Aiming at the problem of poor accuracy of automatic region division of mouse brain slice image using traditional multimodal registration method,an unsupervised multimodal region division method of brain slice image was proposed. Firstly,based on the mouse brain map,the Atlas brain map and the Average Template brain map in the Allen Reference Atlases (ARA) database corresponding to the brain slice region division were obtained. Then the Average Template brain map and the mouse brain slices were pre-registered and modal transformed by affine transformation preprocessing and Principal Component Analysis Net-based Structural Representation(PCANet-SR)network processing. After that,according to U-net and the spatial transformation network,the unsupervised registration was realized,and the registration deformation relationship was applied to the Atlas brain map. Finally,the edge contour of the Atlas brain map extracted by the registration deformation was merged with the original mouse brain slices in order to realize the region division of the brain slice image. Compared with the existing PCANet-SR+B spline registration method,experimental results show that the Root Mean Square Error(RMSE)of the registration accuracy index of this method reduced by 1. 6%,the Correlation Coefficient(CC)and the Mutual Information(MI)increased by 3. 5% and 0. 78% respectively. The proposed method can quickly realize the unsupervised multimodal registration task of the brain slice image,and make the brain slice regions be divided accurately.

In order to improve the accuracy of behavior recognition of multi-athletes in football game video, a behavior representation method of multi-athletes for video football game based on scale adaptive local spatial and temporal characteristics was put forward. Behavior recognition was carried on using spatial-timporal interest point to represent behavior of multi-athletes in video football game. Firstly, multi-athletes behavior in the sequence of video football game was regarded as a collection of spatial-timporal interest points in three-dimensional space. Secondly, the set of spatial-temporal interest points was quantified as histogram which has fixed dimension (ie temporal word) by using quantitative technique of histogram. Finally, spatial-temporal codebook was generated by using K-means clustering algorithm. Each spatial-timporal interest point was normalized to ensure its scaling and translation invariance before clustering codebook generated. Experimental results show that the proposed method can greatly reduce the computational amount of the algorithm,and the accuracy of recognition can be significantly improved.