAX, INT_MAX),
		const View &	roi = View(),
		ptrdiff_t	threadNumber = -1
	)

Prepares Detection structure to work with image of given size.

Parameters

[in]	imageSize	- a size of input image.
[in]	scaleFactor	- a scale factor. To detect objects of different sizes the algorithm uses many scaled image. This parameter defines size difference between neighboring images. This parameter strongly affects to performance.
[in]	sizeMin	- a minimal size of detected objects. This parameter strongly affects to performance.
[in]	sizeMax	- a maximal size of detected objects.
[in]	roi	- a 8-bit image mask which defines Region Of Interest. User can restricts detection region with using this mask. The mask affects to the center of detected object.
[in]	threadNumber	- a number of work threads. It useful for multi core CPU. Use value -1 to auto choose of thread number.

Returns

a result of this operation.

Detect()

bool Detect	(	const View &	src,
		Objects &	objects,
		int	groupSizeMin = 3,
		double	sizeDifferenceMax = 0.2,
		bool	motionMask = false,
		const Rects &	motionRegions = Rects()
	)

Detects objects at given image.

Parameters

[in]	src	- a input image.
[out]	objects	- detected objects.
[in]	groupSizeMin	- a minimal weight (number of elementary detections) of detected image.
[in]	sizeDifferenceMax	- a parameter to group elementary detections.
[in]	motionMask	- an using of motion detection flag. Useful for dynamical restriction of detection region to addition to ROI.
[in]	motionRegions	- a set of rectangles (motion regions) to restrict detection region to addition to ROI. The regions affect to the center of detected object.

Returns

a result of this operation.

Field Documentation

UNDEFINED_OBJECT_TAG

const Tag UNDEFINED_OBJECT_TAG = -1

static

The undefined object tag.