DB-YOLOv5: A UAV Object Detection Model Based on Dual Backbone Network for Security Surveillance

Abstract

Unmanned aerial vehicle (UAV) object detection technology is widely used in security surveillance applications, allowing for real-time collection and analysis of image data from camera equipment carried by a UAV to determine the category and location of all targets in the collected images. However, small-scale targets can be difficult to detect and can compromise the effectiveness of security surveillance. In this work, we propose a novel dual-backbone network detection method (DB-YOLOv5) that uses multiple composite backbone networks to enhance the extraction capability of small-scale targets’ features and improve the accuracy of the object detection model. We introduce a bi-directional feature pyramid network for multi-scale feature learning and a spatial pyramidal attention mechanism to enhance the network’s ability to detect small-scale targets during the object detection process. Experimental results on the challenging UAV aerial photography dataset VisDrone-DET demonstrate the effectiveness of our proposed method, with a 3% improvement over the benchmark model. Our approach can enhance security surveillance in UAV object detection, providing a valuable tool for monitoring and protecting critical infrastructure.

Enhancing Small Object Detection in Aerial Images: A Novel Approach with PCSG Model

“…Shallow networks extract pixel-level information, including color, edges, textures, and corners, while deep networks capture semantic information. Integrating features from different levels of the feature pyramid [21,22] and employing adaptive multi-scale networks [23] are effective strategies to resolve this issue. This paper extends the application of multi-scale information to even shallower feature maps, prunes redundant network structures, and employs the CARAFE module to minimize feature information loss during upsampling, along with the SPD-Conv module to preserve fine-grained feature map information.…”

An In-Depth Analysis of Domain Adaptation in Computer and Robotic Vision

“…This work has 34 citations and five graph references. The most recent works are from 2023, which have six entries in the table [58,61,[63][64][65][66]. These works introduced novel methods and models to improve the performance of small object detection in UAV images by addressing various challenges such as semi-supervised learning, refocusing, dual backbone network, density-aware scale adaptation, cross-layer feature aggregation, and occlusion-guided multi-task learning.…”