Unifying Boundary, Region, Shape into Level Sets for Touching Object Segmentation in Train Rolling Stock High Speed Video
N. Sasikala,
P.V.V. Kishore,
Ch. Raghava Prasad,
E. Kiran Kumar,
D. Anil Kumar,
M. Teja Kiran Kumar,
M.V.D. Prasad
Affiliations
N. Sasikala
Department of Electronics and Communication Engineering, Biomechanics and Vision Computing Research Center, Koneru Lakshmaiah Education Foundation (Deemed to be University), Guntur, India
Department of Electronics and Communication Engineering, Biomechanics and Vision Computing Research Center, Koneru Lakshmaiah Education Foundation (Deemed to be University), Guntur, India
Ch. Raghava Prasad
Department of Electronics and Communication Engineering, Biomechanics and Vision Computing Research Center, Koneru Lakshmaiah Education Foundation (Deemed to be University), Guntur, India
E. Kiran Kumar
Department of Electronics and Communication Engineering, Biomechanics and Vision Computing Research Center, Koneru Lakshmaiah Education Foundation (Deemed to be University), Guntur, India
D. Anil Kumar
Department of Electronics and Communication Engineering, Biomechanics and Vision Computing Research Center, Koneru Lakshmaiah Education Foundation (Deemed to be University), Guntur, India
M. Teja Kiran Kumar
Department of Electronics and Communication Engineering, Biomechanics and Vision Computing Research Center, Koneru Lakshmaiah Education Foundation (Deemed to be University), Guntur, India
M.V.D. Prasad
Department of Electronics and Communication Engineering, Biomechanics and Vision Computing Research Center, Koneru Lakshmaiah Education Foundation (Deemed to be University), Guntur, India
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.
