dc.contributor.author | Shi, Dachuan | |
dc.contributor.author | Šabanovič, Eldar | |
dc.contributor.author | Rizzetto, Luca | |
dc.contributor.author | Skrickij, Viktor | |
dc.contributor.author | Oliverio, Roberto | |
dc.contributor.author | Kaviani, Nadia | |
dc.contributor.author | Ye, Yunguang | |
dc.contributor.author | Bureika, Gintautas | |
dc.contributor.author | Ricci, Stefano | |
dc.contributor.author | Hecht, Markus | |
dc.date.accessioned | 2023-09-18T16:08:51Z | |
dc.date.available | 2023-09-18T16:08:51Z | |
dc.date.issued | 2022 | |
dc.identifier.issn | 0888-3270 | |
dc.identifier.uri | https://etalpykla.vilniustech.lt/handle/123456789/111788 | |
dc.description.abstract | In the application of computer-vision-based displacement measurement, an optical target is usually required to prove the reference. If the optical target cannot be attached to the measuring objective, edge detection and template matching are the most common approaches in target-less photogrammetry. However, their performance significantly relies on parameter settings. This becomes problematic in dynamic scenes where complicated background texture exists and varies over time. We propose virtual point tracking for real-time target-less dynamic displacement measurement, incorporating deep learning techniques and domain knowledge to tackle this issue. Our approach consists of three steps: 1) automatic calibration for detection of region of interest; 2) virtual point detection for each video frame using deep convolutional neural network; 3) domain-knowledge based rule engine for point tracking in adjacent frames. The proposed approach can be executed on an edge computer in a real-time manner (i.e. over 30 frames per second). We demonstrate our approach for a railway application, where the lateral displacement of the wheel on the rail is measured during operation. The numerical experiments have been performed to evaluate our approach’s performance and latency in a harsh railway environment with dynamic complex backgrounds. | eng |
dc.format | PDF | |
dc.format.extent | p. 1-20 | |
dc.format.medium | tekstas / txt | |
dc.language.iso | eng | |
dc.relation.isreferencedby | Science Citation Index Expanded (Web of Science) | |
dc.relation.isreferencedby | Scopus | |
dc.source.uri | https://doi.org/10.1016/j.ymssp.2021.108482 | |
dc.title | Deep learning based virtual point tracking for real-time target-less dynamic displacement measurement in railway applications | |
dc.type | Straipsnis Web of Science DB / Article in Web of Science DB | |
dcterms.references | 46 | |
dc.type.pubtype | S1 - Straipsnis Web of Science DB / Web of Science DB article | |
dc.contributor.institution | Technical University of Berlin | |
dc.contributor.institution | Vilniaus Gedimino technikos universitetas | |
dc.contributor.institution | Sapienza University of Rome | |
dc.contributor.faculty | Transporto inžinerijos fakultetas / Faculty of Transport Engineering | |
dc.subject.researchfield | T 003 - Transporto inžinerija / Transport engineering | |
dc.subject.researchfield | T 001 - Elektros ir elektronikos inžinerija / Electrical and electronic engineering | |
dc.subject.studydirection | E12 - Transporto inžinerija / Transport engineering | |
dc.subject.vgtuprioritizedfields | TD0101 - Autonominis sausumos ir oro transportas / Autonomous land and air transport | |
dc.subject.ltspecializations | L106 - Transportas, logistika ir informacinės ir ryšių technologijos (IRT) / Transport, logistic and information and communication technologies | |
dc.subject.en | point tracking | |
dc.subject.en | computer vision | |
dc.subject.en | displacement measurement | |
dc.subject.en | photogrammetry | |
dc.subject.en | deep learning | |
dc.subject.en | railway | |
dcterms.sourcetitle | Mechanical systems and signal processing | |
dc.description.volume | vol. 166 | |
dc.publisher.name | Elsevier | |
dc.publisher.city | London | |
dc.identifier.doi | 000711292800007 | |
dc.identifier.doi | 10.1016/j.ymssp.2021.108482 | |
dc.identifier.elaba | 107240290 | |