To balance the speed and accuracy in semantic segmentation of the urban street images for autonomous driving, we proposed an improved U-Net network. Firstly, to improve the model representation capability, our improved U-Net network structure was designed as three parts, shallow layer, intermediate layer and deep layer. Different attention mechanisms were used according to their feature extraction characteristics. Specifically, a spatial attention module was used in the shallow network, a dual attention module was used in the intermediate layer network and a channel attention module was used in the deep network. At the same time, the traditional convolution was replaced by depthwise separable convolution in above three parts, which can largely reduce the number of network parameters, and improve the network operation speed greatly. The experimental results on three datasets show that our improved U-Net semantic segmentation model for street images can get better results in both segmentation accuracy and speed. The average mean intersection over union (MIoU) is 68.8%, which is increased by 9.2% and the computation speed is about 38 ms/frame. We can process 27 frames images for segmentation per second, which meets the real-time process and accuracy requirements for semantic segmentation of urban street images.

金属配合物中的水簇研究为研究宏观意义上的水以及与蛋白质分子有关的水分子提供了有效途径。本文合成了一个含有阴离子水簇的带状超分子配合物［Co(2,2-bipy)2(N3)2］(N3)0.5Cl0.5·2H2O(1, 2, 2-bipy=2, 2-联吡啶)。单晶结构解析表明, 配合物属于三斜晶系, P-1空间群, 晶胞参数为: a=0.822 54(7) nm, b=1.175 58(9) nm, c=1.237 06(10) nm, α=91.379 0(10)°, β=92.151 0(10)°, γ=108.119 0(10)°, V=1.135 27(16) nm3, 由一个单核［Co(2,2-bipy)2(N3)2］+配合物阳离子、两个非配位水分子、0.5个游离的叠氮离子和0.5个氯离子组成, 叠氮离子和氯离子位置无序, 占有率各为50%。两个客体水分子通过强烈的分子间氢键作用形成了环状水四聚体, 且与无序的N-3和Cl-通过氢键作用形成了一个［(H2O)4(N3)Cl］2- 阴离子水簇。此外, 本文基于密度泛函理论(DFT)对配合物［Co(2,2-bipy)2(N3)2］+阳离子进行了量子化学计算, 分析了其单点能和原子电荷, 并计算了中心金属离子的氧化态, 计算结果与实验相吻合。

The conventional technology could not fulfill the rapidly growing need for fine conductive lines for its inherent limits. Therefore, in this study laser micro-fine cladding and flexibly direct writing technique is used to obtain conductive lines with high precision and reliability. In the case of different substrates and parameters, film thickness will be different. Film thickness directly influences the reliability and stability of conductive lines with exception of quality and running speed. Therefore, we focus on developing the optimal parameters for the different substrates to achieve expected film thickness and make conductive lines have good performance and quality.