Two-Stage Swarm Intelligence Ensemble Deep Transfer Learning (SI-EDTL) for Vehicle Detection Using Unmanned Aerial Vehicles

2025-09-09

AI Summary

To address low detection accuracy and poor generalization in multi-vehicle detection from UAV imagery, this paper proposes a two-stage deep transfer learning ensemble framework optimized via swarm intelligence. Methodologically, it constructs a heterogeneous feature-decision dual-layer ensemble model by integrating three Faster R-CNN variants with five transfer classifiers; whale optimization algorithm (WOA) is employed for automated hyperparameter search, and a weighted averaging strategy enhances detection balance. The entire framework is implemented in MATLAB R2020b with parallel computing support. Experimental evaluation on the AU-AIR dataset demonstrates that the proposed method significantly outperforms existing state-of-the-art approaches, achieving a 5.3% improvement in mean average precision (mAP) while maintaining high precision and recall. Results confirm its robustness and generalization capability in small-object and densely populated scenarios.

Technology Category

• Machine Learning: Ensemble Methods
• Computer Vision: Learning & Optimization for CV
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

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.

Problem

• Detects multiple vehicles in UAV images
• Optimizes hyperparameters for accuracy and recall
• Combines deep learning models with transfer classifiers

Innovation

• Swarm intelligence optimizes ensemble deep transfer learning
• Combines multiple pre-trained models with transfer classifiers
• Uses whale optimization for hyperparameter tuning