Robust Segmentation Based Tracing Using an Adaptive Wrapper for Inducing Priors

• Published in: IEEE transactions on image processing Vol. 22; no. 12; pp. 4952 - 4963
• Main Authors: Jagadeesh, Vignesh, Manjunath, Bangalore S., Anderson, James, Jones, Bryan W., Marc, Robert, Fisher, Steven K.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.12.2013; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Algorithms; Applied sciences; Biological and medical sciences; Computerized, statistical medical data processing and models in biomedicine; Connectome; electron micrograph; Exact sciences and technology; Facsimile; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image segmentation; Image sequences; Information, signal and communications theory; Markov Chains; Markov random fields; Mathematical model; Medical management aid. Diagnosis aid; Medical sciences; Microscopy, Electron, Transmission; Models, Theoretical; parameter adaptation; Reproducibility of Results; Signal processing; Surveillance; Telecommunications and information theory; Topology; Tracing; Performance evaluation; Multistage method; Probabilistic approach; Segmentation; Markov model; Algorithm; Flow field; Clutter; Markov random fields; Learning; Guidance; electron micrograph; parameter adaptation; Random field; Medical imagery; Tracing; Monitoring; Electrons
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2013.2280002

Segmentation based tracing algorithms detect the extent and borders of an object in a given frame IZ by propagating results from frames . Although application specific tracers have been forthcoming, techniques that automatically adapt across applications have been less explored. We approach this problem by learning a prior model on topological dynamics that encourages segmentation transitions across frames that are most likely for a given application. Further, we augment a generic tracing technique with a locality sensitive prior derived from dense optic flow fields for deformation guidance. The proposed approach comprises two stages where the generic tracer initially yields multiple segmentation transitions when its parameters are perturbed, and the learnt topology prior subsequently propagates high scoring segmentations. Because the learnt topology model wraps around a generic tracer and adapts it by setting its free parameters, the need for careful parameter tuning is completely obviated. Through extensive experimental validation in surveillance, biological and medical image datasets, we verify the applicability of the proposed model while demonstrating good tracing performance under severe clutter.