A Deep Learning-Based Method for Overhead Contact System Component Recognition Using Mobile 2D LiDAR

Chen, Lipei; Xu, Cheng; Lin, Shuai; Li, Siqi; Tu, Xiaohan

doi:10.3390/s20082224

Cited by 14 publications

(19 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, considering the automated measurement techniques, Chen L. and his co-researchers use a methodology to collect information regarding the overhead contact system component, employing data analysis on point clouds imported from a 2D mobile lidar. They also designed an iterative point partitioning algorithm and a module named as the spatial fusion network [ 36 ].…”

Section: Related Workmentioning

confidence: 99%

Robotic Railway Multi-Sensing and Profiling Unit Based on Artificial Intelligence and Data Fusion

Minea

Dumitrescu

Dima

2021

Sensors

View full text Add to dashboard Cite

This article presents the research and results of field tests and simulations regarding an autonomous/robotic railway vehicle, designed to collect multiple information on safety and functional parameters of a surface railway and/or subway section, based on data fusion and machine learning. The maintenance of complex railways, or subway networks with long operating times is a difficult process and intensive resources consuming. The proposed solution delivers human operators in the fault management service and operations from the time-consuming task of railway inspection and measurements, by integrating several sensors and collecting most relevant information on railway, associated automation equipment and infrastructure on a single intelligent platform. The robotic cart integrates autonomy, remote sensing, artificial intelligence, and ability to detect even infrastructural anomalies. Moreover, via a future process of complex statistical filtering of data, it is foreseen that the solution might be configured to offer second-order information about infrastructure changes, such as land sliding, water flooding, or similar modifications. Results of simulations and field tests show the ability of the platform to integrate several fault management operations in a single process, useful in increasing railway capacity and resilience.

show abstract

Section: Related Workmentioning

confidence: 99%

Robotic Railway Multi-Sensing and Profiling Unit Based on Artificial Intelligence and Data Fusion

Minea

Dumitrescu

Dima

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence composition should first extract and represent music data, which will have an important impact on the subsequent composition [ 7 ]. This paper mainly extracts features from MIDI files, which is a file format commonly used by musicians to create and record music information and contains comprehensive music feature information.…”

Section: Network Structure Design Of Melody Composition Of Two-part Folk Songsmentioning

confidence: 99%

Research on the Interaction of Genetic Algorithm in Assisted Composition

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Computer-aided composition is an attempt to use a formalized process to minimize human (or composer) involvement in the creation of music using a computer. Exploring the problem of computer-aided composition can enable us to understand and simulate the thinking mode of composers in the special process of music creation, which is an important application of artificial intelligence in the field of art. Feature extraction on the MIDI files has been introduced in this paper. Based on the genetic algorithm in this paper, a platform of the sampling coding method to optimize the character representation has solved the traditional algorithmic music composition study. Music directly from the pitch and duration can be derived from the characteristics, respectively, in the form of a one-hot encoding independently said. Failure to the rhythm of the characterization of the pitch and duration are problems that lead to the inability of compositional networks to learn musical styles better. Rhythm is the combination of pitch and time values according to certain rules. The rhythm of music affects the overall style of music. By associating the pitch and time value coding, the rhythm style of music can be preserved better so that the composition network can learn the style characteristics of music more easily.

show abstract

“…Another stereo vision method proposed for measuring only the static geometry of OCL is described in [ 8 , 9 , 14 , 15 , 36 ].…”

Section: Introductionmentioning

confidence: 99%

Novel Vision Monitoring Method Based on Multi Light Points for Space-Time Analysis of Overhead Contact Line Displacements

Wilk

Gelman

Skibicki

et al. 2022

Sensors

View full text Add to dashboard Cite

The article presents an innovative vision monitoring method of overhead contact line (OCL) displacement, which utilizes a set of LED light points installed along it. A light point is an, LED fed from a battery. Displacements of the LED points, recorded by a camera, are interpreted as a change of OCL shape in time and space. The vision system comprises a camera, properly situated with respect to the OCL, which is capable of capturing a dozen light points in its field of view. The monitoring system can be scaled by increasing the number of LED points and video cameras; thus, this method can be used for monitoring the motion of other large-size objects (e.g., several hundred meters). The applied method has made it possible to obtain the following novel results: vibration damping in a contact wire is nonlinear by nature and its intensity depends on the wire vibration amplitude; the natural frequency of contact wire vibration varies, and it is a function of vibration amplitude; the natural frequency of contact wire vibration also depends on the wire temperature. The proposed method can be used to monitor the uplift of contact and messenger wires in laboratory conditions, or for experimental OCL testing, as well as for verifying simulation models of OCL.

show abstract

A Deep Learning-Based Method for Overhead Contact System Component Recognition Using Mobile 2D LiDAR

Cited by 14 publications

References 35 publications

Robotic Railway Multi-Sensing and Profiling Unit Based on Artificial Intelligence and Data Fusion

Robotic Railway Multi-Sensing and Profiling Unit Based on Artificial Intelligence and Data Fusion

Research on the Interaction of Genetic Algorithm in Assisted Composition

Novel Vision Monitoring Method Based on Multi Light Points for Space-Time Analysis of Overhead Contact Line Displacements

Contact Info

Product

Resources

About