Hybrid receptive field network for small object detection on drone view  

作　　者：Zhaodong CHEN Hongbing JI Yongquan ZHANG Wenke LIU Zhigang ZHU 

机构地区：[1]School of Electronic Engineering,Xidian University,Xi’an 710071,China

出　　处：《Chinese Journal of Aeronautics》2025年第2期322-338,共17页中国航空学报(英文版)

基　　金：supported by the National Natural Science Foundation of China(Nos.62276204 and 62203343);the Fundamental Research Funds for the Central Universities(No.YJSJ24011);the Natural Science Basic Research Program of Shanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710);the China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470).

摘　　要：Drone-based small object detection is of great significance in practical applications such as military actions, disaster rescue, transportation, etc. However, the severe scale differences in objects captured by drones and lack of detail information for small-scale objects make drone-based small object detection a formidable challenge. To address these issues, we first develop a mathematical model to explore how changing receptive fields impacts the polynomial fitting results. Subsequently, based on the obtained conclusions, we propose a simple but effective Hybrid Receptive Field Network (HRFNet), whose modules include Hybrid Feature Augmentation (HFA), Hybrid Feature Pyramid (HFP) and Dual Scale Head (DSH). Specifically, HFA employs parallel dilated convolution kernels of different sizes to extend shallow features with different receptive fields, committed to improving the multi-scale adaptability of the network;HFP enhances the perception of small objects by capturing contextual information across layers, while DSH reconstructs the original prediction head utilizing a set of high-resolution features and ultrahigh-resolution features. In addition, in order to train HRFNet, the corresponding dual-scale loss function is designed. Finally, comprehensive evaluation results on public benchmarks such as VisDrone-DET and TinyPerson demonstrate the robustness of the proposed method. Most impressively, the proposed HRFNet achieves a mAP of 51.0 on VisDrone-DET with 29.3 M parameters, which outperforms the extant state-of-the-art detectors. HRFNet also performs excellently in complex scenarios captured by drones, achieving the best performance on the CS-Drone dataset we built.

关 键 词：Drone remote sensing Object detection on drone view Small object detector Hybrid receptive field Feature pyramid network Feature augmentation Multi-scale object detection 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]