BRIEF: Binary Robust Independent Elementary Features

By Michael Calonder, Vincent Lepetit, Christoph Strecha, Pascal Fua. European Conference on Computer Vision, 2010

3,955 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2145f5cbac48df8ed9f7695606c34e98b26cf5a9

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Structure from motion photogrammetry in physical geography (2016, methodology): “, 2008), ASIFT (Morel and Yu, 2009), BRIEF (Calonder et al., 2010) and LDAHash (Strecha et al.”
Vision-based autonomous mapping and exploration using a quadrotor MAV (2012, methodology): “First, we extract and match FAST corners [21] and BRIEF descriptors [6] from the left cameras of both the reference and current frames.”
Fast Matching of Binary Features (2012, methodology): “A number of binary visual descriptors have been recently proposed in the literature, including BRIEF [1], ORB [2], and BRISK [3].”
Visual Odometry : Part II: Matching, Robustness, Optimization, and Applications (2012, methodology): “A simple binary descriptor named BRIEF [22] became popular: it uses pairwise brightness comparisons sampled from a patch around the keypoint.”
Pixel-Level Hand Detection in Ego-centric Videos (2013, methodology): “We evaluate the 16 dimensional BRIEF [3] descriptor and a 32 dimensional ORB [20] descriptor to measure relative performance with respect to the task of hand region detection.”
TILDE: A Temporally Invariant Learned DEtector (2014, methodology): “Note that we also tried using other descriptors [3, 32, 6, 1, 21] but due to the drastic difference between the matched images, only SIFT descriptors with ground truth orientation and scale worked.”
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images (2013, background): “Much work has focused on efficiency, scalability, and learning of feature detection [13, 26], description [4, 27, 34], and matching [18, 25, 29].”
A constant-time SLAM back-end in the continuum between global mapping and submapping: application to visual stereo SLAM (2016, methodology): “Built upon the FAST detector (Rosten and Drummond 2006) and the BRIEF descriptor (Calonder et al. 2010), ORB enhances them by providing scale and rotation invariance to the detected keypoints.”
Comparative Evaluation of Binary Features (2012, methodology): “[6], and are the simplest of the methods.”
Evaluation of local detectors and descriptors for fast feature matching (2012, methodology): “The fastest descriptor is BRIEF (32 bytes), followed by ORB (32 bytes) and BRISK (64 bytes).”
ORB-SLAM: A Versatile and Accurate Monocular SLAM System (2015, methodology): “DBoW2 [5] used for the first time bags of binary words obtained from BRIEF descriptors [16] along with the very efficient FAST feature detector [17].”
A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK (2018, methodology): “ORB algorithm is a blend of modified FAST (Features from Accelerated Segment Test) [25] detection and direction-normalized BRIEF (Binary Robust Independent Elementary Features) [26] description methods.”
Visual simultaneous localization and mapping: a survey (2012, methodology): “To solve this problem to some extent, spatial information is normally introduced in the last phase of retrieval, conducting a post-veriﬁcation taking into account the epipolar constraint (Angeli et al. 2008) or, recently, by means of Conditional Random Fields (Calonder et al. 2010).”
Detection Evolution with Multi-order Contextual Co-occurrence (2013, methodology): “[2, 3, 2, 175] means the pixel a locates in the 2-level higher than Ṗ , (2, 3) in (x, y)-dimensions relative to Ṗ , with pixel value 175.”
Scalable Nearest Neighbor Algorithms for High Dimensional Data (2014, background): “For the comparison we used data sets of BRIEF and ORB features extracted from the recognition benchmark images data set of [24], containing close to 5 million features .”
Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks (2016, background): “In order to reduce the computational complexity, several lightweight binary descriptors have been recently proposed such as BRIEF [6], ORB [33], BRISK [22], and FREAK [1].”
Automatic dense visual semantic mapping from street-level imagery (2012, neutral): “computationally efficient binary features like [3], [16].”
Double window optimisation for constant time visual SLAM (2011, methodology): “Afterwards, we use guided BRIEF [1] matching between measurements and candidate points seeded at FAST [15] corners – followed by 3D to 3D robust pose refinement to produce an initial pose estimate.”
RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation (2018, methodology): “Features can be any of the types included in OpenCV like speeded-up robust features (SURF) (Bay, Ess, Tuytelaars, & Gool, 2008), scale-invariant feature transform (SIFT) (Lowe, 2004), ORB (Rublee et al., 2011), or BRIEF (Calonder et al., 2010 When a laser scan or a point cloud is available, link ’ s”