Fast Keypoint Recognition Using Random Ferns

By Mustafa Özuysal, Michael Calonder, Vincent Lepetit, Pascal Fua. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

724 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3ea54da8ba5deba902e34199b63956edf68906ff

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Revisiting Trends in Augmented Reality Research: A Review of the 2nd Decade of ISMAR (2008–2017) (2018, methodology): “They used randomized ferns [105] and simple binary feature tests to encode whole image frames, and so could achieve fast recovery from tracking failures, with seamless continuation of mapping.”
A survey of appearance models in visual object tracking (2013, neutral): “More recently, randomized learning techniques (e.g., Random Forest [Breiman 2001; Shotton et al. 2008; Lepetit and Fua 2006] and Ferns [Özuysal et al. 2009]) have been successfully introduced into the vision community.”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, neutral): “Recently, keypoint matching has been formulated as a classification problem [66], [95].”
A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources (2019, methodology): “Random ferns [117] Same test parameters are used in all nodes of the same tree level.”
Face alignment by coarse-to-fine shape searching (2015, background): “[8], regress selected discriminative pixel-difference features with random ferns [27].”
Decision Forests: A Unified Framework for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2012, methodology): “In this case the additional constraint is that the same test parameters are used in all nodes of the same tree level [75, 77].”
Context tracker: Exploring supporters and distracters in unconstrained environments (2011, background): “[24] to increase the speed of randomized forest [6].”
Detection Evolution with Multi-order Contextual Co-occurrence (2013, methodology): “Our multi-order context representation is inspired by the recent success of randomized binary image descriptors [22, 3, 24].”
Random Forests (2012, neutral): “一方,Random ferns[19] も Random Forests の一種であり,決定木の同じレベルのノードでは同じ分割関数を利用するものである.”
BRIEF: Binary Robust Independent Elementary Features (2010, methodology): “The individual bits are obtained by comparing the intensities of pairs of points along the same lines as in [9] but without requiring a training phase.”
Applied Predictive Modeling (2013, neutral): “Other random forests functions are cforest (in the party package), obliqueRF (forests from oblique trees in the obliqueRF package), rFerns (for the random fern model of Ozuysal et al. (2010) in the rFerns package), and RRF (regularized random forest models in the RRF package).”
Learning 6D Object Pose Estimation Using 3D Object Coordinates (2014, background): “More recently a trend has been to learn interest points [22,10], descriptors [30], and matching [14,19,1].”
The MOPED framework: Object recognition and pose estimation for manipulation (2011, methodology): “In other words, it is equally valid in both an extrinsically calibrated multi-camera setup, and in the simplified case of a single image (M = 1) and a camera-centric world (T1 = I4, where I4 is a 4× 4 identity matrix).”