Learning Instance Motion Segmentation with Geometric Embedding

Zhen Leng*, Jing Chen, Songnan Lin

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

2 引用 (Scopus)

摘要

Most existing deep learning-based motion segmentation methods treat motion segmentation as a binary segmentation problem, which is generally not the real case in dynamic scenes. In addition, the object and camera motion are often mixed, making the motion segmentation problem difficult. This paper proposes a joint learning method which fuses semantic features and motion clues using CNNs with deformable convolution and a motion embedding module, to address multi-object motion segmentation problem. The deformable convolution module serves to fusion color and motion information. And the motion embedding module learns to distinguish objects' motion status with inspiration from geometric modeling methods. We perform extensive quantitative and qualitative experiments on benchmark datasets. Especially, we label over 9000 images of KITTI visual odometry dataset to help training the deformable module. Our method achieves superior performance in comparison to the current state-of-the-art in terms of speed and accuracy.

源语言英语
文章编号9380630
页(从-至)56812-56821
页数10
期刊IEEE Access
9
DOI
出版状态已出版 - 2021

指纹

探究 'Learning Instance Motion Segmentation with Geometric Embedding' 的科研主题。它们共同构成独一无二的指纹。

引用此