scholarly journals A Vehicle-Borne Mobile Mapping System Based Framework for Semantic Segmentation and Modeling on Overhead Catenary System Using Deep Learning

2021 ◽  
Vol 13 (23) ◽  
pp. 4939
Author(s):  
Lei Xu ◽  
Shunyi Zheng ◽  
Jiaming Na ◽  
Yuanwei Yang ◽  
Chunlin Mu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Feature Fusion ◽  
Automatic Detection ◽  
Semantic Segmentation ◽  
Geometric Parameters ◽  
Mobile Mapping ◽  
Mapping System ◽  
Mobile Mapping System ◽  
Catenary System

Overhead catenary system (OCS) automatic detection is of important significance for the safe operation and maintenance of electrified railways. The vehicle-borne mobile mapping system (VMMS) may significantly improve the data acquisition. This paper proposes a VMMS-based framework to realize the automatic detection and modelling of OCS. The proposed framework performed semantic segmentation, model reconstruction and geometric parameters detection based on LiDAR point cloud using VMMS. Firstly, an enhanced VMMS is designed for accurate data generation. Secondly, an automatic searching method based on a two-level stereo frame is designed to filter the irrelevant non-OCS point cloud. Then, a deep learning network based on multi-scale feature fusion and an attention mechanism (MFF_A) is trained for semantic segmentation on a catenary facility. Finally, the 3D modelling is performed based on the OCS segmentation result, and geometric parameters are then extracted. The experimental case study was conducted on a 100 km high-speed railway in Guangxi, China. The experimental results show that the proposed framework has a better accuracy of 96.37%, outperforming other state-of-art methods for segmentation. Compared with traditional manual laser measurement, the proposed framework can achieve a trustable accuracy within 10 mm for OCS geometric parameter detection.

scholarly journals Deep Learning Based Pavement Inspection Using Self-Reconfigurable Robot

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2595
Author(s):  
Balakrishnan Ramalingam ◽  
Abdullah Aamir Hayat ◽  
Mohan Rajesh Elara ◽  
Braulio Félix Gómez ◽  
Lim Yi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Semantic Segmentation ◽  
High Accuracy ◽  
Experimental Results ◽  
Mobile Mapping ◽  
Mapping System ◽  
Mobile Mapping System ◽  
Reconfigurable Robot ◽  
Nvidia Gpu ◽  
Inspection Task

The pavement inspection task, which mainly includes crack and garbage detection, is essential and carried out frequently. The human-based or dedicated system approach for inspection can be easily carried out by integrating with the pavement sweeping machines. This work proposes a deep learning-based pavement inspection framework for self-reconfigurable robot named Panthera. Semantic segmentation framework SegNet was adopted to segment the pavement region from other objects. Deep Convolutional Neural Network (DCNN) based object detection is used to detect and localize pavement defects and garbage. Furthermore, Mobile Mapping System (MMS) was adopted for the geotagging of the defects. The proposed system was implemented and tested with the Panthera robot having NVIDIA GPU cards. The experimental results showed that the proposed technique identifies the pavement defects and litters or garbage detection with high accuracy. The experimental results on the crack and garbage detection are presented. It is found that the proposed technique is suitable for deployment in real-time for garbage detection and, eventually, sweeping or cleaning tasks.

scholarly journals AUTOMATIC DETECTION AND VECTORIZATION OF LINEAR AND POINT OBJECTS IN 3D POINT CLOUD AND PANORAMIC IMAGES FROM MOBILE MAPPING SYSTEM

2021 ◽  
Vol XLIII-B2-2021 ◽  
pp. 305-312
Author(s):  
E. Barçon ◽  
A. Picard
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Automatic Detection ◽  
Lidar Data ◽  
3D Point Cloud ◽  
Mobile Mapping ◽  
Mapping System ◽  
Panoramic Images ◽  
Mobile Mapping System ◽  
Time Required

Abstract. Surveys of roadways with Mobile Laser Scanning (MLS) are nowadays the faster and more secured way to collect topographic data compared with conventional techniques. To deliver topographic plans, the voluminous data collected by the MLS device need to be processed. If the acquisition step is quite fast, the second part of interpretation and vectorization of the LiDAR data and the panoramic images is laborious and time consuming. This paper proposes two approaches that have been developed in order to reduce the time required to process roadway MLS data. The first one is about automatic detection of pole like objects, and the second one is about the detection of linear objects. The presented workflow try to automatically extract a 3D position for each object from MLS Data.

scholarly journals ROAD SIGNS DETECTION AND RECOGNITION UTILIZING IMAGES AND 3D POINT CLOUD ACQUIRED BY MOBILE MAPPING SYSTEM

2016 ◽  
Vol XLI-B1 ◽  
pp. 669-673
Author(s):  
Y. H. Li ◽  
T. Shinohara ◽  
T. Satoh ◽  
K. Tachibana
Keyword(s):  
Template Matching ◽  
Point Cloud ◽  
3D Point Cloud ◽  
Mobile Mapping ◽  
Position Information ◽  
Road Signs ◽  
Road Sign ◽  
Mapping System ◽  
Mobile Mapping System ◽  
Detection And Recognition

High-definition and highly accurate road maps are necessary for the realization of automated driving, and road signs are among the most important element in the road map. Therefore, a technique is necessary which can acquire information about all kinds of road signs automatically and efficiently. Due to the continuous technical advancement of Mobile Mapping System (MMS), it has become possible to acquire large number of images and 3d point cloud efficiently with highly precise position information. In this paper, we present an automatic road sign detection and recognition approach utilizing both images and 3D point cloud acquired by MMS. The proposed approach consists of three stages: 1) detection of road signs from images based on their color and shape features using object based image analysis method, 2) filtering out of over detected candidates utilizing size and position information estimated from 3D point cloud, region of candidates and camera information, and 3) road sign recognition using template matching method after shape normalization. The effectiveness of proposed approach was evaluated by testing dataset, acquired from more than 180 km of different types of roads in Japan. The results show a very high success in detection and recognition of road signs, even under the challenging conditions such as discoloration, deformation and in spite of partial occlusions.

scholarly journals TACK PROJECT: TUNNEL AND BRIDGE AUTOMATIC CRACK MONITORING USING DEEP LEARNING AND PHOTOGRAMMETRY

2020 ◽  
Vol XLIII-B4-2020 ◽  
pp. 741-745
Author(s):  
V. Belloni ◽  
A. Sjölander ◽  
R. Ravanelli ◽  
M. Crespi ◽  
A. Nascetti
Keyword(s):  
Deep Learning ◽  
Crack Detection ◽  
Learning Algorithm ◽  
Primary Source ◽  
Large Set ◽  
Mobile Mapping ◽  
Ongoing Research ◽  
Infrastructure Monitoring ◽  
Mapping System ◽  
Mobile Mapping System

Abstract. Civil infrastructures, such as tunnels and bridges, are directly related to the overall economic and demographic growth of countries. The aging of these infrastructures increases the probability of catastrophic failures that results in loss of lives and high repair costs; all over the world, these factors drive the need for advanced infrastructure monitoring systems. For these reasons, in the last years, different types of devices and innovative infrastructure monitoring techniques have been investigated to automate the process and overcome the main limitation of standard visual inspections that are used nowadays. This paper presents some preliminary findings of an ongoing research project, named TACK, that combines advanced deep learning techniques and innovative photogrammetric algorithms to develop a monitoring system. Specifically, the project focuses on the development of an automatic procedure for crack detection and measurement using images of tunnels and bridges acquired with a mobile mapping system. In this paper, some preliminary results are shown to investigate the potential of a deep learning algorithm in detecting cracks occurred in concrete material. The model is a CNN (Convolutional Neural Network) based on the U-Net architecture; in this study, we tested the transferability of the model that has been trained on a small available labeled dataset and tested on a large set of images acquired using a customized mobile mapping system. The results have shown that it is possible to effectively detect cracks in unseen imagery and that the primary source of errors is the false positive detection of crack-like objects (i.e., contact wires, cables and tile borders).

scholarly journals Creating an OpenDRIVE Model of the Campus of the Budapest University of Technology and Economics for Automotive Simulations

2020 ◽  
Author(s):  
Árpád Barsi ◽  
Vivien Potó ◽  
János Máté Lógó ◽  
Nikol Krausz
Keyword(s):  
Point Cloud ◽  
Virtual Model ◽  
Mobile Mapping ◽  
Environmental Models ◽  
University Of Technology ◽  
Mapping System ◽  
Road Geometry ◽  
Driving Scenario ◽  
Mobile Mapping System ◽  
New Sensors

The development of automotive technologies requires quite a significant amount of time and money. To accelerate this procedure, the technology of now is strongly based on computer simulations, where the whole vehicle or its parts can be analyzed in a virtual environment. The behavior of cars, especially equipped with new sensors or assistants, requires long testing, where the automotive simulators can play a cardinal role. The precise vehicular tests request accurate environmental models. These new kinds of models are still standardized; one of the pioneer de facto standards is OpenDRIVE. This standard was initially defined to be able to express all elements with all potential parameters required in high precision simulations. The actual research focused on creating a compliant virtual model based on mobile mapping measurements. A Leica Pegasus Two mobile mapping system was applied to capture field data about the selected pilot area, which is the campus of Budapest University of Technology and Economics (BME). The obtained Lidar point cloud was georeferenced; the merged point cloud is tailored to the driven trajectory, and then it has been evaluated manually. The acquired land use map is converted – similarly manually – into basic road geometry elements: straight lane and bended lane segments. These objects are finally compiled into an XML format, which is compliant with the OpenDRIVE standard. The achieved virtual model has been tested in Driving Scenario Designer of Mathworks Matlab; however, it is promptly ready for use in other widely applied automotive simulators.

scholarly journals TOPOLOGICAL 3D MODELING USING INDOOR MOBILE LIDAR DATA

2015 ◽  
Vol XL-4/W5 ◽  
pp. 13-18 ◽  
Author(s):  
M. Nakagawa ◽  
T. Yamamoto ◽  
S. Tanaka ◽  
M. Shiozaki ◽  
T. Ohhashi
Keyword(s):  
3D Modeling ◽  
Point Cloud ◽  
Indoor Environment ◽  
Lidar Data ◽  
Range Image ◽  
Mobile Mapping ◽  
Massive Point ◽  
Surface Estimation ◽  
Mapping System ◽  
Mobile Mapping System

We focus on a region-based point clustering to extract a polygon from a massive point cloud. In the region-based clustering, RANSAC is a suitable approach for estimating surfaces. However, local workspace selection is required to improve a performance in a surface estimation from a massive point cloud. Moreover, the conventional RANSAC is hard to determine whether a point lies inside or outside a surface. In this paper, we propose a method for panoramic rendering-based polygon extraction from indoor mobile LiDAR data. Our aim was to improve region-based point cloud clustering in modeling after point cloud registration. First, we propose a point cloud clustering methodology for polygon extraction on a panoramic range image generated with point-based rendering from a massive point cloud. Next, we describe an experiment that was conducted to verify our methodology with an indoor mobile mapping system in an indoor environment. This experiment was wall-surface extraction using a rendered point cloud from some viewpoints over a wide indoor area. Finally, we confirmed that our proposed methodology could achieve polygon extraction through point cloud clustering from a complex indoor environment.

Sign in / Sign up

Export Citation Format

Share Document