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

Misha Urooj Khan*, Maham Misbah, Zeeshan Kaleem, Yansha Deng, Abbas Jamalipour

*Corresponding author for this work

Research output: Contribution to conference typesPaperpeer-review

4 Citations (Scopus)

Abstract

The usage of drones has tremendously increased in different sectors spanning from military to industrial applications. Despite all the benefits they offer, their misuse can lead to mishaps, and tackling them becomes more challenging particularly at night due to their small size and low visibility conditions. To overcome those limitations and improve the detection accuracy at night, we propose an object detector called Ghost Auto Anchor Network (GAANet) for infrared (IR) images. The detector uses a YOLOv5 core to address challenges in object detection for IR images, such as poor accuracy and a high false alarm rate caused by extended altitudes, poor lighting, and low image resolution. To improve performance, we implemented auto anchor calculation, modified the conventional convolution block to ghost-convolution, adjusted the input channel size, and used the AdamW optimizer. To enhance the precision of multiscale tiny object recognition, we also introduced an additional extra-small object feature extractor and detector. Experimental results in a custom IR dataset with multiple classes (birds, drones, planes, and helicopters) demonstrate that GAANet shows improvement compared to state-of-the-art detectors. In comparison to GhostNet-YOLOv5, GAANet has higher overall mean average precision (mAP@50), recall, and precision around 2.5%, 2.3%, and 1.4%, respectively. The dataset and code for this paper are available as open source at https://github.com/ZeeshanKaleem/GhostAutoAnchorNet.

Original languageEnglish
DOIs
Publication statusE-pub ahead of print - 14 Aug 2023
Event97th IEEE Vehicular Technology Conference, VTC 2023-Spring - Florence, Italy
Duration: 20 Jun 202323 Jun 2023

Conference

Conference97th IEEE Vehicular Technology Conference, VTC 2023-Spring
Country/TerritoryItaly
CityFlorence
Period20/06/202323/06/2023

Keywords

  • Drones
  • Multi-class Classification
  • Night-Vision
  • Target Detection
  • YOLOv5

Fingerprint

Dive into the research topics of 'GAANet: Ghost Auto Anchor Network for Detecting Varying Size Drones in Dark'. Together they form a unique fingerprint.

Cite this