arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.17064cs.CV
收藏

基于AI的密度识别

AI-based Density Recognition

Leibniz Supercomputing Centre (LRZ)(莱布尼茨超级计算中心(LRZ));German Aerospace Center (DLR)(德国航空航天中心(DLR));Ludwig-Maximilians-Universität (LMU)(慕尼黑大学(LMU))

Simone Müller, Daniel Kolb, Matthias Müller, Dieter Kranzlmüller

AI总结:

本文提出一种基于AI的概念,通过神经网络从2D图像中提取体积、材料和密度等物理属性,以优化移动与机器人领域的因果相关逻辑交互。

摘要:

基于学习的图像分析通常用于移动和机器人领域,以实现安全的环境运动和交互。这不仅需要物体识别,还需要为它们分配特定属性。借助这些信息,因果相关的动作可以适应不同情况。通过识别物体分配的属性,可以优化此类逻辑交互。密度作为一种物理属性,提供了识别物体多重、由何种材料制成、存在哪些作用力以及随之对环境产生何种影响的可能性。我们的方法引入了一种基于AI的概念,通过使用相关联的图像将物理属性分配给物体。基于合成数据,我们使用神经网络从2D图像中提取特定模式,以提取诸如体积、材料或密度等进一步信息。因此,我们讨论了基于属性的特征提取的可能性,以改善因果相关逻辑。

英文摘要:

Learning-based analysis of images is commonly used in the fields of mobility and robotics for safe environmental motion and interaction. This requires not only object recognition but also the assignment of certain properties to them. With the help of this information, causally related actions can be adapted to different circumstances. Such logical interactions can be optimized by recognizing object-assigned properties. Density as a physical property offers the possibility to recognize how heavy an object is, which material it is made of, which forces are at work, and consequently which influence it has on its environment. Our approach introduces an AI-based concept for assigning physical properties to objects through the use of associated images. Based on synthesized data, we derive specific patterns from 2D images using a neural network to extract further information such as volume, material, or density. Accordingly, we discuss the possibilities of property-based feature extraction to improve causally related logics.

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。

↑