Search

Achieving the accurate perception of occluded objects for autonomous vehicles is a challenging problem. Human vision can always quickly locate important object regions in complex external scenes, while other regions are only roughly analysed or ignored, defined as the visual attention mechanism. However, the perception system of autonomous vehicles cannot know which part of the point cloud is in the region of interest. Therefore, it is meaningful to explore how to use the visual attention mechanism in the perception system of autonomous driving. In this paper, we propose the model of the spatial attention frustum to solve object occlusion in 3D object detection. The spatial attention frustum can suppress unimportant features and allocate limited neural computing resources to critical parts of the scene, thereby providing greater relevance and easier processing for higher-level perceptual reasoning tasks. To ensure that our method maintains good reasoning ability when faced with occluded objects with only a partial structure, we propose a local feature aggregation module to capture more complex local features of the point cloud. Finally, we discuss the projection constraint relationship between the 3D bounding box and the 2D bounding box and propose a joint anchor box projection loss function, which will help to improve the overall performance of our method. The results of the KITTI dataset show that our proposed method can effectively improve the detection accuracy of occluded objects. Our method achieves 89.46%, 79.91% and 75.53% detection accuracy in the easy, moderate, and hard difficulty levels of the car category, and achieves a 6.97% performance improvement especially in the hard category with a high degree of occlusion. Our one-stage method does not need to rely on another refining stage, comparable to the accuracy of the two-stage method. [ABSTRACT FROM AUTHOR]

The vehicle HVAC (heating, ventilating, and air conditioning) system aims to keep passengers thermal comfort and reduce energy consumption. One effective measure is to use temperature prediction to optimize HVAC systems. This paper aimed to comprehensively investigate the potential of machine learning methods applied to cockpit temperature prediction and proposed a deep learning method considering the Spatio-temporal correlation of the temperature field. Specifically, this study constructs a topological description of the temperature field inspired by the spatial and temporal correlations revealed by the Navier-Stokes equations. The Graph Convolutional Network (GCN) is used to capture the topological structure to obtain spatial features, and the Gated Recurrent Unit (GRU) is used to capture the dynamic change of node attribute to obtain temporal features. Finally, the GCGRU model can extract Spatio-temporal features of the temperature field. The experimental results show that the prediction method using Spatio-temporal features for the temperature field is feasible. The prediction performance is better than all the baseline methods and has the robustness to the data noise. This work is enlightening and may have a further reference to the feasibility study of the vehicle cabin air temperature prediction model. [ABSTRACT FROM AUTHOR]

In this paper, we report the synthesis of a multifunctional fluorescent probe Tb-CP, Tb(HL)(EtOH) 2 (NO 3) 2 (HPU-10) (H 2 L = 2,6-bis-(5-pyridin-4-yl-1H-[1,2,4]triazol-3-yl)- pyridine), and demonstrate that this novel chemosensor has the property of ratiometric detection of Zn2+ and Cd2+. The detection limit of HPU-10 sensing Zn2+ and Cd2+ is 0.319 and 0.965 μM, respectively. The sensing mechanism can be explained by (i) the decomposition of HPU-10 and (ii) the recombination of Zn2+ or Cd2+ with ligand forming 2HL--Zn2+ or 2HL--Cd2+, respectively. Moreover, the fluorescent sensor HPU-10 can detect the nitroaromatic compound 2, 4-DNP via a fluorescence quenching mechanism. The detection limits obtained from linear regression curve plots of 2, 4-DNP is calculated to be 1.69 μM. In addition, the possible use of the probe coated paper for tracing the target analytes has also been presented. A highly selective and sensitive multi-functional luminescent chemosensor Tb-CP for ratiometric detecting Cd2+ and Zn2+ and selective discrimination of 2, 4-DNP by fluorescence quenching was successfully obtained. Image 1 • HPU-10 displays ratiometric sensing of Zn2+ and Cd2+ by forming 2HL--Zn2+ and 2HL--Cd2+. • HPU-10 exhibited fluorescence quenching detection of 2, 4-DNP. • HPU-10 can be used as a multifunctional sensor for Zn2+, Cd2+ and 2, 4-DNP in practical. [ABSTRACT FROM AUTHOR]

Nanocomposite AgBr@HPU-4 was synthesized based on a 3D Cu-MOF, {[Cu(L) 0.5 (H 2 O) 2 ]·4H 2 O} n (HPU-4) through a facile reaction route and confirmed by XRD, TEM, SEM. UV–Vis absorption spectrum indicates that AgBr@HPU-4 nanocomposite has strong optical capability nearly in the whole range of visible light spectrum. The as-prepared AgBr@HPU-4 photocatalyst, as compared to AgBr or HPU-4 , exhibits enhanced photocatalytic activity towards the degradation of Methylene Blue and Methyl Orange dyes. [ABSTRACT FROM AUTHOR]

A Cu(I)/Cu(II) 3D framework, {[(CuII) 3 (CuI) 3 (pbt) 3 Cl 2 ]·ClO 4 ·H 2 O} n ( HPU-3 ) (H 2 pbt = 5′-(pyridin-2-yl)–2H,4′H-3,3′-bi(1,2,4-triazole)), has been synthesized by using solvothermal method. UV–Vis absorption spectrum indicates that HPU-3 has strong optical capability nearly in the whole range of visible light spectrum. HPU-3 photocatalyst exhibits good photocatalytic activity toward the degradation of Methylene Blue and Methyl Orange dyes. [ABSTRACT FROM AUTHOR]

This paper reports a metal ion-exchange material which can significantly enhance the degradation of acetamiprid and methylene blue. [Display omitted] A Metal-Organic Framework (MOF) by the formula of {[Cd 4 (L) 2 (H 2 O) 3 ]·4·.5H 2 O} n (HPU-15-Cd) (H 4 L = 5, 5′-oxydiisophthalic acid) has been synthesized via solvothermal method. The central ions of HPU-15-Cd can occur ion-exchange with Co2+/Cu2+ ions to form the isostructural HPU-15-Co, HPU-15-Cu in a single-crystal-to-single-crystal fashion. Photocatalytic experiments showed that HPU-15-Co, HPU-15-Cu had better photocatalytic activity for the degradation of acetamiprid (ACT) and methylene blue (MB) than HPU-15-Cd. The reason is that the band gap width of HPU-15-Co and HPU-15-Cu is narrow, which makes it have higher absorption and utilization of UV–visible light. Besides, HPU-15-Cd, HPU-15-Co, HPU-15-Cu have excellent stability, and the catalytic effect of HPU-15-Cu are basically unchanged after three cycles of catalytic degradation of ACT and MB. [ABSTRACT FROM AUTHOR]

Luminescence porous HPU-12 displays selective quenching detection for Fe3+ and nitrophenolic compound by the interaction between the Fe3+ and N and O atoms in the channels and the overlap of the absorption of nitrophenols with the excitation and emission of HPU-12 , respectively. • Luminescent porous metal-organic framework HPU-12 was prepared. • Two-fold interpenetrated HPU-12 contains 3D pore channels covered with N- and O-coordinated active sites. • HPU-12 was investigated as a luminescent probe for the selective detection of Fe3+ and nitrophenols. • The luminescence quenching mechanism of Fe3+ and nitrophenols on HPU-12 was studied. A porous luminescent MOF {[Zn(L)]·4H 2 O·2CH 3 CN} n (HPU-12) based on a bifunctional ligand, 5-(3,5-Di-pyridin-4-yl- [1,2,4] triazol-1-ylmethyl)-isophthalic acid (H 2 L), has been synthesized. Structural analysis shows that the two-fold interpenetrated HPU-12 contains 3D pore channels covered with N- and O-coordinated active sites. The luminescence investigation demonstrates that the luminescent HPU-12 can realize the selective detection for Fe3+ by quenching the emission of the HPU-12 via the interaction between the Fe3+ and N and O atoms in the pore channels. In addition, the luminescence of the HPU-12 could be selectively and sensitively quenched by nitrophenolic compound because of the overlap of the absorption of the nitrophenolic compound with the excitation and emission of HPU-12. [ABSTRACT FROM AUTHOR]

In order to solve the problem of overheating of the engine and cooling system of the vehicle in the plateau low-pressure environment, it is necessary to study air-side thermal-hydraulic performance of the vehicle cooling system heat exchanger under low-pressure environment. In this paper, the experimental study on the louvered fin and flat tube heat exchanger of the vehicle is carried out on the low-pressure wind tunnel test bench. The results show that at a gauge pressure of −44 kPa, the air-side convective heat transfer coefficient is reduced by 33.5%~23.3% compared with 0 kPa; the Colburn j-factor is increased by 36.8% on average; the f factor is increased by 51.2% on average. Based on this, numerical simulations are carried out to study the heat transfer and flow characteristics of louvered fins with different structural parameters under low-pressure environment. The empirical correlations of Colburn j-factor and Friction factor f are fitted by multiple linear regression. In the range of gauge pressure from 0 kPa to −44 kPa, the average deviation of the correlation calculation result of Colburn j-factor is 3.4%, and the average deviation of the correlation calculation result of f factor is 5.5%. The research results can provide a basis for the design of louvered fin heat exchangers utilized in the plateau environment. [ABSTRACT FROM AUTHOR]