No abstract

Measuring the similarity between point clouds is required in many areas. In autonomous driving, point clouds for 3D perception are estimated from camera images but these estimations are error-prone. Furthermore, there is a lack of measures for quality quantification using ground truth. In this paper, we derive conditions point cloud comparisons need to fulfill and accordingly evaluate the Chamfer distance, a lower bound of the Gromov Wasserstein metric, and the ratio measure. We show that the ratio measure is not affected by erroneous points and therefore introduce the new measure “average ratio”. All measures are evaluated and compared using exemplary point clouds. We discuss characteristics, advantages and drawbacks with respect to interpretability, noise resistance, environmental representation, and computation.

Sensory data is essential for the training of methods in autonomous driving like object detection, odometry, or SLAM. MEMS LiDAR sensors can be very valuable for autonomous vehicles because they are less prone to shock and wear compared to motorized optomechanical LiDAR sensors. Recording real-world data is complicated and expensive. An alternative is simulated data, but for MEMS LiDAR sensors there is no publicly available software to simulate this type of sensor. With this paper, we introduce a method to simulate data recorded by a MEMS LiDAR sensor like the Blickfeld Cube~1 (and other MEMS LiDAR sensors as well). For this, we use the open-source autonomous driving simulation environment CARLA (our method is available online\footnote[1]{https://github.com/BerensRWU/MEMS-LiDAR-Generator}). We compare our synthetic point cloud with a real-world point cloud and evaluate the similarity. Moreover, we demonstrate the application of our method on the problem of the optimal sensor configuration.

The scarcity of high-quality annotated data is omnipresent in machine learning. Especially in biomedical segmentation applications, experts need to spend a lot of their time into annotating due to the complexity. Hence, methods to reduce such efforts are desired. Methods: Self-Supervised Learning (SSL) is an emerging field that increases performance when unannotated data is present. However, profound studies regarding segmentation tasks and small datasets are still absent. A comprehensive qualitative and quantitative evaluation is conducted, examining SSL's applicability with a focus on biomedical imaging. We consider various metrics and introduce multiple novel application-specific measures. All metrics and state-of-the-art methods are provided in a directly applicable software package (https://osf.io/gu2t8/). Results: We show that SSL can lead to performance improvements of up to 10%, which is especially notable for methods designed for segmentation tasks. Conclusion: SSL is a sensible approach to data-efficient learning, especially for biomedical applications, where generating annotations requires much effort. Additionally, our extensive evaluation pipeline is vital since there are significant differences between the various approaches. Significance: We provide biomedical practitioners with an overview of innovative data-efficient solutions and a novel toolbox for their own application of new approaches. Our pipeline for analyzing SSL methods is provided as a ready-to-use software package.

In autonomous driving, prediction tasks address complex spatio-temporal data. This article describes the examination of Recurrent Neural Networks (RNNs) for object trajectory prediction in the image space. The proposed methods enhance the performance and spatio-temporal prediction capabilities of Recurrent Neural Networks. Two different data augmentation strategies and a hyperparameter search are implemented for this purpose. A conventional data augmentation strategy and a Generative Adversarial Network (GAN) based strategy are analyzed with respect to their ability to close the generalization gap of Recurrent Neural Networks. The results are then discussed using single-object tracklets provided by the KITTI Tracking Dataset. This work demonstrates the benefits of augmenting spatio-temporal data with GANs.