JUDOCA: JUnction Detection Operator Based on Circumferential Anchors

Abstract

In this paper, we propose an edge-based junction detector. In addition to detecting the locations of junctions, this operator specifies their orientations as well. In this respect, a junction is defined as a meeting point of two or more ridges in the gradient domain into which an image can be transformed through Gaussian derivative filters. To accelerate the detection process, two binary edge maps are produced; a thick-edge map is obtained by imposing a threshold on the gradient magnitude image, and another thin-edge map is obtained by calculating the local maxima. Circular masks are centered at putative junctions in the thick-edge map, and the so-called circumferential anchors or CA points are detected in the thin map. Radial lines are scanned to determine the presence of junctions. Comparisons are made with other well-known detectors. This paper proposes a new formula for measuring the detection accuracy. In addition, the so-called junction coordinate systems are introduced. Our operator has been successfully used to solve many problems such as wide-baseline matching, 3-D reconstruction, camera parameter enhancing, and indoor and obstacle localization.

An approach-path independent framework for place recognition and mobile robot localization in interior hallways

“…With regard to approach-path independence, we show that our 3D junction features based on the JUDOCA junctions [8] extracted from the images possess far greater invariance than several other popular interest points such as SIFT and SURF. (We refer to these features as 3D-JUDOCA for obvious reasons.)…”

“…The algorithm for extracting 2D JUDOCA junction features is described in [8] and [5]. Basically, a 2D JUDOCA junction feature is defined by a triangle corresponding to the vertex where two edge fragments meet.…”

“…This descriptor consists of the following: (i) the 2D/3D locations of the junction and the associated anchors (q 1 , q 2 ); (ii) the orientations (θ 1 , θ 2 ), the strengths (s 1 , s 2 ) of the edges forming the junction, and the center of the junction in a local coordinate frame in relation to the junction vertex [8]; (iii) the width and the height of the minimum bounding rectangle for the junction, as shown in Fig. 2(a); (iv) the average color of the triangle formed at the junction; (v) pointers to the neighboring 3D-JUDOCA features; and (vi) the normal vector to the plane confined to the 3D-JUDOCA feature triangle.…”

Contour-Based Corner Detection and Classification by Using Mean Projection Transform

“…These methods can be divided into three main categories: intensity-based detectors [13–17], model-based detectors [18,19], and contour-based detectors [1,4,20–25]. Each category has its own competencies for different types of areas and images.…”

“…Thus, ANDD is insufficient for detecting corners with both a high detection rate and repeatability with an acceptable L e . Elias and Laganiere [25] proposed a method named JUDOCA, which defined the junctions as a meeting point of two or more ridges in the gradient domain. The region of a circle mask to measure the cornerness is used after edge detection and Gaussian filtering to detect the corners.…”