DV-DETR: Improved UAV Aerial Small Target Detection Algorithm Based on RT-DETR

Xiaolong Wei, Ling Yin, Liangliang Zhang, Fei Wu · 2024

Read DV-DETR: Improved UAV Aerial Small Target Detection Algorithm Based on RT-DETR by Xiaolong Wei, Ling Yin, Liangliang Zhang, Fei Wu (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11598011.txt.

Description

Xiaolong Wei, Ling Yin, Liangliang Zhang, and Fei Wu built a faster computer vision model for spotting small objects in drone footage. People, bikes, and walkers are hard to pick out from the air, above all in crowded city scenes. Their model, DV-DETR, upgrades an existing real-time design in three ways.

A lighter backbone net cuts computing load, attention units sharpen detail across scales, and a new scoring rule handles hard cases better. On a standard drone test set, accuracy rose over the base model and speed hit ninety frames per second. The authors aim at live watch and monitoring work in dense city areas.

Catalog record

CREATORXiaolong Wei, Ling Yin, Liangliang Zhang, Fei Wu
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE37 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11598011

Browse the full library · About the Tower of Babel