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

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.

Surface conductivity measurements in nanometric to micrometric foam films.

Foam films (a liquid lamella in air covered by surfactants) are tools of choice for nanofluidic characterization as they are intrinsically nanometric. Their size is indeed fixed by a balance between external pressure and particular molecular interactions in the vicinity of interfaces. To probe the exact nature of these interfaces, different characterizations can be performed. Among them, conductivity in confined systems is a direct probe of the electrostatic environment in the vicinity of the surface. Therefore, we designed a dedicated experiment to measure this conductivity in a cylindrical bubble coupled to interferometry for film thickness characterization. We then show that this conductivity depends on the surfactant nature. These conductivity measurements have been performed in an extremely confined system, the so called Newton black foam films. Unexpectedly in this case, a conductivity close to surface conductivity is recovered.