3. Producción

Browse

Search Results

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
SHREC 2022: Pothole and crack detection in the road pavement using images and RGB-D data
(Elsevier Ltd, 2022-10-01)
This paper describes the methods submitted for evaluation to the SHREC 2022 track on pothole and crack detection in the road pavement. A total of 7 different runs for the semantic segmentation of the road surface are compared, 6 from the participants plus a baseline method. All methods exploit Deep Learning techniques and their performance is tested using the same environment (i.e., a single Jupyter notebook). A training set, composed of 3836 semantic segmentation image/mask pairs and 797 RGB-D video clips collected with the latest depth cameras was made available to the participants. The methods are then evaluated on the 496 image/masks pairs in the validation set, on the 504 pairs in the test set and finally on 8 video clips. The analysis of the results is based on quantitative metrics for image segmentation and qualitative analysis of the video clips. The participation and the results show that the scenario is of great interest and that the use of RGB-D data is still challenging in this context.
Some of the metrics are blocked by your
consent settings
Building semantic segmentation using UNet convolutional network on SpaceNet public data sets for monitoring surrounding area of Chan Chan (Peru)
(AGH University of Science and Technology Press, 2024-01-01)
The amount of damage to cultural heritage sites is increasing rapidly every year. This is due to inadequate heritage management and uncontrolled urban growth as well as unpredictable seismic and atmospheric events that manifest themselves in a continuously deteriorating ecosystem. Thus, applications of artificial intelligence (AI) in remote-sensing (RS) techniques (machine-learning and deep-learning algorithms) for monitoring archaeological sites have increased in recent years. This research involves the surrounding area of the archaeological site of Chan Chan in Peru in particular. An approach that is based on the use of AI algorithms for building footprint segmentation and change-detection analysis by means of RS images is proposed. It involves a UNet con-volutional network based on an EfficientNet B0 to B7 encoder. The network was trained on two public data sets from SpaceNet that were based on WV2 and WV3 satellite images: SpaceNet V1 (Rio), and SpaceNet V2 (Shanghai). In the pre-processing phase, the images from the two data sets have been equalized in order to improve their quality and avoid overfitting. The building segmentation has been performed on HRV images of the study area that were downloaded from Google Earth Pro. The value that was achieved in the IoU metric was around 70% in both experiments. The purpose of this proposed methodology is to assist scientists in drafting monitoring and conservation protocols based on already-recorded data in order to prevent future disasters and hazards.
Some of the metrics are blocked by your
consent settings
A study of cross-dataset generalization on liver vessel segmentation improved by a topological loss
(Springer Science and Business Media Deutschland GmbH, 2026-01-01)
Abstract: Our research addresses the critical task of localizing liver vascularity for medical applications such as surgical planning and intraoperative navigation. We conduct a comprehensive and unbiased evaluation of contemporary segmentation architectures for liver vessel segmentation, comparing UNet-based, mask-based, and foundational models. Our analysis emphasizes cross-dataset generalization by assessing model performance on multiple datasets. Notably, we achieve strong generalization by integrating region-based and topologically based Dice loss functions. This approach substantially improves cross-domain generalization, yielding clDice scores of 0.7132 on the IRCAD dataset and 0.6704 on the MSD dataset, even when these datasets were not included in the training set. Additionally, training with a mixed dataset further increases the MSD Dice score to 0.7472.
Some of the metrics are blocked by your
consent settings
Semantic Segmentation of Fish and Underwater Environments Using Deep Convolutional Neural Networks and Learned Active Contours
(Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
The conservation of marine resources requires constant monitoring of the underwater environment by researchers. For this purpose, visual automated monitoring systems are of great interest, especially those that can describe the environment using semantic segmentation based on deep learning. Although they have been successfully used in several applications, such as biomedical ones, obtaining optimal results in underwater environments is still a challenge due to the heterogeneity of water and lighting conditions, and the scarcity of labeled datasets. Even more, the existing deep learning techniques oriented to semantic segmentation only provide low resolution results, lacking the enough spatial details for a high performance monitoring. To address these challenges, a combined loss function based on the active contour theory and level set methods is proposed to refine the spatial segmentation resolution and quality. To evaluate the method, a new underwater dataset with pixel annotations for three classes (fish, seafloor, and water) was created using images from publicly accessible datasets like SUIM, RockFish, and DeepFish. The performance of architectures of convolutional neural networks (CNNs), such as UNet and DeepLabV3+, trained with different loss functions (cross entropy, dice, and active contours) was compared, finding that the proposed combined loss function improved the segmentation results by around 3%, both in the metric Intercept Over Union (IoU) as in Hausdorff Distance (HD).
Some of the metrics are blocked by your
consent settings
Land-Cover Semantic Segmentation for Very-High-Resolution Remote Sensing Imagery Using Deep Transfer Learning and Active Contour Loss
(Institute of Electrical and Electronics Engineers Inc., 2025-01-01)
An accurate land-cover segmentation of very-high-resolution aerial images is essential for a wide range of applications, including urban planning and natural resource management. However, the automation of this process remains a challenge owing to the complexity of images, variability in land surface features, and noise. In this study, a method for training convolutional neural networks and transformers to perform land-cover segmentation on very-high-resolution aerial images in a regional context was proposed. We assessed the U-Net-scSE, FT-U-NetFormer, and DC-Swin architectures, incorporating transfer learning and active contour loss functions to improve performance on semantic segmentation tasks. Our experiments conducted using the OpenEarthMap dataset, which includes images from 44 countries, demonstrate the superior performance of U-Net-scSE models with the EfficientNet-V2-XL and MiT-B4 encoders, achieving an mIoU of over 0.80 on a test dataset of urban and rural images from Peru.
1

3. Producción

Browse

Filters

Settings

Sort By

Results per page

Search Results