论文阅读 [TPAMI-2022] Differential Viewpoints for Ground Terrain Material Recognition

论文阅读 [TPAMI-2022] Differential Viewpoints for Ground Terrain Material Recognition

论文搜索(studyai.com)

搜索论文: Differential Viewpoints for Ground Terrain Material Recognition

搜索论文: http://www.studyai.com/search/whole-site/?q=Differential+Viewpoints+for+Ground+Terrain+Material+Recognition

关键字(Keywords)

Databases; Image recognition; Cameras; Robots; Lighting; Image capture; Material recognition; deep convolutional neural networks; texture reflectance; robot navigation

机器视觉; AI与交通

自动驾驶; 图像分类; 室外场景; 材料分类识别

摘要(Abstract)

Computational surface modeling that underlies material recognition has transitioned from reflectance modeling using in-lab controlled radiometric measurements to image-based representations based on internet-mined single-view images captured in the scene.

作为材料识别基础的计算表面建模已经从使用实验室控制辐射测量的反射建模过渡到基于互联网挖掘的场景中捕获的单视图图像的图像表示。.

We take a middle-ground approach for material recognition that takes advantage of both rich radiometric cues and flexible image capture.

我们采用了一种中间地带的材料识别方法，该方法利用了丰富的辐射测量线索和灵活的图像捕获。.

A key concept is differential angular imaging, where small angular variations in image capture enables angular-gradient features for an enhanced appearance representation that improves recognition.

一个关键概念是差分角度成像，在这种成像中，图像捕获中的小角度变化可以利用角度梯度特征来增强外观表现，从而提高识别能力。.

We build a large-scale material database, Ground Terrain in Outdoor Scenes (GTOS) database, to support ground terrain recognition for applications such as autonomous driving and robot navigation.

我们建立了一个大规模的材料数据库，室外场景中的地面地形（GTOS）数据库，以支持自动驾驶和机器人导航等应用中的地面地形识别。.

The database consists of over 30,000 images covering 40 classes of outdoor ground terrain under varying weather and lighting conditions.

该数据库由30000多幅图像组成，涵盖了不同天气和光照条件下的40类室外地面地形。.

We develop a novel approach for material recognition called texture-encoded angular network (TEAN) that combines deep encoding pooling of RGB information and differential angular images for angular-gradient features to fully leverage this large dataset.

我们开发了一种新的材料识别方法，称为纹理编码角度网络（TEAN），它结合了RGB信息的深度编码池和角度梯度特征的差分角度图像，以充分利用这个大型数据集。.

With this novel network architecture, we extract characteristics of materials encoded in the angular and spatial gradients of their appearance.

利用这种新颖的网络结构，我们提取了编码在其外观的角度和空间梯度中的材料特征。.

Our results show that TEAN achieves recognition performance that surpasses single view performance and standard (non-differential/large-angle sampling) multiview performance…

我们的结果表明，TEAN的识别性能优于单视图性能和标准（非差分/大角度采样）多视图性能。。.

作者(Authors)

[‘Jia Xue’, ‘Hang Zhang’, ‘Ko Nishino’, ‘Kristin J. Dana’]