Joint optical flow estimation, segmentation, and 3D interpretation with level sets
Computer Vision and Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-frame simultaneous motion estimation and segmentation
IEEE Transactions on Consumer Electronics
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
Segmenting and tracking fluorescent cells in dynamic 3-D microscopy with coupled active surfaces
IEEE Transactions on Image Processing
Hi-index | 0.01 |
A new method is proposed for joint tracking of cell morphology and motion from 3D temporal cellular images. We adopt the framework of region-based active contours for segmentation, which is able to cope with objects having blurred boundaries. Motion estimation is performed by optical flow to increase the robustness and accuracy. Cell morphology and motion are modelled via a unified energy formulation and estimated iteratively searching for the minimum energy configuration. Experiments are carried out on synthetic and real cellular images to demonstrate the performance of the method.