文献类型：期刊文献

英文题名：PFE-Det: Progressive Feature Evolution for Small Object Detection in UAV Aerial Images

作者：Fang, Aolin[1];Zhang, Yongzi[1];Dong, Xiaotong[2];Gu, Liuyang[2];Li, Shengshi[2];Zhu, Daoheng[2];Xiao, Xiuchun[2]

机构：[1]Guangdong Ocean Univ, Coll Math & Comp Sci, Zhanjiang 524088, Peoples R China;[2]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524088, Peoples R China

年份：2026

卷号：26

期号：15

外文期刊名：SENSORS

收录：SCI-EXPANDED(收录号：WOS:001847223200001)、、EI(收录号：20263321295202)、Scopus(收录号：2-s2.0-105047164436)、WOS

基金：This work was supported in part by National Natural Science Foundation of China under Grant 62472107, in part by Natural Science Foundation of Guangdong Province, China, under Grant 2023A1515011477, in part by the Science and Technology Project of Zhanjiang City, under Grant 2025B01061, in part by the University-level College Students' Innovation and Entrepreneurship Training Program of Guangdong Ocean University under Grant CXXL2026095, and in part by the Program for Scientific Research Start-up Funds of Guangdong Ocean University (060302112503).

语种：英文

外文关键词：UAV object detection; small object detection; progressive feature evolution; state space model; multi-scale feature fusion; receptive field modeling; gated nonlinear selection; aerial image analysis

外文摘要：Object detection in UAV aerial images remains fundamentally constrained by extremely small object scales, strong background interference, and progressive structural information degradation along the feature extraction pipeline. Current small-object detection methods suffer from two fundamental deficiencies rooted in their convolutional feature extraction pipelines: the smoothing effect of strided convolutions in early layers, which attenuates fine-grained details before backbone processing, and the feature overwriting phenomenon, where sequential transformations progressively erase structural information from earlier layers. We propose PFE-Det (Progressive Feature Evolution Detector), built upon the DEIM framework and constructing a continuous optimization pathway across three stages. A Feature Adaptive Enhancement Network (FAENet) is adopted as a front-end preprocessor to decouple high- and low-frequency components via a Laplacian pyramid at the input stage, mitigating early-layer smoothing at the input. A Multi-Receptive-Field Adaptive Fusion Module (MFAM) is designed to reorganize single-path features into structure-retaining and progressive enhancement paths and is further coupled with hierarchical receptive-field modeling, suppressing feature overwriting through multi-scale context modeling. A Multi-Path Gated State Space Modeling Block (MG-SSM Block) couples HSM-SSD-based long-range dependency extraction with Convolutional Gated Linear Units (CGLU) for adaptive feature selection in the encoder. Experiments on VisDrone2019 demonstrate an AP of 0.225 and an APs of 0.134, yielding a 13.5% relative improvement in small-object precision over the baseline. Cross-dataset evaluations on DIOR and UAVVaste, each under independent training and testing, further support the effectiveness of progressive feature evolution for UAV small-object detection.