用无人机图像检测车辆，融合多模型+智能优化，效果更优。
Two-Stage Swarm Intelligence Ensemble Deep Transfer Learning (SI-EDTL) for Vehicle Detection Using Unmanned Aerial Vehicles
- 两阶段集成：先提取特征，再加权融合15个基学习器
- 在AU-AIR数据集上准确率超现有方法，平衡了查准率与召回率
- 适合做无人机目标检测的科研人员或工程开发者参考
本文提出SI-EDTL，一种用于无人机图像中多车辆检测的两阶段群智能集成深度迁移学习模型。该模型融合三个预训练Faster R-CNN特征提取器（InceptionV3、ResNet50、GoogLeNet）与五个迁移分类器（KNN、SVM、MLP、C4.5、Naïve Bayes），构成15种不同基学习器，通过加权平均进行分类，识别结果为汽车、厢车、卡车、公交车或背景。超参数通过鲸鱼优化算法优化，以平衡准确率、精确率和召回率。基于MATLAB R2020b实现并启用并行计算，在AU-AIR无人机数据集上表现优于现有方法。
原文摘要 · Abstract (English)
This paper introduces SI-EDTL, a two-stage swarm intelligence ensemble deep transfer learning model for detecting multiple vehicles in UAV images. It combines three pre-trained Faster R-CNN feature extractor models (InceptionV3, ResNet50, GoogLeNet) with five transfer classifiers (KNN, SVM, MLP, C4.5, Naïve Bayes), resulting in 15 different base learners. These are aggregated via weighted averaging to classify regions as Car, Van, Truck, Bus, or background. Hyperparameters are optimized with the whale optimization algorithm to balance accuracy, precision, and recall. Implemented in MATLAB R2020b with parallel processing, SI-EDTL outperforms existing methods on the AU-AIR UAV dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。