WatchPose: A View-Aware Approach for Camera Pose Data Collection in Industrial Environments

Sensors

卷:20

John See¹  Cong Yang²  Marie-Odile Berger²  Gilles Simon²  Wenyong Wang³ 

[1] Faculty of Computing and Informatics, Multimedia University, 63100 Cyberjaya, Selangor, Malaysia;

[2] MAGRIT Team, INRIA/LORIA, 54600 Nancy, France;

[3] School of Information Science and Technology, Northeast Normal University, 130000 Changchun, Jilin, China;

关键词: data acquisition;    augmented reality;    pose estimation;    deep learning;    industrial environments;   

DOI  :  10.3390/s20113045

来源: DOAJ

【 摘 要 】

Collecting correlated scene images and camera poses is an essential step towards learning absolute camera pose regression models. While the acquisition of such data in living environments is relatively easy by following regular roads and paths, it is still a challenging task in constricted industrial environments. This is because industrial objects have varied sizes and inspections are usually carried out with non-constant motions. As a result, regression models are more sensitive to scene images with respect to viewpoints and distances. Motivated by this, we present a simple but efficient camera pose data collection method, WatchPose, to improve the generalization and robustness of camera pose regression models. Specifically, WatchPose tracks nested markers and visualizes viewpoints in an Augmented Reality- (AR) based manner to properly guide users to collect training data from broader camera-object distances and more diverse views around the objects. Experiments show that WatchPose can effectively improve the accuracy of existing camera pose regression models compared to the traditional data acquisition method. We also introduce a new dataset, Industrial10, to encourage the community to adapt camera pose regression methods for more complex environments.

【 授权许可】

Unknown