Unifying Boundary, Region, Shape into Level Sets for Touching Object Segmentation in Train Rolling Stock High Speed Video

التفاصيل البيبلوغرافية
العنوان: Unifying Boundary, Region, Shape into Level Sets for Touching Object Segmentation in Train Rolling Stock High Speed Video
المؤلفون: Ch. Raghava Prasad, M. V. D. Prasad, D. Anil Kumar, M. Teja Kiran Kumar, P. V. V. Kishore, N. Sasikala, E. Kiran Kumar
المصدر: IEEE Access, Vol 6, Pp 70368-70377 (2018)
بيانات النشر: Institute of Electrical and Electronics Engineers (IEEE), 2018.
سنة النشر: 2018
مصطلحات موضوعية: General Computer Science, automated maintenance, business.industry, Computer science, 020208 electrical & electronic engineering, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, General Engineering, 02 engineering and technology, Image segmentation, computer vision based condition monitoring, Level set, High speed video, train rolling stock, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, General Materials Science, Segmentation, Computer vision, lcsh:Electrical engineering. Electronics. Nuclear engineering, Artificial intelligence, Level sets, hybrid high speed video segmentation, business, lcsh:TK1-9971, Boundary region
الوصف: Traditional level sets suffer from two major limitations: 1) unable to detect touching object boundaries and 2) segment partially occluded objects. In this paper, we present a model and simulation of a level set functional with unified knowledge of objects region, boundary, and shape models. The simulations of the proposed model were tested on high-speed videos of the train rolling stock for bogie part segmentation. The proposed model will resolve single- and multi-object segmentation of touching boundaries and partially occulted mechanical parts on a train bogie. Simulations on high-speed videos of four trains with 1 0720 frames have resulted in near perfect segmentation of 10 touching and occluded bogie parts. The proposed model performed better than the state-of-the-art level set segmentation models, showing faster and more accurate segmentations of moving mechanical parts in high-speed videos.
تدمد: 2169-3536
DOI: 10.1109/access.2018.2877712
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::30d5c5ad3e8215dc96c5314e9f54a2e3
https://doi.org/10.1109/access.2018.2877712
Rights: OPEN
رقم الانضمام: edsair.doi.dedup.....30d5c5ad3e8215dc96c5314e9f54a2e3
قاعدة البيانات: OpenAIRE
الوصف
تدمد:21693536
DOI:10.1109/access.2018.2877712