Speeded-Up Robust Features (SURF)

By Herbert Bay, Andreas Ess, Tinne Tuytelaars, Luc Van Gool. 2008

14,012 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

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

Do Better ImageNet Models Transfer Better? (2018, neutral): “Before the rise of convolutional neural networks, most approaches to image understanding relied on hand-engineered feature descriptors [45, 15, 3].”
Curriculum learning of multiple tasks (2014, methodology): “As our feature representation, we use 2000 dimensional bag-of-words histograms obtained from SURF descriptors [3] provided with the dataset.”
P-CNN: Pose-Based CNN Features for Action Recognition (2015, methodology): “A recent approach [37] removes trajectories consistent with the camera motion (estimated computing a homography using optical ﬂow and SURF [1] point matches and RANSAC [14]).”
CloudCV: Large-Scale Distributed Computer Vision as a Cloud Service (2015, background): “Feature Extraction: distinctive points (or keypoints) are identified in each image and a feature descriptor [20, 40] is computed for each keypoint.”
Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection (2017, methodology): “Early approaches, such as [6], heavily depend on extracting local features such as SIFT [30], SURF [3], MSER [32] and matching them to retrieve instances [29, 48].”
Domain Adaptive Neural Networks for Object Recognition (2014, methodology): “The standard evaluation protocol on this data set is based on using the SURF feature descriptor (Bay et al., 2008) as inputs to the model.”
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition (2014, background): “D features, such as SIFT [23], HOG [17] and SURF [1] have been successfully employed in static images, and some have been extended to 3-”
BSIF: Binarized statistical image features (2012, methodology): “For example, interest regions are typically represented using descriptors like SIFT [8], SURF [3], or BRIEF [4], and their variants.”
Universal Correspondence Network (2016, methodology): “Several hand-designed features, such as SIFT, HOG, SURF and DAISY have found widespread applications [22, 3, 29, 8].”
Using Deep Learning for Image-Based Plant Disease Detection (2016, methodology): “Previously, the traditional approach for image classiﬁcation tasks has been based on hand-engineered features such as SIFT[18], HoG[19], SURF[20], etc., and then to use some form of learning algorithm in these feature spaces.”
A Review on Human Activity Recognition Using Vision-Based Method (2017, methodology): “The speeded-up robust features (SURF) [47] approach is a scale and rotation invariant detector and descriptor.”
Content-based visual search learned from social media (2012, methodology): “In particular, we adopt dense sampling for keypoint localization and SURF [9] for keypoint description, using a fast implementation of dense-SURF [120].”