Vision-Based Anti-UAV Detection Based on YOLOv7-GS in Complex Backgrounds
Open Access
Abstract
Unauthorized unmanned aerial vehicles (UAVs) pose threats to public safety and individual privacy. Traditional object-detection approaches often fall short during their application in anti-UAV technologies. To address this issue, we propose the YOLOv7-GS model, which is designed specifically for the identification of small UAVs in complex and low-altitude environments. This research primarily aims to improve the model’s detection capabilities for small UAVs in complex backgrounds. Enhancements were applied to the YOLOv7-tiny model, including adjustments to the sizes of prior boxes, incorporation of the InceptionNeXt module at the end of the neck section, and introduction of the SPPFCSPC-SR and Get-and-Send modules. These modifications aid in the preservation of details about small UAVs and heighten the model’s focus on them. The YOLOv7-GS model achieves commendable results on the DUT Anti-UAV and the Amateur Unmanned Air Vehicle Detection datasets and performs to be competitive against other mainstream algorithms.Keywords
Funding Information
- National Natural Science Foundation of China (62176041, 2022RY21, 04442024040, 04442024041)
- Excellent Science and Technique Talent Foundation of Dalian (62176041, 2022RY21, 04442024040, 04442024041)
- Fundamental Research Funds for the Central Universities (62176041, 2022RY21, 04442024040, 04442024041)
This publication has 38 references indexed in Scilit:
- End-to-End Object Detection with Transformers2020
- A review of UAV monitoring in mining areas: current status and future perspectivesInternational Journal of Coal Science & Technology, 2019
- A Simple and Efficient Network for Small Target DetectionIEEE Access, 2019
- Unmanned Aerial Vehicles (UAVs): A Survey on Civil Applications and Key Research ChallengesIEEE Access, 2019
- Path Aggregation Network for Instance Segmentation2018
- Feature Pyramid Networks for Object Detection2017
- Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network2017
- SSD: Single Shot MultiBox Detector2016
- Learning Deep Features for Discriminative Localization2016
- Development of an UAV for search & rescue applications2011