Evaluation of Features Detectors and Descriptors based on 3D Objects

By Pierre Moreels, Pietro Perona. Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005

607 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0481840f39b8c1560b7137ad3ad0eae0346fe11e

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 Computer Vision and Pattern Recognition

Citations in the corpus

Visual simultaneous localization and mapping: a survey (2012, methodology): “One method to solve the problem of SfM incrementally is the visual odometry published by Nistér et al. (2004). Visual odometry consist in determine simultaneously the camera pose for each video frame and the position of features in 3D world, using only images in a causal way and in real time.”
A comprehensive review of current local features for computer vision (2008, methodology): “Existing detector performance evaluations [49,53] have demonstrated that: (i) under viewpoint changes, MSER out-perform others for both structured and textured images; (ii) under scale changes, Hessian afﬁne detector achieves the best results for both structured and textured images; (iii) under…”
A Comprehensive Performance Evaluation of 3D Local Feature Descriptors (2015, background): “…al. 2000; Mikolajczyk and Schmid 2004; Mikolajczyk et al. 2005; Moreels and Perona 2007), 2D local feature descriptors (Mikolajczyk and Schmid 2005; Moreels and Perona 2005, 2007; Burghouts and Geusebroek 2009), and 3D keypoint detectors (Bronstein et al. 2010; Boyer et al. 2011; Salti et al.…”
Structure from motion photogrammetry in physical geography (2016, background): “Angular changes of >25–30 between adjacent camera locations should be avoided because identification of correct keypoint correspondence is limited for larger changes of perspective (Moreels and Perona, 2007).”
Comparative Evaluation of Binary Features (2012, methodology): “While we could have used the three camera arrangement test described by Moreels and Perona [11], we opted for the single epipolar line approach as it allowed us to compare only a given pair of images, without the need for a third image to provide correspondences and closely mimics typical uses of fe”
ASIFT: A New Framework for Fully Affine Invariant Image Comparison (2009, methodology): “The SIFT method and its variants have been popularly applied for scene recognition [10, 40, 50, 61, 15, 52, 65, 41] and detection [14, 46], robot localization [6, 53, 47, 43], image registration [64], image retrieval [16], motion tracking [59, 20], 3D modeling and reconstruction [49, 62], building p”
Discriminative Learning of Local Image Descriptors (2011, methodology): “We note that Moreels and Perona have also proposed a technique for evaluating 3D feature matches based on trifocal constraints [28].”
Description of interest regions with local binary patterns (2009, background): “There exist several recent comparative studies on region descriptors [15,7,16].”
Performance evaluation of local colour invariants (2009, neutral): “[1,55] or the one proposed by Moreels and Perona [56].”
RGBD Datasets: Past, Present and Future (2016, background): “Following earlier stereo setups such as [78], RGBD turntable datasets offer multiple unoccluded views of the same object from different angles (Table 1).”
Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking (2011, background): “Affine-invariant detectors provide higher repeatability for large affine distortions (Lowe 2004; Mikolajczyk and Schmid 2002), but are typically expensive to compute (Mikolajczyk et al. 2005; Moreels and Perona 2007).”
Fast Keypoint Recognition Using Random Ferns (2010, methodology): “Recently, an extensive comparison of different keypoint detection and matching algorithms on a large database of 3D objects has been published [26].”
Performance Evaluation of 3D Keypoint Detectors (2012, methodology): “A parallel line of research has targeted the evaluation of 2D detectors and descriptors on 3D objects (Moreels and Perona 2007).”
Generic 3D Representation via Pose Estimation and Matching (2016, background): “Therefore, we presume (and empirically observe) that the generality of our 3D representation is mostly attributed to the camera pose estimation component. scribing, and matching image features, either through a handcrafting the feature [35,11,39,38,5,40] or learning it [50,25,65,9,66,49,19].”