Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal con- straints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).
An approach for generating interactive 3D graphical visualization of the genetic architectures of complex traits in multiple environments is described. 3D graphical visualization is utilized for making improvements on traditional plots in quan- titative trait locus (QTL) mapping analysis. Interactive 3D graphical visualization for abstract expression of QTL, epistasis and their environmental interactions for experimental populations was developed in framework of user-friendly software QTLNetwork (http://ibi.zju.edu.cn/software/qtlnetwork). Novel definition of graphical meta system and computation of virtual coordinates are used to achieve explicit but meaningful visualization. Interactive 3D graphical visualization for QTL analysis provides geneticists and breeders a powerful and easy-to-use tool to analyze and publish their research results.
HU Cheng-chengYE Xiu-ziZHANG YinYU Rong-dongYANG JianZHU Jun
