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

Real-time object detection on Unmanned Aerial Vehicles (UAVs) is achallenging issue due to the limited computing resources of edge GPU devices asInternet of Things (IoT) nodes. To solve this problem, in this paper, wepropose a novel lightweight deep learning architectures named FasterX based onYOLOX model for real-time object detection on edge GPU. First, we design aneffective and lightweight PixSF head to replace the original head of YOLOX tobetter detect small objects, which can be further embedded in the depthwiseseparable convolution (DS Conv) to achieve a lighter head. Then, a slimmerstructure in the Neck layer termed as SlimFPN is developed to reduce parametersof the network, which is a trade-off between accuracy and speed. Furthermore,we embed attention module in the Head layer to improve the feature extractioneffect of the prediction head. Meanwhile, we also improve the label assignmentstrategy and loss function to alleviate category imbalance and box optimizationproblems of the UAV dataset. Finally, auxiliary heads are presented for onlinedistillation to improve the ability of position embedding and featureextraction in PixSF head. The performance of our lightweight models arevalidated experimentally on the NVIDIA Jetson NX and Jetson Nano GPU embeddedplatforms.Extensive experiments show that FasterX models achieve bettertrade-off between accuracy and latency on VisDrone2021 dataset compared tostate-of-the-art models.

FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications