A fast and effective ellipse detector for embedded vision applications

Fornaciari, Michele; Prati, Andrea; Cucchiara, Rita

doi:10.1016/j.patcog.2014.05.012

Cited by 146 publications

(150 citation statements)

References 38 publications

Supporting

Mentioning

149

Contrasting

Order By: Relevance

“…In order to show the performance of the proposed method, we compare it against three state-of-the-art ellipse detection methods in terms of precision, recall, F-measure, reliability, and runtime. The state-of-the-art methods considered here are the methods proposed by Libuda et al [23] , Fornaciari et al [1] , and Prasad et al [8] . All these methods belong to the class of edge following techniques and have been shown to possess good detection abilities.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…And then we find a rotated rectangle of the minimum area enclosing e i and denote it as R edge . If the shortest side of R edge is less than Th edge which is usually selected as 3 suggested in [1] , we discard e i since it may be a straight line. Next we fit a least square ellipse to e i and compute the fitting error which is defined as the average value of the geometrical distance from edge points to the fitted ellipse.…”

Section: Extraction Of Candidate Elliptic Arcsmentioning

confidence: 99%

“…In order to determine which candidate elliptic arc can be grouped with seed arc, we need to study the associated convexity e e1 1 of a pair of edge contours. Prasad shows five scenarios of the associated convexity between two edge contours in [8] , which can be seen in Fig.…”

Section: Finding the Associated Edge Contours Of Each Seed Arc Withinmentioning

confidence: 99%

“…Thus, we need to exclude the clutter arcs and get the correct ellipse from remaining arcs. In order to achieve that, we let r i ( i is ranging from 1 to n − 1 ) be the set which elements are groups of arcs gotten by excluding i arcs from S e , such as r 1 above are all satisfied. If ˆ r 1 is not empty, we select the ellipse corresponding to the member which have the maximum number of edge pixels in ˆ r 1 as the hypothetical ellipse, otherwise the same process on r i ( i = 2 to n − 1 ) is repeated till either the above criteria are satisfied or i is greater than n − 1 .…”

Section: Generating Hypothetical Ellipsesmentioning

confidence: 99%

“…Ellipse detection is the starting point for many computer vision applications since the ellipse is one of the most commonly occurring geometric shapes [1,2] . For instance, ellipse detection can be used in surface inspection problems, camera calibration [3] , object segmentation [4] , eye gaze estimation [5] , road sign detection and classification [6] , and so on.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A hybrid method for ellipse detection in industrial images

Chen

Xia

Zhao

et al. 2017

Pattern Recognition

View full text Add to dashboard Cite

Section: Experiments Resultsmentioning

confidence: 99%

Section: Extraction Of Candidate Elliptic Arcsmentioning

confidence: 99%

Section: Finding the Associated Edge Contours Of Each Seed Arc Withinmentioning

confidence: 99%

Section: Generating Hypothetical Ellipsesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A hybrid method for ellipse detection in industrial images

Chen

Xia

Zhao

et al. 2017

Pattern Recognition

View full text Add to dashboard Cite

Ellipse proposal and convolutional neural network discriminant for autonomous landing marker detection

Ren

Owais

Lin

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

Autonomous landing in complex environments is a critical problem for unmanned aerial vehicle autonomous control, and efficiently detecting landing identification mark in real‐world scenario is still challenging. Due to the limited computational power of airborne computing equipment, current target detection algorithms cannot meet the demand efficiently. In this paper, we proposed a new landing marker detection algorithm for autonomous landing systems in a real environment. We used an ellipse detection algorithm to detect the ellipse landmark or other elliptical objects. Furthermore, convolution neural networks were utilized to obtain the correct landmarks, which is robust, fast and can achieve a speed of 25 fps with 720p resolution video on an Intel NUC onboard computer. Unlike the other methods, the accuracy and speed of our algorithm is verified in a real‐time application with more harsh conditions. During system testing, the flight system can detect the object above 20 m, track it, and automatically land on it with this vision algorithm. The algorithm has helped us achieve the first position at Mohamed Bin Zayed International Robotics Challenge in Abu Dhabi this year.

show abstract

Fast vision‐based autonomous detection of moving cooperative target for unmanned aerial vehicle landing

Cai

Zhou

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

We propose a fast and effective method, fast target detection (FTD), to detect the moving cooperative target for the unmanned aerial vehicle landing, and the target is composed of double circles and a cross. The purpose of our strategy is to land on the target. The FTD method needs to detect the target at the high and low heights. At the high height, the target appears completely and stably in the camera field. The FTD method can detect the circle and cross to rapidly reach the target center, named cross and circle–FTD ( C 2 − F T D). To detect the cross, we propose a slope distance equation to obtain the distance between two slopes. The proposed slopes cluster method, based on the distance equation and K‐means, is used to determine the cross center. At the low height, the target appears incompletely and unstably. Therefore, FTD methods detect only the cross, named cross–FTD ( C 1 − F T D). We extract the cross features ( CFs) based on line segments. Then, four CFs are combined based on graph theory. Experiments on our four datasets show that FTD has rapid speed and good performance. (Our method is implemented in C++ and is available at https://github.com/Li-Zhaoxi/UAV-Vision-Servo.) On the Mohamed Bin Zayed International Robotics Challenge datasets made we constructed, C 2 − F T D detects the target from a 960 × 540 image approximately 20 ⁢ normalm normals per pipeline with 82.24 % F‐measure and tracks target approximately 6.27 ⁢ normalm normals per pipeline with 94.39 % F‐measure. C 1 − F T D detects centers from a 480 × 270 image at approximately 4.69 ⁢ normalm normals per image with 86.05 % F‐measure.

show abstract

A fast and effective ellipse detector for embedded vision applications

Cited by 146 publications

References 38 publications

A hybrid method for ellipse detection in industrial images

A hybrid method for ellipse detection in industrial images

Ellipse proposal and convolutional neural network discriminant for autonomous landing marker detection

Fast vision‐based autonomous detection of moving cooperative target for unmanned aerial vehicle landing

Contact Info

Product

Resources

About