🤖 AIによる機械翻訳(非公式) — これは OpenCV 5.0.0 公式リファレンス(英語)を AI (Claude) で自動翻訳したものです。訳に誤りを含む場合があります。正確な情報は 公式英語版(原文) を参照してください。
Package org.opencv.video
クラス DISOpticalFlow
- java.lang.Object
-
- org.opencv.core.Algorithm
-
- org.opencv.video.DenseOpticalFlow
-
- org.opencv.video.DISOpticalFlow
public class DISOpticalFlow extends DenseOpticalFlow
DIS オプティカルフローアルゴリズム。このクラスは Dense Inverse Search (DIS) オプティカルフローアルゴリズムを実装する。アルゴリズムの詳細は CITE: Kroeger2016 を参照。速度と品質の妥当なトレードオフを実現するため、あらかじめ選択された引数を持つ 3 つのプリセットを含む。ただし、最も遅いプリセットでも比較的高速であり、より高い品質が必要で速度を問わない場合は DeepFlow を使用するとよい。本実装には、論文で説明されているアルゴリズムと比較していくつかの追加機能が含まれており、フローベクトルの空間的伝播 (REF: getUseSpatialPropagation) や、REF: calc に渡される初期フロー近似を利用するオプション(これは本質的に時間的伝播であり、直前のフレームのフローフィールドを渡す場合に該当する)が含まれる。
-
-
フィールドの要約
フィールド Modifier and Type Field Description static intPRESET_FASTstatic intPRESET_MEDIUMstatic intPRESET_ULTRAFAST
-
コンストラクタの要約
コンストラクタ Modifier Constructor Description protectedDISOpticalFlow​(long addr)
-
メソッドの要約
すべてのメソッド 静的メソッド インスタンスメソッド 具象メソッド Modifier and Type Method Description static DISOpticalFlow__fromPtr__​(long addr)static DISOpticalFlowcreate()Creates an instance of DISOpticalFlowstatic DISOpticalFlowcreate​(int preset)Creates an instance of DISOpticalFlowintgetCoarsestScale()Gets the coarsest scaleintgetFinestScale()Finest level of the Gaussian pyramid on which the flow is computed (zero level corresponds to the original image resolution).intgetGradientDescentIterations()Maximum number of gradient descent iterations in the patch inverse search stage.intgetPatchSize()Size of an image patch for matching (in pixels).intgetPatchStride()Stride between neighbor patches.booleangetUseMeanNormalization()Whether to use mean-normalization of patches when computing patch distance.booleangetUseSpatialPropagation()Whether to use spatial propagation of good optical flow vectors.floatgetVariationalRefinementAlpha()Weight of the smoothness term SEE: setVariationalRefinementAlphafloatgetVariationalRefinementDelta()Weight of the color constancy term SEE: setVariationalRefinementDeltafloatgetVariationalRefinementEpsilon()Norm value shift for robust penalizer SEE: setVariationalRefinementEpsilonfloatgetVariationalRefinementGamma()Weight of the gradient constancy term SEE: setVariationalRefinementGammaintgetVariationalRefinementIterations()Number of fixed point iterations of variational refinement per scale.voidsetCoarsestScale​(int val)Sets the coarsest scalevoidsetFinestScale​(int val)getFinestScale SEE: getFinestScalevoidsetGradientDescentIterations​(int val)getGradientDescentIterations SEE: getGradientDescentIterationsvoidsetPatchSize​(int val)getPatchSize SEE: getPatchSizevoidsetPatchStride​(int val)getPatchStride SEE: getPatchStridevoidsetUseMeanNormalization​(boolean val)getUseMeanNormalization SEE: getUseMeanNormalizationvoidsetUseSpatialPropagation​(boolean val)getUseSpatialPropagation SEE: getUseSpatialPropagationvoidsetVariationalRefinementAlpha​(float val)getVariationalRefinementAlpha SEE: getVariationalRefinementAlphavoidsetVariationalRefinementDelta​(float val)getVariationalRefinementDelta SEE: getVariationalRefinementDeltavoidsetVariationalRefinementEpsilon​(float val)getVariationalRefinementEpsilon SEE: getVariationalRefinementEpsilonvoidsetVariationalRefinementGamma​(float val)getVariationalRefinementGamma SEE: getVariationalRefinementGammavoidsetVariationalRefinementIterations​(int val)getGradientDescentIterations SEE: getGradientDescentIterations-
クラス org.opencv.video.DenseOpticalFlow から継承されたメソッド
calc, collectGarbage
-
クラス org.opencv.core.Algorithm から継承されたメソッド
clear, empty, getDefaultName, getNativeObjAddr, save
-
-
-
-
メソッドの詳細
-
__fromPtr__
public static DISOpticalFlow __fromPtr__​(long addr)
-
getFinestScale
public int getFinestScale()
Finest level of the Gaussian pyramid on which the flow is computed (zero level corresponds to the original image resolution). The final flow is obtained by bilinear upscaling. SEE: setFinestScale- 戻り値:
- 自動生成
-
setFinestScale
public void setFinestScale​(int val)
getFinestScale SEE: getFinestScale- 引数:
val- 自動生成
-
setCoarsestScale
public void setCoarsestScale​(int val)
Sets the coarsest scale- 引数:
val- フローを計算するガウシアンピラミッドの最も粗いレベル。-1 を設定すると、自動計算された最も粗いスケールが使用される。
-
getCoarsestScale
public int getCoarsestScale()
Gets the coarsest scale- 戻り値:
- 自動生成
-
getPatchSize
public int getPatchSize()
Size of an image patch for matching (in pixels). Normally, default 8x8 patches work well enough in most cases. SEE: setPatchSize- 戻り値:
- 自動生成
-
setPatchSize
public void setPatchSize​(int val)
getPatchSize SEE: getPatchSize- 引数:
val- 自動生成
-
getPatchStride
public int getPatchStride()
Stride between neighbor patches. Must be less than patch size. Lower values correspond to higher flow quality. SEE: setPatchStride- 戻り値:
- 自動生成
-
setPatchStride
public void setPatchStride​(int val)
getPatchStride SEE: getPatchStride- 引数:
val- 自動生成
-
getGradientDescentIterations
public int getGradientDescentIterations()
Maximum number of gradient descent iterations in the patch inverse search stage. Higher values may improve quality in some cases. SEE: setGradientDescentIterations- 戻り値:
- 自動生成
-
setGradientDescentIterations
public void setGradientDescentIterations​(int val)
getGradientDescentIterations SEE: getGradientDescentIterations- 引数:
val- 自動生成
-
getVariationalRefinementIterations
public int getVariationalRefinementIterations()
Number of fixed point iterations of variational refinement per scale. Set to zero to disable variational refinement completely. Higher values will typically result in more smooth and high-quality flow. SEE: setGradientDescentIterations- 戻り値:
- 自動生成
-
setVariationalRefinementIterations
public void setVariationalRefinementIterations​(int val)
getGradientDescentIterations SEE: getGradientDescentIterations- 引数:
val- 自動生成
-
getVariationalRefinementAlpha
public float getVariationalRefinementAlpha()
Weight of the smoothness term SEE: setVariationalRefinementAlpha- 戻り値:
- 自動生成
-
setVariationalRefinementAlpha
public void setVariationalRefinementAlpha​(float val)
getVariationalRefinementAlpha SEE: getVariationalRefinementAlpha- 引数:
val- 自動生成
-
getVariationalRefinementDelta
public float getVariationalRefinementDelta()
Weight of the color constancy term SEE: setVariationalRefinementDelta- 戻り値:
- 自動生成
-
setVariationalRefinementDelta
public void setVariationalRefinementDelta​(float val)
getVariationalRefinementDelta SEE: getVariationalRefinementDelta- 引数:
val- 自動生成
-
getVariationalRefinementGamma
public float getVariationalRefinementGamma()
Weight of the gradient constancy term SEE: setVariationalRefinementGamma- 戻り値:
- 自動生成
-
setVariationalRefinementGamma
public void setVariationalRefinementGamma​(float val)
getVariationalRefinementGamma SEE: getVariationalRefinementGamma- 引数:
val- 自動生成
-
getVariationalRefinementEpsilon
public float getVariationalRefinementEpsilon()
Norm value shift for robust penalizer SEE: setVariationalRefinementEpsilon- 戻り値:
- 自動生成
-
setVariationalRefinementEpsilon
public void setVariationalRefinementEpsilon​(float val)
getVariationalRefinementEpsilon SEE: getVariationalRefinementEpsilon- 引数:
val- 自動生成
-
getUseMeanNormalization
public boolean getUseMeanNormalization()
Whether to use mean-normalization of patches when computing patch distance. It is turned on by default as it typically provides a noticeable quality boost because of increased robustness to illumination variations. Turn it off if you are certain that your sequence doesn't contain any changes in illumination. SEE: setUseMeanNormalization- 戻り値:
- 自動生成
-
setUseMeanNormalization
public void setUseMeanNormalization​(boolean val)
getUseMeanNormalization SEE: getUseMeanNormalization- 引数:
val- 自動生成
-
getUseSpatialPropagation
public boolean getUseSpatialPropagation()
Whether to use spatial propagation of good optical flow vectors. This option is turned on by default, as it tends to work better on average and can sometimes help recover from major errors introduced by the coarse-to-fine scheme employed by the DIS optical flow algorithm. Turning this option off can make the output flow field a bit smoother, however. SEE: setUseSpatialPropagation- 戻り値:
- 自動生成
-
setUseSpatialPropagation
public void setUseSpatialPropagation​(boolean val)
getUseSpatialPropagation SEE: getUseSpatialPropagation- 引数:
val- 自動生成
-
create
public static DISOpticalFlow create​(int preset)
Creates an instance of DISOpticalFlow- 引数:
preset- PRESET_ULTRAFAST, PRESET_FAST, PRESET_MEDIUM のいずれか- 戻り値:
- 自動生成
-
create
public static DISOpticalFlow create()
Creates an instance of DISOpticalFlow- 戻り値:
- 自動生成
-
-