Human detection area warper interface. More...

Inheritance diagram for fsdk::IHumanWarper:

Public Member Functions
virtual Result< FSDKError >	warp (const Image image, const Detection &detection, Image &transformedImage) const noexcept=0
	Warp human detection. More...

virtual Result< FSDKError >	warp (Span< const Image > images, Span< const Detection > detections, Span< Image > transformedImages) const noexcept=0
	Warps humans on multiple images. More...

Public Member Functions inherited from fsdk::IRefCounted
virtual int32_t	retain () noexcept=0
	Increase strong reference count. More...

virtual int32_t	release () noexcept=0
	Decrease strong reference count. More...

virtual int32_t	getRefCount () const noexcept=0
	Get actual strong reference count. More...

virtual int32_t	retainWeak () noexcept=0
	Increase weak reference count. More...

virtual int32_t	releaseWeak () noexcept=0
	Decrease weak reference count. More...

virtual int32_t	getWeakRefCount () const noexcept=0
	Get actual weak reference count. More...

Detailed Description

Human detection area warper interface.

Performs cropping and resizing of an image for human descriptor extraction.

Member Function Documentation

virtual Result<FSDKError> fsdk::IHumanWarper::warp	(	const Image	image,
		const Detection &	detection,
		Image &	transformedImage
	)		const

pure virtualnoexcept

Warp human detection.

Parameters

[in]	image	source
[in]	Detection	detection of a human.
	[in/out]	transformedImage warped image output.

Note: if transformedImage has the same width, height, format as the standard human warp and the same memory residence as source image has, then output data will be just copied to transformedImage without any memory allocation. New image will be allocated otherwise.

virtual Result<FSDKError> fsdk::IHumanWarper::warp	(	Span< const Image >	images,
		Span< const Detection >	detections,
		Span< Image >	transformedImages
	)		const

pure virtualnoexcept

Warps humans on multiple images.

Parameters

[in]	images	array of images from which to warp humans.
[in]	Detection	is an array of detection structs.
	[in/out]	transformedImages is an array of input/output images where result will be stored.

Note: each detection in detections array corresponds to an image where this detection was taken from by the same index(i.e detections[i] <–> images[i]), therefore, if there are multiple detections on the same image user must duplicate those images in order for the first statement to hold true.; if output images in transformed images array has the same image parameters as the standard warped image, then output data will be just copied to those images without any memory allocation. New images will be allocated otherwise.

The documentation for this struct was generated from the following file: