KLTBoundingBoxTracker

Data Structures
struct	VPIKLTBoundingBoxTrackerParams
	Structure that defines the parameters for vpiCreateKLTBoundingBoxTracker. More...

Enumerations
enum	VPIKLTBoundingBoxTrackerType { VPI_KLT_INVERSE_COMPOSITIONAL }
	KLT Tracker type. More...

Functions
VPIStatus	vpiCreateKLTBoundingBoxTracker (VPIStream stream, uint32_t imageWidth, uint32_t imageHeight, VPIImageType imageType, VPIPayload *payload)
	Creates payload for vpiSubmitKLTBoundingBoxTracker. More...
VPIStatus	vpiSubmitKLTBoundingBoxTracker (VPIPayload payload, VPIImage templateImage, VPIArray inputBoxList, VPIArray inputPredictionList, VPIImage referenceImage, VPIArray outputBoxList, VPIArray outputEstimationList, const VPIKLTBoundingBoxTrackerParams *params)
	Runs KLT Tracker on two frames. More...

Detailed Description

Runs KLT Tracking on two frames.

---

Data Structure Documentation

VPIKLTBoundingBoxTrackerParams

struct VPIKLTBoundingBoxTrackerParams

Structure that defines the parameters for vpiCreateKLTBoundingBoxTracker.

Parameters

thresholdUpdate	[in] threshold to update template
thresholdKill	[in] threshold to kill tracking
thresholdStop	[in] threshold to stop iteration
maxScaleChange	[in] maximum scale change for valid tracking
maxTranslationChange	[in] maximum translation change for valid tracking
imageType	[in] input image type

Definition at line 104 of file KLTBoundingBoxTracker.h.

Collaboration diagram for VPIKLTBoundingBoxTrackerParams:

Data Fields
float	maxScaleChange	Maximum relative scale change. Scale changes larger than this will make KLT consider that tracking was lost.
float	maxTranslationChange	Maximum relative translation change. Translation changes larger than this will make KLT consider that tracking was lost.
float	nccThresholdKill	Threshold to consider template tracking was lost. Must be a value between 0 and 1.
float	nccThresholdStop	Threshold to stop estimating.
float	nccThresholdUpdate	Threshold for requiring template update. Must be a value between 0 and 1.
uint32_t	numberOfIterationsScaling	Number of Inverse compositional iterations of scale estimations.
VPIKLTBoundingBoxTrackerType	trackingType	Type of KLT tracking that will be performed.

Enumeration Type Documentation

VPIKLTBoundingBoxTrackerType

enum VPIKLTBoundingBoxTrackerType

#include <vpi/algo/KLTBoundingBoxTracker.h>

KLT Tracker type.

Enumerator
VPI_KLT_INVERSE_COMPOSITIONAL	Inverse compositional algorithm for KLT tracker. The inverse compositional algorithm is a reformulation of the classic Lucas-Kanade algorithm to make the steepest-descent images and Hessian constant. Ref: Simon Baker, Iain Matthew, "Lucas-Kanade 20 Years On: A Unified Framework". International Journal of Computer Vision, February 2004, Volume 56, issue 3, pp. 228-231.

Definition at line 80 of file KLTBoundingBoxTracker.h.

Function Documentation

vpiCreateKLTBoundingBoxTracker()

VPIStatus vpiCreateKLTBoundingBoxTracker	(	VPIStream	stream,
		uint32_t	imageWidth,
		uint32_t	imageHeight,
		VPIImageType	imageType,
		VPIPayload *	payload
	)

#include <vpi/algo/KLTBoundingBoxTracker.h>

Creates payload for vpiSubmitKLTBoundingBoxTracker.

Parameters

stream	[in] a stream handle
imageWidth	[in] input image width
imageHeight	[in] input image height
imageType	[in] input image type
payload	[out] pointer to a payload handle

Returns

an error code on failure else VPI_SUCCESS

vpiSubmitKLTBoundingBoxTracker()

VPIStatus vpiSubmitKLTBoundingBoxTracker	(	VPIPayload	payload,
		VPIImage	templateImage,
		VPIArray	inputBoxList,
		VPIArray	inputPredictionList,
		VPIImage	referenceImage,
		VPIArray	outputBoxList,
		VPIArray	outputEstimationList,
		const VPIKLTBoundingBoxTrackerParams *	params
	)

#include <vpi/algo/KLTBoundingBoxTracker.h>

Runs KLT Tracker on two frames.

Outputs tracked bounding boxes and estimated transform array.

Parameters

payload	[in] payload created with vpiCreateKLTBoundingBoxTracker
referenceImage	[in] reference image
templateImage	[in] template image
inputBoxList	[in] input bounding box array, must have type VPI_ARRAY_TYPE_KLT_TRACKED_BOUNDING_BOX
inputPredictionList	[in] input predicted transform array, must have type VPI_ARRAY_TYPE_HOMOGRAPHY_TRANSFORM_2D
params	[in] parameters for the KLT tracker
outputBoxList	[out] output bounding box array, must have type VPI_ARRAY_TYPE_KLT_TRACKED_BOUNDING_BOX
outputEstimationList	[out] estimated transform array, must have type VPI_ARRAY_TYPE_HOMOGRAPHY_TRANSFORM_2D

Returns

an error code on failure else VPI_SUCCESS