Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben
Pattern Analysis and Applications
Erschienen in: Pattern Analysis and Applications 1/2007

01.02.2007 | Theoretical Advances

Quadtree-based eigendecomposition for pose estimation in the presence of occlusion and background clutter

verfasst von: Chu-Yin Chang, Anthony A. Maciejewski, Venkataramanan Balakrishnan, Rodney G. Roberts, Kishor Saitwal

Erschienen in: Pattern Analysis and Applications | Ausgabe 1/2007

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Eigendecomposition-based techniques are popular for a number of computer vision problems, e.g., object and pose estimation, because they are purely appearance based and they require few on-line computations. Unfortunately, they also typically require an unobstructed view of the object whose pose is being detected. The presence of occlusion and background clutter precludes the use of the normalizations that are typically applied and significantly alters the appearance of the object under detection. This work presents an algorithm that is based on applying eigendecomposition to a quadtree representation of the image dataset used to describe the appearance of an object. This allows decisions concerning the pose of an object to be based on only those portions of the image in which the algorithm has determined that the object is not occluded. The accuracy and computational efficiency of the proposed approach is evaluated on 16 different objects with up to 50% of the object being occluded and on images of ships in a dockyard.
Vorheriger Artikel Breadth-first search strategies for trie-based syntactic pattern recognition
Nächster Artikel A writer identification and verification system using HMM based recognizers

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren
Fußnoten
1
For purely appearance-based techniques, no modeling is required and thus no feature extraction/selection needs to be performed. Hence these techniques can be applied to any class of objects and can be effectively used in a wide variety of applications [23].
 
2
Note that when the actual object location is not of rank one, the rank one candidate is frequently far from the correct location (due to occlusion) so that local optimization techniques such as gradient descent [32] are not effective.
 
3
Specifically, the image data matrices corresponding to the training sub-images, whose rank is below 12, are automatically discarded.
 
4
Empirical results showed that using a constant subspace dimension at every sub-image performs consistently better than using a constant energy recovery ratio. The main reason behind this is that a constant subspace dimension tends to make the energy recovery ratio increase as the algorithm searches further down the quadtree.
 
5
The generation of the occluded test images in this manner can induce artifacts, like large step edges along the boundaries, however, our results indicate that these artifacts do not affect the performance of the algorithm.
 
6
We elected not to use one of the “standard” object data sets, like COIL-100 [49], COIL-10 [50], SOIL-47 [51], and ALOI [52], because they only contain 72 orientations per object.
 
7
A video sequence of ship images with resolution of 720 × 1,280 pixels each was provided by the National Imagery and Mapping Agency.
 
8
The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory or the US Government.
 
Literatur
1.
Fukunaga K (1990) Introduction to Statistical Pattern Recognition, 2nd edn. Academic, LondonMATH
2.
Martinez AM, Kak AC (2001) PCA versus LDA. IEEE Trans PAMI 23(2):228–233
3.
Sirovich L, Kirby M (1987) Low-dimensional procedure for the characterization of human faces. J Opt Soc Am 4(3):519–524CrossRef
4.
Kirby M, Sirovich L (1990) Application of the Karhunen–Loeve procedure for the characterization of human faces. IEEE Trans PAMI 12(1):103–108
5.
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cogn Neurosci 3(1):71–86CrossRef
6.
Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Trans PAMI 19(7):711–720
7.
Brunelli R, Poggio T (1993) Face recognition: Features versus templates. IEEE Trans PAMI 15(10):1042–1052
8.
Pentland A, Moghaddam B, Starner T (1994) View-based and modular eigenspaces for face recognition. In: Proceedings of IEEE conference computer vision and pattern recognition. Seattle, WA, pp 84–91
9.
Yang MH, Kriegman DJ, Ahuja N (2002) Detecting faces in images: A survey. IEEE Trans PAMI 24(1):34–58
10.
Murase H, Sakai R (1996) Moving object recognition in eigenspace representation: Gait analysis and lip reading. Pattern Recogn Lett 17(2):155–162CrossRef
11.
Chiou G, Hwang J-N (1997) Lipreading from color video. IEEE Trans Image Process 6(8):1192–1195CrossRef
12.
Murase H, Nayar SK (1994) Illumination planning for object recognition using parametric eigenspaces. IEEE Trans PAMI 16(12):1219–1227
13.
Huang CY, Camps OI, Kanungo T (1997) Object recognition using appearance-based parts and relations. In: Proceedings of IEEE conference on computer vision and pattern recognition. San Juan, PR, USA, pp 877–883
14.
Campbell RJ, Flynn PJ (1999) Eigenshapes for 3D object recognition in range data. In: Proceedings of IEEE conference on computer vision and pattern recognition. Fort Collins, CO, USA, pp 505–510
15.
Jogan M, Leonardis A (2000) Robust localization using eigenspace of spinning-images. In: Proceedings of IEEE workshop omnidirectional vision. Hilton Head Island, South Carolina, USA, pp 37–44
16.
Borgefors G (1988) Hierarchical chamfer matching: A parametric edge matching algorithm. IEEE Trans PAMI 10(6):849–865
17.
Yoshimura S, Kanade T (1994) Fast template matching based on the normalized correlation by using multiresolution eigenimages. In: 1994 IEEE workshop motion of non-rigid and articulated objects, Austin, Texas, pp 83–88
18.
Winkeler J, Manjunath BS, Chandrasekaran S (1999) Subset selection for active object recognition. In: Proceedings of IEEE conference computer vision and pattern recognition. Fort Collins, Colorado, USA, pp 511–516
19.
Martinez AM, Vitria J (2001) Clustering in image space for place recognition and visual annotations for human–robot interaction. IEEE Trans Syst Man Cybern 31(5):669–682CrossRef
20.
Crowley JL, Pourraz F (2001) Continuity properties of the appearance manifold for mobile robot position estimation. Image Vis Comput 19(11):741–752CrossRef
21.
Nayar SK, Murase H, Nene SA (1994) Learning, positioning, and tracking visual appearance. In: Proceedings of IEEE international conference on robotics and automation, San Diego, CA, USA, pp 3237–3246
22.
Black MJ, Jepson AD (1998) Eigentracking: robust matching and tracking of articulated objects using a view-based representation. Int J Comput Vis 26(1):63–84CrossRef
23.
Murase H, Nayar SK (1995) Visual learning and recognition of 3-D objects from appearance. Int J Comput Vis 14(1):5–24CrossRef
24.
Murase H, Nayar SK (1997) Detection of 3D objects in cluttered scenes using hierarchical eigenspace. Pattern Recogn Lett 18(4):375–384CrossRef
25.
Nayar SK, Nene SA, Murase H (1996) Subspace method for robot vision. IEEE Trans Rob Autom 12(5):750–758CrossRef
26.
Moghaddam B, Pentland A (1997) Probabilistic visual learning for object representation. IEEE Trans PAMI 19(7):696–710
27.
Chang C-Y, Maciejewski AA, Balakrishnan V (2000) Fast eigenspace decomposition of correlated images. IEEE Trans Image Process 9(11):1937–1949CrossRefMathSciNetMATH
28.
Martinez AM (2002) Recongnizing imprecisely localized, partially occluded, and expression varient faces from a single sample per class. IEEE Trans PAMI 24(6):748–763
29.
Nayar SK, Murase H (1995) Image spotting of 3D objects using parametric eigenspace representation. In: Proceedings of 9th Scandinavian conference on image analysis, pp 325–332
30.
Edward J, Murase H (1997) Appearance matching of occluded objects using coarse-to-fine adaptive masks. In: Proceedings of IEEE conference on computer vision and pattern recognition, Los Alamitos, CA, USA, pp 533–539
31.
Rao RPN (1997) Dynamic appearance-based recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition, San Juan, PR, USA, pp 540–546
32.
Krumm J (1996) Eigenfeatures for planar pose measurement of partially occluded objects. In: Proceedings of IEEE conference on computer vision and pattern recognition, Los Alamitos, CA, USA, pp 55–60
33.
Ohba K, Ikeuchi K (1997) Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects. IEEE Trans PAMI 19(9):1043–1048
34.
Leonardis A, Bischof H (2000) Robust recognition using eigenimages. Comput Vis Image Understand 78(1):99–118CrossRef
35.
Huttenlocher DP, Lilien RH, Olson CF (1999) View-based recognition using an eigenspace approximation to the Hausdorff measure. IEEE Trans PAMI 21(9):951–955
36.
Wang Z, Ben-arie J (2001) Detection and segmentation of generic shapes based on affine modeling of energy in eigenspace. IEEE Trans Image Process 10(11):1621–1629CrossRefMATH
37.
Bischof H, Leonardis A (1998) Robust recognition of scaled eigenimages through a hierarchical approach. In: Proceedings of IEEE conference on computer vision and pattern recognition, Santa Barbara, CA, USA, pp 664–670
38.
Schneiderman H, Kanade T (2000) A histogram-based method for detection of faces and cars. In: Proceedings of IEEE international conference on image processing, Vancouver, BC, pp 504–507
39.
Mohan A, Papageorgiou C, Poggio T (2001) Example-based object detection in images by components. IEEE Trans PAMI 23(4):349–361
40.
Stauffer C, Grimson E (2001) Similarity templates for detection and recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition, Kauai, HI, pp I221–I228
41.
Lee DD, Seung HS (1999) Learning the parts of objects by non-negative matrix factorization. Lett Nat 401(6755):788–791CrossRef
42.
Guillamet D, Vitria J (2003) Evaluation of distance metrics for recognition based on non-negative matrix factorization. Pattern Recogn Lett 24(9–10):1599–1605CrossRefMATH
43.
Li SZ, Hou XW, Zhang HJ, Cheng QS (2001) Learning spatially localized, parts-based representation. In: Proceedings of IEEE conference computer vision and pattern recognition, Kauai, HI, pp I207–I212
44.
Jugessur D, Dubek G (2000) Local appearance for robust object recognition. In: Proceedings of IEEE conference on computer vision and pattern recognition, Hilton Head Island, SC, USA, pp 834–839
45.
Nene SA, Nayar SK (1997) A simple algorithm for nearest neighbor search in high dimensions. IEEE Trans PAMI 19(9):989–1003
46.
Kakarala R, Ogunbona PO (2001) Signal analysis using a multiresolution form of the singular value decomposition. IEEE Trans Image Process 10(5):724–735CrossRefMathSciNetMATH
47.
Uenohara M, Kanade T (1997) Use of Fourier and Karhunen–Loeve decomposition for fast pattern matching with a large set of templates. IEEE Trans PAMI 19(8):891–898
48.
Ohba K, Ikeuchi K (1996) Recognition of the multi specularity objects for bin-picking task. In: Proceedings of IEEE international conference on intelligent robots and systems, Osaka, Japan, pp 1440–1447
49.
50.
51.
Koubaroulis D, Matas J, Kittler J (2002) Evaluating colour-based object recognition algorithms using the SOIL-47 database. In: Proceedings of Asian conference on computer vision, Melbourne, Australia, pp 840–845
52.
Geusebroek JM, Burghouts GJ, Smeulders AWM (2004) The Amsterdam library of object images. Int J Comput Vis 61(1):103–112CrossRef
53.
Chang C-Y (1999) Eigenspace methods for correlated images. PhD Dissertation, Purdue University, USA
Metadaten
Titel
Quadtree-based eigendecomposition for pose estimation in the presence of occlusion and background clutter
verfasst von
Chu-Yin Chang
Anthony A. Maciejewski
Venkataramanan Balakrishnan
Rodney G. Roberts
Kishor Saitwal
Publikationsdatum
01.02.2007
Verlag
Springer-Verlag
Erschienen in
Pattern Analysis and Applications / Ausgabe 1/2007
Print ISSN: 1433-7541
Elektronische ISSN: 1433-755X
DOI
https://doi.org/10.1007/s10044-006-0046-6

Weitere Artikel der Ausgabe 1/2007

Pattern Analysis and Applications 1/2007 Zur Ausgabe

Theoretical Advances

A writer identification and verification system using HMM based recognizers

Theoretical Advances

Breadth-first search strategies for trie-based syntactic pattern recognition

Theoretical Advances

Using string matching to detect video transitions

Theoretical Advances

Pairwise feature evaluation for constructing reduced representations

Premium Partner

    Bildnachweise