共查询到13条相似文献,搜索用时 82 毫秒
1.
针对特征点法视觉里程计(visual odometry,VO)中,描述子匹配算力要求较高,而光流追踪算法存在误差累积的问题,提出了一种双目混合追踪的视觉里程计算法,并通过实验对该方法的定位结果与计算效率进行分析.在该算法中,前端在影像关键帧提取ORB(oriented brief)特征点并生成路标点,优先采用Inverse Compositional光流进行追踪,使用卡方检验等检测外点;为检测定位粗差,提出通过由相邻帧位姿恢复的极线进行检验;光流追踪失败或未通过极线检验时,提取ORB特征点维持跟踪或进行重定位;同时,后端进行相机位姿、路标点联合优化以减小误差累积.实验结果表明,该算法定位精度低于ORB-SLAM2(simultaneous location and mapping)算法,但运算效率有明显提升. 相似文献
2.
基于单一传感器的同时定位与地图构建技术已经逐渐不能满足移动机器人、无人机及自动驾驶车辆等智能移动载体日益复杂的应用场景。为了进一步提升移动载体在复杂环境下的定位与建图性能,基于多传感器融合的SLAM技术成为目前研究的热点内容。本文提出了一种基于图优化的紧耦合双目视觉/惯性/激光雷达SLAM方法(S-VIL SLAM),该方法在视觉惯性系统中引入激光雷达原始观测,基于滑动窗口实现了IMU量测、视觉特征及激光点云特征的多源数据联合非线性优化。利用视觉与激光雷达的互补特性设计了视觉增强的激光雷达闭环优化算法,进一步提升了多源融合SLAM系统的全局定位与建图精度。为了验证本文算法的性能,利用自主搭建的集成多传感器的硬件采集平台在室外场景下进行了车载试验。试验结果表明,本文提出的紧耦合双目视觉/惯性/激光雷达里程计相比于紧耦合双目视觉惯性里程计和激光雷达里程计定位定姿性能显著提升,视觉增强的激光雷达闭环优化算法能够在大尺度场景下有效探测出轨迹中的闭环信息,并实现高精度的全局位姿图优化,经过闭环优化的点云地图具有良好的分辨率和全局一致性。 相似文献
3.
针对传统光流法检测障碍物准确性不高、适应性差的问题,提出了一种基于金字塔LK光流的旋翼无人机单目视觉自主障碍物检测方法。该方法通过金字塔LK光流法获取光流信息,结合光流大小和拍摄间距与物距的关系设定自适应阈值,比较光流与阈值的大小并对障碍物进行检测与判定。实验证明:该方法可以有效地检测到障碍物,能满足无人机在多种条件下的避障需求,具有较高的准确性、鲁棒性和适应性。 相似文献
4.
5.
6.
7.
8.
AbstractThe analysis of remote sensing (RS) images, which is often accomplished using unsupervised image classification techniques, requires an effective method to determine an appropriate number of classification clusters. This paper proposes a preliminary analytical method to evaluate the input parameters for unsupervised RS image classification. Our approach involves first analysing the colour spaces of RS images based on the human visual perception theory. This enables the initial number of clusters and their corresponding centres to be automatically established based on the interaction of different forces in our supposed force field. The proposed approach can automatically determine the appropriate initial number of clusters and their corresponding centres for unsupervised image classification. A comparison of the experimental results with those of existing methods showed that the proposed method can considerably facilitate unsupervised image classification for acquiring accurate results efficiently and effectively without any prior knowledge. 相似文献
9.
10.
针对传统城市腹地划分方法很少考虑阻碍因素的不足,该文将阻碍因素引入场模型,改进场模型中的城市综合规模,提出了基于改进场模型的城市腹地划分方法,较好地界定了城市影响范围;基于改进的场模型,实现了城市势力范围合理划分。以山东省17个地级市为研究对象,开展了城市腹地划分验证分析,实验结果表明:山东省各城市势力范围差异较大,中心城市的势力范围远远超出其行政范围,各城市势力圈与市域行政范围吻合性有待提高。研究表明城市腹地范围是由中心城市和周边城市的实力共同决定,是对城市经济区的重新界定,对城市体系规划和结构调整有一定参考意义。 相似文献
11.
ABSTRACTAnimations have become a frequently utilized illustration technique on maps but changes in their graphical loading remain understudied in empirical geovisualization and cartographic research. Animated streamlets have gained attention as an illustrative animation technique and have become popular on widely viewed maps. We conducted an experiment to investigate how altering four major animation parameters of animated streamlets affects people’s reading performance of field maxima on vector fields. The study involved 73 participants who performed reaction-time tasks on pointing maxima on vector field stimuli. Reaction times and correctness of answers changed surprisingly little between visually different animations, with only a few occasional statistical significances. The results suggest that motion of animated streamlets is such a strong visual cue that altering graphical parameters makes only little difference when searching for the maxima. This leads to the conclusion that, for this kind of a task, animated streamlets on maps can be designed relatively freely in graphical terms and their style fitted to other contents of the map. In the broader visual and geovisual analytics context, the results can lead to more generally hypothesizing that graphical loading of animations with continuous motion flux could be altered without severely affecting their communicative power. 相似文献
12.
增量式运动恢复结构(ISFM)实现了无序影像的三维重建,在精细化建模、现实场景三维记录以及互联网影像三维重建等领域发挥了重要的作用。但增量式运动恢复结构方法仍存在稳健性差和精度低等方面的问题,常导致三维重建结果难以令人满意甚至三维重建失败,严重限制了增量式运动恢复结构技术的发展应用。本文提出了一种增强稳健性、提升精度的运动恢复结构方法。本文方法有如下3点贡献:①针对立体影像特征匹配结果误差点多的问题,提出了一种顾及特征响应值的参数自适应RANSAC方法,在有效剔除误匹配的同时,最大限度地保留了正确的匹配点; 相似文献