Visual perception modeling for intelligent avatars can play subsidiary roles in controlling the behavior and animation of avatars in Intelligent Virtual Environments (IVE). We present a visual perception recognition model by integrating the color model, 3D object matching, sensors perception and path planning, therefore, it is quite useful for the avatar to make appropriate decisions in real-time in an IVE. In our approach, the 3D objects in the IVE are recognized and the moving directions of the avatar are obtained by using the avatar’s perception viewpoint and sensor. The avatar’s path planning employs our motion path synthesis proposed previously, called two-stage process synthesis. Experimental results show the efficiency and high prospect of our approach.