DBOW2

Algorithm Implementations

match_descriptor_sets

class match_descriptor_sets : public kwiver::vital::algo::match_descriptor_sets

class for bag of words image matching

This class implements bag of words image matching with DBoW2

Public Functions

virtual std::vector<vital::frame_id_t> query_and_append(const vital::descriptor_set_sptr desc, vital::frame_id_t frame) override

Query the inverted file system for similar images and append the querying image. Query the inverted file system and return the most similar images. This method may be faster than first querying and then appending if both operations are required.

Parameters:
  • desc[in] set of descriptors for the image

  • frame[in] id of the query image

Returns:

vector of possibly matching frames found by the query

virtual bool check_configuration(vital::config_block_sptr config) const override

Check that the algorithm’s currently configuration is valid.

Get this algorithm’s configuration block This checks solely within the provided config_block and not against the current state of the instance. This isn’t static for inheritence reasons.

Parameters:

config – The config block to check configuration of.

Returns:

true if the configuration check passed and false if it didn’t.

class priv

Public Functions

inline vital::algo::detect_features_sptr c_detector() const

The feature detector algorithm to use.

inline vital::algo::extract_descriptors_sptr c_extractor() const

The descriptor extractor algorithm to use.