基于图像运动区域的车辆遮挡跟踪算法

针对区域跟踪算法难以解决因车辆遮挡而引起误检的问题,提出了基于图像运动区域的车辆跟踪算法:采用背景剪除法提取运动区域,通过计算相邻帧运动区域的位置变化实现区域跟踪;建立车辆的二维矩形框模型,分析"区域--车辆"关系,结合区域跟踪的结果来判定车辆之间是否发生遮挡,并根据车辆行为来初始化车辆模型轮廓及速度;采用Kalman滤波器预测车辆在当前帧的位置,并以此预测位置作为车辆模型的初始位置进行模型轮廓的自适应调整,得到模型新的矩形轮廓;将新轮廓其所确定的几何中心位置作为测量值反馈回Kalman滤波器,修正Kalman系数,进行自回归运算和计算最佳匹配位置,从而实现车辆跟踪.算法测试实验使用的视频采集自江苏省通启高速公路视频监控系统,采用P4/2.4单CPU,结果表明,在为25帧/s视频流下,该算法准确跟踪率达到94.72%,有效解决遮挡问题,并具有较好的鲁棒性.     

四川藏区沼泽湿地植物区系探讨及湿地资源面临的问题

本文分析了四川藏区沼泽湿地植物区系的结构特点,剖析了湿地资源存在的问题,并提出了解决方案.     

四川藏区传统藏文化对生物多样性保护的意义

本文在大量实地调查和分析基础上,较为详细地总结了四川藏区传统藏文化、传统生活与生产方式在当地生态系统、生物多样性的保护和可持续利用中的作用.几千年来,传统藏文化中的禁忌、倡导、宗教、文化和游牧等对维持藏区生态系统正常的服务功能、保存与永续利用当地生物多样性起到了不可磨灭的贡献.当代市场经济扩张和外来文化的冲击使当地生态系统和生物多样性面临诸多问题,因此,在促进社会经济全面发展的同时,应该大力弘扬传统藏文化中积极有效的因素,保护和恢复生态系统,保护和永续利用生物资源,实现人与自然的和谐发展.     

从博弈论谈南水北调西线工程的四川对策

南水北调西线工程,从博弈论的角度考虑,属于非零和博弈,各方效益的和大于零,从而具有南北两利的可能.四川的最佳策略,应根据西北的优势策略和中央的决策而选择,应坚持有偿调水,有偿调水可以实现南水北调博弈的纳什均衡.在西线工程中,应将调水藏区的可持续发展和民族区域的稳定作为四川的重点战略选择,借机推动藏区社会经济的跨越式发展.     

中国西北干旱区土地退化与生态建设问题

本文阐述了西北干旱区自然环境的基本特点，讨论了土地退化中土地沙漠化、土地盐渍化和草地退化问题。指出生态建设应当尊重自然,不宜大面积植树造林，采取生态修复措施和建立自然保护区有助于环境整治与生态建设。在区域发展中应当重视土地与水资源的合理开发利用以及区域间环境与发展协调等问题。     

若尔盖地区湿地萎缩、草地退化沙化与北方沙尘干旱地区因果关系探索

分析若尔盖高原盆地的地质地貌、高原特有的热力学特性、流经此地的季风与控制北方干旱区的西风带的相互关系以及环境退化后下垫面改变引起的地空传递关系变化等因素；对近半个世纪以来若尔盖的降雨等气候条件与北方地区的干旱沙尘天气发生情况进行对比分析，发现北方地区的干旱风沙天气与若尔盖的降水频率存在很大程度上的相互关系。表明沙化中的若尔盖地区是一个潜在的沙源地，并有可能通过季风影响到我国北方主要干旱地区的干旱程度。在研究卫星图片、大量的气象资料的基础上，设计出了探索若尔盖地区与我国北方干旱沙尘地区关系研究的野外考查路线。并组成了多学科的联合研究小组展开了研究工作。     

基于Kalman滤波与多特征模糊聚类的图像融合

为了减低图像的噪声，保留有用的信息，获得更为可靠的融合图像，将Kalman滤波引入图像融合中，提出基于Kalman滤波与多特征模糊聚类的图像融合算法．该方法结合滤波和多特征优点，实验结果表明了该方法的有效性．     

Data fusion based on fuzzy measures

Choquet integral based on fuzzy measure is a very popular data fusion approach. A major problem in applying the Choquet integral is how to determine a large number of fuzzy measures as the number of attributes increases. The λ-fuzzy measure proposed by Sugeno is a powerful method to resolve this problem. However, the modeling ability of the λ-fuzzy measure is too limited to satisfy actual requirements. In this paper, an extended λ-fuzzy measure is proposed using Shapley value index, and the limitation of the λ-fuzzy measure is significantly overcome under little additional computational loads. The extended fuzzy measure has stronger modeling power than the λ-fuzzy measure, straightforwardly representing interaction among attributes. We apply the extended fuzzy measure to an artificial data set and a real dataset in an iron-steel plant. The results verify the usefulness of the extended fuzzy measure compared with other main existing methods.     

Data fusion based on fuzzy measures

Choquet integral based on fuzzy measure is a very popular data fusion approach.A major problem in applying the Cho- quet integral is how to determine a large number of fuzzy measures as the number of attributes increases.Theλ-fuzzy measure proposed by Sngeno is a powerful method to resolve this problem.However,the modeling ability of theλ-fuzzy measure is too limited to satisfy actual requirements.In this paper,an extendedλ-fuzzy measure is proposed using Shapley value index,and the limitation of theλ-fuzzy measure is significantly overcome under little additional computational loads.The extended fuzzy measure has stronger modeling power than theλ- fuzzy measure,straightforwardly representing interaction among attributes.We apply the extended fuzzy measure to an artificial data set and a real dataset in an iron-steel plant.The results verify the usefulness of the extended fuzzy measure compared with other main existing methods.     

Enhancement of monacolin K production via intergeneric protoplast fusion between Aspergillus terreus and Monascus anka

Intergenric protoplast fusion between Aspergillus terreus CA99 and Monascus anka M-3, the high and low producers of monacolin K respectively,was performed for enhancement of monacolin K production. The 24-hour-old mycelia of A. terreus CA99 and M. anka M-3 were treated with 0.5% lywallzyme, 0.3% snailase and 0.3% cellulase at 34℃ for 5 h and at 30℃ for 3.5 h, and their protoplasts formation reached 1.76×107/mL and 1.68×107/mL respectively. Parental protoplasts were irradiated with a 30 W UV light away from 30 cm for 3 min and then mixed. The mixture was incubated with 30% PEG 6000 for 15 min. The reviving fusants were isolated on the regeneration plates. Of the 363 fusants isolated, over 100 showed enhanced monacolin K production compared with the parental strain M. anka M-3. Ten of them produced monacolin K about 1.6-fold of that M.anka M-3 does and the monacolin K titer of two fusants (F49 and F104) increased by about 1-fold. The monacolin K yields of F49 and F104 were 460 μg/mL and 457 μg/mL respectively. In optimized fermentation medium, the monacolin K titer of F49 reached 1216 μg/mL.