Defines the interface for per-target pose estimation.
Definition at line 35 of file sources/libs/nvmultiobjecttracker/include/modules/PoseEstimator/IPoseEstimator.hpp.

Public Member Functions | |
| virtual | ~IPoseEstimator () |
| Release resources owned by the IPoseEstimator instance. More... | |
| virtual void | initializeRuntime (const SourceFrameInfo &frameInfo, const uint maxTargetsPerStream, const std::shared_ptr< NvTrackedObjectManager > &targetManager)=0 |
| Initialize variables and allocate memories. More... | |
| virtual void | initializeModel ()=0 |
| Create TensorRT inference engine; if engine does not exist, serialize from model file. More... | |
| virtual void | queryParams (NvMOTQuery ¶msQuery)=0 |
| Populate the capabilities reported to the tracker. More... | |
| virtual void | doInference (const std::map< NvMOTStreamId, NvMOTFrame * > &inputMeta, std::map< NvMOTStreamId, std::deque< DetectedObjInfo >> &detectedObjects, const bool isForReAssoc)=0 |
| Run pose inference on cropped targets from the input frames. More... | |
| virtual void | update ()=0 |
| Update the pose estimator after data association. More... | |
| virtual void | removeStream (const NvMOTStreamId videoStreamId)=0 |
| Remove a stream from the pose estimator. More... | |
| virtual const POSEESTIMATOR_TYPES | getPoseEstimatorType ()=0 |
| Get the configured pose-estimator type. More... | |
| virtual | ~IPoseEstimator () |
| Release resources owned by the IPoseEstimator instance. More... | |
| virtual void | initializeRuntime (const SourceFrameInfo &frameInfo, const uint maxTargetsPerStream, const std::shared_ptr< NvTrackedObjectManager > &targetManager)=0 |
| Initialize variables and allocate memories. More... | |
| virtual void | initializeModel ()=0 |
| Create TensorRT inference engine; if engine does not exist, serialize from model file. More... | |
| virtual void | queryParams (NvMOTQuery ¶msQuery)=0 |
| Populate the capabilities reported to the tracker. More... | |
| virtual void | doInference (const std::map< NvMOTStreamId, NvMOTFrame * > &inputMeta, std::map< NvMOTStreamId, std::deque< DetectedObjInfo >> &detectedObjects, const bool isForReAssoc)=0 |
| Run pose inference on cropped targets from the input frames. More... | |
| virtual void | update ()=0 |
| Update the pose estimator after data association. More... | |
| virtual void | removeStream (const NvMOTStreamId videoStreamId)=0 |
| Remove a stream from the pose estimator. More... | |
| virtual const POSEESTIMATOR_TYPES | getPoseEstimatorType ()=0 |
| Get the configured pose-estimator type. More... | |
|
inlinevirtual |
Release resources owned by the IPoseEstimator instance.
Definition at line 39 of file sources/libs/nvmultiobjecttracker/include/modules/PoseEstimator/IPoseEstimator.hpp.
|
inlinevirtual |
Release resources owned by the IPoseEstimator instance.
Definition at line 39 of file 9.2/sources/libs/nvmultiobjecttracker/include/modules/PoseEstimator/IPoseEstimator.hpp.
|
pure virtual |
Run pose inference on cropped targets from the input frames.
| [in] | inputMeta | A batch of input frames. |
| [in,out] | detectedObjects | Newly detected objects in each stream. |
| [in] | isForReAssoc | Whether this inference is for reassociation. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Run pose inference on cropped targets from the input frames.
| [in] | inputMeta | A batch of input frames. |
| [in,out] | detectedObjects | Newly detected objects in each stream. |
| [in] | isForReAssoc | Whether this inference is for reassociation. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Get the configured pose-estimator type.
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Get the configured pose-estimator type.
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Create TensorRT inference engine; if engine does not exist, serialize from model file.
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Create TensorRT inference engine; if engine does not exist, serialize from model file.
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Initialize variables and allocate memories.
| [in] | frameInfo | Metadata about the source image, such as size and color. |
| [in] | maxTargetsPerStream | Maximum number of targets to track in each stream. |
| [in] | targetManager | Target manager of the tracked objects. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Initialize variables and allocate memories.
| [in] | frameInfo | Metadata about the source image, such as size and color. |
| [in] | maxTargetsPerStream | Maximum number of targets to track in each stream. |
| [in] | targetManager | Target manager of the tracked objects. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Populate the capabilities reported to the tracker.
| [out] | paramsQuery | The output query parameters. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Populate the capabilities reported to the tracker.
| [out] | paramsQuery | The output query parameters. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Remove a stream from the pose estimator.
| [in] | videoStreamId | Video stream id. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Remove a stream from the pose estimator.
| [in] | videoStreamId | Video stream id. |
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Update the pose estimator after data association.
Implemented in PoseInference, and PoseInference.
|
pure virtual |
Update the pose estimator after data association.
Implemented in PoseInference, and PoseInference.