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

Accurate drone detection is strongly desired in drone collision avoidance,drone defense and autonomous Unmanned Aerial Vehicle (UAV) self-landing. Withthe recent emergence of the Vision Transformer (ViT), this critical task isreassessed in this paper using a UAV dataset composed of 1359 drone photos. Weconstruct various CNN and ViT-based models, demonstrating that for single-dronedetection, a basic ViT can achieve performance 4.6 times more robust than ourbest CNN-based transfer learning models. By implementing the state-of-the-artYou Only Look Once (YOLO v7, 200 epochs) and the experimental ViT-based YouOnly Look At One Sequence (YOLOS, 20 epochs) in multi-drone detection, weattain impressive 98% and 96% mAP values, respectively. We find that ViToutperforms CNN at the same epoch, but also requires more training data,computational power, and sophisticated, performance-oriented designs to fullysurpass the capabilities of cutting-edge CNN detectors. We summarize thedistinct characteristics of ViT and CNN models to aid future researchers indeveloping more efficient deep learning models.

Towards a High-Performance Object Detector: Insights from Drone Detection Using ViT and CNN-based Deep Learning Models