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

As autonomous vehicles and autonomous racing rise in popularity, so does theneed for faster and more accurate detectors. While our naked eyes are able toextract contextual information almost instantly, even from far away, imageresolution and computational resources limitations make detecting smallerobjects (that is, objects that occupy a small pixel area in the input image) agenuinely challenging task for machines and a wide-open research field. Thisstudy explores how the popular YOLOv5 object detector can be modified toimprove its performance in detecting smaller objects, with a particularapplication in autonomous racing. To achieve this, we investigate how replacingcertain structural elements of the model (as well as their connections andother parameters) can affect performance and inference time. In doing so, wepropose a series of models at different scales, which we name `YOLO-Z', andwhich display an improvement of up to 6.9% in mAP when detecting smallerobjects at 50% IOU, at the cost of just a 3ms increase in inference timecompared to the original YOLOv5. Our objective is to inform future research onthe potential of adjusting a popular detector such as YOLOv5 to addressspecific tasks and provide insights on how specific changes can impact smallobject detection. Such findings, applied to the broader context of autonomousvehicles, could increase the amount of contextual information available to suchsystems.

YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles