Edge detection and motion detection

doi:10.1016/0262-8856(86)90007-7

Image and Vision Computing

Volume 4, Issue 1, February 1986, Pages 43-56

https://doi.org/10.1016/0262-8856(86)90007-7 Get rights and content

Abstract

This paper presents an integrated theory of edge detection, curvature measurement and motion detection during the earliest stages of visual processing. No assumptions are necessary about the viewed objects or about surface properties and the viewing geometry. New methods are outlined for edge detection, curvature measurement and correspondence matching by successive refinement.

References (39)

JW Modestino et al.
Edge detection in noisy images using recursive digital filtering
JW Modestino et al.
Perception
(1977)
E Argyle
Techniques for edge detection
HP Moravec
Towards automatic visual obstacle avoidance
D Marr
Visual information processing: the structure and creation of visual representations
Phil. Trans. R. Soc. Lond.
(1980)
D Marr
Vision
(1980)
D Marr et al.
Theory of edge detection
WK Pratt
Digital image processing
(1978)
A Herskowitz et al.
On boundary detection
MIT AI Lab Memo 183
(1970)
D Marr
Early processing of visual information
Phil. Trans. H. Soc. Lond.
(1976)
LG Roberts
Machine perception of three-dimensional solids

JF Canny

Finding edges and lines in images

MIT AI Lab Tech Report 720

(1983)

A Rosenfeld et al.

Edge and curve detection for visual scene analysis

IEEE Trans. Comput

(1971)

D Marr et al.

Directional selectivity and its use in early visual processing

WEL Grimson

A computer implementation of a theory of human stereo vision

Phil. Trans. R. Soc. Lond.

(1980)

WEL Crimson

From images to surfaces

(1981)

R Courant et al.

TO Binford

Inferring surfaces from images

Artif. Intell.

(1981)

AV Oppenheim et al.

Digital signal processing

(1975)

KA Stevens

Computation of locally parallel structure

Biol. Cybernetics

(1978)

Cited by (90)

Development of an unwanted-feature removal system for Structure from Motion of repetitive infrastructure piers using deep learning
2020, Advanced Engineering Informatics
Citation Excerpt :
One of the most useful applications of this deep learning is structural health inspections, which Spencer et al. [30] separated into the heuristic feature-based and deep learning-based studies. Heuristic feature-based methods rely on thresholds or classifiers, such as edge detection [31], region growing [32], histogram shape-based threshold [33], and wavelet-based algorithm [34], to generate the output. However, the automation level of these techniques is low because they require manual or semi-manual tuning for each specific problem [30].
Structure from Motion (SfM) is a photogrammetric technique that uses similar features between images to construct a point cloud or model. These outputs can be utilized for monitoring and inspection of civil infrastructure. However, feature matching is very delicate and prone to errors that can lead to the failure of the outputs. In our previous research, removal of unwanted features such as vegetation and boulders before processing raised the number of feature matches inside the region of interest (ROI). In theory, raising the number of feature matches should raise the quality of the SfM point cloud, but to date no quantitative evidence has been found to support this. Moreover, the removal of unwanted features must be performed manually during each inspection and is thus labor-intensive and time-consuming. To address these issues, in this study, a deep learning-based system was developed to assist the removal of unwanted features by using a deep convolutional neural network to segment and remove unwanted features from the input images before processing into an SfM application. The results showed that the removal of unwanted features increased the number of cloud points inside the ROI. The proposed system decreased the processing time by 75.33% and 85.85% compared with the manual process in the monorail pier and motorway pier samples, respectively, without complicating the image alignment. The proposed system could potentially support the monitoring and the inspection of infrastructure construction and maintenance projects, which have numerous similar components, by archiving more cloud points inside the ROI and lowering the burden from the manual removal of unwanted features.
Instantaneous robot self-localization and motion estimation with omnidirectional vision
2007, Robotics and Autonomous Systems
This paper presents two related methods for autonomous visual guidance of robots: localization by trilateration, and interframe motion estimation. Both methods use coaxial omnidirectional stereopsis (omnistereo), which returns the range $r$ to objects or guiding points detected in the images. The trilateration method achieves self-localization using $r$ from the three nearest objects at known positions.
The interframe motion estimation is more general, being able to use any features in an unknown environment. The guiding points are detected automatically on the basis of their perceptual significance and thus they need not have either special markings or be placed at known locations.
The interframe motion estimation does not require previous motion history, making it well suited for detecting acceleration (in 20th of a second) and thus supporting dynamic models of robot’s motion which will gain in importance when autonomous robots achieve useful speeds.
An initial estimate of the robot’s rotation $ω$ (the visual compass) is obtained from the angular optic flow in an omnidirectional image. A new noniterative optic flow method has been developed for this purpose. Adding $ω$ to all observed (robot relative) bearings $θ$ gives true bearings towards objects (relative to a fixed coordinate frame).
The rotation $ω$ and the $r, θ$ coordinates obtained at two frames for a single fixed point at unknown location are sufficient to estimate the translation of the robot. However, a large number of guiding points are typically detected and matched in most real images. Each such point provides a solution for the robot’s translation. The solutions are combined by a robust clustering algorithm Clumat that reduces rotation and translation errors.
Simulator experiments are included for all the presented methods. Real images obtained from ScitosG5 autonomously moving robot were used to test the interframe rotation and to show that the presented vision methods are applicable to real images in real robotics scenarios.
Efficient, recursively implemented differential operator, with application to edge detection
2006, Pattern Recognition Letters
The estimation of derivatives is an important and sensitive task in digital image processing and analysis, both accuracy and computational efficiency being expected of a differential operator. Here we propose a new filter—designed through a strategy based on the Green’s function of a signal matching equation—that responds to such demands. When used for edge detection, it yields theoretical performance indices that rival, and even top, the best reported marks. It is also computationally efficient, allowing very simple recursive implementation. The results of extensive edge-detection experimentation are reported here. Being explicitly designed as a first-derivative operator, our filter should also find application in other signal processing domains.
A catadioptric sensor with multiple viewpoints
2005, Robotics and Autonomous Systems
Citation Excerpt :
The polar edge finding approach entirely avoids the slow unwarping process. The unwarping is needed only for the convenience of human viewing, such as in Fig. 10, showing a traditional edge map of the unwarped image, using [30]. In this example, a naive coaxial stereopsis implementation would match edges with close to vertical image gradients along the vertical epipolar lines.
Conventional cameras with a limited field of view often lose sight of objects when their bearings change suddenly due to a significant turn of the observer (robot), the object, or both. Catadioptric omnidirectional sensors, consisting of a camera and a mirror, can track objects and estimate their distances more robustly.
The shapes of mirrors used by such sensors have differing merits. This paper discusses several advantages of the conical mirror over other shapes of mirrors in current use. A perspective projection unwarping of the conical mirror images is developed and demonstrated. This has hitherto been considered impossible for mirrors with multiple viewpoints.
An estimation of distance (range) over a large surrounding area is crucial in mobile robotics. A solution is proposed here in the form of an omnidirectional stereo apparatus with two catadioptric sensors in a vertical coaxial arrangement. The coaxial stereo requires very simple matching since the epipolar lines are the radial lines of identical orientations in both omnidirectional images. The radial matching is supported by a novel polar edge finder which uses discrete cosine transform and returns image gradients expressed in polar coordinates.
Geometric-photometric approach to monocular shape estimation
2003, Image and Vision Computing
Monocular, reflectance map-based shape estimation has traditionally relied exclusively on photometric data, but the recently introduced disparity-based photometric stereo (DBPS) and Green's function shape from shading (GSFS) have brought more geometry into it by incorporating a matching equation, and can appropriately be termed a geometric–photometric approach. In DBPS, the matching equation is used for obtaining disparities from the input image pair, while in GSFS it is used for generating the matching image, a uniform disparity field being considered. In both cases, depth can be recovered if one assumes the disparities to result from the displacement of the irradiance pattern over the imaged surface. Starting from the analysis of such displacement under perspective projection, we show that the original DBPS/GSFS formulation must be amended: reconstructions with no free parameters are no longer feasible, but we are able to propose an approximate procedure which yields higher quality estimates, up to a multiplicative factor.
Signal differentiation through a Green's function approach
2002, Pattern Recognition Letters

View all citing articles on Scopus

^☆: This paper was presented at the Alvey Computer Vision and Image Interpretation meeting held at the University of Sussex, Brighton, UK, on 15–18 September 1985

View full text

Edge detection and motion detection☆

Abstract

Perception

Visual information processing: the structure and creation of visual representations

Phil. Trans. R. Soc. Lond.

Vision

Theory of edge detection

Digital image processing

On boundary detection

MIT AI Lab Memo 183

Early processing of visual information

Phil. Trans. H. Soc. Lond.

Machine perception of three-dimensional solids

Finding edges and lines in images

MIT AI Lab Tech Report 720

Edge and curve detection for visual scene analysis

IEEE Trans. Comput

Directional selectivity and its use in early visual processing

A computer implementation of a theory of human stereo vision

Phil. Trans. R. Soc. Lond.

From images to surfaces

Inferring surfaces from images

Artif. Intell.

Digital signal processing

Computation of locally parallel structure

Biol. Cybernetics