Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

Role of Co in formation of Ni-Ti clusters in maraging stainless steel

The effect of Co addition on the formation of Ni-Ti clusters in maraging stainless steel was studied by three dimensional atom probe (3DAP) and first-principles calculation. The cluster analysis based on the maximum separation approach showed an increase in size but a decrease in density of Ni-Ti clusters with increasing the Co content. The first-principles calculation indicated weaker Co-Ni (Co-Ti) interactions than Co-Ti (Fe-Ti) interactions, which should be the essential reason for the change of distribution characteristics of Ni-Ti clusters in bcc Fe caused by Co addition.     

Operating Range Scheduled Robust Dahlin Algorithm to Typical Industrial Process with Input Constraint

International Journal of Control, Automation and Systems - There is a class of typical nonlinear industrial process, which can be characterized by a first-order inertia plus pure delay model in an...     

Structure, properties, and thermal stability of nanocrystallite Fe-Ti-N soft magnetic films

We deposited Fe-Ti-N magnetic films with a high sputtering power of 7 W/cm/sup 2/. When the composition of the films was in the range of Fe-Ti(3.9 at.%)-N(8.8 at.%) to Fe-Ti(3.3 at.%)-N(13.5 at.%), the films were composed of /spl alpha/' and Ti/sub 2/N precipitates. With the addition of nitrogen, 4/spl pi/M/sub s/ became higher than that of pure iron, reaching a maximum of 23.8 kG. At the same time, H/sub c/ was reduced to a minimum of 1.12 Oe. The best films can meet the needs of the recording head in dual-element giant magnetoresistive/inductive heads, yielding high storage density (10 Gb/in/sup 2/). The incorporation of N in /spl alpha/-Fe brought about the /spl alpha/' phase with its higher saturation magnetization. Ti additions inhibited the equilibrium decomposition /spl alpha/'/spl rarr//spl alpha/+/spl gamma/'. Because H/sub C//sup D//spl prop/D/sup 6/, where D is average grain diameter, grain size control is very important. The nitrogen induces severe distortion of the /spl alpha/' lattice, which can cause the grains to break into pieces and reduce the grain size. High sputtering power also led to the formation of fine grains, with diameter in the order of 14 nm. Probably Ti/sub 2/N is preferentially precipitated on the grain boundary, pinning the grain boundary and stabilizing the grain size during high-temperature heat treatment. The temperature limit for stability of the structure and its associated low coercivity was not less than 520/spl deg/C.     

超声波强化原油破乳电脱盐技术的工业实践

报道了采用超声波强化原油破乳电脱盐技术的开发与工业应用.经过实验室开发确定的超声波强化原油破乳电脱盐专利技术--超声波-电场联合破乳脱盐组合技术采用顺逆流方式.该技术于2003年9月在齐鲁分公司完成工业应用试验后,超声波强化原油破乳设备直接投入生产运行,在不加入化学破乳剂的情况下,可使胜利混输原油(平均盐浓度为50 mg/L,平均水质量分数为0.5%～1.0%)脱后盐浓度低于3 mg/L,水质量分数小于0.3%.     

泥页岩井壁稳定研究及在临盘地区的应用

从岩石力学和物理化学两个主要因素简要分析了井壁失稳的机理，指出泥页岩井壁失稳是由力学与化学两方面因素共同作用的结果。钻井液与泥页岩存在化学势差，并改变了井壁附近的孔隙压力，降低岩石强度。借助于井壁处有效应力的变化,将泥页岩与钻井液相互作用时页岩水化所产生的力学效应与纯力学效应结合起来，计算出任意井斜方位井眼围岩应力状态，利用测井资料求出有关岩石力学参数和Mohr Couloumb准则，计算得出防塌的临界钻井液密度。     

多介质立体取样及在北黄海油气化探中的应用

由于不同环境条件下,不同化探测试指标受到不同的因素干扰,所以不同介质样品的应用条件存在一定的差异。针对不同介质样品特点,分别采集海底沉积物、底部海水和低空大气3种介质样品,并采用在海底沉积物柱状样不同深度部位取样的立体取样方法,通过多指标综合分析,对不同介质和深度样品的多项化探指标互相进行了验证和补充,可以抑制干扰因素的影响,为油气资源远景评价提供依据。运用该方法在北黄海盆地油气勘查中进行初步尝试,并据此划分了三级化探异常区,提出了有利的含油气远景区,均与已知油气区和区域地质分析的结果相符合,取得了很好的效果。      

自然伽马能谱资料预处理程序PRECNG在塔河油田的应用

PRECNG是自然伽玛能谱资料预处理程序，是一种转换处理256道CSNG高能谱数据和总伽马的方法。文章阐述了处理模型的建立和实现，并介绍了该程序在实际测井中的应用情况。