Search Results (10)

The automatic identification and three-dimensional reconstruction of house plans has emerged as a significant research direction in intelligent building and smart city applications. Three-dimensional models reconstructed from two-dimensional floor plans provide more intuitive visualization for building safety assessments and spatial suitability evaluations. To address the limitations of existing public datasets—including low quality, inaccurate annotations, and poor alignment with residential architecture characteristics—this study constructs a high-quality vector dataset of raster house plans. We collected and meticulously annotated over 5000 high-quality floor plans representative of urban housing typologies, covering the majority of common residential layouts in the region. For architectural element recognition, we propose a key point-based detection approach for walls, doors, windows, and scale indicators. To improve wall localization accuracy, we introduce CPN-Floor, a method that achieves precise key point detection of house plan primitives. By generating and filtering candidate primitives through axial alignment rules and geometric constraints, followed by post-processing to refine the positions of walls, doors, and windows, our approach achieves over 87% precision and 88% recall, with positional errors within 1% of the floor plan’s dimensions. Scale recognition combines YOLOv8 with Shi–Tomasi corner detection to identify measurement endpoints, while leveraging the pre-trained multimodal OFA-OCR model for digital character recognition. This integrated solution achieves scale calculation accuracy exceeding 95%. We design and implement a house model recognition and 3D reconstruction system based on the WebGL framework and use the front-end MVC design pattern to interact with the data and views of the house model. We also develop a high-performance house model recognition and reconstruction system to support the rendering of reconstructed walls, doors, and windows; user interaction with the reconstructed house model; and the history of the house model operations, such as forward and backward functions. Full article

Failures in solar photovoltaic (PV) modules generate heat, leading to various hotspots observable in infrared images. Automated hotspot detection technology enables rapid fault identification in PV systems, while PV array detection, leveraging geometric cues from infrared images, facilitates the precise localization of defects. This study tackles the complexities of detecting PV array regions and diverse hotspot defects in infrared imaging, particularly under the conditions of complex backgrounds, varied rotation angles, and the small scale of defects. The proposed model encodes infrared images to extract semantic features, which are then processed through an PV array detection branch and a hotspot detection branch. The array branch employs a diffusion-based anchor-free mechanism with rotated bounding box regression, enabling the robust detection of arrays with diverse rotational angles and irregular layouts. The defect branch incorporates a novel inside-awareness loss function designed to enhance the detection of small-scale objects. By explicitly modeling the dependency distribution between arrays and defects, this loss function effectively reduces false positives in hotspot detection. Experimental validation on a comprehensive PV dataset demonstrates the superiority of the proposed method, achieving a mean average precision (mAP) of 71.64% for hotspot detection and 97.73% for PV array detection. Full article

Variation prediction and quality control for complex-shaped workpieces in automotive and aerospace fields with multi-stage machining processes have drawn significant attention because of the widespread application and increasing diversity of these kinds of workpieces. To finish the final workpieces with complex shapes, multiple setups and operations are often applied in machining processes. However, sources of geometric error, such as fixture error, datum error, machine tool path error, and the dimensional quality of the product, interact complicatedly at different stages. These complex interactions pose significant challenges to final product error prediction and reduction. Manufacturing error prediction based on stream of variation is an effective way to control the machining quality. However, there are few integrated models that can describe the interactions among types of geometric error sources from different stages for different kinds of complex workpieces. This paper proposes a modified error prediction model to systematically capture the interactions of different error sources among different operations for complex-shaped workpieces in multi-stage machining processes. Using differential motion vectors, the connection of all key variations from machine, fixture, and workpiece is established. This modified model can not only handle general fixture layouts for complex workpieces, but also introduce machining-induced variations. Based on this model, the main error sources identification method and error compensation method are proposed. In order to evaluate the effectiveness of the proposed method, engine blocks are used to be machined as an example. Compared with a machining process without a compensating strategy, the average machining error of the key feature is reduced by 80.5% after compensating for the main error sources. Full article

Problems such as complex image backgrounds, low image quality, diverse text forms, and similar or common character layouts in different script categories in natural scenes pose great challenges to scene script identification. This paper proposes a new Res2Net-based improved script identification method, namely FAS-Res2Net. In the feature extraction part, the feature pyramid network (FPN) module is introduced, which is beneficial to aggregate the geometric feature information extracted by the shallow network and the semantic feature information extracted by the deep network. Integrating the Adaptive Spatial Feature Fusion (ASFF) module is beneficial to obtain local feature information for optimal weight fusion. In addition, the global feature information of the image is extracted by introducing the swin transformer coding block, which makes the extracted feature information more abundant. In the classification part, the convolutional classifier is used to replace the traditional Linear classification, and the classification confidence of each category is output, which improves the identification efficiency. The improved algorithm achieved identification rates of 94.7% and 96.0% on public script identification datasets SIW-13 and CVSI-2015, respectively, which verified the superiority of the method. Full article

This paper presents a detailed algorithm for determining the curvature of a track axis with the use of a moving chord method, and then discusses the procedure for identifying the geometric layout of an exploited railway route on the basis of the determined curvature. In the moving chord method, the measured coordinates of the track axis allow one to directly determine the existence of the horizontal curvature without the need for additional measurements. This enables comprehensively identifying the existing geometric elements—straight lines, circular arcs, and transition curves. The conducted activities were illustrated with a calculation example, including a 5.5 km long test section with five areas of directional change. This showed a sequential procedure that led to the solution of the given problem. Based on the curvature diagram, the coordinates of the segmentation points, which define the connections of the existing geometric elements with each other, were determined. Full article

The layout of microseismic monitoring (MSM) station networks is very important to ensure the effectiveness of source location inversion; however, it is difficult to meet the complexity and mobility requirements of the technology in this new era. This paper proposes a network optimization method based on the geometric parameters of the proposed sensor-point database. First, according to the monitoring requirements and mine-working conditions, the overall proposed point database and model are built. Second, through the developed model, the proposed coverage area, envelope volume, effective coverage radius, and minimum energy level induction value are comprehensively calculated, and the evaluation reference index is constructed. Third, the effective maximum envelope volume is determined by taking the analyzed limit of monitoring induction energy level as the limit. Finally, the optimal design method is identified and applied to provide a sensor station layout network with the maximum energy efficiency. The method, defined as the S-V-E-R-V model, is verified by a comparison with the existing layout scheme and numerical simulation. The results show that the optimization method has strong practicability and efficiency, compared with the mine’s layout following the current method. Simulation experiments show that the optimization effect of this method meets the mine’s engineering requirements for the variability, intelligence, and high efficiency of the microseismic monitoring station network layout, and satisfies the needs of event identification and location dependent on the station network. Full article

We present the main assumptions about the algorithmization of the analysis of measurement data recorded in mobile satellite measurements. The research team from the Gdańsk University of Technology and the Maritime University in Gdynia, as part of a research project conducted in cooperation with PKP PLK (Polish Railway Infrastructure Manager), developed algorithms supporting the identification and assessment of track axis layout. This article presents selected issues concerning the identification of a tramway line’s axis system. For this purpose, the supporting algorithm was developed and measurement data recorded using Global Navigation Satellite System (GNSS) techniques was evaluated and analyzed. The discussed algorithm identifies main track directions from multi-device data and repeated position recordings. In order to observe the influence of crucial factors, the investigated route was carefully selected. The chosen tramway track was characterized by its location in various field conditions and a diversified and complex geometric layout. The analysis of the obtained results was focused on the assessment of the signal’s dispersion and repeatability using residuals in relation to the estimated track’s direction. The presented methodology is intended to support railway infrastructure management processes, mainly in planning and maintenance through an efficient inventory of the infrastructure in service. Full article

The safety of at grade road intersections is a relevant issue with social, economic, and environmental implications. It is related to the behavior of a driver approaching an intersection that, in its turn, is affected by kinematic and physiological variables. This study proposes a model to calculate the intersection operation time (IOT) for typical non-signalized 4-leg and 3-leg (or T-leg) urban intersections. Data available in the literature have been considered in order to identify the points of interest and assess the number and the time of a driver’s eye fixation on them. When approaching an intersection, the probability of glancing in a particular area changes with the distance to the yield or stop line; for this reason, a probabilistic approach was used to model the phenomenon. All possible maneuvers have been considered: left turning, right turning, and through-movement. The proposed model allowed an objective comparison between time spent by drivers for various maneuvers and layout conditions, and identification of the critical conditions. Indeed, significant differences in terms of IOT were found: they could lead to modification of the traffic management considering different needs of road users, traffic demand, and geometrical and functional constraints. Full article

In this paper, we investigate the stochastic effects of the microstructure of polysilicon films on the overall response of microelectromechanical systems (MEMS). A device for on-chip testing has been purposely designed so as to maximize, in compliance with the production process, its sensitivity to fluctuations of the microstructural properties; as a side effect, its sensitivity to geometrical imperfections linked to the etching process has also been enhanced. A reduced-order, coupled electromechanical model of the device is developed and an identification procedure, based on a genetic algorithm, is finally adopted to tune the parameters ruling microstructural and geometrical uncertainties. Besides an initial geometrical imperfection that can be considered specimen-dependent due to its scattering, the proposed procedure has allowed identifying an average value of the effective polysilicon Young’s modulus amounting to 140 GPa, and of the over-etch depth with respect to the target geometry layout amounting to $O=-0.09$ $\mathsf{\mu }$ m. The procedure has been therefore shown to be able to assess how the studied stochastic effects are linked to the scattering of the measured input–output transfer function of the device under standard working conditions. With a continuous trend in miniaturization induced by the mass production of MEMS, this study can provide information on how to handle the foreseen growth of such scattering. Full article

The paper proposes an information technology framework for the development of an embedded remote system for non-destructive observation and study of sensitive archaeological sites. The overall concept and motivation are described. The general hardware layout and software configuration are presented. The paper concentrates on the implementation of the following informational technology components: (a) a geographically unique identification scheme supporting a global key space for a key-value store; (b) a common method for octree modeling for spatial geometrical models of the archaeological artifacts, and abstract object representation in the global key space; (c) a broadcast of the archaeological information as an Extensible Markup Language (XML) stream over the Web for worldwide availability; and (d) a set of testing methods increasing the fault tolerance of the system. This framework can serve as a foundation for the development of a complete system for remote archaeological exploration of enclosed archaeological sites like buried churches, tombs, and caves. An archaeological site is opened once upon discovery, the embedded computer system is installed inside upon a robotic platform, equipped with sensors, cameras, and actuators, and the intact site is sealed again. Archaeological research is conducted on a multimedia data stream which is sent remotely from the system and conforms to necessary standards for digital archaeology. Full article