Optic flow field segmentation and motion estimation using a robustgenetic partitioning algorithm

Optic flow motion analysis represents an important family of visual information processing techniques in computer vision. Segmenting an optic flow field into coherent motion groups and estimating each underlying motion is a very challenging task when the optic flow field is projected from a scene of several independently moving objects. The problem is further complicated if the optic flow data are noisy and partially incorrect. In this paper, the authors present a novel framework for determining such optic flow fields by combining the conventional robust estimation with a modified genetic algorithm. The baseline model used in the development is a linear optic flow motion algorithm due to its computational simplicity. The statistical properties of the generalized linear regression (GLR) model are thoroughly explored and the sensitivity of the motion estimates toward data noise is quantitatively established. Conventional robust estimators are then incorporated into the linear regression model to suppress a small percentage of gross data errors or outliers. However, segmenting an optic flow field consisting of a large portion of incorrect data or multiple motion groups requires a very high robustness that is unattainable by the conventional robust estimators. To solve this problem, the authors propose a genetic partitioning algorithm that elegantly combines the robust estimation with the genetic algorithm by a bridging genetic operator called self-adaptation     

Loss of heterozygosity of the von Hippel Lindau gene locus in polypoid dysplasia but not flat dysplasia in ulcerative colitis or sporadic adenomas

Carcinoma in ulcerative colitis (UC) develops from dysplastic precursor lesions, which include flat dysplasia (FD) and polypoid dysplasias (PD). PD may present as single or multiple polypoid structures or as plaque-like lesions that, independent of histological grade, are an indication for colectomy. PDs are histologically similar to adenomas and may not be readily distinguished by light microscopy. It is not known whether FD and PD are different entities, or whether they represent etiologically similar lesions with different morphological expression. We microdissected 25 cases of UC with PD and 19 samples of FD with surrounding chronic colitis (CC) in UC. Loss of heterozygosity (LOH) at the von Hippel Lindau (vHL) gene locus and the putative tumor suppressor genes APC, INK4A (9p16), and p53 was studied. LOH of the vHL gene, INK4A (9p16), and APC was also studied in 11 sporadic adenomas of the colon. LOH at the vHL locus was present in 50% of the samples of PD and in 12% of the samples of FD. LOH was seen in CC close to PD and FD in 26% and 12% of cases, respectively. No adenoma showed LOH of the vHL gene markers studied. LOH in p53 was seen in PD in 16% cases and in FD in 42% cases and in CC close to PD and FD in 0% and 14% cases, respectively. LOH patterns between PD and FD of the markers for APC and 9p16 were not different. LOH in APC was seen in two of five cases of adenoma. We conclude that PD and FD share genetic alterations in APC and 9p16 genes. More frequent involvement of the VHL gene in PD and surrounding CC and involvement of p53 in HGD and CC in FD may represent genetic differences between the development of PD and FD and may be the cause of the different morphology. The infrequency of LOH at the vHL locus in adenomas versus PD may serve as a discriminator between adenomas and PD in diagnostically problematic cases.     

激光技术推广应用中安全防护问题

论述加强激光安全防护工作的紧迫性,介绍我国激光安全工作的进展,提出下一步工作建议。     

特种钢用结晶器铜管破裂原因分析

通过对某特钢厂破裂的结晶器铜管进行金相实验、扫描电镜和能谱分析,并结合结晶器的生产、使用及失效过程情况,综合受力分析,认为铜管破裂原因主要是环境介质硫渗入形成硫化物,在拉应力作用下,裂纹沿脆性质点扩展导致的破坏。     

半导体光开关工作电流和速率的理论分析

本文从载流子连续性方程出发，采用半导体双异质结概念，从理论上推出了计算半导体光波导开关工作电流和速率的理论公式，为器件选取工作电流和提高开关速率提供了理论依据．     

智能建筑中空调监控系统的交互界面设计

智能建筑是根据用户需求将建筑物的结构、设备、服务和管理进行最优组合以提供高效、舒适、便利的人性化建筑环境。文章以交互界面为切入点,用户需求为核心,对某智能建筑中空调监控系统的交互界面设计进行了探讨,以期为其它工业控制系统的交互界面设计提供参考。     

基于SAP接口技术的移动终端解决方案

越来越多的企业正在或者即将用SAP作为ERP的应用载体。企业在得益于ERP精细化管理的同时,往往也为ERP与其他子系统整合集成所烦恼。介绍了几种应用于SAP的接口技术,其中包括RFC、ALE-IDOC、BAPI、SAP-DCOM以及Web Service接口技术。并且在此基础上,列举了企业内部的一个实例,展现了SAP通过接口技术与外部的PDA移动终端系统整合,从而解决了维修服务行业从接收工单、记录维修、备件管理等在移动环境下的应用需求。     

车联网中基于轨迹预测的无人机动态协同优化覆盖算法

针对城市车联网中出现的基站覆盖空洞及局部流量过载等问题,提出了一种基于车辆轨迹预测信息的动态预部署方案。首先,为了训练得到统一的seq2seq-GRU轨迹预测模型,多个携带边缘计算服务器的无人机在分布式联邦学习与区块链的架构下,去除中心聚合节点,采取改进的Raft算法,在每轮训练中根据贡献数据量的大小,选举得到节点来完成参数聚合及模型更新任务。其次,基于模型预测结果,提出了一种改进的虚拟力向导部署算法,通过各虚拟力来引导无人机进行动态地部署以提升车辆的接入率及通信质量。仿真结果表明,提出的训练架构能够加速模型的训练,部署算法在提升车辆接入率的同时提升了车辆与无人机之间的通信质量。     

Modeling polypharmacy effects with heterogeneous signed graph convolutional networks

Applied Intelligence - Pharmaceutical drug combinations can effectively treat various medical conditions. However, some combinations can cause serious adverse drug reactions (ADR). Therefore,...     

适用于复杂环境下的实时目标跟踪技术

针对复杂环境下目标跟踪过程中目标存在旋转、视角、尺度等变化以及噪声干扰的问题,提出了一种基于尺度不变特征与快速模板匹配相结合的目标跟踪技术;该技术通过分别提取预先存储模板和实时采集图像的尺度不变特征,建立初始模板;采用菱形搜索策略对模板的低分辨率子图和待跟踪图像的低分辨率子图进行快速互相关检测,根据检测结果在该帧高分辨率图像中建立紧凑ROI,在此区域内进行模板匹配,对目标进行精确定位;在目标跟踪的过程中采用自适应模板更新策略,以保证在目标发生变化时跟踪的稳定性;实验结果表明,该技术在稳定性、准确性和实时性等方面均优于传统方法。