See: Description
| Interface | Description |
|---|---|
| SpatialVectorAggregator<FEATURE extends FeatureVector,LOCATION extends Location,BOUNDS> |
Interface describing an object that can convert a list of local features from
a single image into an aggregated vector form, using both the featurevector
and spatial location of each local feature.
|
| VectorAggregator<FEATURE extends FeatureVector,AGGREGATE extends FeatureVector> |
Interface describing an object that can convert a list of local features from
a single image into an aggregated vector form.
|
| Class | Description |
|---|---|
| BagOfVisualWords<T> |
Implementation of an object capable of extracting basic (hard-assignment) Bag
of Visual Words (BoVW) representations of an image given a list of local
features and an
HardAssigner with an associated codebook. |
| BlockSpatialAggregator<T,AGGREGATE extends FeatureVector & Concatenatable<AGGREGATE,AGGREGATE>> |
A
BlockSpatialAggregator performs spatial pooling of local features
by grouping the local features into non-overlapping, fixed-size spatial
blocks, and applying a VectorAggregator (i.e. |
| FisherVector<T> |
Implementation of the Fisher Vector (FV) encoding scheme.
|
| PyramidSpatialAggregator<T,AGGREGATE extends FeatureVector & Concatenatable<AGGREGATE,AGGREGATE>> |
A
PyramidSpatialAggregator performs spatial pooling of local features
by grouping the local features into fixed-size spatial blocks within a
pyramid, and applying a VectorAggregator (i.e. |
| SoftBagOfVisualWords<DATATYPE,DISTANCE> |
Implementation of an object capable of extracting the soft-assigned Bag of
Visual Words (BoVW) representation of an image given a list of local features
and an
SoftAssigner with an associated codebook. |
| VLAD<T> |
Implementation of VLAD, the "Vector of Locally Aggregated Descriptors"
algorithm.
|