MESSRS: A model-based 3D system for of recognition, semantic annotation and calculating the spatial relationships of a factory's digital facilities

Abstract Obtaining a detailed, orderly and valued relationship of elements belonging to a factory, that is, making an inventory, can be a complex task; this is because it is necessary to consider both general aspects, such as the characteristics of the factory and specific aspects such as elements to be inventoried. Automatic recognition, semantic rules and calculation of spatial relationships can help in the description of elements in digital mockups. The traditional geometric primitives recognition algorithms can recognize primitives, but the real elements can be large and complex because they are composed of several geometric primitives. Therefore, it is necessary to improve the traditional approach by incorporating semantics in order to identify and characterize recognized geometric primitives, along with rules for composing real objects. With this in mind, this paper presents MESSRS, a novel and conceptual model for semantic representation of digital mockups. MESSRS applies 3D recognition techniques, topology mechanisms and semantic rules to identify and tag elements of a factory in order to make a complete inventory. The proposed model serves as a basis for the exchange of logical, physical and semantic information obtained from real objects in a factory. In addition, an evaluation of a real use case of this model is also presented as proof of the concept.

[1]  Marco Attene,et al.  Hierarchical Structure Recovery of Point‐Sampled Surfaces , 2010, Comput. Graph. Forum.

[2]  Christophe Cruz,et al.  Knowledge Base Approach for 3D Objects Detection in Point Clouds Using 3D Processing and Specialists Knowledge , 2013, ArXiv.

[3]  François Pachet,et al.  Automatic X Traditional Descriptor Extraction: the Case of Chord Recognition , 2005, ISMIR.

[4]  Guillaume Damiand,et al.  Split-and-merge algorithms defined on topological maps for 3D image segmentation , 2003, Graph. Model..

[5]  Ron Meir,et al.  Semantic-oriented 3d shape retrieval using relevance feedback , 2005, The Visual Computer.

[6]  Kerstin Fischer,et al.  Spatial Knowledge Representation for Human-Robot Interaction , 2003, Spatial Cognition.

[7]  S. Levinson.  Frames of reference and Molyneux's question: Cross-linguistic evidence , 1996 .

[8]  James H. Cross,et al.  Reverse engineering and design recovery: a taxonomy , 1990, IEEE Software.

[9]  Nanning Zheng,et al.  IAIR-CarPed: A psychophysically annotated dataset with fine-grained and layered semantic labels for object recognition , 2012, Pattern Recognit. Lett..

[10]  Nico Blodow,et al.  Close-range scene segmentation and reconstruction of 3D point cloud maps for mobile manipulation in domestic environments , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Sisi Zlatanova,et al.  Topological models and frameworks for 3D spatial objects , 2004, Comput. Geosci..

[12]  Lizhuang Ma,et al.  Qualitative Spatial Representation and Reasoning in 3D Space , 2009, 2009 Second International Conference on Intelligent Computation Technology and Automation.

[13]  Lucian Cosmin Goron,et al.  3D semantic interpretation for robot perception inside office environments , 2014, Eng. Appl. Artif. Intell..

[14]  Alexandre Escolà,et al.  Deciduous tree reconstruction algorithm based on cylinder fitting from mobile terrestrial laser scanned point clouds , 2014 .

[15]  Bernhard Nebel,et al.  Qualitative Spatial Reasoning about Relative Position: The Tradeoff between Strong Formal Properties and Successful Reasoning about Route Graphs , 2003, Spatial Cognition.

[16]  Vladimir G. Kim,et al.  Shape-based recognition of 3D point clouds in urban environments , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[17]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .