DBScan Based Object Clustering API

Detailed Description

Defines the API for DBScan-based object clustering.

Data Structures
struct	NvDsInferDBScanClusteringParams
	Holds object clustering parameters required by DBSCAN. More...

Typedefs
typedef struct NvDsInferDBScan *	NvDsInferDBScanHandle
	Holds an opaque DBScan clustering context handle. More...

Functions
NvDsInferDBScanHandle	NvDsInferDBScanCreate ()
	Creates a new DBScan object clustering context. More...
void	NvDsInferDBScanDestroy (NvDsInferDBScanHandle handle)
	Destroys a DBScan object clustering context. More...
void	NvDsInferDBScanCluster (NvDsInferDBScanHandle handle, NvDsInferDBScanClusteringParams *params, NvDsInferObjectDetectionInfo *objects, size_t *numObjects)
	Clusters an array of objects in place using specified clustering parameters. More...
void	NvDsInferDBScanClusterHybrid (NvDsInferDBScanHandle handle, NvDsInferDBScanClusteringParams *params, NvDsInferObjectDetectionInfo *objects, size_t *numObjects)
	Clusters an array of objects in place using specified clustering parameters. More...

Typedef Documentation

typedef struct NvDsInferDBScan* NvDsInferDBScanHandle

Holds an opaque DBScan clustering context handle.

Definition at line 44 of file nvdsinfer_dbscan.h.

Function Documentation

void NvDsInferDBScanCluster	(	NvDsInferDBScanHandle	handle,
		NvDsInferDBScanClusteringParams *	params,
		NvDsInferObjectDetectionInfo *	objects,
		size_t *	numObjects
	)

Clusters an array of objects in place using specified clustering parameters.

Parameters

[in]	handle	A handle to the context be used for clustering.
[in]	params	A pointer to a clustering parameter structure.
[in,out]	objects	A pointer to an array of objects to be clustered. The function places the clustered objects in the same array.
[in,out]	numObjects	A pointer to the number of valid objects in the objects array. The function sets this value after clustering.

void NvDsInferDBScanClusterHybrid	(	NvDsInferDBScanHandle	handle,
		NvDsInferDBScanClusteringParams *	params,
		NvDsInferObjectDetectionInfo *	objects,
		size_t *	numObjects
	)

Clusters an array of objects in place using specified clustering parameters.

The outputs are partially only clustered i.e to merge close neighbors of the same cluster together only and the mean normalization of all the proposals in a cluster is not performed. The outputs from this stage are later fed into another clustering algorithm like NMS to obtain the final results.

Parameters

[in]	handle	A handle to the context be used for clustering.
[in]	params	A pointer to a clustering parameter structure.
[in,out]	objects	A pointer to an array of objects to be clustered. The function places the clustered objects in the same array.
[in,out]	numObjects	A pointer to the number of valid objects in the objects array. The function sets this value after clustering.

NvDsInferDBScanHandle NvDsInferDBScanCreate

(

)

Creates a new DBScan object clustering context.

Returns

A handle to the created context.

void NvDsInferDBScanDestroy

(

NvDsInferDBScanHandle

handle

)

Destroys a DBScan object clustering context.

Parameters

[in]

handle

The handle to the context to be destroyed.