Tracker

Detailed Description

Defines the tracker module.

Data Structures
struct	dwFeatureTrackerConfig
	Holds configuration parameters for a feature tracker. More...

Functions
DW_API_PUBLIC dwStatus	dwFeatureTracker_detectNewFeatures (dwFeatureListHandle_t list, dwConstPyramidHandle_t pyramid, dwFeatureTrackerHandle_t obj)
	Detects new features and adds them to the feature list. More...
DW_API_PUBLIC dwStatus	dwFeatureTracker_getCUDAStream (cudaStream_t *stream, dwFeatureTrackerHandle_t obj)
	Gets the CUDA stream used by the feature tracker. More...
DW_API_PUBLIC dwStatus	dwFeatureTracker_initialize (dwFeatureTrackerHandle_t *obj, dwContextHandle_t context, cudaStream_t stream, const dwFeatureTrackerConfig config)
	Creates and initializes a feature tracker. More...
DW_API_PUBLIC dwStatus	dwFeatureTracker_release (dwFeatureTrackerHandle_t *obj)
	Releases the feature tracker. More...
DW_API_PUBLIC dwStatus	dwFeatureTracker_reset (dwFeatureTrackerHandle_t obj)
	Resets a feature tracker. More...
DW_API_PUBLIC dwStatus	dwFeatureTracker_setCUDAStream (cudaStream_t stream, dwFeatureTrackerHandle_t obj)
	Sets the CUDA stream for CUDA related operations. More...
DW_API_PUBLIC dwStatus	dwFeatureTracker_setMask (const uint8_t *d_mask, const uint32_t maskStrideBytes, const uint32_t maskWidth, const uint32_t maskHeight, dwFeatureTrackerHandle_t obj)
	Sets a mask to ignore areas of the image. More...
DW_API_PUBLIC dwStatus	dwFeatureTracker_trackFeatures (dwFeatureListHandle_t list, dwConstPyramidHandle_t previousPyramid, dwConstPyramidHandle_t currentPyramid, const float32_t *d_predictedPositions, dwFeatureTrackerHandle_t obj)
	Tracks features from the internal list between the previous and current images. More...

---

Data Structure Documentation

dwFeatureTrackerConfig

struct dwFeatureTrackerConfig

Data Fields
float32_t	detectorScoreThreshold	Higher thresholds detect less features.
uint32_t	imageHeight
uint32_t	imageWidth
uint32_t	interationsLK	Upper bound on number of Lucas-Kanade iterations per level.
uint32_t	maxFeatureCount	Upper bound on number of features handled.
uint32_t	windowSizeLK	Window size used in the Lucas-Kanade tracker. Supported sizes are 6,8,10,12,14.

Function Documentation

dwFeatureTracker_detectNewFeatures()

DW_API_PUBLIC dwStatus dwFeatureTracker_detectNewFeatures	(	dwFeatureListHandle_t	list,
		dwConstPyramidHandle_t	pyramid,
		dwFeatureTrackerHandle_t	obj
	)

Detects new features and adds them to the feature list.

Features are added only in areas where the mask!=0xff and where features are not currently being tracked.

Parameters

[in]	list	Specifies the feature list where new features are stored.
[in]	pyramid	Specifies the pryamid on which feature detection takes place.
[in]	obj	Specifies the object handle.

Returns

DW_INVALID_ARGUMENT if feature tracker handle or feature list handle or pyramid handle are NULL.
DW_SUCCESS otherwise.

dwFeatureTracker_getCUDAStream()

DW_API_PUBLIC dwStatus dwFeatureTracker_getCUDAStream	(	cudaStream_t *	stream,
		dwFeatureTrackerHandle_t	obj
	)

Gets the CUDA stream used by the feature tracker.

Parameters

[out]	stream	The CUDA stream currently used.
[in]	obj	A handle to the feature tracker module.

Returns

DW_INVALID_ARGUMENT if feature tracker handle or stream are NULL.
DW_SUCCESS otherwise.

dwFeatureTracker_initialize()

DW_API_PUBLIC dwStatus dwFeatureTracker_initialize	(	dwFeatureTrackerHandle_t *	obj,
		dwContextHandle_t	context,
		cudaStream_t	stream,
		const dwFeatureTrackerConfig	config
	)

Creates and initializes a feature tracker.

Parameters

[out]	obj	A pointer to the feature tracker handle is returned here.
[in]	context	Specifies the handle to the context under which it is created.
[in]	stream	Specifies the CUDA stream to use for pyramid operations.
[in]	config	Specifies the configuration parameters.

Returns

DW_INVALID_ARGUMENT if feature tracker handle or context are NULL or config is invalid.
DW_SUCCESS otherwise.

dwFeatureTracker_release()

DW_API_PUBLIC dwStatus dwFeatureTracker_release

(

dwFeatureTrackerHandle_t *

obj

)

Releases the feature tracker.

This method releases all resources associated with a feature tracker.

Note

This method renders the handle unusable.

Parameters

[in]

obj

A pointer to the object handle to be released.

Returns

DW_INVALID_ARGUMENT if feature tracker handle is NULL.
DW_SUCCESS otherwise.

dwFeatureTracker_reset()

DW_API_PUBLIC dwStatus dwFeatureTracker_reset

(

dwFeatureTrackerHandle_t

obj

)

Resets a feature tracker.

Parameters

[in]

obj

Specifies the feature tracker handle to be reset.

Returns

DW_INVALID_ARGUMENT if feature tracker handle is NULL.
DW_SUCCESS otherwise.

dwFeatureTracker_setCUDAStream()

DW_API_PUBLIC dwStatus dwFeatureTracker_setCUDAStream	(	cudaStream_t	stream,
		dwFeatureTrackerHandle_t	obj
	)

Sets the CUDA stream for CUDA related operations.

Note

The ownership of the stream remains by the callee.

Parameters

[in]	stream	The CUDA stream to be used. Default is the one passed during dwFeatureTracker_initialize.
[in]	obj	A handle to the feature tracker module to set CUDA stream for.

Returns

DW_INVALID_ARGUMENT if feature tracker handle is NULL.
DW_SUCCESS otherwise.

dwFeatureTracker_setMask()

DW_API_PUBLIC dwStatus dwFeatureTracker_setMask	(	const uint8_t *	d_mask,
		const uint32_t	maskStrideBytes,
		const uint32_t	maskWidth,
		const uint32_t	maskHeight,
		dwFeatureTrackerHandle_t	obj
	)

Sets a mask to ignore areas of the image.

Areas where mask==0xff will not produce new features when detectNewFeatures() is called. The size of the mask must be the same as the image.

Parameters

[in]	d_mask	A GPU pointer to the mask data.
[in]	maskStrideBytes	Specifies the stride, in bytes, for each row of the mask.
[in]	maskWidth	Specifies the width of the mask.
[in]	maskHeight	Specifies the height of the mask.
[in]	obj	Specifies the object handle.

Returns

DW_INVALID_ARGUMENT if feature tracker handle or d_mask are NULL or maskWidth or maskHeight are invalid.
DW_SUCCESS otherwise.

dwFeatureTracker_trackFeatures()

DW_API_PUBLIC dwStatus dwFeatureTracker_trackFeatures	(	dwFeatureListHandle_t	list,
		dwConstPyramidHandle_t	previousPyramid,
		dwConstPyramidHandle_t	currentPyramid,
		const float32_t *	d_predictedPositions,
		dwFeatureTrackerHandle_t	obj
	)

Tracks features from the internal list between the previous and current images.

Parameters

[in]	list	Specifies the list of features to be tracked and updated.
[in]	previousPyramid	Specifies the pyramid constructed from the last image.
[in]	currentPyramid	Specifies the pyramid constructed from the current image.
[in]	d_predictedPositions	A GPU pointer to a list of expected positions of the features to be tracked. The indexes of this list must match the indexes of the internal feature list. if this is NULL(== 0), then use previous locations of the list as predicted positions.
[in]	obj	Specifies the feature tracker handle.

Returns

DW_INVALID_ARGUMENT if any parameter is NULL or previous and current pyramids have a different number of levels.
A specific CUDA error in case of an underlying cuda failure.
DW_SUCCESS otherwise.