Extending CLP(FD) with Interactive Data Acquisition for 3D Visual Object Recognition
نویسندگان
چکیده
This paper addresses the 3D object recognition problem modelled as a Constraint Satisfaction Problem. In this setting, each object view can be modelled as a constraint graph where nodes are object parts and constraints are topological and geometrical relationships among them. By modelling the problem as a CSP, we can recognize an object when all constraints are satis ed by exploiting results from the CSP eld. However, in classical CSPs variable domains have to be statically de ned at the beginning of the constraint propagation process. Thus, not only feature acquisition should be completed before the constraint solving process starts, but all image features should be extracted even if not belonging to signi cant image parts. In visual applications, this requirement turns out to be ine cient since visual features acquisition is a very time consuming task. We present an Interactive Constraint Satisfaction model for problems where variable domains may not be completely known at the beginning of the computation, and can be interactively acquired during the computational process. Some variable domain values may be already at disposal when the constraint propagation process starts, while others can be dynamically acquired during the computation only when needed (on demand). The constraint propagation process works on already known domain values and adds new constraints on unknown domain parts. These new constraints can be used to incrementally process new information without restarting the constraint propagation process from scratch each time new information is available. In addition, these constraints can guide the feature acquisition process, thus focussing attention on signi cant image parts. We present the Interactive CSP model and a propagation algorithm for it. We propose an implementation of the framework in Constraint Logic Programming on Finite Domains, CLP(FD).
منابع مشابه
3D Object Recognition by VC-Graphs and Interactive Constraint Satisfaction
We propose a novel approach for recognizing 3D CADmade objects in complex range images containing several overlapped and different objects. Objects are modeled by a graph whose nodes are surfaces and arcs are surface relations. We propose an object-centered graph model, called Visual Constraint graph (VC-graph), with special visual constraints modeling occlusions between object surfaces. The VC...
متن کاملTutorial Notes for the DAGM 2001 A Framework for the Acquisition , Processing and Interactive Display of High Quality 3 D Models Research
This tutorial highlights some recent results on the acquisition and interactive display of high quality 3D models. For further use in photorealistic rendering or object recognition, a high quality representation must capture two different things: the shape of the model represented as a geometric description of its surface and on the other hand the appearance of the material or materials it is m...
متن کاملExtending clp(FD) by Negative Constraint Solving
In this paper we present a novel extension to the constraint logic programming on Finite Domains (clp(FD)) which combines the usual clp(FD) primitive constraint X in range with a new primitive constraint X notin range. We show that, together, they are more expressive and provide better constraint propagation than having X in range on its own. It is shown how the standard clp(FD) framework can b...
متن کاملClp a Technology for the Interactive Resolution of Spatial Configuration Tasks in a Virtual Environment
In this paper, we present a new framework for the use of Virtual Reality (VR) in engineering design for configuration applications that, while preserving the natural interaction of traditional VR Systems, support the expression of design knowledge in the Virtual Environment (VE) and the visualisation of the user’s interactions with the configuration. Traditional VR systems support the visual ex...
متن کاملA Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation
Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D scene data. Such data, if completely and well annotated, can serve as useful ingredients for a wide spectrum of computer vision and graphics works such as data-driven modeling and scene understanding, object detection and recognition. However, annotating a vast amount of 3D scene data remains challenging due to...
متن کامل