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

Movie-Map, an interactive first-person-view map that engages the user in asimulated walking experience, comprises short 360{\deg} video segmentsseparated by traffic intersections that are seamlessly connected according tothe viewer's direction of travel. However, in wide urban-scale areas withnumerous intersecting roads, manual intersection segmentation requiressignificant human effort. Therefore, automatic identification of intersectionsfrom 360{\deg} videos is an important problem for scaling up Movie-Map. In thispaper, we propose a novel method that identifies an intersection fromindividual frames in 360{\deg} videos. Instead of formulating the intersectionidentification as a standard binary classification task with a 360{\deg} imageas input, we identify an intersection based on the number of the possibledirections of travel (PDoT) in perspective images projected in eight directionsfrom a single 360{\deg} image detected by the neural network for handlingvarious types of intersections. We constructed a large-scale 360{\deg} ImageIntersection Identification (iii360) dataset for training and evaluation where360{\deg} videos were collected from various areas such as school campus,downtown, suburb, and china town and demonstrate that our PDoT-based methodachieves 88\% accuracy, which is significantly better than that achieved by thedirect naive binary classification based method. The source codes and a partialdataset will be shared in the community after the paper is published.

Intersection Prediction from Single 360{\deg} Image via Deep Detection of Possible Direction of Travel