DocumentCode :
1978063
Title :
Improving the efficiency and effectiveness of railcar safety appliance inspection using machine vision technology
Author :
Edwards, Riley ; Barkan, Christopher P L ; Hart, John M. ; Todorovic, Sinisa ; Ahuja, Narendra
Author_Institution :
Dept. of Civil & Environ. Eng., Illinois Univ., Urbana, IL, USA
fYear :
2006
fDate :
4-6 April 2006
Firstpage :
81
Lastpage :
89
Abstract :
Before a train departs a yard, many aspects of the freight cars and locomotives undergo inspection, including their safety appliances. Safety appliances are handholds, ladders and other objects that serve as the interface between humans and railcars during transportation. Federal safety rules govern the design and condition of safety appliances. The current car inspection process is primarily visual making it laborious, redundant, and generally lacking of memory. There exists a potential to increase both the effectiveness and efficiency of safety appliance inspections by utilizing machine vision technology to enhance the railcar inspection process. Machine vision consists of capturing digital video and using algorithms capable of detecting and analyzing the particular objects or patterns of interest. Computer algorithms can objectively inspect railcars without tiring or becoming distracted and can also focus on certain parts of the railcar not easily seen by an inspector on the ground. Thus far, algorithms have been developed that can detect deformed ladders, handholds, and brake wheels on open-top gondolas and hoppers. Next, visual learning will be employed to teach the algorithm the differences between Federal Railroad Administration (FRA) safety appliance defects and other types of deformation not requiring a car to be bad ordered. The final product will be a wayside inspection system capable of detecting safety appliance defects on passing railcars.
Keywords :
automatic optical inspection; computer vision; deformation; ladders; locomotives; railway engineering; railway safety; Federal Railroad Administration; Federal safety rules; car inspection process; deformation; digital video; freight cars; handholds; ladders; locomotives; machine vision technology; railcar inspection process; railcar safety appliance inspection; safety appliance defects; visual learning; Home appliances; Humans; Inspection; Machine vision; Object detection; Pattern analysis; Rail transportation; Railway safety; US Department of Transportation; Vehicle safety;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Rail Conference, 2006. Proceedings of the 2006 IEEE/ASME Joint
Print_ISBN :
0-7918-4203-7
Type :
conf
DOI :
10.1109/RRCON.2006.215296
Filename :
1634061
Link To Document :
بازگشت