A Combined Corner and Edge Detector

  title={A Combined Corner and Edge Detector},
  author={Christopher G. Harris and M. J. Stephens},
  booktitle={Alvey Vision Conference},
The problem we are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a diversity of objects for topdown recognition techniques to work. [] Key Method The solution to this problem that we are pursuing is to use a computer vision system based upon motion analysis of a monocular image sequence from a mobile camera. By extraction and tracking of image features, representations of the 3D…

Figures from this paper

Attending, Foveating and Recognizing Objects in Real World Scenes

A binocular system able to overcome two conflicting requirements for robust recognition, foveated and segmented in 3D, that is fully automised and runs at real-time speed.

Feature Points Densification and Refinement

This work suggests a feature refinement technique based on a Harris corner detector, which replaces a set of initially detected feature points with a more accurate and dense set of matching features.

Vision-based natural feature tracking for augmented reality

A new approach is presented to detect and track the natural features of unprepared scenes from sequential images which can be used in the outdoor AR system. Firstly, a corner detection system


An automated processing pipeline that, from a sequence of images, reconstructs a 3D model that can deal with a hand-held camera without the need for an a priori calibration or explicit knowledge about the recorded scene is presented.

A new approach to detecting the corners in digital images

  • E. Sojka
  • Computer Science
    Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)
  • 2003
A new corner detector is presented that is based on a theory that takes into account relatively complicated situations that may occur in the neighbourhoods of the corner candidates and was better in the tests than the other algorithms used for comparison.

A method for detection of known objects in visual search tasks

  • A. Sluzek
  • Computer Science
    2008 IEEE Conference on Cybernetics and Intelligent Systems
  • 2008
A novel method for visual detection of known objects in images of arbitrary contents using keypoint detectors that can be used primarily for vision-guided search in mobile autonomous devices is outlined.

Detailed Visual Recognition of Road Scenes for Guiding Autonomous Vehicles

  • E. Dickmanns
  • Computer Science
    Advances in Real-Time Systems
  • 2012
The article concentrates on the new corner detection scheme looking directly for curvature components of the intensity function in several pairs of orthogonal directions, which is especially suited for recognizing blinking spot lights and brake (stop) lights.

Shape recognition with edge-based features

An approach to recognizing poorly textured objects, that may contain holes and tubular parts, in cluttered scenes under arbitrary viewing conditions is described and a new edge-based local feature detector that is invariant to similarity transformations is introduced.

Fast and cheap object recognition by linear combination of views

The proposed approach does not require a segmentation stage, and it is applicable to cluttered scenes, and the small size of the model and the rapidity of the detection make this algorithm particularly suitable for real-time applications on mobile devices.



Finding Edges and Lines in Images

This thesis is an attempt to formulate a set of edge detection criteria that capture as directly as possible the desirable properties of an edge operator.

Obstacle avoidance and navigation in the real world by a seeing robot rover

Abstract : The Stanford AI Lab cart is a card-table sized mobile robot controlled remotely through a radio link, and equipped with a TV camera and transmitter. A computer has been programmed to drive

Gray-level corner detection

Fast and Reliable Passive Trinocular Stereovision

  • Proceedings first ICCV
  • 1987