Face Engine SDK  5.21.0
A face detection, recognition and tracking engine.
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Macros Groups Pages
fsdk::IFightsEstimator Struct Referenceabstract

FightsEstimator estimator interface. More...

#include <IFightsEstimator.h>

Inheritance diagram for fsdk::IFightsEstimator:
fsdk::IRefCounted

Public Member Functions

virtual size_t getBatchSize () const noexcept=0
 Returns the required size for each batch from the video for analysis.
 
virtual size_t getMinBatchCount () const noexcept=0
 Returns the minimun count of batches from the video for analysis. More...
 
virtual ResultValue< FSDKError,
IFightsEstimatorContextPtr > 
estimate (Span< const Image > framesBatch, IFightsEstimatorContextPtr context) const noexcept=0
 
virtual Result< FSDKErrorvalidate (Span< const Image > framesBatch, Span< Result< FSDKError >> errors) const noexcept=0
 Validates input batch of frames in a single function call. More...
 
- Public Member Functions inherited from fsdk::IRefCounted
virtual int32_t retain () noexcept=0
 Increase strong reference count. More...
 
virtual int32_t retainLocked () noexcept=0
 Increase strong reference count thread safely. More...
 
virtual int32_t release () noexcept=0
 Decrease strong reference count. More...
 
virtual int32_t getRefCount () const noexcept=0
 Get actual strong reference count. More...
 
virtual int32_t retainWeak () noexcept=0
 Increase weak reference count. More...
 
virtual int32_t releaseWeak () noexcept=0
 Decrease weak reference count. More...
 
virtual int32_t getWeakRefCount () const noexcept=0
 Get actual weak reference count. More...
 

Detailed Description

FightsEstimator estimator interface.

Note
This estimator is designed for video analysis to find the fights. The video should be passes as an array of frames in the Format::R8G8B8 format, grouped by batches with size M. Note: the M value could be known by getBathSize() call

Member Function Documentation

virtual ResultValue<FSDKError, IFightsEstimatorContextPtr> fsdk::IFightsEstimator::estimate ( Span< const Image framesBatch,
IFightsEstimatorContextPtr  context 
) const
pure virtualnoexcept

Esimates current fight state for the batch from the video for analysis.

Parameters
[in]framesBatchsource frames batch.
[in][out]context - context structure with current state of processing.
Returns
ResultValue with error code and the IFightsEstimatorContext object.
See Also
Image, Span, ResultValue, IFightsEstimatorContext and FSDKError for details.
Note
The context in an input-output parrameter. At the first call the context should be empty (IFightsEstimatorContextPtr{}). And it will be returned by the call. At the next calls the contenxt should contain the object from the previous call.
virtual size_t fsdk::IFightsEstimator::getMinBatchCount ( ) const
pure virtualnoexcept

Returns the minimun count of batches from the video for analysis.

Note
The estimator will return IFightsEstimatorContext::State::NotReady until all required frames batches have been passed for processing.
See Also
IFightsEstimatorContext::State for details.
virtual Result<FSDKError> fsdk::IFightsEstimator::validate ( Span< const Image framesBatch,
Span< Result< FSDKError >>  errors 
) const
pure virtualnoexcept

Validates input batch of frames in a single function call.

Parameters
[in]framesBatchsource frames batch.
[out]errorsoutput span of errors for each image.
Returns
Result with error code.
See Also
Image, Span, Result and FSDKError for details.
Note
Images format must be Format::R8G8B8,
See Also
Format.
Note
all spans should be based on user owned continuous collections.
all spans should be equal size.

The documentation for this struct was generated from the following file: