Detecting 3-D parallel lines for perceptual organization

Lebegue, X.; Aggarwal, J. K.

doi:10.1007/3-540-55426-2_80

Cited by 8 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, the odometer heading reading is periodically corrected by an algorithm that computes the heading from the vanishing points of the lines extracted in three significant 3-D orientations from an image. Vanishing points have been used for camera calibration [16] and methods to extract vanishing points from indoor and outdoor scenes have been presented in [17] and [18]. Line segments in three prominent 3-D orientations (one vertical and two horizontal orientations perpendicular to each other), are extracted from an image using a fast line detector [17].…”

Section: B Robot Orientationmentioning

confidence: 99%

“…Vanishing points have been used for camera calibration [16] and methods to extract vanishing points from indoor and outdoor scenes have been presented in [17] and [18]. Line segments in three prominent 3-D orientations (one vertical and two horizontal orientations perpendicular to each other), are extracted from an image using a fast line detector [17]. The line detector uses the a priori knowledge of the location of the vanishing points to extract line segments.…”

Section: B Robot Orientationmentioning

confidence: 99%

“…1, is the distance of the world point from the image plane, is the radial coordinate of the world point on the image plane and is the angular coordinate of the world point in the image plane. The partial derivatives of with respect to are (17)…”

Section: A Obtaining the Time To Impactmentioning

confidence: 99%

See 2 more Smart Citations

Moving obstacle detection from a navigating robot

Nair

Aggarwal

1998

IEEE Trans. Robot. Automat.

View full text Add to dashboard Cite

This paper presents a system that detects unexpected moving obstacles that appear in the path of a navigating robot, and estimates the relative motion of the object with respect to the robot. The system is designed for a robot navigating in a structured environment with a single wide-angle camera. The objective of the system is to detect moving obstacles in order to gradually stop the robot to avoid collision; maneuvering around the obstacle is not considered here. The system has been assembled using pieces of existing vision techniques with a strong emphasis on real-world applications and very fast processing with conventional hardware. The system uses polar mapping to simplify the segmentation of the moving object from the background. The polar mapping is performed with the focus of expansion (FOE) as the center. A vision-based algorithm that uses the vanishing points of segments extracted from a scene in a few threedimensional (3-D) orientations provides an accurate estimate of the robot orientation. This is used to maintain the motion of the robot along a purely translational path and also used to subtract the effects of any drifts from this path from each image acquired by robot. By doing so, the determination of the FOE is simplified. In the transformed space qualitative estimate of moving obstacles is obtained by detecting the vertical motion of edges extracted in a few specified directions. Relative motion information about the obstacle is then obtained by computing the time to impact between the obstacles and robot from the radial component of the optical flow. The system was implemented and tested on an indoor mobile robot at our laboratory. Results from the robot navigating in real environments are presented and analyzed here. The system is able to detect moving obstacles at 100 ms/frame and can be used as a cueing mechanism for moving obstacles.

show abstract

Section: B Robot Orientationmentioning

confidence: 99%

Section: B Robot Orientationmentioning

confidence: 99%

See 1 more Smart Citation

Moving obstacle detection from a navigating robot

Nair

Aggarwal

1998

IEEE Trans. Robot. Automat.

View full text Add to dashboard Cite

show abstract

“…Since, on earth, there exists a constant homogeneous gravity field always and everywhere present, defining an absolute 3D-directioq and since this 3D-direction can be measured either from inertial sensors [ll], or by the determination of vertical lines in a image (see [6,81 for instance).…”

Section: Specificity Of the Approachmentioning

confidence: 99%

Computation of ego-motion and structure from visual and inertial sensors using the vertical cue

Viéville

Clergue

Facao

1993 (4th) International Conference on Computer Vision

View full text Add to dashboard Cite

This paper describes the development and implementation of some layers of a line-segment based module t o recover ego-motion whale building a 30 map of the environment in which the absolute vertical is taken into account.Given a monocular sequence of images and 20-line-segments in this sequence, the goal is to reduce the disparity between two frames in such a way that 3D vision is samplified, while an initial value for the SD rotation is provided.Using the vertical as a basic cue f o r 3D-orientation tremendously simplifies and enrichs the structure from motion paradigm, but the usual equations have to be worked out in a different way.

show abstract

“…Στο διάστημα αυτό έχουν αναπτυχθεί πολλές διαφορετικές τεχνικές γιά την αυ τόματη ανίχνευση ορίων (γιά μιά γενική παρουσίαση των σχετικών μεθόδων βλέπε πχ. da Silva, 1990' Kasturi and Jain, 1991' Russ, 1994 (Fritsch and Strunz, 1988• Lemmens and Han, 1988" Lebègue and Aggarwal, 1992. Στην κατηγορία αυτή, η μέθοδος των Burns et al (1986) είναι ιδιαίτερα προσανατολισμένη στην εξαγωγή ευθύγραμμων ορίων, ενώ οι Liu and (Witkin, 1983• Stefanidis and Schenk, 1992" Beil, 1994" Boulanger, 1994• El-Fallah and Ford, 1994-Lindeberg, 1994" Pauwels et al, 1995.…”

Section: τεχνικές αυτόματης εξαγωγής ορίων και ευθειώνunclassified

Φωτογραμμετρία Με Ευθείες: Ανάπτυξη Διερεύνηση Και Έλεγχος Φωτογραμμετρικών Αλγορίθμων Με Ευθείες Για Τις Σύγχρονες Ψηφιακές Εφαρμογές

Πέτσα¹

View full text Add to dashboard Cite

3.3.3 Αριθμός λύσεων από οριακές διατάξεις τριών ευθειών 80 3.3.4 Ελάχιστες απαιτήσεις γιά μοναδική λύση 3.3.4.1 Σημείο λήψης 3.3.4.2 Πίνακας στροφής 3.3.4.3 Πίνακας στροφής και σταθερά της μηχανής 3.3.4.4 Πίνακας στροφής και εσωτερικός προσανατολισμός 3.3.4.5 Ενιαία διαδικασία οπισθοτομίας 3.3.4.6 Ενιαία διαδικασία οπισθοτομίας και βαθμονόμησης 3.3.4.7 Η πρακτική σημασία της μοναδικής λύσης 3.4 Αλγόριθμοι 3.4.1 Ενιαίος αλγόριθμος 3.4.2 Χωριστοί αλγόριθμοι 3.5 Αποτελέσματα από προσομοιώσεις Παράρτημα Κεφαλαίου 3 Κεφάλαιο 4 Εμπροσθοτομία Ευθειών 4.1 Γενικά 98 4.2 Το μαθηματικό μοντέλο 99 4.2.1 Βασικές εξισώσεις 4.2.2 Η κρίσιμη γεωμετρία της εμπροσθοτομίας ευθειών 102 4.2.2.1 Απροσδιοριστία της εμπροσθοτομίας 102 4.2.2.2 Η γωνία τομής των ομόλογων επιπέδων 103 4.2.3 Η ενίσχυση της λύσης με γεωμετρικές δεσμεύσεις 105 4.3 Αλγόριθμοι 105 4.3.1 Εμπροσθοτομία ευθειών με δύο εικόνες 106 4.3.2 Εμπροσθοτομία ευθειών με περισσότερες εικόνες 106 4.3.3 Εμπροσθοτομία προσομοιωμένων ευθειών 107 4.4 Η αβεβαιότητα αναπλασμένης ευθείας του χώρου 110 4.4.1 Η έννοια του σφάλματος ευθείας 110 4.4.1.1 Η έλλειψη σφάλματος σημείου της ευθείας 110 4.4.1.2 Το μέτρο του σφάλματος ευθείας 112 4.4.2 Η ισοπιθανοτική επιφάνεια σφάλματος ευθείας 113 viii 4.4.3 Το μέτρο του σφάλματος ευθύγραμμου τμήματος

show abstract

Detecting 3-D parallel lines for perceptual organization

Cited by 8 publications

References 4 publications

Moving obstacle detection from a navigating robot

Moving obstacle detection from a navigating robot

Computation of ego-motion and structure from visual and inertial sensors using the vertical cue

Φωτογραμμετρία Με Ευθείες: Ανάπτυξη Διερεύνηση Και Έλεγχος Φωτογραμμετρικών Αλγορίθμων Με Ευθείες Για Τις Σύγχρονες Ψηφιακές Εφαρμογές

Contact Info

Product

Resources

About