ABSTRACT
Recently, new semantic segmentation and object detection methods have been proposed for the direct processing of three-dimensional (3D) LiDAR sensor point clouds. LiDAR can produce highly accurate and detailed 3D maps of natural and man-made environments and is used for sensing in many contexts due to its ability to capture more information, its robustness to dynamic changes in the environment compared to an RGB camera, and its cost, which has decreased in recent years and which is an important factor for many application scenarios. The challenge with high-resolution 3D LiDAR sensors is that they can output large amounts of 3D data with up to a few million points per second, which is difficult to process in real time when applying complex algorithms and models for efficient semantic segmentation. Most existing approaches are either only suitable for relatively small point clouds or rely on computationally intensive sampling techniques to reduce their size. As a result, most of these methods do not work in real time in realistic field robotics application scenarios, making them unsuitable for practical applications. Systematic point selection is a possible solution to reduce the amount of data to be processed. Although our approach is memory and computationally efficient, it selects only a small subset of points, which may result in important features being missed. To address this problem, our proposed systematic sampling method called SyS3DS (Systematic Sampling for 3D Semantic Segmentation) incorporates a technique in which the local neighbours of each point are retained to preserve geometric details. SyS3DS is based on the graph colouring algorithm and ensures that the selected points are non-adjacent in order to obtain a subset of points that are representative of the 3D points in the scene. To take advantage of the ensemble learning method, we pass a different subset of nodes for each epoch. This leverages a new technique called auto-ensemble, where ensemble learning is proposed as a collection of different learning models instead of tuning different hyperparameters individually during training and validation. SyS3DS has been shown to process up to 1 million points in a single pass. It outperforms the state of the art in efficient semantic segmentation on large datasets such as Semantic3D. We also present a preliminary study on the validity of the performance of LiDAR-only data, i.e., intensity values from LiDAR sensors without RGB values for semi-autonomous robot perception.
ABSTRACT
The strengthening of concrete structures with laminates of Carbon-Fiber-Reinforced Polymers (CFRP) is a widely adopted technique. retained The application is more effective if pre-stressed CFRP laminates are adopted. The measurement of the strain level during the pre-stress application usually involves laborious and time-consuming applications of instrumentation. Thus, the development of expedited approaches to accurately measure the pre-stressed application in the laminates represents an important contribution to the field. This paper proposes and benchmarks contact-free architecture for measuring the strain level of CFRP laminate based on computer vision. The main objective is to provide a solution that might be economically feasible, automated, easy to use, and accurate. The architecture is fed by digitally deformed synthetic images, generated based on a low-resolution camera. The adopted methods range from traditional machine learning to deep learning. Furthermore, dropout and cross-validation methods for quantifying traditional machine learning algorithms and neural networks are used to efficiently provide uncertainty estimates. ResNet34 deep learning architecture provided the most accurate results, reaching a root mean square error (RMSE) of 0.057‱ for strain prediction. Finally, it is important to highlight that the architecture presented is contact-free, automatic, cost-effective, and measures directly on the laminate surfaces, which allows them to be widely used in the application of pre-stressed laminates.
