An official website of the United States government
Road extraction is a sub-domain of remote sensing applications; it is a subject of extensive and ongoing research. The procedure of automatically extracting roads from satellite imagery encounters significant challenges due to the multi-scale and diverse structures of roads; improvement in this field is needed. Convolutional neural networks (CNNs), especially the DeepLab series known for its proficiency in semantic segmentation due to its efficiency in interpreting multi-scale objects’ features, address some of these challenges caused by the varying nature of roads. The present work proposes the utilization of DeepLabV3+, the latest version of the DeepLab series, by introducing an innovative Dense Depthwise Dilated Separable Spatial Pyramid Pooling (DenseDDSSPP) module and integrating it in the place of the conventional Atrous Spatial Pyramid Pooling (ASPP) module. This modification enhances the extraction of complex road structures from satellite images. This study hypothesizes that the integration of DenseDDSSPP with a CNN backbone network and a Squeeze-and-Excitation block will generate an efficient dense feature map by focusing on relevant features, leading to more precise and accurate road extraction from remote sensing images. The Results Section presents a comparison of our model’s performance against state-of-the-art models, demonstrating better results that highlight the effectiveness and success of the proposed approach.
more »
« less
Automated Detection of Roadway Obstructions Using UAVs and Reference Images
Natural disasters such as wildfires, landslides, and earthquakes result in obstructions on roads due to fallen trees, landslides, and rocks. Such obstructions can cause significant mobility problems for both evacuees and first responders, especially in the immediate aftermath of disasters. Unmanned Aerial Vehicles (UAVs) provide an opportunity to perform rapid and remote reconnaissance of planned routes and thus provide decision-makers with information relating to a route’s feasibility. However, detecting obstacles on roads manually is a laborious and error-prone task, especially when attention is diverted to needs that are more urgent during disaster scenarios. This paper thus proposes a computer vision and machine-learning framework to detect obstacles on a road automatically to ensure its possibility in the aftermath of disasters. The framework implements the YOLO algorithm to detect and segment roads on images from UAVs and reference images from publicly available datasets. The images retrieved from UAVs and reference images are segmented and counted pixels of the roadway for comparison of the difference in pixels to identify the obstruction on the road. In addition, the method is proposed to automatically detect obstructions found in the region of interest (ROI) only on a roadway with images and videos from UAVs. Preliminary results from test runs are presented along with the future steps for implementing a real-time UAV-based road obstruction system.
more »
« less
- Award ID(s):
- 2103713
- PAR ID:
- 10521756
- Publisher / Repository:
- American Society of Civil Engineers
- Date Published:
- ISBN:
- 9780784485262
- Page Range / eLocation ID:
- 1029 to 1038
- Format(s):
- Medium: X
- Location:
- Des Moines, Iowa
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In Augmented Reality (AR), improper virtual content placement can obstruct real-world elements, causing confusion and degrading the experience. To address this, we present LOBSTAR (Language model-based OBSTruction detection for Augmented Reality), the first system leveraging a vision language model (VLM) to detect key objects and prevent obstructions in AR. We evaluated LOBSTAR using both real-world and virtual-scene images and developed a mobile app for AR content obstruction detection. Our results demonstrate that LOBSTAR effectively understands scenes and detects obstructive content with well-designed VLM prompts, achieving up to 96% accuracy and a detection latency of 580ms on a mobile app.more » « less
-
Abstract It is challenging to locate small-airway obstructions induced by chronic obstructive pulmonary disease (COPD) directly from visualization using available medical imaging techniques. Accordingly, this study proposes an innovative and noninvasive diagnostic method to detect obstruction locations using computational fluid dynamics (CFD) and convolutional neural network (CNN). Specifically, expiratory airflow velocity contours were obtained from CFD simulations in a subject-specific 3D tracheobronchial tree. One case representing normal airways and 990 cases associated with different obstruction sites were investigated using CFD. The expiratory airflow velocity contours at a selected cross section in the trachea were labeled and stored as the database for training and testing two CNN models, i.e., ResNet50 and YOLOv4. Gradient-weighted class activation mapping (Grad-CAM) and the Pearson correlation coefficient were employed and calculated to classify small-airway obstruction locations and pulmonary airflow pattern shifts and highlight the highly correlated regions in the contours for locating the obstruction sites. Results indicate that the airflow velocity pattern shifts are difficult to directly visualize based on the comparisons of CFD velocity contours. CNN results show strong relevance exists between the locations of the obstruction and the expiratory airflow velocity contours. The two CNN-based models are both capable of classifying the left lung, right lung, and both lungs obstructions well using the CFD simulated airflow contour images with total accuracy higher than 95.07%. The two automatic classification algorithms are highly transformative to clinical practice for early diagnosis of obstruction locations in the lung using the expiratory airflow velocity distributions, which could be imaged using hyperpolarized magnetic resonance imaging.more » « less
-
We study how Turing pattern formation on a growing domain is affected by discrete domain discontinuities. We use the Lengyel–Epstein reaction–diffusion model to numerically simulate Turing pattern formation on radially expanding circular domains containing a variety of obstruction geometries, including obstructions spanning the length of the domain, such as walls and slits, and local obstructions, such as small blocks. The pattern formation is significantly affected by the obstructions, leading to novel pattern morphologies. We show that obstructions can induce growth mode switching and disrupt local pattern formation and that these effects depend on the shape and placement of the objects as well as the domain growth rate. This work provides a customizable framework to perform numerical simulations on different types of obstructions and other heterogeneous domains, which may guide future numerical and experimental studies. These results may also provide new insights into biological pattern growth and formation, especially in non-idealized domains containing noise or discontinuities.more » « less
-
Detecting Cracks and Spalling Automatically in Extreme Events by End-to-end Deep Learning FrameworksIn this paper, we develop and implement end-to-end deep learning approaches to automatically detect two important types of structural failures, cracks and spalling, of buildings and bridges in extreme events such as major earthquakes. A total of 2,229 images were annotated, and are used to train and validate three newly developed Mask Regional Convolutional Neural Networks (Mask R-CNNs). In addition, three sets of public images for different disasters were used to test the accuracy of these models. For detecting and marking these two types of structural failures, one of proposed methods can achieve an accuracy of 67.6% and 81.1%, respectively, on low- and high-resolution images collected from field investigations. The results demonstrate that it is feasible to use the proposed end-to-end method for automatically locating and segmenting the damage using 2D images which can help human experts in cases of disasters.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1061/9780784485262.105
