3D scene viewpoint selection based on chaos-particle swarm optimization
Feiyu Zhang, Mingxue Li, Xinran Wang, Meili Wang, Qing Tang · 2019
The efficiency in perception of 3D scenes is a significant problem. This paper presents a novel viewpoint evaluation method combining geometric and visual perception information. Firstly, we generalize the criteria of the best viewpoint selection from the references. Then, we introduce a dynamic inertia weight and Multi-start PSO algorithm into original particle swarm algorithm to prevent the problem of local optimum. Finally, we develop a system with friendly interfaces to demonstrate the practicality of our method. The experimental results verify that this approach can achieve viewpoint selection automatically and adapt to multi-model scene.