MoT - Mixture of trees probabilistic graphical model for video segmentation

We present a novel mixture of trees (MoT) graphical model for video segmentation. Each component in this mixture represents a tree structured temporal linkage between super-pixels from the first to the last frame of a video sequence. Our time-series model explicitly captures the uncertainty in temporal linkage between adjacent frames which improves segmentation accuracy. We provide a variational inference scheme for this model to estimate super-pixel labels and their confidences in nearly realtime. The efficacy of our approach is demonstrated via quantitative comparisons on the challenging SegTrack joint segmentation and tracking dataset [23].

The level and distribution of chromosomal aberration of tomato seeds at different penetration depths of carbon ions

The relationship between the penetration depth and the level and distribution of chromosomal aberration of the root tip cells were investigated by exposure of the superposed tomato seeds to 80 MeV/u carbon ions. The results showed that on the entrance of the beam the chromosomal aberration level was low. Damage such as breaks and gaps were dominant. At the Bragg peak, the chromosomal aberration level was high. The yields of dicentrics, rings and disintegrated small chromosomes increased but the yields of breaks and gaps decreased. These results are consistent with the distribution of the physical depth dose pro. le of carbon ions. It is effective to deposit the Bragg peak on the seeds to induce hereditary aberration in the mutation breeding with heavy ions.