segmentation methods | Advantage | Disadvantage |
---|---|---|
Can detect the edges of different areas very intuitively for point cloud. | sensitive to noise and not suitable for objects with smooth surface changes. | |
More accurate than edge-based methods. | The segmentation result depends on the quality of the seeds and the merging rules. There will be over-segmentation or under-segmentation. | |
Fast segmentation speed, and heterogeneous,suitable for simple geometric models. | Difficult to use in complex scenarios. | |
Suitable for complex scenes. | Lack of real-time. | |
Point cloud segmentation has high accuracy, good recognition effect. | lack of real-time. |