Automatic Roadside Camera Calibration with Transformers

In this paper, we propose a more practical and accurate method for calibrating the roadside camera used in traffic surveillance systems. Considering the characteristics of the traffic scenes, we propose a minimum calibration condition that consists of two vanishing points and a vanishing line, which can be easily satisfied in most traffic scenes. Based on the minimum calibration condition, we provide a calibration method to estimate camera intrinsic parameters and rotation angles, which employs least squares optimization instead of closed-form computation. Compared with the existing calibration methods, our method is suitable for more traffic scenes and is able to accurately determine more camera parameters including the principal point. By making full use of video information, multiple observations of the vanishing points are available from different objects. For more accurate calibration, we present a dynamic calibration method using these observations to correct camera parameters. As for the estimation of the camera translation vector, known lengths in the road or known heights above the road are exploited. The experimental results on synthetic data and real traffic images demonstrate the accuracy, robustness, and practicability of the proposed calibration method.

Some tasks in the construction industry and urban management field such as site selection and fire response management are usually managed by using a Geographical Information System (GIS), as the tasks in these processes require a high level and amount of integrated geospatial information. Recently, a key element of this integrated geospatial information to emerge is detailed geometrical and semantic information about buildings. In parallel, Building Information Models (BIMs) of today have the capacity for storing and representing such detailed geometrical and semantic information. In this context, the research aimed to investigate the applicability of BIMs in geospatial environment by focusing specifically on these two domains; site selection and fire response management. In the first phase of the research two use case scenarios were developed in order to understand the processes in these domains in a more detailed manner and to establish the scope of a possible software development for transferring information from BIMs into the geospatial environment. In the following phase of the research two data models were developed – a Schema-Level Model View and a geospatial data model. The Schema-Level Model View was used in simplifying the information acquired from the BIM, while the geospatial data model acted as the template for creating physical files and databases in the geospatial environment. Following this, three software components to transfer building information into the geospatial environment were designed, developed, and validated. The first component served for acquiring the building information from the BIM, while the latter two served for transforming the information into the geospatial environment. The overall research demonstrated that it is possible to transfer (high level of geometric and semantic) information acquired from BIMs into the geospatial environment. The results also demonstrated that BIMs provide a sufficient level and amount of (geometric and semantic) information (about the building) for the seamless automation of data management tasks in the site selection and fire response management processes.

<title>Abstract</title> A critical challenge in volcanic seismology is the human interpretation of complex seismo-acoustic signals, which hinders the development of reliable warning systems for hazards (lahars, for instance) in active regions, such as Costa Rica. Computational methods for early warnings struggle with high background noise and manual parameter tuning, making reliable and reproducible analysis difficult. To address this, we developed a comprehensive computational framework for automated evaluation and optimization of volcanic eruption detectors. The solution proposed performs a seismo-acoustic analysis of time-series data, employing a partial waveform stacking strategy with an adaptive Z-detector as the characteristic function for event triggering. A key contribution of this work is its configurable brute-force optimization strategy, which systematically tunes detector parameters by evaluating the predictions against real-world event catalogs. This approach overcomes significant challenges in this research field, such as manual and suboptimal tuning methods, by measuring the uncertainty of the detection performed with different parameter combinations. Initial experiments on a single day's data from a Costa Rican volcano yielded perfect classification, achieving an F1-score of 1.00. However, scaling the methodology to a full month of data resulted in a significant decrease in performance (F1-score 0.27). Despite the diminished performance on the complete dataset, this preliminary research constitutes a crucial advancement over manual, inefficient tuning methods, offering a more reproducible and analytical approach to the field of volcano-seismology.

TEFISTA-Net: A learnable method for high-resolution range profile reconstruction with low-frequency ultra-wideband radar

Piscis: A loss estimator of the F1 score enables accurate spot detection in fluorescence microscopy images via deep learning.

We present a statistical learning framework for robust identification of differential equations from noisy spatio-temporal data. We address two issues that have so far limited the application of such methods, namely their robustness against noise and the need for manual parameter tuning, by proposing stability-based model selection to determine the level of regularization required for reproducible inference. This avoids manual parameter tuning and improves robustness against noise in the data. Our stability selection approach, termed PDE-STRIDE, can be combined with any sparsity-promoting regression method and provides an interpretable criterion for model component importance. We show that the particular combination of stability selection with the iterative hard-thresholding algorithm from compressed sensing provides a fast and robust framework for equation inference that outperforms previous approaches with respect to accuracy, amount of data required, and robustness. We illustrate the performance of PDE-STRIDE on a range of simulated benchmark problems, and we demonstrate the applicability of PDE-STRIDE on real-world data by considering purely data-driven inference of the protein interaction network for embryonic polarization in Caenorhabditis elegans. Using fluorescence microscopy images of C. elegans zygotes as input data, PDE-STRIDE is able to learn the molecular interactions of the proteins.

In recent years, dynamic local search (DLS) clause weighting algorithms have emerged as the local search state-of-the-art for solving propositional satisfiability problems. However, most DLS algorithms require the tuning of domain dependent parameters before their performance becomes competitive. If manual parameter tuning is impractical then various mechanisms have been developed that can automatically adjust a parameter value during the search. To date, the most effective adaptive clause weighting algorithm is RSAPS. However, RSAPS is unable to convincingly outperform the best non-weighting adaptive algorithm AdaptNovelty + , even though manually tuned clause weighting algorithms can routinely outperform the Novelty + heuristic on which AdaptNovelty + is based.In this study we introduce R+DDFW + , an enhanced version of the DDFW clause weighting algorithm developed in 2005, that not only adapts the total amount of weight according to the degree of stagnation in the search, but also incorporates the latest resolution-based preprocessing approach used by the winner of the 2005 SAT competition (R+ AdaptNovelty + ). In an empirical study we show R+DDFW + improves on DDFW and outperforms the other leading adaptive (R+Adapt-Novelty + , R+RSAPS) and non-adaptive (R+G2WSAT) local search solvers over a range of random and structured benchmark problems.

Semantic segmentation technology in traffic scenes can help vehicles make accurate analyses and positioning of the road ahead. In traffic scenarios, the trade-off between real-time performance and the accuracy of semantic segmentation is particularly important. This paper proposes a lightweight deep convolutional network, which can be applied to traffic scenes to complete accurate semantic segmentation tasks, considering both real-time performance and accuracy. The Cross Channel Attention Fusion Mechanism proposed in this paper can better integrate the context information and improve accuracy. The Depth-wise Separable Pyramid Module proposed based on the feature pyramid idea can improve the segmentation accuracy and effectively trade off the real-time performance.

At the current stage, the rapid Development of autonomous driving has made object detection in traffic scenarios a vital research task. Object detection is the most critical and challenging task in computer vision. Deep learning, with its powerful feature extraction capabilities, has found widespread applications in safety, military, and medical fields, and in recent years has expanded into the field of transportation, achieving significant breakthroughs. This survey is based on the theory of deep learning. It systematically summarizes the Development and current research status of object detection algorithms, and compare the characteristics, advantages and disadvantages of the two types of algorithms. With a focus on traffic signs, vehicle detection, and pedestrian detection, it summarizes the applications and research status of object detection in traffic scenarios, highlighting the strengths, limitations, and applicable scenarios of various methods. It introduces techniques for optimizing object detection algorithms, summarizes commonly used object detection datasets and traffic scene datasets, along with evaluation criteria, and performs comparative analysis of the performance of deep learning algorithms. Finally, it concludes the development trends of object detection algorithms in traffic scenarios, providing research directions for intelligent transportation and autonomous driving.

Accurate identification of road object is crucial for intelligent traffic systems. However, due to the complexity of road traffic scenarios, developing efficient and accurate road object detection methods has been a challenging task. In this study, a new improved method for road object detection is proposed, named Enhanced YOLOv5 algorithm and Deep Schedule Object Detection (DSOD) algorithm. Real traffic scenes from the BDD100k dataset are used for training and testing the object detection model. The dataset consists of 9 different types of road objects in various traffic scenarios. The Mosaic data augmentation algorithm is applied to merge images in the dataset. Mean Average Precision (mAP), Precision (P), and Recall (R) are used as evaluation metrics to compare the enhanced YOLOv5 model with the most common models. Experimental results demonstrate that the DSOD algorithm achieves success in intelligent traffic object detection, significantly improving the accuracy and robustness of road object recognition. Additionally, the developed model shows significant performance improvement in accurately identifying objects in complex traffic scenes. These results suggest that the DSOD algorithm is a promising choice for intelligent road recognition and can easily adapt to different traffic scenarios. Furthermore, employing cloud computing for real-time detection meets the requirements of intelligent cooperative vehicles and enhances their visual perception capabilities.

<strong class="journal-contentHeaderColor">Abstract.</strong> Aeolian dust has significant impacts on climate, public health, infrastructure and ecosystems. Assessing dust concentrations and these impacts is challenging because the emissions depend on many environmental factors and can vary greatly with meteorological conditions. We present a data-driven aeolian dust scheme that combines machine learning components and physical equations to predict atmospheric dust concentrations and quantify the sources. The numerical scheme was trained to reproduce dust aerosol optical depth retrievals by the Infrared Atmospheric Sounding Interferometer on board the MetOp-A satellite. The input parameters included meteorological variables from the fifth generation atmospheric reanalysis of the European Centre for Medium-Range Weather Forecasts. The trained dust scheme can be applied as an emission submodel, to be used in climate and Earth system models, which is reproducibly derived from observational data so that a priori assumptions and manual parameter tuning can be largely avoided. We compared the trained emission submodel to a state-of-the-art emission parametrisation, showing that it substantially improves the representation of aeolian dust in the global atmospheric chemistry-climate model EMAC.

We study stochastic models to mitigate the risk of poor Quality-of-Service (QoS) in computational markets. Consumers whopurchase services expect both price and performance guarantees. They need to predict future demand to budget for sustained performance despite price fluctuations. Conversely, providers need to estimate demand to price future usage. The skewed and bursty nature of demand in large-scale computer networks challenges the common statistical assumptions of symmetry, independence, and stationarity. This discrepancy leads to under estimation of investment risk. We confirm this non-normal distribution behavior in our study of demand in computational markets.The high agility of a dynamic resource market requires flexible, efficient, and adaptable predictions. Computational needs are typically expressed using performance levels, hence we estimate worst-case bounds of price distributions to mitigate the risk of missing execution deadlines.To meet these needs, we use moving time windows of statistics to approximate price percentile functions. We use snapshots of summary statistics to calculate prediction intervals and estimate model uncertainty. Our approach is model-agnostic, distribution-free both in prices and prediction errors, and does not require extensive sampling nor manual parameter tuning. Our simulations and experiments show that a Chebyshev inequality model generates accurate predictions with minimal sample data requirements. We also show that this approach mitigates the risk of dropped service level performance when selecting hosts to run a bag-of-task Grid application simulation in a live computational market cluster.

Integrating Big Data, such as large-scale transcriptomic datasets across diseases, continues to be a major challenge. This is in part due to inconsistent preprocessing and the lack of a standardized, reproducible analytical framework. Existing pipelines often rely on manual parameter tuning and fragmented scripts, which limits cross-dataset comparability and downstream interpretability. We developed disint (disease integration and clustering toolkit), an open-source Python framework for standardized cross-dataset expression integration, embedding, and clustering. The pipeline implements housekeeping gene-based normalization, disease-specific log2 fold-change computation, automated Uniform Manifold Approximation and Projection hyperparameter optimization, and adaptive K-means clustering. Building on its outputs, we further implemented a prototype downstream module, disease reposition, which extracts disease-specific gene signatures, evaluates their shared components, and explores potential drug repositioning candidates. The framework was validated on 28 transcriptomic datasets encompassing 34 disease categories and 386 samples, including 255 patient and 131 healthy control samples, covering 194,182 genes in total. These results highlight the reproducibility, scalability, and translational versatility of our proposed framework.

This study takes the PUMA560 manipulator as the research object, selects its first three rotating joints to construct a 3-degree-of-freedom (3-DOF) manipulator system, and aims to improve the control accuracy of the manipulator and environmental adaptability. First, the Denavit-Hartenberg (DH) parameter method is used to establish the manipulator’s kinematic model; the MATLAB Robotics Toolbox is employed to define the link coordinate system, joint angles, link lengths, and other DH parameters, and a velocity ellipsoid is constructed to analyze the motion characteristics of the end effector. In the trajectory planning stage, the Joint Trajectory Planning (JTRAJ) function (for smooth interpolation in joint space) and the Cartesian Trajectory Planning (CTRAJ) function (for linear path interpolation at the end effector) are compared, and finally, the JTRAJ function is selected to plan the target path. To achieve precise control of the manipulator, a PID (Proportional-Integral-Derivative) control simulation model based on Simulink is built. Simulation results show that compared with manual parameter tuning, the PID control optimized by Genetic Algorithm (GA) has a smaller error fluctuation range, and the error tends to be stable at the end of the simulation, significantly improving the manipulator’s control robustness and trajectory accuracy. This study realizes the effective integration of machine learning and traditional control algorithms, providing a feasible solution for the optimization of manipulator adaptive control; future research can further explore the influence of parameter ranges and fitness function definitions on control effects, and improve data horizontal comparison to deepen the research.

The problem of extracting bearing weak fault features under variable-speed conditions with strong background noise interference remains challenging due to the limitations of existing feature extraction methods. These methods, especially those that rely on manual parameter tuning and rigid regularization, often struggle with noise suppression and robustness optimization, resulting in inaccurate extraction of weak fault features. To overcome this drawback, this study proposes a novel weak fault feature extraction method based on tensor decomposition model for bearings. First, the time–frequency tensor is constructed based on the short-time Fourier transform. Then, two types of fault properties in tensor are explored and an improved tensor decomposition model is proposed to realize the accurate extraction of weak fault features under variable-speed conditions. In addition, the decomposed feature tensor is conducted by a multichannel global energy-weighted fusion strategy, which significantly improves the robustness in extracting multichannel weak fault features. The effectiveness and superiority of the proposed method are systematically investigated through both simulated and experimental case studies. The results demonstrate that the method effectively eliminates background noise interference in measurements while augmenting the resolution of fault features.