Depth-Aware Pothole Detection Using YOLO and RT-DETR at the Edge

• URL: http://arxiv.org/abs/2608.27633v1
• Date: Thu, 27 Aug 2026 19:18:08 GMT
• Title: Depth-Aware Pothole Detection Using YOLO and RT-DETR at the Edge
• Abstract summary: Existing approaches depend on 2D RGB images and cannot measure physical depth of potholes.<n>We present a depthaware pothole detection framework and then compare five architectures.<n>YOLOv8n, YOLOv8nSeg, YOLOv9t, RTDETRL, and RTDETRX for RGB-D sensor fusion-based detection and automated depth measurement.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Pothole detection and its severity measurement is still an important challenges in urban infrastructure management, where late maintenance directly contributes to vehicle damage, road accidents, and escalating repair costs. Existing automated approaches depend on 2D RGB images and cannot measure physical depth of potholes. In this paper, we present a depthaware pothole detection framework and then compare five architectures: YOLOv8n, YOLOv8nSeg, YOLOv9t, RTDETRL, and RTDETRX for RGB-D sensor fusion-based detection and automated depth measurement. A custom offline augmentation pipeline is used here to simulate adverse road monitoring conditions. All models are trained on the PothRGBD dataset with an 80% training and 20% validation split and evaluated using Precision, Recall, mAP@50, and mAP@50_95. Before measuring the depth data, all depth maps are corrected for camera tilt using RANSAC ground-plane orthorectification and all zero-valued sensor pixels are cast to NaN before any statistic is computed. YOLOv8nSeg achieves the highest mAP@50 of 0.9556 and mAP@50_95 of 0.6758 with the most accurate depth estimate of 2.96 cm with the pixel-precise Dseg algorithm. YOLOv8n achieves the fastest inference at 3.6ms. RTDETRX achieves the highest detection confidence at 92.70%. An important finding is that even after full RANSAC orthorectification, bounding box models overestimate pothole depth by 0.16 to 0.21 cm compared to pixel precise segmentation masks. This confirms that the pavement inclusion bias is structural rather than a calibration artifact.

Related papers

• YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling [2.274915755738124]
  This paper tests the premise that a stride-4 level would claim 75.3% of anchors, and complete misses rather than localisation errors dominate baseline failures.<n>Fifteen models were trained from scratch under one recipe, five scales each of YOLO26-RD and of matched YOLO26 and YOLOv12 families.<n>YOLO26-RD-l is the best of the fifteen at 0.809 mAP50 and 0.497 mAP50-95, improving on the YOLO26 reference by 0.031 and 0.030 and leading all six per class entries.
  arXiv  Detail & Related papers  (2026-08-16T12:36:12Z)
• Depth-Enhanced YOLO-SAM2 Detection for Reliable Ballast Insufficiency Identification [6.122855247403851]
  YOLO-SAM2 is a framework for detecting ballast insufficiency in railway tracks using RGB-D data.<n>To improve reliability, we incorporate depth-based geometric analysis enabled by a sleeper-aligned pipeline.<n>Experiments show that depth-enhanced configurations substantially improve the detection of insufficient ballast.
  arXiv  Detail & Related papers  (2026-02-21T21:49:06Z)
• Detection Fire in Camera RGB-NIR [0.0]
  This report presents an additional NIR dataset, a two-stage detection model, and Patched-YOLO.<n>To improve night-time fire detection accuracy while reducing false positives caused by artificial lights, we propose a two-stage pipeline combining YOLOv11 and EfficientNetV2-B0.<n>Finally, to improve fire detection in RGB images, especially for small and distant objects, we introduce Patched-YOLO.
  arXiv  Detail & Related papers  (2025-12-29T16:48:24Z)
• Robust Video-Based Pothole Detection and Area Estimation for Intelligent Vehicles with Depth Map and Kalman Smoothing [4.579830400562906]
  Road potholes pose a serious threat to driving safety and comfort, making their detection and assessment a critical task in fields such as autonomous driving.<n>Most existing vision-based methods rely on distance priors to construct geometric models.<n>To address these problems, a robust pothole area estimation framework that integrates object detection and monocular depth estimation in a video stream is proposed in this paper.
  arXiv  Detail & Related papers  (2025-05-27T11:32:45Z)
• An Enhanced YOLOv8 Model for Real-Time and Accurate Pothole Detection and Measurement [0.0]
  Existing detection methods are usually only based on 2D RGB images and cannot accurately analyze the physical characteristics of potholes.<n>In this paper, a dataset of RGB-D images (PothRGBD) is created and an improved YOLOv8-based model is proposed for both pothole detection and pothole physical features analysis.
  arXiv  Detail & Related papers  (2025-05-07T07:58:57Z)
• Data-driven Detection and Evaluation of Damages in Concrete Structures: Using Deep Learning and Computer Vision [0.0]
  This study explores advanced data-driven techniques using deep learning for automated damage detection and analysis.<n>Two state-of-the-art instance segmentation models, YOLO-v7 instance segmentation and Mask R-CNN, were evaluated.<n>YOLO-v7 achieved a superior mAP@0.5 of 96.1% and processed 40 FPS, outperforming Mask R-CNN, which achieved a mAP@0.5 of 92.1% with a slower processing speed of 18 FPS.
  arXiv  Detail & Related papers  (2025-01-21T02:44:05Z)
• MEDeA: Multi-view Efficient Depth Adjustment [45.90423821963144]
  MEDeA is an efficient multi-view test-time depth adjustment method that is an order of magnitude faster than existing test-time approaches. Our method sets a new state-of-the-art on TUM RGB-D, 7Scenes, and ScanNet benchmarks and successfully handles smartphone-captured data from ARKitScenes dataset.
  arXiv  Detail & Related papers  (2024-06-17T19:39:13Z)
• Real-Time Deepfake Detection in the Real-World [39.96935319559675]
  This paper introduces "Locally Aware Deepfake Detection" Algorithm (LaDeDa) LaDeDa accepts a single 9x9 image patch and outputs its deepfake score. We introduce WildRF, a new deepfake detection dataset curated from several popular social networks.
  arXiv  Detail & Related papers  (2024-06-13T17:59:23Z)
• SDGE: Stereo Guided Depth Estimation for 360$^\circ$ Camera Sets [65.64958606221069]
  Multi-camera systems are often used in autonomous driving to achieve a 360$circ$ perception. These 360$circ$ camera sets often have limited or low-quality overlap regions, making multi-view stereo methods infeasible for the entire image. We propose the Stereo Guided Depth Estimation (SGDE) method, which enhances depth estimation of the full image by explicitly utilizing multi-view stereo results on the overlap.
  arXiv  Detail & Related papers  (2024-02-19T02:41:37Z)
• CU-Net: LiDAR Depth-Only Completion With Coupled U-Net [42.35466006061206]
  We propose an effective Coupled U-Net (CU-Net) architecture for depth-only completion. We employ the local U-Net to estimate accurate values in the normal areas and provide the global U-Net with reliable initial values in the overlap and blank areas. Our proposed method boosts the final results with fewer parameters and achieves state-of-the-art results on the KITTI benchmark.
  arXiv  Detail & Related papers  (2022-10-26T17:57:13Z)
• EAutoDet: Efficient Architecture Search for Object Detection [110.99532343155073]
  EAutoDet framework can discover practical backbone and FPN architectures for object detection in 1.4 GPU-days. We propose a kernel reusing technique by sharing the weights of candidate operations on one edge and consolidating them into one convolution. In particular, the discovered architectures surpass state-of-the-art object detection NAS methods and achieve 40.1 mAP with 120 FPS and 49.2 mAP with 41.3 FPS on COCO test-dev set.
  arXiv  Detail & Related papers  (2022-03-21T05:56:12Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)
• Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera [74.45649274085447]
  We propose a robust method for estimating road curb 3D parameters using a calibrated monocular camera equipped with a fisheye lens. Our approach is able to estimate the vehicle to curb distance in real time with mean accuracy of more than 90%.
  arXiv  Detail & Related papers  (2020-02-28T00:24:18Z)

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.