An algorithm of two stages collision detection is presented for moving objectives in virtual scene. Firstly, AABB bounding box was used to test the intersection of interesting objects in coarse detection stage. Then combining space projection with Z-buffer algorithm, the potential intersecting objects in previous step were tested in precision detection stage, thus we can obtain objects collision data information and complete object collision detection. Finally experimental results show that the algorithm is more efficiency than traditional bounding box detection, the improved technology can realize further accurate collision detection.

Combining level set image segmentation with the prior shape information, we proposed an improved prior shape model in face recognition. Firstly, we introduced a local tensile invariant to X and Y direction and a shear invariant based on the shape statistics. Then, shape energy term with rotation, scale, shear and translation invariance was reconstructed in level set C-V model. The new model considers global and local image change and makes face contour evolving stably. Experimental results demonstrate that our model can segment obscured face images effectively.