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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper proposes an end-to-end trainable one-stage parking slot detectionmethod for around view monitor (AVM) images. The proposed method simultaneouslyacquires global information (entrance, type, and occupancy of parking slot) andlocal information (location and orientation of junction) by using aconvolutional neural network (CNN), and integrates them to detect parking slotswith their properties. This method divides an AVM image into a grid andperforms a CNN-based feature extraction. For each cell of the grid, the globaland local information of the parking slot is obtained by applying convolutionfilters to the extracted feature map. Final detection results are produced byintegrating the global and local information of the parking slot throughnon-maximum suppression (NMS). Since the proposed method obtains most of theinformation of the parking slot using a fully convolutional network without aregion proposal stage, it is an end-to-end trainable one-stage detector. Inexperiments, this method was quantitatively evaluated using the public datasetand outperforms previous methods by showing both recall and precision of99.77%, type classification accuracy of 100%, and occupancy classificationaccuracy of 99.31% while processing 60 frames per second.

End-to-End Trainable One-Stage Parking Slot Detection Integrating Global and Local Information