Search

Kalman filter (KF)-based methods for 3D multi-object tracking (MOT) in autonomous driving often face challenges when detections are missed due to occlusions, sensor noise, or objects moving out of view. This leads to data association failures and cumulative errors in the update stage, as traditional Kalman filters rely on linear state estimates that can drift significantly without measurement updates. To address this issue, we propose an enhanced Kalman filter with dummy nodes and prediction confidence (KDPBTracker) to improve tracking continuity and robustness in these challenging scenarios. First, we designed dummy nodes to act as pseudo-observations generated from past and nearby frame detections in cases of missed detection, allowing for stable associations within the data association matrix when real detections were temporarily unavailable. To address the uncertainty in these dummy nodes, we then proposed a prediction confidence score to reflect their reliability in data association. Additionally, we modified a constant acceleration motion model combined with position-based heading estimation to better control high-dimensional numerical fluctuations in the covariance matrix, enhancing the robustness of the filtering process, especially in highly dynamic scenarios. We further designed bipartite graph data association to refine Kalman filter updates by integrating geometric and motion information weighted by the prediction confidence of the dummy nodes. Finally, we designed a confidence-based retention track management module to dynamically manage track continuity and deletion based on temporal and reliability thresholds, improving tracking accuracy in complex environments. Our method achieves state-of-the-art performance on the nuScenes validation set, improving AMOTA by 1.8% over the baseline CenterPoint. Evaluation on the nuScenes dataset demonstrates that KDPBTracker significantly improves tracking accuracy, reduces ID switches, and enhances overall tracking continuity under challenging conditions. [ABSTRACT FROM AUTHOR]

The dry/wet environment's effects on the sliding friction properties of fabric-silicone rubber composites are studied, and the wear resistance of polyester fabric is evaluated. The yarn directions of the fabrics (inner and outer) have significant influence on the coefficient of friction (COF) of fabric-silicone rubber composites during sliding friction due to the difference in fabric texture and yarn modulus. The COF's variation laws of fabric-silicone rubber composites under different vertical loads and sliding rates are observed, respectively. Additionally, the outer fabric is more sensitive to the changes of vertical loads than those of the sliding rates under the wet environment, which can be attributed to the destruction of the fabric original structure by high load, resulting in the fabric fibers' pulling and breaking during the steel ball's sliding. This study provides new ideas for the design of fabric-silicone rubber composites applied in friction conditions and complex environments. KEYWORDS coefficient of friction, fabric-silicone rubber composites, friction, silicone rubber, yarn direction, 1 | INTRODUCTION Silicone rubber is a synthetic elastomer with both inorganic and organic properties, which has good biocompatibility, heat-resistant performance, and is widely used in biomedical and machinery manufacturing [...]

With the growing demand for high‐performance smart windows, the discover of a class of thermochromic materials with reversible cycling and rapid response characteristics has become urgent. In this work, we have uncovered a two‐dimensional (2D) Ruddlesden‐Popper (RP) phase halide perovskite, (PMA)2MAPb2I7−xClx, where PMA=C6H5CH2NH3 and MA=CH3NH3, exhibiting exceptional reversible thermochromic properties. The 2D RP phase perovskite thin film features a low transition temperature (Tc=30 °C from the hydrated state to the hot state, along with a fast transition time of 40 s. Furthermore, the addition of 0.5 times excess MAI significantly enhances the visible light transmittance of the hydrated state. Characteristic hydration peaks in X‐ray diffraction patterns and O−H bond absorption peaks Fourier‐transform infrared spectra are observed in the thin film in its hydrated state, which disappear in the hot state, validating its reversible thermochromic properties. Additionally, a solar cell based on the thermochromic 2D RP phase thin film achieves a power conversion efficiency of 2.31 %, offering a promising solution for advanced smart window technologies. [ABSTRACT FROM AUTHOR]

Deep learning is currently the mainstream approach for building extraction tasks in remote-sensing imagery, capable of automatically learning features of buildings in imagery and yielding satisfactory extraction results. However, due to the diverse sizes, irregular layouts, and complex spatial relationships of buildings, extracted buildings often suffer from incompleteness and boundary issues. Gaofen-7 (GF-7), as a high-resolution stereo mapping satellite, provides well-rectified images from its rear-view imagery, which helps mitigate occlusions in highly varied terrain, thereby offering rich information for building extraction. To improve the integrity of the edges of the building extraction results, this paper proposes a dual-task network (Edge-UNet, EUnet) based on UNet, incorporating an edge extraction branch to emphasize edge information while predicting building targets. We evaluate this method using a self-made GF-7 Building Dataset, the Wuhan University (WHU) Building Dataset, and the Massachusetts Buildings Dataset. Comparative analysis with other mainstream semantic segmentation networks reveals significantly higher F1 scores for the extraction results of our method. Our method exhibits superior completeness and accuracy in building edge extraction compared to unmodified algorithms, demonstrating robust performance. [ABSTRACT FROM AUTHOR]

Silicone rubber is widely used in medical and equipment manufacturing fields due to its excellent sealing and solvent resistance. However, the hydrophobicity of silicone rubber was unsatisfactory for many advanced engineering structures and applications. Generally, the preparation of artificial superhydrophobic materials suffered from either complicated in process or poor in environmental protection. Here, we reported a simple method to prepare silicone rubber composites with excellent superhydrophobic properties (water contact angle [WCA] = 155.2°) from low‐cost hydrophilic silica. Tests showed that the uniform micro‐nano structures were the key to the superhydrophobic properties of silicone rubber composites. The bounce test observed the rebound of water droplets with different initial velocities (0.77, 1, and 2 m/s) impacting silicone rubber surface, and verified the great advantages of silicone rubber modified by silica in hydrophobic. The modification method shown in this work provides a simple way to manufacture non‐fluorinated, robustness superhydrophobic surfaces for a wide range of potential applications. Highlights: Based on the improvement of micro‐nano structure of the matrix surface by industrial silica, the preparation of superhydrophobic silicone rubber composites was realized.A process method for preparing fluorine‐free superhydrophobic silicone rubber composites from hydrophilic silica was proposed.Stretchability and robustness were the key factors for successful superhydrophobic modification of silicone rubber elastomers. [ABSTRACT FROM AUTHOR]

Defects within perovskite have been known to act as the nonradiative recombination centers, negatively impacting the carrier transport, which degrades the photovoltaic performance of perovskite solar cells (PSCs). Therefore, preparing a high‐quality perovskite film is of vital significance. To this end, a room‐temperature molten salt, dimethylamine formate (DMAFa), is introduced into perovskite precursor solution to regulate the crystallization process of CsPbI3 films. DMAFa can coordinate with Pb2+ as HCOO−‐Pb2+ in the early stages, then HCOO−‐Pb2+ is gradually displaced by I−‐Pb2+ due to its decomposition during the subsequent annealing, thus delaying the crystallization rate, meanwhile, the DMA+ can interact with the uncoordinated Pb2+ to passivate defects of perovskite films, thereby, forming a high‐quality CsPbI3 film with large grain size and low‐defect density. As a result of this strategy, the power conversion efficiency is increased to 20.40%, and the open‐circuit voltage is up to 1.21 V. These findings indicate that the introduction of DMAFa offers a fundamental way to achieve high‐performance CsPbI3 PSCs. [ABSTRACT FROM AUTHOR]

In this work, low density hollow glass beads (HGB)/silicon rubber (SR) composites were prepared by solution method and flocculation process. The prepared samples were characterized by scanning electron microscopy, Fourier transform infrared spectroscopy, tensile test, and friction test. The results show that the densities of SR composites decrease from 1.140 to 0.792 g/cm3 with the addition of HGB. By comparing theoretical density with true density, it can be estimated that the ratio of shattered HGB increase from 8.79% to 24.76%. Especially, the mechanical properties of SR composites were improved by surface modification of HGB. By adding surface‐modified HGB at 5 and 10 wt%, the tensile strengths of SR composites were enhanced by 17.8% and 28.2%, respectively. In addition, tear strength, shore A hardness, compression set, and friction property were significantly ameliorated. Furthermore, the mechanism of surface‐modified HGB in mechanical properties was analyzed. [ABSTRACT FROM AUTHOR]

The aggregate content in the fresh glazed hollow bead mortar was separated. The aggregate content and damage situation in the mortar under different stirring conditions was analyzed. The test results show that the aggregate breakage rate of the fresh vitrified microbead mortar increasing steadily with the extension of the stirring time. When the stirring time reaches a certain length, the particle size breakage rate will increase greatly. Compared with the vertical mixer, the horizontal mixer can reduce the particle size breakage rate by 16.3% and increase the aggregate integrity rate by 2.9%. The higher mixer speed will accelerate the speed of reduction of aggregate integrity rate; the thermal conductivity of glazed hollow bead mortar is mainly affected by the particle size damage rate. [ABSTRACT FROM AUTHOR]