Documentation Status

Cannot load information on name: anj_featurenav, distro: electric, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.
Cannot load information on name: anj_featurenav, distro: fuerte, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.
Cannot load information on name: anj_featurenav, distro: groovy, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.
Cannot load information on name: anj_featurenav, distro: hydro, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.

Package Summary

Released Continuous integration Documented

The anj_featurenav package provides a learning jockey and a navigating jockey for the Large Maps framework (LaMa). It learns a path by saving image features and is able to follow the same path. It is based on algorithms provided by OpenCV (free ones).

Cannot load information on name: anj_featurenav, distro: jade, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.
Cannot load information on name: anj_featurenav, distro: kinetic, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.
Cannot load information on name: anj_featurenav, distro: lunar, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.
Cannot load information on name: anj_featurenav, distro: melodic, which means that it is not yet in our index. Please see this page for information on how to submit your repository to our index.

Overview

anj_featurenav implements a feature-based learning and navigating jockey based on free OpenCV feature descriptor and matcher. The package defines the feature extractor and the descriptor matcher functions required by the featurenav_base package to obtain a working couple learning/navigating jockeys.

Usage

ROS API

The words feature and descriptor are used as synonymous.

Parameters

General
~<name>/feature_detector/type (String, default: "FAST")
  • algorithm for feature detection. Can be one of "FAST", "STAR", "ORB", "MSER", "GFTT" (GoodFeaturesToTrack), "Dense", "SimpleBlob". They make use of their corresponding algorithm in the OpenCV library (for example "FAST" implies the use of "cv::FastFeatureDetector")
~<name>/descriptor_extractor/type (String, default: "BRIEF")
  • algorithm for feature extraction. Can be one of "ORB", "BRIEF". They make use of their corresponding algorithm in the OpenCV library (for example, "SIFT" implies the use of "cv::BriefDescriptorExtractor")
~<name>/descriptor_matcher/type (String, default: "FlannBased")
  • algorithm for feature matching. Can be one of "BruteForce", "FlannBased". They make use of their corresponding algorithm in the OpenCV library (for example, "FlannBased" implies the use of "cv::FlannBasedMatcher")
For the FAST algorithm
~<name>/feature_detector/threshold (Int, default: 1) ~<name>/feature_detector/nonmax_suppression (Bool, default: true)
  • cf. OpenCV documentation
For the STAR algorithm
~<name>/feature_detector/max_size (Int, default: 16) ~<name>/feature_detector/response_threshold (Int, default: 30)
  • cf. OpenCV documentation
~<name>/feature_detector/line_threshold_projected (Int, default: 10)
  • cf. OpenCV documentation
~<name>/feature_detector/line_threshold_binarized (Int, default: 8)
  • cf. OpenCV documentation
~<name>/feature_detector/suppress_nonmax_size (Int, default: 5)
  • cf. OpenCV documentation
For the ORB algorithm, as feature detector
~<name>/feature_detector/scale_factor (Float, default: 1.2) ~<name>/feature_detector/n_features (Int, default: 500)
  • cf. OpenCV documentation
~<name>/feature_detector/n_levels (Int, default: 8)
  • cf. OpenCV documentation
~<name>/feature_detector/edge_threshold (Int, default: 31)
  • cf. OpenCV documentation
~<name>/feature_detector/first_level (Int, default: 0)
  • cf. OpenCV documentation
~<name>/feature_detector/wta_k (Int, default: 2)
  • cf. OpenCV documentation
~<name>/feature_detector/score_type (Int, default: 0 (i.e. Harris score))
  • 0 for Harris score, 1 for FAST score, cf. OpenCV documentation
~<name>/feature_detector/patch_size (Int, default: 31)
  • cf. OpenCV documentation
For the MSER algorithm
~<name>/feature_detector/delta (Int, default: 5) ~<name>/feature_detector/min_area (Int, default: 60)
  • cf. OpenCV documentation
~<name>/feature_detector/max_area (Int, default: 14400)
  • cf. OpenCV documentation
~<name>/feature_detector/max_variation (Float, default: 0.25)
  • cf. OpenCV documentation
~<name>/feature_detector/min_diversity (Float, default: 0.2)
  • cf. OpenCV documentation
~<name>/feature_detector/max_evolution (Int, default: 200)
  • cf. OpenCV documentation
~<name>/feature_detector/area_threshold (Float, default: 1.01)
  • cf. OpenCV documentation
~<name>/feature_detector/min_margin (Float, default: 0.003)
  • cf. OpenCV documentation
~<name>/feature_detector/edge_blur_size (Int, default: 5)
  • cf. OpenCV documentation
For the GFTT algorithm
~<name>/feature_detector/max_corners (Int, default: 1000) ~<name>/feature_detector/block_size (Int, default: 3)
  • cf. OpenCV documentation
~<name>/feature_detector/quality_level (Float, default: 0.01)
  • cf. OpenCV documentation
~<name>/feature_detector/min_distance (Float, default: 1)
  • cf. OpenCV documentation
~<name>/feature_detector/k (Float, default: 0.04)
  • cf. OpenCV documentation
~<name>/feature_detector/use_harris_detector (Bool, default: false)
  • cf. OpenCV documentation
For the Dense algorithm
~<name>/feature_detector/feature_scale_levels (Int, default: 1) ~<name>/feature_detector/init_xy_step (Int, default: 6)
  • cf. OpenCV documentation
~<name>/feature_detector/init_img_bound (Int, default: 0)
  • cf. OpenCV documentation
~<name>/feature_detector/init_feature_scale (Float, default: 1)
  • cf. OpenCV documentation
~<name>/feature_detector/feature_scale_mul (Float, default: 0.1)
  • cf. OpenCV documentation
~<name>/feature_detector/vary_xy_step_with_scale (Bool, default: true)
  • cf. OpenCV documentation
~<name>/feature_detector/vary_img_bound_with_scale (Bool, default: false)
  • cf. OpenCV documentation
For the ORB algorithm, as descriptor extractor
~<name>/descriptor_extractor/scale_factor (Float, default: 1.2) ~<name>/descriptor_extractor/n_features (Int, default: 500)
  • cf. OpenCV documentation
~<name>/descriptor_extractor/n_levels (Int, default: 8)
  • cf. OpenCV documentation
~<name>/descriptor_extractor/edge_threshold (Int, default: 31)
  • cf. OpenCV documentation
~<name>/descriptor_extractor/first_level (Int, default: 0)
  • cf. OpenCV documentation
~<name>/descriptor_extractor/wta_k (Int, default: 2)
  • cf. OpenCV documentation
~<name>/descriptor_extractor/score_type (Int, default: 0 (i.e. Harris score))
  • 0 for Harris score, 1 for FAST score, cf. OpenCV documentation
~<name>/descriptor_extractor/patch_size (Int, default: 31)
  • cf. OpenCV documentation
For the BRIEF algorithm
~<name>/descriptor_extractor/bytes (Int, default: 32)
For the BruteForce algorithm
~<name>/descriptor_matcher/norm (String, default: "L2") ~<name>/descriptor_matcher/cross_check (Bool, default: false)
  • cf. OpenCV documentation

The SimpleBlog algorithm takes no parameter, cf. http://docs.opencv.org/modules/features2d/doc/common_interfaces_of_feature_detectors.html?highlight=simpleblob#simpleblobdetector.

The FlannBased algorithm takes no parameter, cf. http://docs.opencv.org/modules/features2d/doc/common_interfaces_of_descriptor_matchers.html?highlight=flannbasedmatcher#bfmatcher.

Wiki: anj_featurenav (last edited 2015-01-20 15:07:14 by GaelEcorchard)