Detailed Description

Defines ObjectDetector module for object detection.

Note: SW Release Applicability: These APIs are available in NVIDIA DRIVE Software releases.

Data Structures
struct	dwObjectDetectorParams
	Object detector configuration parameters. More...

Macros
#define	DW_OBJECT_DETECTOR_MAX_IMAGES 4
	Maximum number of images the detector can process at a time. More...

Typedefs
typedef struct dwObjectDetectorObject *	dwObjectDetectorHandle_t
	Handle to an object detector. More...

Enumerations
enum	dwObjectDetectorDLAStage { DW_OBJECT_DETECTOR_DLA_STAGE_GPU_ASYNC_PREPROCESSING = 0, DW_OBJECT_DETECTOR_DLA_STAGE_DLA_ASYNC_INFERENCE, DW_OBJECT_DETECTOR_DLA_STAGE_GPU_ASYNC_INTERPRET_DETECTIONS, DW_OBJECT_DETECTOR_DLA_STAGE_CPU_SYNC_POSTPROCESSING }
	The DLA process stages of the ObjectDetector. More...

enum	dwObjectDetectorOutputType { DW_OBJECT_DETECTOR_OUTPUT_TYPE_PROPOSAL, DW_OBJECT_DETECTOR_OUTPUT_TYPE_DETECTION }
	The type of the detector output. More...

enum	dwObjectDetectorStage { DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_PREPROCESSING = 0, DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INFERENCE, DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INTERPRET_DETECTIONS, DW_OBJECT_DETECTOR_STAGE_CPU_SYNC_POSTPROCESSING }
	The GPU process stages of the ObjectDetector. More...

Functions
DW_API_PUBLIC dwStatus	dwObjectDetector_bindInput (const dwImageCUDA const images, uint32_t imageCount, dwObjectDetectorHandle_t obj)
	Binds the input to the detector as a list of images. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_bindOutput (dwObjectArray *objectArray, uint32_t imageIdx, dwObjectClass objectClass, dwObjectDetectorOutputType type, dwObjectDetectorHandle_t obj)
	Bind the ouput of the detector to array of objects. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_clearOutputMask (dwObjectClass objectClass, dwObjectDetectorHandle_t obj)
	Clears output mask. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_detectObjects (dwObjectArray detections, const dwImageCUDA image, dwObjectDetectorHandle_t obj)
	Detects objects from the given input image. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_getCoverageThreshold (float32_t *covThreshold, dwObjectClass objectClass, dwObjectDetectorHandle_t obj)
	Get coverage threshold for a given class. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_getCUDAStream (cudaStream_t *stream, dwObjectDetectorHandle_t obj)
	Gets the CUDA stream used. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_getOutputMaskDimensions (uint32_t width, uint32_t height, dwObjectDetectorHandle_t obj)
	Returns output mask dimensions. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_getROI (dwRect ROI, dwTransformation2f outputToObject, uint32_t imageIdx, dwObjectDetectorHandle_t obj)
	Returns the region of interest and the 2D transformation from the image coordinate system to object coordinate system at given index. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_initDefaultParams (dwObjectDetectorParams *detectorParams)
	Initializes ObjectDetector parameters with default values. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_initializeFromDriveNet (dwObjectDetectorHandle_t obj, const dwObjectDetectorParams detectorParams, dwDriveNetHandle_t drivenet, dwContextHandle_t ctx)
	Initializes ObjectDetector module with a DriveNet module. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_isDistanceEnabled (bool *enabled, dwObjectDetectorHandle_t obj)
	Returns a boolean indicating whether DNN distance output is enabled. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_isFuseObjectsEnabled (bool *enabled, dwObjectDetectorHandle_t obj)
	Returns a boolean indicating whether object fusing is enabled. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_isObjectDepthEnabled (bool *enabled, dwObjectDetectorHandle_t obj)
	Returns a boolean indicating whether object depth output is enabled. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_isObjectUrgencyEnabled (bool *enabled, dwObjectDetectorHandle_t obj)
	Returns a boolean indicating whether DNN urgency output is enabled. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_process (dwObjectDetectorStage stage, dwObjectDetectorHandle_t obj)
	Perform object detection GPU stages. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_processDLA (dwObjectDetectorDLAStage stage, dwObjectDetectorHandle_t obj)
	Perform object detection DLA stages. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_release (dwObjectDetectorHandle_t obj)
	Releases the ObjectDetector module. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_reset (dwObjectDetectorHandle_t obj)
	Resets ObjectDetector. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_setActiveImageIndices (const uint32_t *imageMap, uint32_t numImages, dwObjectDetectorHandle_t obj)
	Set active images to infer (DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INFERENCE) or interpret (DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INTERPRET_DETECTIONS).The detector can hold multiple images but only need to process a subset of them. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_setCoverageThreshold (float32_t covThreshold, dwObjectClass objectClass, dwObjectDetectorHandle_t obj)
	Set coverage threshold for a given class. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_setCUDAStream (cudaStream_t stream, dwObjectDetectorHandle_t obj)
	Sets the CUDA stream used. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_setEnableFuseObjects (bool enable, dwObjectDetectorHandle_t obj)
	Enables or disables objectFusing. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_setOutputMask (const uint8_t *mask, uint32_t maskWidth, uint32_t maskHeight, dwObjectClass objectClass, dwObjectDetectorHandle_t obj)
	Set output mask. More...

DW_API_PUBLIC dwStatus	dwObjectDetector_setROI (uint32_t imageIdx, const dwRect ROI, const dwTransformation2f outputToObject, dwObjectDetectorHandle_t obj)
	Sets the region of interest for an image at given index, and the 2D transformation from the image coordinate system to object coordinate system. More...

Data Structure Documentation

◆ dwObjectDetectorParams

struct dwObjectDetectorParams

Data Fields
bool	enableBoundingBoxClipping	If enableBoundingBoxClipping is set to true, the bounding boxes are clipped to the image edges. Default is true since it has been used during training.
bool	enableFuseObjects	If enableFuseObjects is set to true, all the objects proposals coming from all the images are treated as a single list of proposals. Clustering is applied to this entire list, which results in a single list of objects. Default is false.
uint32_t	maxNumImages	Maximum number of images (cannot be larger than DW_DETECTOR_MAX_IMAGES). Default is 1.
dwRect	ROIs[DW_OBJECT_DETECTOR_MAX_IMAGES]	Region of interest for each image at the corresponding index. The image is cropped at the given ROI. The cropped region is then be scaled while keeping the aspect ratio and is padded to have the right size for DNN. Default ROI is the whole image.
uint32_t	sensorId	camera sensor id of the camera the detector runs on
dwTransformation2f	transformations[DW_OBJECT_DETECTOR_MAX_IMAGES]	List of transformations from each image coordinate system to object coordinate system at the corresponding image index. By default, the transformation matrices are identity.

Macro Definition Documentation

◆ DW_OBJECT_DETECTOR_MAX_IMAGES

#define DW_OBJECT_DETECTOR_MAX_IMAGES 4

Maximum number of images the detector can process at a time.

Definition at line 64 of file ObjectDetector.h.

Typedef Documentation

◆ dwObjectDetectorHandle_t

typedef struct dwObjectDetectorObject* dwObjectDetectorHandle_t

Handle to an object detector.

Definition at line 70 of file ObjectDetector.h.

Enumeration Type Documentation

◆ dwObjectDetectorDLAStage

enum dwObjectDetectorDLAStage

The DLA process stages of the ObjectDetector.

Enumerator
DW_OBJECT_DETECTOR_DLA_STAGE_GPU_ASYNC_PREPROCESSING	Input images are prepared by scaling, padding and performing other transformations set in dataConditionerParams at initialization time in order to have the right properties required by the DNN. If the given DNN model expects batched input, the given images are divided into batches, where each batch has the expected batch size.
DW_OBJECT_DETECTOR_DLA_STAGE_DLA_ASYNC_INFERENCE	DNN inference is run on the prepared images / batches asynchronously on the DLA device.
DW_OBJECT_DETECTOR_DLA_STAGE_GPU_ASYNC_INTERPRET_DETECTIONS	After inference the GPU postprocesses the detections in device memory.
DW_OBJECT_DETECTOR_DLA_STAGE_CPU_SYNC_POSTPROCESSING	DW_OBJECT_DETECTOR_STAGE_CPU_SYNC_POSTPROCESSING waits for the previous stage to finish processing and then performs postprocessing on the host.

Definition at line 90 of file ObjectDetector_processpipeline.h.

◆ dwObjectDetectorOutputType

enum dwObjectDetectorOutputType

The type of the detector output.

Enumerator
DW_OBJECT_DETECTOR_OUTPUT_TYPE_PROPOSAL
DW_OBJECT_DETECTOR_OUTPUT_TYPE_DETECTION

Definition at line 105 of file ObjectDetector.h.

◆ dwObjectDetectorStage

enum dwObjectDetectorStage

The GPU process stages of the ObjectDetector.

Enumerator
DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_PREPROCESSING	Input images are prepared by scaling, padding and performing other transformations set in dataConditionerParams at initialization time in order to have the right properties required by the DNN. If the given DNN model expects batched input, the given images are divided into batches, where each batch has the expected batch size.
DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INFERENCE	DNN inference is run on the prepared images / batches asynchronously on the GPU.
DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INTERPRET_DETECTIONS	After inference the GPU postprocesses the detections in device memory.
DW_OBJECT_DETECTOR_STAGE_CPU_SYNC_POSTPROCESSING	DW_OBJECT_DETECTOR_STAGE_CPU_SYNC_POSTPROCESSING waits for the previous stage to finish processing and then performs postprocessing on the host.

Definition at line 59 of file ObjectDetector_processpipeline.h.

Function Documentation

◆ dwObjectDetector_bindInput()

DW_API_PUBLIC dwStatus dwObjectDetector_bindInput	(	const dwImageCUDA const	images,
		uint32_t	imageCount,
		dwObjectDetectorHandle_t	obj
	)

Binds the input to the detector as a list of images.

Parameters

[in]	images	Array storing pointers to images where the detector is to be applied.
[in]	imageCount	Number of images provided in the array.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

Note: numImages must be divisible by the batch size of the network.

◆ dwObjectDetector_bindOutput()

DW_API_PUBLIC dwStatus dwObjectDetector_bindOutput	(	dwObjectArray *	objectArray,
		uint32_t	imageIdx,
		dwObjectClass	objectClass,
		dwObjectDetectorOutputType	type,
		dwObjectDetectorHandle_t	obj
	)

Bind the ouput of the detector to array of objects.

Parameters

[in,out]	objectArray	Pointer to an object array structure.
[in]	imageIdx	The image index for the list.
[in]	objectClass	The class for the list.
[in]	type	The type of the output
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_clearOutputMask()

DW_API_PUBLIC dwStatus dwObjectDetector_clearOutputMask	(	dwObjectClass	objectClass,
		dwObjectDetectorHandle_t	obj
	)

Clears output mask.

Parameters

[in]	objectClass	The class of the object
[in]	obj	A pointer to the ObjectDetector handle that is updated

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST

◆ dwObjectDetector_detectObjects()

DW_API_PUBLIC dwStatus dwObjectDetector_detectObjects	(	dwObjectArray *	detections,
		const dwImageCUDA *	image,
		dwObjectDetectorHandle_t	obj
	)

Detects objects from the given input image.

The array for the output detections has to be allocated beforehand.

Parameters

[out]	detections	Detections will be stored in this dwObjectArray. The array has to be previously initialized with the type DW_OBJECT_TYPE_CAMERA. The array will contain detections of all classes supported by the detector.
[in]	image	Input image to detect objects from.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_getCoverageThreshold()

DW_API_PUBLIC dwStatus dwObjectDetector_getCoverageThreshold	(	float32_t *	covThreshold,
		dwObjectClass	objectClass,
		dwObjectDetectorHandle_t	obj
	)

Get coverage threshold for a given class.

Parameters

[out]	covThreshold	Coverage threshold in [0.0, 1.0]
[in]	objectClass	The class for which the coverage threshold should be returned.
[in]	obj	A pointer to the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_getCUDAStream()

DW_API_PUBLIC dwStatus dwObjectDetector_getCUDAStream	(	cudaStream_t *	stream,
		dwObjectDetectorHandle_t	obj
	)

Gets the CUDA stream used.

Parameters

[out]	stream	The CUDA stream used.
[in]	obj	A pointer to the ObjectDetector handle.

Returns: DW_INVALID_ARGUMENT, DW_SUCCESS

◆ dwObjectDetector_getOutputMaskDimensions()

DW_API_PUBLIC dwStatus dwObjectDetector_getOutputMaskDimensions	(	uint32_t *	width,
		uint32_t *	height,
		dwObjectDetectorHandle_t	obj
	)

Returns output mask dimensions.

Parameters

[out]	width	Output mask width.
[out]	height	Output mask height.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_getROI()

DW_API_PUBLIC dwStatus dwObjectDetector_getROI	(	dwRect *	ROI,
		dwTransformation2f *	outputToObject,
		uint32_t	imageIdx,
		dwObjectDetectorHandle_t	obj
	)

Returns the region of interest and the 2D transformation from the image coordinate system to object coordinate system at given index.

Parameters

[out]	ROI	Region of interest to be fed as input to network.
[out]	outputToObject	2D Transformation from output of the network to object coordinate system.
[in]	imageIdx	Index of the image for which to set ROI and transformation.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_initDefaultParams()

DW_API_PUBLIC dwStatus dwObjectDetector_initDefaultParams ( dwObjectDetectorParams * detectorParams )

Initializes ObjectDetector parameters with default values.

Parameters

[out] detectorParams ObjectDetector parameters.

Returns: DW_SUCCESS, DW_INVALID_ARGUMENT

◆ dwObjectDetector_initializeFromDriveNet()

DW_API_PUBLIC dwStatus dwObjectDetector_initializeFromDriveNet	(	dwObjectDetectorHandle_t *	obj,
		const dwObjectDetectorParams *	detectorParams,
		dwDriveNetHandle_t	drivenet,
		dwContextHandle_t	ctx
	)

Initializes ObjectDetector module with a DriveNet module.

Parameters

[out]	obj	A pointer to ObjectDetector handle that is initialized from parameters.
[in]	detectorParams	A pointer to ObjectDetector parameters.
[in]	drivenet	Specifies the handle to the DriveNet module.
[in]	ctx	Specifies the handle to the context.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_isDistanceEnabled()

DW_API_PUBLIC dwStatus dwObjectDetector_isDistanceEnabled	(	bool *	enabled,
		dwObjectDetectorHandle_t	obj
	)

Returns a boolean indicating whether DNN distance output is enabled.

Parameters

[out]	enabled	Boolean indicating whether DNN distance output is enabled.
[in]	obj	A pointer to the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_isFuseObjectsEnabled()

DW_API_PUBLIC dwStatus dwObjectDetector_isFuseObjectsEnabled	(	bool *	enabled,
		dwObjectDetectorHandle_t	obj
	)

Returns a boolean indicating whether object fusing is enabled.

Parameters

[out]	enabled	Boolean indicating whether object fusing is enabled.
[in]	obj	A pointer to the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_isObjectDepthEnabled()

DW_API_PUBLIC dwStatus dwObjectDetector_isObjectDepthEnabled	(	bool *	enabled,
		dwObjectDetectorHandle_t	obj
	)

Returns a boolean indicating whether object depth output is enabled.

Parameters

[out]	enabled	Boolean indicating whether object depth output is enabled.
[in]	obj	A pointer to the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_isObjectUrgencyEnabled()

DW_API_PUBLIC dwStatus dwObjectDetector_isObjectUrgencyEnabled	(	bool *	enabled,
		dwObjectDetectorHandle_t	obj
	)

Returns a boolean indicating whether DNN urgency output is enabled.

Parameters

[out]	enabled	Boolean indicating whether DNN urgency output is enabled.
[in]	obj	A pointer to the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

◆ dwObjectDetector_process()

DW_API_PUBLIC dwStatus dwObjectDetector_process	(	dwObjectDetectorStage	stage,
		dwObjectDetectorHandle_t	obj
	)

Perform object detection GPU stages.

Inputs and outputs must be bound before this call.

Parameters

[in]	stage	Processing stage to run.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_INVALID_ARGUMENT DW_GL_ERROR DW_FAILURE DW_SUCCESS DW_NOT_SUPPORTED

◆ dwObjectDetector_processDLA()

DW_API_PUBLIC dwStatus dwObjectDetector_processDLA	(	dwObjectDetectorDLAStage	stage,
		dwObjectDetectorHandle_t	obj
	)

Perform object detection DLA stages.

Inputs and outputs must be bound before this call.

Parameters

[in]	stage	Processing stage to run.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_INVALID_ARGUMENT DW_GL_ERROR DW_FAILURE DW_SUCCESS DW_NOT_SUPPORTED

◆ dwObjectDetector_release()

DW_API_PUBLIC dwStatus dwObjectDetector_release ( dwObjectDetectorHandle_t obj )

Releases the ObjectDetector module.

Parameters

[in] obj The object handle to release.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST

Note: This method renders the handle unusable.

◆ dwObjectDetector_reset()

DW_API_PUBLIC dwStatus dwObjectDetector_reset ( dwObjectDetectorHandle_t obj )

Resets ObjectDetector.

Parameters

[in] obj Handle to reset.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST

◆ dwObjectDetector_setActiveImageIndices()

DW_API_PUBLIC dwStatus dwObjectDetector_setActiveImageIndices	(	const uint32_t *	imageMap,
		uint32_t	numImages,
		dwObjectDetectorHandle_t	obj
	)

Set active images to infer (DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INFERENCE) or interpret (DW_OBJECT_DETECTOR_STAGE_GPU_ASYNC_INTERPRET_DETECTIONS).The detector can hold multiple images but only need to process a subset of them.

By default, all the images provided to infer API and interpret API will be used. This function is used to assign the images that needs to be processed when detector holds multiple images but want to skip (not process) some images when infer or interpret. The integer(s) of the iput imageMap are used to index to the internal list of ROIs and post-detection transformations.

Parameters

[in]	imageMap	Specifies the images needed to process.
[in]	numImages	Specifies the number of images needed to process.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

Note: This function only affects one following infer or interpret call. Any later infer or interpret call will go back to default behavior (process all images).

◆ dwObjectDetector_setCoverageThreshold()

DW_API_PUBLIC dwStatus dwObjectDetector_setCoverageThreshold	(	float32_t	covThreshold,
		dwObjectClass	objectClass,
		dwObjectDetectorHandle_t	obj
	)

Set coverage threshold for a given class.

Parameters

[in]	covThreshold	Coverage threshold in [0.0, 1.0]
[in]	objectClass	The class for which the coverage threshold should be set.
[in]	obj	A pointer to the ObjectDetector handle that is updated

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST

◆ dwObjectDetector_setCUDAStream()

DW_API_PUBLIC dwStatus dwObjectDetector_setCUDAStream	(	cudaStream_t	stream,
		dwObjectDetectorHandle_t	obj
	)

Sets the CUDA stream used.

Parameters

[in]	stream	The CUDA stream used.
[in]	obj	A pointer to the ObjectDetector handle that is updated.

Returns: DW_INVALID_ARGUMENT, DW_SUCCESS

◆ dwObjectDetector_setEnableFuseObjects()

DW_API_PUBLIC dwStatus dwObjectDetector_setEnableFuseObjects	(	bool	enable,
		dwObjectDetectorHandle_t	obj
	)

Enables or disables objectFusing.

Parameters

[in]	enable	Boolean indicating whether object fusing should be enabled.
[in]	obj	A pointer to the ObjectDetector handle that is updated.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST

◆ dwObjectDetector_setOutputMask()

DW_API_PUBLIC dwStatus dwObjectDetector_setOutputMask	(	const uint8_t *	mask,
		uint32_t	maskWidth,
		uint32_t	maskHeight,
		dwObjectClass	objectClass,
		dwObjectDetectorHandle_t	obj
	)

Set output mask.

Areas where mask==0 will be ignored during detection. The size of the mask must be the same as the network output. The required mask dimensions can be obtained via dwObjectDetector_getOutputMaskDimensions.

Parameters

[in]	mask	A CPU pointer to the mask data
[in]	maskWidth	Mask width
[in]	maskHeight	Mask height
[in]	objectClass	Class of the object
[in]	obj	A pointer to the ObjectDetector handle that is updated

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST

Note: Mask will be copied. Changes on the mask after this function call will not be reflected.

◆ dwObjectDetector_setROI()

DW_API_PUBLIC dwStatus dwObjectDetector_setROI	(	uint32_t	imageIdx,
		const dwRect *	ROI,
		const dwTransformation2f *	outputToObject,
		dwObjectDetectorHandle_t	obj
	)

Sets the region of interest for an image at given index, and the 2D transformation from the image coordinate system to object coordinate system.

Parameters

[in]	imageIdx	Index of the image for which to set ROI and transformation.
[in]	ROI	Region of interest to be fed as input to network.
[in]	outputToObject	2D Transformation from output of the network to object coordinate system.
[in]	obj	Specifies the ObjectDetector handle.

Returns: DW_SUCCESS, DW_INVALID_HANDLE, DW_BAD_CAST, DW_INVALID_ARGUMENT

Detailed Description

Data Structures

Macros

Typedefs

Enumerations

Functions

Data Structure Documentation

◆ dwObjectDetectorParams

Macro Definition Documentation

◆ DW_OBJECT_DETECTOR_MAX_IMAGES

Typedef Documentation

◆ dwObjectDetectorHandle_t

Enumeration Type Documentation

◆ dwObjectDetectorDLAStage

◆ dwObjectDetectorOutputType

◆ dwObjectDetectorStage

Function Documentation

◆ dwObjectDetector_bindInput()

◆ dwObjectDetector_bindOutput()

◆ dwObjectDetector_clearOutputMask()

◆ dwObjectDetector_detectObjects()

◆ dwObjectDetector_getCoverageThreshold()

◆ dwObjectDetector_getCUDAStream()

◆ dwObjectDetector_getOutputMaskDimensions()

◆ dwObjectDetector_getROI()

◆ dwObjectDetector_initDefaultParams()

◆ dwObjectDetector_initializeFromDriveNet()

◆ dwObjectDetector_isDistanceEnabled()

◆ dwObjectDetector_isFuseObjectsEnabled()

◆ dwObjectDetector_isObjectDepthEnabled()

◆ dwObjectDetector_isObjectUrgencyEnabled()

◆ dwObjectDetector_process()

◆ dwObjectDetector_processDLA()

◆ dwObjectDetector_release()

◆ dwObjectDetector_reset()

◆ dwObjectDetector_setActiveImageIndices()

◆ dwObjectDetector_setCoverageThreshold()

◆ dwObjectDetector_setCUDAStream()

◆ dwObjectDetector_setEnableFuseObjects()

◆ dwObjectDetector_setOutputMask()

◆ dwObjectDetector_setROI()