A Combined Corner and Edge Detector

By C. G. Harris, M. Stephens. 1988

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “In feature point detectors [12], NMS is effective in performing local thresholding to obtain unique feature point detections.”
ScaleNet: An Unsupervised Representation Learning Method for Limited Information (2023, methodology): “The corner information of images is extracted by the Harris corner detector [19].”
Simplifying Graph Convolutional Networks (2019, background): “Similarly, simple pre-defined linear image filters (Sobel & Feldman, 1968; Harris & Stephens, 1988) eventually gave rise to nonlinear CNNs with learned convolutional kernels (Waibel et al., 1989; LeCun et al., 1989).”
Learning monocular reactive UAV control in cluttered natural environments (2012, background): “2) In addition to the lack of feedback, providing the correct actions in real-time after the first iteration when the drone is in control can be hard for the pilot as he must react to what the drone is doing and not what he expects to happen: e.g., if the drone suddenly starts turning towards a…”
Diagram Understanding in Geometry Questions (2014, methodology): “We use Harris Corner detectors (Harris and Stephens 1988) to identify possible locations of corners.”
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification (2015, neutral): “For instance, Laptev [23] extended the 2D Harris corner detector [10] into 3D space to ﬁnd space-time interest points.”
SIFT Flow: Dense Correspondence across Scenes and Its Applications (2011, background): “For example, a car moving forward can appear in a street scene with an empty road, and a fish may swim in a fish tank scene.”
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch (2019, methodology): “The module provides differentiable versions of the Harris corner detector[20], Hessian detector [6], their scale and affine covariant versions [38], DoG [33], patch dominant gradient orientation [33] and the SIFT descriptor [33].”
Markerless tracking using planar structures in the scene (2000, unknown): “Our implementation uses public-domain code for the Harris corner detector [15], from www.targetjr.org .”
Reliable feature matching across widely separated views (2000, methodology): “Hence we have found that a better approach is to detect spatial Harris features [9] at a set of scales and order these features based on a scalenormalised feature strength as follows.”
Component Divide-and-Conquer for Real-World Image Super-Resolution (2020, methodology): “Inspired by Harris corner points [8], image contents are divided into three primary visual components: ﬂat, edges and corner points according to their gradient changes.”
Evaluation of Local Spatio-temporal Features for Action Recognition (2009, unknown): “The Harris3D detector was proposed by Laptev and Lindeberg in [14], as a space-time extension of the Harris detector [9].”
Deep Imitation Learning of Sequential Fabric Smoothing Policies (2019, methodology): “In among the most relevant prior on fabric smoothing, Willimon et al. [53] present an algorithm that pulls at eight ﬁxed angles, and then uses a six-step stage to identify corners from depth images using the Harris Corner Detector [14].”
Distinctive Image Features from Scale-Invariant Keypoints Abstract by Matthijs Dorst Based on the paper by (2011, background): “To eliminate these the ratio of principal curves at the keypoint can be computed at the location and scale of the keypoint without explicitly calculating the eigenvalues [6]:”
Scene modelling, recognition and tracking with invariant image features (2004, methodology): “Some of the most common choices are the Harris corner detector [9], applied in [4, 5], and the Kanade-LucasTomasi (KLT) tracker [18], used in [25, 8, 20].”
Saliency, Scale and Image Description (2001, methodology): “2 Schmid and Mohr (1997) select Interest points using the Harris Corner detector (Harris and Stephens, 1988), and then extract descriptors at these locations for an image retrieval application.”
A sparse object category model for efficient learning and exhaustive recognition (2005, methodology): “The majority of approaches using feature-based methods rely on region detectors such as Kadir and Brady or multi-scale Harris [9] [11] which favor interest points or circular regions.”