Functions
VPIStatus	vpiCreateExtractHOGFeatures (VPIStream stream, uint32_t width, uint32_t height, uint32_t features, uint32_t cellSize, uint32_t numOrientations, VPIPayload payload, uint32_t outNumFeatures)
	Create a payload for the non-batch version of HOG algorithm. More...

VPIStatus	vpiCreateExtractHOGFeaturesBatch (VPIStream stream, uint32_t maxBatchWidth, uint32_t maxBatchHeight, uint32_t imgWidth, uint32_t imgHeight, uint32_t features, uint32_t cellSize, uint32_t numOrientations, VPIPayload payload, uint32_t outNumFeatures)
	Create a payload for the batch version of HOG algorithm. More...

VPIStatus	vpiSubmitExtractHOGFeatures (VPIPayload payload, VPIImage input, VPIImage *outFeatures, uint32_t numFeatures)
	Submit the HOG algorithm to the stream associated with the payload. More...

HOG flags
Defines what features will be returned.
#define	VPI_HOG_CONTRAST_SENSITIVE 0x01
	Return contrast sensitive features.

#define	VPI_HOG_CONTRAST_INSENSITIVE 0x02
	Return contrast insensitive features.

#define	VPI_HOG_TEXTURE 0x04
	Return texture-related features.

#define	VPI_HOG_ALL_FEATURES (VPI_HOG_CONTRAST_SENSITIVE \| VPI_HOG_CONTRAST_INSENSITIVE \| VPI_HOG_TEXTURE)
	Helper flag to return all features.

Detailed Description

Extracts Histogram of Oriented Gradients features from input image.

Function Documentation

VPIStatus vpiCreateExtractHOGFeatures	(	VPIStream	stream,
		uint32_t	width,
		uint32_t	height,
		uint32_t	features,
		uint32_t	cellSize,
		uint32_t	numOrientations,
		VPIPayload *	payload,
		uint32_t *	outNumFeatures
	)

Create a payload for the non-batch version of HOG algorithm.

Parameters

[in]	stream	Stream that will execute the algorithm.
[in]	width,height	Dimensions of the input image to be used.
[in]	features	Flags to specify which features will be returned
[in]	cellSize	Cell size, typically 8 or 16 for 8x8 and 16x16 cells respectively.
[in]	numOrientations	Number of orientations used. This is typically 18.
[out]	payload	Pointer to a payload handle that will receive the allocated payload.
[out]	outNumFeatures	Receives the number of features that will be returned. Pass NULL if not needed.

Returns: VPI_SUCCESS if payload was created successfully, or some other VPIStatus code in case of error.

VPIStatus vpiCreateExtractHOGFeaturesBatch	(	VPIStream	stream,
		uint32_t	maxBatchWidth,
		uint32_t	maxBatchHeight,
		uint32_t	imgWidth,
		uint32_t	imgHeight,
		uint32_t	features,
		uint32_t	cellSize,
		uint32_t	numOrientations,
		VPIPayload *	payload,
		uint32_t *	outNumFeatures
	)

Create a payload for the batch version of HOG algorithm.

The input images are assumed to be laid out in memory as a 2D matrix of images. All images must have the same dimensions.

Parameters

[in]	stream	Stream that will execute the algorithm.
[in]	maxBatchWidth,maxBatchHeight	Maximum number of images horizontally and vertically, respectively.
[in]	imgWidth,imgHeight	Dimensions each of the batch images.
[in]	features	Flags to specify which features will be returned
[in]	cellSize	Cell size, typically 8 or 16 for 8x8 and 16x16 cells respectively.
[in]	numOrientations	Number of orientations used. This is typically 18.
[out]	payload	Pointer to a payload handle that will receive the allocated payload.
[out]	outNumFeatures	Receives the number of features that will be returned. Pass NULL if not needed.

Returns: VPI_SUCCESS if payload was created successfully, or some other VPIStatus code in case of error.

VPIStatus vpiSubmitExtractHOGFeatures	(	VPIPayload	payload,
		VPIImage	input,
		VPIImage *	outFeatures,
		uint32_t	numFeatures
	)

Submit the HOG algorithm to the stream associated with the payload.

It handles both batch and non-batch payloads.

Parameters

[in]	payload	Payload to be submitted.
[in]	input	If using a non batch payload, this is the input image to be processed. Its dimensions must match what was passed to vpiCreateExtractHOGFeatures. If using a batch payload, the image dimensions must be a multiple of (`imgWidth`,`imgHeight`), and it must be at most (`imgWidthmaxBatchWidth`, `imgHeightmaxBatchHeight`).
[out]	outFeatures	Pointer to an array of images that will receive the features. The dimensions of each image must be (`input.width / cellSize`, `input.height / cellSize`). In case of batch processing, the output features position in the 2D matrix be the same position of the corresponding input image.
[in]	numFeatures	Number of images in the output array.

Returns: VPI_SUCCESS if payload was created successfully, or some other VPIStatus code in case of error.