Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features

The commercial far-range (>10 m) spatial data collection methods for acquiring infrastructure’s geometric data are not completely automated because of the necessary manual pre- and/or post-processing work. The required amount of human intervention and, in some cases, the high equipment costs associated with these methods impede their adoption by the majority of infrastructure mapping activities. This paper presents an automated stereo vision-based method, as an alternative and inexpensive solution, to producing a sparse Euclidean 3D point cloud of an infrastructure scene utilizing two video streams captured by a set of two calibrated cameras. In this process SURF features are automatically detected and matched between each pair of stereo video frames. 3D coordinates of the matched feature points are then calculated via triangulation. The detected SURF features in two successive video frames are automatically matched and the RANSAC algorithm is used to discard mismatches. The quaternion motion estimation method is then used along with bundle adjustment optimization to register successive point clouds. The method was tested on a database of infrastructure stereo video streams. The validity and statistical significance of the results were evaluated by comparing the spatial distance of randomly selected feature points with their corresponding tape measurements.

Video segmentation with superpixels

Due to its importance, video segmentation has regained interest recently. However, there is no common agreement about the necessary ingredients for best performance. This work contributes a thorough analysis of various within- and between-frame affinities suitable for video segmentation. Our results show that a frame-based superpixel segmentation combined with a few motion and appearance-based affinities are sufficient to obtain good video segmentation performance. A second contribution of the paper is the extension of [1] to include motion-cues, which makes the algorithm globally aware of motion, thus improving its performance for video sequences. Finally, we contribute an extension of an established image segmentation benchmark [1] to videos, allowing coarse-to-fine video segmentations and multiple human annotations. Our results are tested on BMDS [2], and compared to existing methods. © 2013 Springer-Verlag.

Investigating landing gear noise using fly-over data: The case of a Boeing 747-400

Modeling the noise originating from a landing gear has proven to be a challenging task, because of its complicated structure. In full-scale, landing gear noise can only be investigated experimentally by source localization techniques and fly-over measurements with microphone arrays. In the present work, measurements of a Boeing B747-400 were used to determine the contribution of the landing gear to the overall noise emitted during a fly-over and how the broadband noise from the landing gear scales with the flight velocity. A tonal source from the nose landing gear was identified at 380 Hz with a harmonic at 760 Hz and it most likely originates from a cavity. It was also found that the Power Spectral Density (PSD) of the high frequency broadband component varies linearly with frequency and there is some scaling with the ow velocity. Finally, the nose landing gear was shown to be a significant contributor to the overall airframe noise as expected.