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/

Zendy Plus

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

Zendy Tools

Zendy Open

The usage of drones has tremendously increased in different sectors spanningfrom military to industrial applications. Despite all the benefits they offer,their misuse can lead to mishaps, and tackling them becomes more challengingparticularly at night due to their small size and low visibility conditions. Toovercome those limitations and improve the detection accuracy at night, wepropose an object detector called Ghost Auto Anchor Network (GAANet) forinfrared (IR) images. The detector uses a YOLOv5 core to address challenges inobject detection for IR images, such as poor accuracy and a high false alarmrate caused by extended altitudes, poor lighting, and low image resolution. Toimprove performance, we implemented auto anchor calculation, modified theconventional convolution block to ghost-convolution, adjusted the input channelsize, and used the AdamW optimizer. To enhance the precision of multiscale tinyobject recognition, we also introduced an additional extra-small object featureextractor and detector. Experimental results in a custom IR dataset withmultiple classes (birds, drones, planes, and helicopters) demonstrate thatGAANet shows improvement compared to state-of-the-art detectors. In comparisonto GhostNet-YOLOv5, GAANet has higher overall mean average precision (mAP@50),recall, and precision around 2.5\%, 2.3\%, and 1.4\%, respectively. The datasetand code for this paper are available as open source athttps://github.com/ZeeshanKaleem/GhostAutoAnchorNet.

GAANet: Ghost Auto Anchor Network for Detecting Varying Size Drones in Dark