Improved Object Recognition – The RoboCup 4-Legged League

Estivill‐Castro, Vladimir; Lovell, Nathan

doi:10.1007/978-3-540-45080-1_163

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the teams do not deal with the problem of multiple blobs and multiple robots in a same image, explicitly or implicitly assuming a one-to-one correspondence between blobs and robots [3,13].…”

Section: A Case Studymentioning

confidence: 99%

“…Other common approaches for deformable object recognition are: graph-based representation of the silhouette's skeleton [3,6] or Point Distribution Models (PDMs) approaches [1]. Both methods rely on the extraction of the object's silhouette for the analyzed image and, thus, either are sensitive to partial occlusions or need a manual initialization.…”

Section: Introductionmentioning

confidence: 99%

“…), posture recognition (e.g., in smart rooms), gesture recognition [11] and human motion estimation [9] (e.g., for human-computer interaction or medical purposes), etc.. Other interesting articulated and/or deformable objects are the human face in its different expressions, biological individuals [4] or articulated artifacts (e.g., robots [3,13] or utensils [5]). …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Articulated Object Recognition: A General Framework and a Case Study

Cinque

Sangineto

Tanimoto

2006

2006 IEEE International Conference on Video and Signal Based Surveillance

View full text Add to dashboard Cite

We present in this paper a general-purpose approach for articulated object recognition. We split the recognition process in two distinct phases. In the former we use standard model-based techniques in order to recognize and localize in the input image the rigid components the articulated object is composed of. In the second phase the spatial configurations formed by the recognized components are analyzed and compared with the valid configurations of the object we are searching. The comparison is based on a constraint satisfaction method which can deal with both missing components and false positives. The proposed method is based on a redundant set of constraints which represent the valid spatial configurations of the object's components. Such constraints are not embedded in the system nor are domain-specific but they are learned during a suitable training phase.We show how this approach can be used in different scenarios with different kinds of articulated objects and we present a case study concerning a robotic application.

show abstract

Section: A Case Studymentioning

confidence: 99%