Category-level 6D object pose estimation aims at determining the pose of an object of a given category. Most current state-of-the-art methods require a significant amount of real training data to supervise their models. Moreover, annotating the 6D pose is very time consuming, error-prone, and it does not scale well to a large amount of object classes. Therefore, a handful of methods have recently been proposed to use unlabelled data to establish weak supervision. In this letter we propose a self-supervised method that leverages the 2D optical flow as a proxy for supervising the 6D pose. To this purpose, we estimate the 2D optical flow between consecutive frames based on the pose estimation. Then, we harness an off-the-shelf optical flow method to enable weak supervision using a 2D-3D optical flow based consistency loss. Experiments show that our approach for self-supervised learning yields state-of-the-art performance on the NOCS benchmark, and it reaches comparable results with some fully-supervised approaches.
15 March 2019 in IEEE Geoscience and Remote Sensing Letters
A novel formulation of the set cover problem is presented to find the optimal placement of the scan stations in a terrestrial laser scanning survey. The problem is formulated in 2-D by including sensor-based constraints such as coverage and overlap. The coverage constraint ensures a minimum density of horizontal scan lines on the ground. The overlap constraint enables automatic scan alignment and registration. The optimization problem takes into account both environment occlusions and a maximum allowed incidence angle of the laser beams. The adopted laser model includes fixed parameters such as laser height, angular resolution, field of view, and minimum and maximum sensor range. The sensor placement problem is solved using a numerical approach implemented on graphics processing unit (GPU). Thanks to the GPU acceleration, experiments have been performed in large-scale environments with internal structures.
22 November 2018 in IEEE Geoscience and Remote Sensing Letters
This letter presents a novel approach for automatic floorplan generation of indoor environments. The floorplan is computed from a large-scale point cloud obtained from registered terrestrial laser scans. In contrast to previous work, the proposed method does not assume either a flat ground, or flat ceiling, or planar walls. Moreover, the method exploits the detection of structural elements, i.e., parts having a constant section over the entire height of the building (such as walls and columns), which is beneficial in cluttered regions to compensate for the lack of information due to occlusions. The evaluation was performed in complex buildings, like industrial warehouses, that include machines and pallet racks, whose layout is included in the generated floorplan. The algorithm achieves a floorplan reconstruction with accuracy comparable to the resolution of the adopted sensor. Results are also compared to a ground truth acquired using a total station.