#讀原始碼+論文# 三維點雲分割Deep Learning Based Semantic Labelling of 3D Point Cloud in Visual SLAM
阿新 • • 發佈:2018-11-27
from Deep Learning Based Semantic Labelling of 3D Point Cloud in Visual SLAM
-
超體素方法進行預分割,將點雲根據相似性變成表層面片(surface patches)降低計算複雜度。
將場景分割問題轉換為圖分割問題(graph partitioning problem)
- Method 1:Mean-shift聚類演算法 計算node之間的距離
-
node指的是每個patch,連線node之間的line就是相鄰patch的共邊;
- 距離可以是歐氏距離,也可以是馬氏距離;
- Mean-shift演算法可見簡單介紹及Python實現或者簡單的機器學習演算法Mean-shift演算法
缺點:計算量太大
- Method 2:利用面片的法向量方法 聚類 法向量可以表示出區域性凸性資訊。
缺點:當noise太多的時候可靠性降低。
- 最終使用method 2 結合可靠性平面來做分割 最後使用圖割法分割
關於2D Object Detection and Semantic Segmentation
An essential component to get semantic information is object detection
Semantic segmentation is to understand an image at a pixel level, which can label each pixel with a class identity. Similar to object detection, state-of-the-art semantic segmentation approaches also rely on CNN. FCN [4] by Long et al. is the first end-to-end system, which popularizes CNN architecture for semantic segmentation. U-Net [5] is a popular encoder-decoder architecture which can make use of annotated samples more efficiently and have a higher accuracy. SegNet [6] is a similar encoderdecoder architecture. SegNet copies indices from max-pooling for up-sampling, which makes it more memory efficient. RefineNet [7] proposes a method called RefineNet block which fuses both high resolution and low resolution features. It solves the problem of significant decrease in image resolution when we repeat the sub-sampling operation. PSPNet [8] introduces a pyramid pooling method to aggregate the context. DeepLab [9-11] utilizes dilated convolutions to increase the field of view.