Centre de documentation
scientifique

Real-time object detection with sub-pixel accuracy using the level set method / F. Burkert in Photogrammetric record, vol 26 n° 134 (June - August 2011)  

Public [article]  inPhotogrammetric record > vol 26 n° 134 (June - August 2011) . - pp 154 - 170 Titre : Real-time object detection with sub-pixel accuracy using the level set method Type de document : Article/Communication Auteurs : F. Burkert, Auteur ; Matthias Butenuth, Auteur ; M. Ulrich, Auteur Année de publication : 2011 Article en page(s) : pp 154 - 170 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] classification à base de connaissances [Termes IGN] détection d'objet [Termes IGN] détection de contours [Termes IGN] niveau de gris (image) [Termes IGN] précision infrapixellaire [Termes IGN] reconnaissance d'objets [Termes IGN] temps réel Résumé : (Auteur) This paper presents a method for object detection with sub-pixel accuracy in digital images satisfying real-time applications. The method uses an approximation of the level-set-based contour evolution, which applies only integer operations in a fast two-cycle algorithm to achieve real-time performance. Level-set-based contour evolution forms a part of the geometric active contour process, which combines image data and a priori geometric knowledge of an object to be evolved over an image towards the object border. The algorithm avoids the solution of partial differential equations. Instead only integer operations are applied and the contour evolution is performed by using a two-cycle algorithm. The proposed method for object detection with sub-pixel accuracy refines the pixel-accurate result of the level-set-based contour evolution algorithm by using a fast parabolic fitting mechanism. Sub-pixel accuracy of the resulting object contours is achieved by adjusting every contour point towards the nearby maximum of the image gradient. Real-time performance can be provided because the adjustment is performed only once after the contour evolution. Experimental results with images from industry, photogrammetry, remote sensing and medicine show the functionality and applicability of this method to several fields of work. In addition, the experiments are evaluated by applying quality measures for the geometric accuracy and the run time. Numéro de notice : A2011-238 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1111/j.1477-9730.2011.00633.x Date de publication en ligne : 06/06/2011 En ligne : https://doi.org/10.1111/j.1477-9730.2011.00633.x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31016 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
106-2011021	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Hierarchical real-time recognition of compound objects in images / M. Ulrich (2003)

Public Titre : Hierarchical real-time recognition of compound objects in images Type de document : Thèse/HDR Auteurs : M. Ulrich, Auteur Editeur : Munich : Bayerische Akademie der Wissenschaften Année de publication : 2003 Collection : DGK - C Sous-collection : Dissertationen num. 568 Importance : 142 p. Format : 21 x 30 cm ISBN/ISSN/EAN : 978-3-7696-5007-5 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] approche hiérarchique [Termes IGN] méthode robuste [Termes IGN] objet géographique [Termes IGN] reconnaissance de formes [Termes IGN] temps réel [Termes IGN] transformation de Hough Index. décimale : 35.20 Traitement d'image Résumé : (Auteur) This dissertation proposes a novel approach for the recognition of compound 2D objects [objets composés en 2 dimensions] in images under real-time conditions. A compound object consists of a number of rigid object parts that show arbitrary relative movements. The underlying principle of the approach is based on minimizing the overall search effort, and hence the computation time. This is achieved by restricting the search according to the relative movements of the object parts. Minimizing the search effort leads to the use of a hierarchical model : only a selected root object part, which stands at the top of the hierarchy, is searched within the entire search space. In contrast, the remaining parts are searched recursively with respect to each other within very restricted search spaces. By using the hierarchical model, prior knowledge about the spatial relations, i.e., relative movements, between the object parts is exploited already in an early stage of the recognition. Thus, the computation time can be reduced considerably. Another important advantage of the hierarchical model is that it provides an inherent determination of correspondence, i.e.. because of the restricted search spaces, ambiguous matches are avoided. Consequently, a complicated and computationally expensive solution of the correspondence problem is not necessary. The approach shows additional remarkable features : it is general with regard to the type of object, it shows a very high robustness, and the compound object is localized with high accuracy. Furthermore, several instances of the object in the image can he found simultaneously. One substantial concern of this dissertation is to achieve a high degree of automation. Therefore, a method that automatically trains and creates the hierarchical model is proposed. For this, several example images that show the relative movements of the object parts are analyzed. The analysis automatically determines the rigid object parts as well as the spatial relations between the parts. This is very comfortable for the user because a complicated manual description of the compound object is avoided. The obtained hierarchical model is used to recognize the compound object in real-time. The proposed strategy for recognizing compound objects requires an appropriate approach for recognizing rigid objects. Therefore, the performance of the generalized Hough transform, which is a voting scheme to recognize rigid objects, is further improved by applying several novel modifications. The performance of the new approach is evaluated thoroughly by comparing it to several other rigid object recognition methods. The evaluation shows that the proposed modified generalized Hough transform fulfills even stringent industrial demands. As a by-product, a novel method for rectifying images in real-time is developed. The rectification is based on the result of a preceding camera calibration. Thus, a very fast elimination of projective distortions and radial lens distortions from images becomes possible. This is exploited to extend the object recognition approach in order to be able to recognize objects in real-time even in projectively distorted images. Numéro de notice : 13193 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=54908

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
13193-02	35.20	Livre	Centre de documentation	Télédétection	Disponible
13193-01	35.20	Livre	Centre de documentation	Télédétection	Disponible