arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.03070cs.CV
收藏

基于学习Stixel的实例分割

Learning Stixel-based Instance Segmentation

Kiel University(基尔大学);Daimler AG R&D(戴姆勒股份公司研发部)

Monty Santarossa, Lukas Schneider, Claudius Zelenka, Lars Schmarje, Reinhard Koch, Uwe Franke

摘要:

Stixels已成功应用于自动驾驶中的各种视觉任务,最近包括实例分割。然而,由于它们在图像中的稀疏出现,到目前为止,Stixels很少用作深度学习算法的输入,限制了它们在这种方法中的实用性。在这项工作中,我们提出了StixelPointNet,一种新的方法来执行快速实例分割直接对Stixels。通过将Stixel表示视为类似于点云的非结构化数据,PointNet等架构能够从Stixel中学习特征。我们使用一个限界框检测器来提出候选实例,从输入图像中提取相关的Stixels。在这些Stixels上,PointNet模型学习二进制分割,然后在最终的选择步骤中统一整个图像。StixelPointNet在Stixel级别上实现了最先进的性能,比基于像素的分割方法快得多,并表明通过我们的方法,Stixel域可以引入许多新的3D深度学习任务。

英文摘要:

Stixels have been successfully applied to a wide range of vision tasks in autonomous driving, recently including instance segmentation. However, due to their sparse occurrence in the image, until now Stixels seldomly served as input for Deep Learning algorithms, restricting their utility for such approaches. In this work we present StixelPointNet, a novel method to perform fast instance segmentation directly on Stixels. By regarding the Stixel representation as unstructured data similar to point clouds, architectures like PointNet are able to learn features from Stixels. We use a bounding box detector to propose candidate instances, for which the relevant Stixels are extracted from the input image. On these Stixels, a PointNet models learns binary segmentations, which we then unify throughout the whole image in a final selection step. StixelPointNet achieves state-of-the-art performance on Stixel-level, is considerably faster than pixel-based segmentation methods, and shows that with our approach the Stixel domain can be introduced to many new 3D Deep Learning tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑