TileNet: Tile-Based CNN-SVM Architecture for Autonomous Unmanned Aerial Systems Inspection of Flat Roofs

• URL: http://arxiv.org/abs/2609.13013v1
• Date: Fri, 11 Sep 2026 16:11:35 GMT
• Title: TileNet: Tile-Based CNN-SVM Architecture for Autonomous Unmanned Aerial Systems Inspection of Flat Roofs
• Abstract summary: This paper presents a real-time, Unmanned Aerial System (UAS)-based deep learning framework that autonomously detects defects using live imagery captured during dual-altitude aerial passes.<n>The framework integrates a tile-based architecture with a lightweight Convolution Neural Network-Support Vector Machine (CNN-SVM)<n>The final model-comprising five convolutional layers and four dense layers, achieved a mean test accuracy of $94.4%$ ($95%$ confidence interval $pm0.4%$ over three seeds) on a photo-level split.
• Score: 6.316693022958222
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flat roofs are among the most influential components of the building envelope, governing both structural performance and thermal efficiency, and thereby contributing directly to household energy consumption, carbon emissions, and long-term environmental sustainability. Timely detection of roof defects is essential for reducing heating and cooling losses, preventing moisture-driven degradation such as mold growth, and supporting national climate-change mitigation goals. This paper presents a real-time, Unmanned Aerial System (UAS)-based deep learning framework that autonomously detects defects using live imagery captured during dual-altitude aerial passes. The multi-resolution flight strategy is designed to aid the identification of both small, fine-scale defects and larger structural issues, enabling more comprehensive assessments. To meet the strict computational and power constraints of embedded UAS hardware, the proposed framework integrates a tile-based architecture with a lightweight Convolution Neural Network-Support Vector Machine (CNN-SVM) classifier designed for low-latency onboard inference. The final model-comprising five convolutional layers and four dense layers, the last a linear SVM head, achieved a mean test accuracy of $94.4\%$ ($95\%$ confidence interval $\pm0.4\%$ over three seeds) on a photo-level split ($43,383$ training, $3,869$ validation, and $2,540$ test tiled and augmented images), outperforming GoogLeNet ($89.2\%$) and AlexNet ($79.8\%$). Experimental evaluations using real UAS imagery collected by onsite visits with DJI Matrice 350 RTK drone demonstrate that the system supports rapid, repeatable, and safe roof inspections while reducing human risk, lowering operational costs, and enabling more sustainable building maintenance.

Related papers

• TRISTAR: Triple-Signal Stair Recognition and Vision-Only Indoor Navigation for Search-and-Rescue Micro-UAVs [0.0]
  This paper presents a complete autonomous indoor navigation framework for low-cost unmanned aerial vehicles based exclusively on monocular vision.<n>The framework consists of two independent behaviors: (i) corridor exploration with automatic door detection, room entry, OCR-based room identification, and victim inspection; and (ii) autonomous stair ascent based on TRISTAR.
  arXiv  Detail & Related papers  (2026-07-04T11:06:00Z)
• Dot-Flik: A Scalable Edge AI Architecture for Distributed Insect Monitoring [5.357664591834458]
  We propose a motion-informed frame filtering algorithm that discards irrelevant frames at the edge while preserving insect activity.<n>Second, we introduce a distributed, hierarchical IoT architecture that decouples data acquisition from AI classification.<n>Third, we validate the complete system through real-world outdoor deployments on low-cost commodity hardware.
  arXiv  Detail & Related papers  (2026-05-27T10:10:44Z)
• TinyNina: A Resource-Efficient Edge-AI Framework for Sustainable Air Quality Monitoring via Intra-Image Satellite Super-Resolution [3.995685365847731]
  TinyNina is a resource-efficient Edge-AI framework for sustainable environmental monitoring.<n>It implements a novel intra-image learning paradigm that leverages the multi-spectral hierarchy of Sentinel-2 as internal training labels.<n>TinyNina achieves a state-of-the-art Mean Absolute Error (MAE) of 7.4 $$g/m$3$ against 3,276 matched satellite-ground station pairs.
  arXiv  Detail & Related papers  (2026-04-06T05:43:21Z)
• Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection [53.59823657644554]
  We propose an Adaptive Multi-stage non-edge Pruning framework for Edge Detection(Amped)<n>Amped identifies high-confidence non-edge tokens and removes them as early as possible to substantially reduce computation.<n>To mitigate the structural complexity of existing edge detection networks, we introduce a simple yet high-performance Transformer-based model, termed Streamline Edge Detector(SED)
  arXiv  Detail & Related papers  (2026-03-29T12:26:35Z)
• $D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation [72.9912717963138]
  Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications.<n>Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality.<n>We propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D3$-RSMDE) to overcome these limitations.<n>$D3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric.
  arXiv  Detail & Related papers  (2026-03-17T10:50:36Z)
• KAN-FIF: Spline-Parameterized Lightweight Physics-based Tropical Cyclone Estimation on Meteorological Satellite [22.99496587694237]
  Timely monitoring of tropical cyclones is crucial for reducing loss of life and property.<n>Current physics-guided models suffer from linear feature interactions that fail to capture high-order relationships between TC attributes.<n>This study introduces the Kolmogorov-Arnold Network-based Network-based Interaction Feature Framework (KAN-FIF)
  arXiv  Detail & Related papers  (2026-02-12T16:07:39Z)
• Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights [50.52704854147297]
  We present a new vision transformer (ViT) model optimized with a classification (discrete) and a continuous loss function. This model achieves better accuracy than previously used convolutional based approaches (ConvNets) optimized with only a continuous loss function.
  arXiv  Detail & Related papers  (2023-04-22T22:39:03Z)
• LightDefectNet: A Highly Compact Deep Anti-Aliased Attention Condenser Neural Network Architecture for Light Guide Plate Surface Defect Detection [71.40595908386477]
  An essential step in the manufacturing of light guide plates is the quality inspection of defects such as scratches, bright/dark spots, and impurities. Advances in deep learning-driven computer vision has led to the exploration of automated visual quality inspection of light guide plates. LightDetectNet is a highly compact deep anti-aliased attention condenser neural network architecture tailored specifically for light guide plate surface defect detection.
  arXiv  Detail & Related papers  (2022-04-25T16:33:37Z)
• A Multi-Stage model based on YOLOv3 for defect detection in PV panels based on IR and Visible Imaging by Unmanned Aerial Vehicle [65.99880594435643]
  We propose a novel model to detect panel defects on aerial images captured by unmanned aerial vehicle. The model combines detections of panels and defects to refine its accuracy. The proposed model has been validated on two big PV plants in the south of Italy.
  arXiv  Detail & Related papers  (2021-11-23T08:04:32Z)
• Automated Quality Control of Vacuum Insulated Glazing by Convolutional Neural Network Image Classification [5.2183907457242915]
  We develop, trained, and tested a deep learning computer vision system using convolutional neural networks. The system flawlessly classified the test dataset with an area under the curve (AUC) for the receiver operating characteristic (ROC) of 100%. We employ the state-of-the-art methods Grad-CAM and Score-CAM of explainable Artificial Intelligence (XAI) to provide an understanding of the internal mechanisms.
  arXiv  Detail & Related papers  (2021-10-15T13:10:54Z)
• NeurOpt: Neural network based optimization for building energy management and climate control [58.06411999767069]
  We propose a data-driven control algorithm based on neural networks to reduce this cost of model identification. We validate our learning and control algorithms on a two-story building with ten independently controlled zones, located in Italy.
  arXiv  Detail & Related papers  (2020-01-22T00:51:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.