Most of the existing opportunistic network routing protocols are based on some type of utility function that is directly or indirectly dependent on the past behavior of devices. The past behavior or history of a devic...Most of the existing opportunistic network routing protocols are based on some type of utility function that is directly or indirectly dependent on the past behavior of devices. The past behavior or history of a device is usually referred to as contacts that the device had in the past. Whatever may be the metric of history, most of these routing protocols work on the realistic premise that node mobility is not truly random. In contrast, there are several oracles based methods where such oracles assist these methods to gain access to information that is unrealistic in the real world. Although, such oracles are unrealistic, they can help to understand the nature and behavior of underlying networks. In this paper, we have analyzed the gap between these two extremes. We have performed max-flow computations on three different opportunistic networks and then compared the results by performing max-flow computations on history generated by the respective networks. We have found that the correctness of the history based prediction of history is dependent on the dense nature of the underlying network. Moreover, the history based prediction can deliver correct paths but cannot guarantee their absolute reliability.展开更多
针对现有的交互式图像分割算法在处理高分辨率图像时仍不够高效的问题,提出了一种基于简单线性迭代聚类(simple linear iterative clustering,SLIC)与Delaunay图割的交互式图像分割算法。使用一种简化但是高效的SLIC算法将图像分割为多...针对现有的交互式图像分割算法在处理高分辨率图像时仍不够高效的问题,提出了一种基于简单线性迭代聚类(simple linear iterative clustering,SLIC)与Delaunay图割的交互式图像分割算法。使用一种简化但是高效的SLIC算法将图像分割为多个在感知上有意义的原子区域,并提取这些区域的代表像素点;对处在背景矩形框内的代表像素点进行Delaunay三角剖分,构建图结构;最后利用最小割最大流算法将图中的节点分为两部分,并将这些节点对应为相应的原子区域,达到将图像分割为前景和背景的目的。与其他交互式图像分割算法进行实验对比,结果表明所提算法在计算效率上有较大提升,并更为准确。展开更多
文摘Most of the existing opportunistic network routing protocols are based on some type of utility function that is directly or indirectly dependent on the past behavior of devices. The past behavior or history of a device is usually referred to as contacts that the device had in the past. Whatever may be the metric of history, most of these routing protocols work on the realistic premise that node mobility is not truly random. In contrast, there are several oracles based methods where such oracles assist these methods to gain access to information that is unrealistic in the real world. Although, such oracles are unrealistic, they can help to understand the nature and behavior of underlying networks. In this paper, we have analyzed the gap between these two extremes. We have performed max-flow computations on three different opportunistic networks and then compared the results by performing max-flow computations on history generated by the respective networks. We have found that the correctness of the history based prediction of history is dependent on the dense nature of the underlying network. Moreover, the history based prediction can deliver correct paths but cannot guarantee their absolute reliability.
文摘针对现有的交互式图像分割算法在处理高分辨率图像时仍不够高效的问题,提出了一种基于简单线性迭代聚类(simple linear iterative clustering,SLIC)与Delaunay图割的交互式图像分割算法。使用一种简化但是高效的SLIC算法将图像分割为多个在感知上有意义的原子区域,并提取这些区域的代表像素点;对处在背景矩形框内的代表像素点进行Delaunay三角剖分,构建图结构;最后利用最小割最大流算法将图中的节点分为两部分,并将这些节点对应为相应的原子区域,达到将图像分割为前景和背景的目的。与其他交互式图像分割算法进行实验对比,结果表明所提算法在计算效率上有较大提升,并更为准确。
