Shape determination of horticultural produce using two-dimensional computer vision - A review

Shape uniformity of fruits and vegetables is important whether they are to be fresh marketed or processed. To achieve the desired uniformity, fruits must be inspected and classified. Although manual sorting of agricultural products is potentially accurate, in practice it reveals subjective and inconsistent. Computer vision has become a proven, reliable tool for describing product shape. Depending on the product, misshapenness or malformation expresses as poor axial symmetry, excessive curvature of the fruit longitudinal axis, several types of protruding zones and abnormal concavities, lack of cross section circularity, etc. Here we review some two-dimensional computer vision methods applied throughout the past 25 years for determining the shape of horticultural produce. While a number of the works cited achieved high classification accuracy in two categories (well-formed, misshapen), only a few of the systems referred were able to classify in more than two classes, or have been tested online.     

结合EFD与NCut的彩色图像分割方法

为了克服边缘流引导的各向异性扩散(EFD)方法过分割和归一化分割(NCut)方法计算复杂度高的缺点,提出结合EFD和NCut的彩色图像分割方法。首先利用EFD对图像进行预分割,然后将分割区域作为节点构建带权无向图G,用NCut对图进行全局最优化分类,并进行相应后处理,得到最终结果。由于图G是基于过分割区域而非像素点的,所以算法效率得到较大提高。另外,EFD方法可有效利用图像的局部信息,NCut方法则考虑到图像的全局特征,因此文中方法综合两者的优点。实验结果表明,文中方法能够取得较好的分割效果。     

4W大功率LED照明灯散热结构研究

采用热阻法建立了4w大功率LED照明灯的热传导模型,从而得出散热器有效散热面积;然后对所设计的散热器采用有限元仿真得到稳态温度分布,并进一步利用EFD方法进行自然对流热分析;最后通过热测试实验验证来理论和仿真分析结果。结果表明,所设计的散热器满足LED使用要求,最高温度小于65℃。该研究成果对设计高散热效率的LED灯具具有指导意义。     

某电子设备热设计的数值模拟研究

基于计算流体动力学(CFD)和数值传热技术,应用通用流体传热分析软件对某电子设备自然对流与强迫对流散热进行了数值模拟,获得该电子设备的温度分布情况以及机箱内气体的复杂流动状态,为优化和改善机箱的热设计方案提供了有用数据,同时可以大大缩短电子设备的开发周期和降低研发成本.