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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In recent years, unmanned aerial vehicle (UAV) imaging is a suitable solutionfor real-time monitoring different vehicles on the urban scale. Real-timevehicle detection with the use of uncertainty estimation in deep meta-learningfor the portable platforms (e.g., UAV) potentially improves video understandingin real-world applications with a small training dataset, while many vehiclemonitoring approaches appear to understand single-time detection with a bigtraining dataset. The purpose of real-time vehicle detection from oblique UAVimages is to locate the vehicle on the time series UAV images by using semanticsegmentation. Real-time vehicle detection is more difficult due to the varietyof depth and scale vehicles in oblique view UAV images. Motivated by thesefacts, in this manuscript, we consider the problem of real-time vehicledetection for oblique UAV images based on a small training dataset and deepmeta-learning. The proposed architecture, called SA-Net.v2, is a developedmethod based on the SA-CNN for real-time vehicle detection by reformulating thesqueeze-and-attention mechanism. The SA-Net.v2 is composed of two components,including the squeeze-and-attention function that extracts the high-levelfeature based on a small training dataset, and the gated CNN. For the real-timevehicle detection scenario, we test our model on the UAVid dataset. UAVid is atime series oblique UAV images dataset consisting of 30 video sequences. Weexamine the proposed method's applicability for stand real-time vehicledetection in urban environments using time series UAV images. The experimentsshow that the SA-Net.v2 achieves promising performance in time series obliqueUAV images.

the international archives of the photogrammetry, remote sensing and spatial information sciences/international archives of the photogrammetry, remote sensing and spatial information sciences

SA-NET.v2: Real-time vehicle detection from oblique UAV images with use of uncertainty estimation in deep meta-learning