English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Technology to recognize the type of component represented by a point cloud isrequired in the reconstruction process of an as-built model of a process plantbased on laser scanning. The reconstruction process of a process plant throughlaser scanning is divided into point cloud registration, point cloudsegmentation, and component type recognition and placement. Loss of shape dataor imbalance of point cloud density problems generally occur in the point clouddata collected from large-scale facilities. In this study, we experimented withthe possibility of applying object recognition technology based on 3D deeplearning networks, which have been showing high performance recently, andanalyzed the results. For training data, we used a segmented point cloudrepository about components that we constructed by scanning a process plant.For networks, we selected the multi-view convolutional neural network (MVCNN),which is a view-based method, and PointNet, which is designed to allow thedirect input of point cloud data. In the case of the MVCNN, we also performedan experiment on the generation method for two types of multi-view images thatcan complement the shape occlusion of the segmented point cloud. In thisexperiment, the MVCNN showed the highest retrieval accuracy of approximately87%, whereas PointNet showed the highest retrieval mean average precision ofapproximately 84%. Furthermore, both networks showed high recognitionperformance for the segmented point cloud of plant components when there wassufficient training data.

Deep-learning-based classification and retrieval of components of a process plant from segmented point clouds