Extending Semantic Edge Labelling
نویسندگان
چکیده
In earlier work [9, 10], we developed an approach to edge labelling and depth reconstruction based on fusion of registered depth and intensity images. This paper presents a new method and extensions to the first stage of that approach, that is the detection and semantic labelling of the edge data. Reflectance edges are extracted from an intensity image, and quadratic curves are fitted to range and intensity data along each row and column using a intensity guided splitting and merging process. Edge labels are determined by examination of the changes in depth, surface orientation and intensity at each edge site.
منابع مشابه
Semantic Role Labelling of Prepositional Phrases
We propose a method for labelling prepositional phrases according to two different semantic role classifications, as contained in the Penn treebank and the CoNLL 2004 Semantic Role Labelling data set. Our results illustrate the difficulties in determining preposition semantics, but also demonstrate the potential for PP semantic role labelling to improve the performance of a holistic semantic ro...
متن کاملSemantic Labelling for Termination of Combinatory Reduction Systems
We give a method of proving termination of Klop’s higher-order rewriting format, combinatory reduction system (CRS). Our method called higher-order semantic labelling is an extension of Zantema’s semantic labelling for first-order term rewriting systems. We systematically define the labelling by using the complete algebraic semantics of CRS.
متن کاملGood edge-labelling of graphs
A good edge-labelling of a graph G is a labelling of its edges such that for any two distinct vertices u, v, there is at most one (u, v)-path with non-decreasing labels. This notion was introduced in [3] to solve wavelength assignment problems for specific categories of graphs. In this paper, we aim at characterizing the class of graphs that admit a good edge-labelling. First, we exhibit infini...
متن کاملTotal edge irregularity strength of trees
A total edge-irregular k-labelling ξ : V (G) ∪ E(G) → {1, 2, . . . , k} of a graph G is a labelling of vertices and edges of G in such a way that for any different edges e and f their weights wt(e) and wt(f) are distinct. The weight wt(e) of an edge e = xy is the sum of the labels of vertices x and y and the label of the edge e. The minimum k for which a graph G has a total edge-irregular k-lab...
متن کاملExploiting a Verb Lexicon in Automatic Semantic Role Labelling
We develop an unsupervised semantic role labelling system that relies on the direct application of information in a predicate lexicon combined with a simple probability model. We demonstrate the usefulness of predicate lexicons for role labelling, as well as the feasibility of modifying an existing role-labelled corpus for evaluating a different set of semantic roles. We achieve a substantial i...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1995