A Novel Bimodal Forecasting Model for Solar Cycle 25

In this paper, a novel bimodal model to predict a complete sunspot cycle based on comprehensive precursor information is proposed. We compare the traditional 13 month moving average with the Gaussian filter and find that the latter has less missing information and can better describe the overall trend of the raw data. Unlike the previous models that usually only use one precursor, here we combine the implicit and geometric information of the solar cycle (peak and skewness of the previous cycle and start value of the predicted cycle) with the traditional precursor method based on the geomagnetic index and adopt a multivariate linear approach with a higher goodness of fit (>0.85) in the fitting. Verifications for cycles 22–24 demonstrate that the model has good performance in predicting the peak and peak occurrence time. It also successfully predicts the complete bimodal structure for cycle 22 and cycle 24, showing a certain ability to predict whether the next solar cycle is unimodal or bimodal. It shows that cycle 25 is a single-peak structure and that the peak will come in 2024 October with a peak of 145.3.

Real-Time LiDAR Point Cloud Semantic Segmentation for Autonomous Driving

LiDAR has been widely used in autonomous driving systems to provide high-precision 3D geometric information about the vehicle’s surroundings for perception, localization, and path planning. LiDAR-based point cloud semantic segmentation is an important task with a critical real-time requirement. However, most of the existing convolutional neural network (CNN) models for 3D point cloud semantic segmentation are very complex and can hardly be processed at real-time on an embedded platform. In this study, a lightweight CNN structure was proposed for projection-based LiDAR point cloud semantic segmentation with only 1.9 M parameters that gave an 87% reduction comparing to the state-of-the-art networks. When evaluated on a GPU, the processing time was 38.5 ms per frame, and it achieved a 47.9% mIoU score on Semantic-KITTI dataset. In addition, the proposed CNN is targeted on an FPGA using an NVDLA architecture, which results in a 2.74x speedup over the GPU implementation with a 46 times improvement in terms of power efficiency.

Denoising Diffusion MRI via Graph Total Variance in Spatioangular Domain

Diffusion MRI (DMRI) plays an essential role in diagnosing brain disorders related to white matter abnormalities. However, it suffers from heavy noise, which restricts its quantitative analysis. The total variance (TV) regularization is an effective noise reduction technique that penalizes noise-induced variances. However, existing TV-based denoising methods only focus on the spatial domain, overlooking that DMRI data lives in a combined spatioangular domain. It eventually results in an unsatisfactory noise reduction effect. To resolve this issue, we propose to remove the noise in DMRI using graph total variance (GTV) in the spatioangular domain. Expressly, we first represent the DMRI data using a graph, which encodes the geometric information of sampling points in the spatioangular domain. We then perform effective noise reduction using the powerful GTV regularization, which penalizes the noise-induced variances on the graph. GTV effectively resolves the limitation in existing methods, which only rely on spatial information for removing the noise. Extensive experiments on synthetic and real DMRI data demonstrate that GTV can remove the noise effectively and outperforms state-of-the-art methods.

CFNet: LiDAR-Camera Registration Using Calibration Flow Network

As an essential procedure of data fusion, LiDAR-camera calibration is critical for autonomous vehicles and robot navigation. Most calibration methods require laborious manual work, complicated environmental settings, and specific calibration targets. The targetless methods are based on some complex optimization workflow, which is time-consuming and requires prior information. Convolutional neural networks (CNNs) can regress the six degrees of freedom (6-DOF) extrinsic parameters from raw LiDAR and image data. However, these CNN-based methods just learn the representations of the projected LiDAR and image and ignore the correspondences at different locations. The performances of these CNN-based methods are unsatisfactory and worse than those of non-CNN methods. In this paper, we propose a novel CNN-based LiDAR-camera extrinsic calibration algorithm named CFNet. We first decided that a correlation layer should be used to provide matching capabilities explicitly. Then, we innovatively defined calibration flow to illustrate the deviation of the initial projection from the ground truth. Instead of directly predicting the extrinsic parameters, we utilize CFNet to predict the calibration flow. The efficient Perspective-n-Point (EPnP) algorithm within the RANdom SAmple Consensus (RANSAC) scheme is applied to estimate the extrinsic parameters with 2D–3D correspondences constructed by the calibration flow. Due to its consideration of the geometric information, our proposed method performed better than the state-of-the-art CNN-based methods on the KITTI datasets. Furthermore, we also tested the flexibility of our approach on the KITTI360 datasets.

An OpenBIM workflow to support collaboration between Acoustic Engineers and Architects

Architects require the insight of acoustic engineers to understand how to improve and/or optimize the acoustic performance of their buildings. Normally this is supported by the architect providing digital models of the design to the acoustic engineer for analysis in the acoustician’s disciplinary software, for instance Odeon. This current workflow suffers from the following challenges: (1) architects typically require feedback on architectural disciplinary models that have too much geometric information unnecessarily complicating the acoustic analysis process; (2) the acoustician then has to waste time simplifying that geometry, (3) finally, this extra work wastes money which could otherwise be spent on faster design iterations supported by frequent feedback between architects and acousticians early in the design process. This paper focuses on the architect / acoustician workflow, however similar challenges can be found in other disciplines. OpenBIM workflows provide opportunities to increase the standardization of processes and interfaces between disciplines by reducing the reliance on the proprietary discipline specific file formats and tools. This paper lays the foundation for an OpenBIM workflow to enable the acoustic engineer to provide near real time feedback on the acoustic performance of the architectural design. The proposed workflow investigates the use of the international standard IFC as a design format rather than simply an exchange format. The workflow is presented here with the intention that this will be further explored and developed by other researchers, architects and acousticians.