Title :
Point cloud data enhancement based on layer connected region
Author :
Hongjuan Yang ; Jiwen Chen
Author_Institution :
Sch. of Inf. & Electr. Eng., Shandong Jianzhu Univ., Jinan, China
Abstract :
Point cloud data of complex product with small changes of surface has narrow data range, high spatial relativity and smooth data change. It is not sensitive to feature extraction and shape recognition. Point cloud data enhancement based on layer connected region is proposed. The two-dimensional matrix is calculated to describe point cloud data reflecting the product shape and spacial relationship. Point cloud data is divided into two layers. Local point cloud data is enhanced in the connected region of each layer. The point cloud data enhancement is evaluated by contrast enhancement index and equivalent number of looks. Example shows that point cloud data enhancement based on layer connected region can convert non uniform distribution point cloud data to uniform distribution point cloud data, improving the contrast of the point cloud data.
Keywords :
computational geometry; complex product; contrast enhancement index; feature extraction; layer connected region; nonuniform distribution point cloud data; point cloud data enhancement; product shape; shape recognition; smooth data change; spacial relationship; spatial relativity; two-dimensional matrix; uniform distribution point cloud data; Coordinate measuring machines; Educational institutions; Feature extraction; Indexes; Lasers; Shape; Three-dimensional displays; data enhancement; layer connected region; point cloud data;
Conference_Titel :
Audio, Language and Image Processing (ICALIP), 2014 International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4799-3902-2
DOI :
10.1109/ICALIP.2014.7009865
