A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads

• URL: http://arxiv.org/abs/2411.16295v1
• Date: Mon, 25 Nov 2024 11:27:42 GMT
• Title: A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads
• Authors: Rafael S. Toledo, Cristiano S. Oliveira, Vitor H. T. Oliveira, Eric A. Antonelo, Aldo von Wangenheim,
• Abstract summary: A representative dataset for emerging countries consists of low-resolution images of poorly maintained roads. In this scenario, three challenges arise: objects with few pixels, objects with undefined shapes, and highly underrepresented classes. To tackle these challenges, this work proposes the Performance Increment Strategy for Semantic (PISSS) as a methodology of 14 training experiments to boost performance.
• Score: 0.0
• License:
• Abstract: Autonomous driving needs good roads, but 85% of Brazilian roads have damages that deep learning models may not regard as most semantic segmentation datasets for autonomous driving are high-resolution images of well-maintained urban roads. A representative dataset for emerging countries consists of low-resolution images of poorly maintained roads and includes labels of damage classes; in this scenario, three challenges arise: objects with few pixels, objects with undefined shapes, and highly underrepresented classes. To tackle these challenges, this work proposes the Performance Increment Strategy for Semantic Segmentation (PISSS) as a methodology of 14 training experiments to boost performance. With PISSS, we reached state-of-the-art results of 79.8 and 68.8 mIoU on the Road Traversing Knowledge (RTK) and Technik Autonomer Systeme 500 (TAS500) test sets, respectively. Furthermore, we also offer an analysis of DeepLabV3+ pitfalls for small object segmentation.

Related papers

• RSRD: A Road Surface Reconstruction Dataset and Benchmark for Safe and Comfortable Autonomous Driving [67.09546127265034]
  Road surface reconstruction helps to enhance the analysis and prediction of vehicle responses for motion planning and control systems. We introduce the Road Surface Reconstruction dataset, a real-world, high-resolution, and high-precision dataset collected with a specialized platform in diverse driving conditions. It covers common road types containing approximately 16,000 pairs of stereo images, original point clouds, and ground-truth depth/disparity maps.
  arXiv  Detail & Related papers  (2023-10-03T17:59:32Z)
• R2S100K: Road-Region Segmentation Dataset For Semi-Supervised Autonomous Driving in the Wild [11.149480965148015]
  Road Region dataset (R2S100K) is a large-scale dataset and benchmark for training and evaluation of road segmentation. R2S100K comprises 100K images extracted from a large and diverse set of video sequences covering more than 1000 KM of roadways. We present an Efficient Data Sampling method (EDS) based self-training framework to improve learning by leveraging unlabeled data.
  arXiv  Detail & Related papers  (2023-08-11T21:31:37Z)
• CarPatch: A Synthetic Benchmark for Radiance Field Evaluation on Vehicle Components [77.33782775860028]
  We introduce CarPatch, a novel synthetic benchmark of vehicles. In addition to a set of images annotated with their intrinsic and extrinsic camera parameters, the corresponding depth maps and semantic segmentation masks have been generated for each view. Global and part-based metrics have been defined and used to evaluate, compare, and better characterize some state-of-the-art techniques.
  arXiv  Detail & Related papers  (2023-07-24T11:59:07Z)
• Pavementscapes: a large-scale hierarchical image dataset for asphalt pavement damage segmentation [9.160763314165367]
  This study has proposed Pavementscapes, a large-scale dataset to develop and evaluate methods for pavement damage segmentation. A total of 8,680 damage instances are manually labeled with six damage classes at the pixel level. The numeral experiments propose the top-performing deep neural networks capable of segmenting pavement damages.
  arXiv  Detail & Related papers  (2022-07-24T03:40:27Z)
• CV 3315 Is All You Need : Semantic Segmentation Competition [14.818852884385015]
  This competition focus on Urban-Sense based on the vehicle camera view. Class highly unbalanced Urban-Sense images dataset challenge the existing solutions. Deep Conventional neural network-based semantic segmentation methods become flexible solutions applicable to real-world applications.
  arXiv  Detail & Related papers  (2022-06-25T06:27:57Z)
• SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation [111.61261419566908]
  Deep neural networks (DNNs) are usually trained on a closed set of semantic classes. They are ill-equipped to handle previously-unseen objects. detecting and localizing such objects is crucial for safety-critical applications such as perception for automated driving.
  arXiv  Detail & Related papers  (2021-04-30T07:58:19Z)
• OFFSEG: A Semantic Segmentation Framework For Off-Road Driving [6.845371503461449]
  We propose a framework for off-road semantic segmentation called as OFFSEG. Off-road semantic segmentation is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures.
  arXiv  Detail & Related papers  (2021-03-23T09:45:41Z)
• Detecting 32 Pedestrian Attributes for Autonomous Vehicles [103.87351701138554]
  In this paper, we address the problem of jointly detecting pedestrians and recognizing 32 pedestrian attributes. We introduce a Multi-Task Learning (MTL) model relying on a composite field framework, which achieves both goals in an efficient way. We show competitive detection and attribute recognition results, as well as a more stable MTL training.
  arXiv  Detail & Related papers  (2020-12-04T15:10:12Z)
• BoMuDANet: Unsupervised Adaptation for Visual Scene Understanding in Unstructured Driving Environments [54.22535063244038]
  We present an unsupervised adaptation approach for visual scene understanding in unstructured traffic environments. Our method is designed for unstructured real-world scenarios with dense and heterogeneous traffic consisting of cars, trucks, two-and three-wheelers, and pedestrians.
  arXiv  Detail & Related papers  (2020-09-22T08:25:44Z)
• 3D-DEEP: 3-Dimensional Deep-learning based on elevation patterns forroad scene interpretation [0.0]
  A new net architecture (3D-DEEP) and its end-to-end training methodology for CNN-based semantic segmentation are described. The developed models were trained and validated over Cityscapes dataset. On the other hand, over KITTIdataset the model has achieved an F1 error value of 97.85% invalidation and 96.02% using the test images.
  arXiv  Detail & Related papers  (2020-09-01T10:18:08Z)
• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification [116.1587709521173]
  We propose to build a large-scale vehicle dataset (called VehicleNet) by harnessing four public vehicle datasets. We design a simple yet effective two-stage progressive approach to learning more robust visual representation from VehicleNet. We achieve the state-of-art accuracy of 86.07% mAP on the private test set of AICity Challenge.
  arXiv  Detail & Related papers  (2020-04-14T05:06:38Z)

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.