A Word Bank for Academic Writing

A Collection of important words and great expressions.

245 important words and 205 great expressions.


Useful links:
Google, WIKI, COCA, Google Translate, Baidu Translate, Youdao Translate


Learning:


Words

  1. 90th percentile  第90%的数 [?]
  2. Albeit conj. 尽管,虽然 [?]
  3. Augmented Reality  虚拟现实 [?]
  4. absence n. 缺席,不在 [?]
  5. accordance n. 一致 [?]
  6. acoustic sensor n. 声波传感器 [?]
  7. acquaint adj. 使...熟悉 [?]
  8. adverse adj. 不利的,有害的 [?]
  9. advocate v. 提倡 [?]
  10. aforementioned adj. 前面提到的 [?]
  11. aggravation n. 加重,恶化 [?]
  12. alleviate v. 减轻,缓和 [?]
  13. ambiguity n. 模棱两可 [?]
  14. ambiguity n. 模棱两可 [?]
  15. analogous adj. 模拟的 [?]
  16. annotate v. 注释 [?]
  17. annotation n. 注释 [?]
  18. appealling adj. 有吸引力的 [?]
  19. artifact n. 人工制品 [?]
  20. auxiliary adj. 辅助的,备用的 [?]
  21. auxiliary adj. 辅助的,备用的 [?]
  22. avionic n. 航空电子设备 [?]
  23. backhoe n. 挖掘机 [?]
  24. barometer n. 气压计 [?]
  25. bearing n. 轴承 [?]
  26. bearing angle  方位角,象限角 [?]
  27. bias n. 偏差 [?]
  28. bias n. 偏差,差异 [?]
  29. binocular adj. 双目并用的,双眼的 [?]
  30. boostrapping n. 引导程序 [?]
  31. breadth n. 宽度,广泛 [?]
  32. bulldozer n. 推土机 [?]
  33. bump sensor n. 碰撞传感器 [?]
  34. by leveraging...  通过依靠,使用... [?]
  35. camcorder n. 摄像机 [?]
  36. captioning n. 在图片上加说明 [?]
  37. caveat n. 警告,告诫 [?]
  38. cleanroom n. 无尘室 [?]
  39. cluster v. 集中,成群 [?]
  40. cluttered adj. 杂乱的,挤满的 [?]
  41. coarse-grained  粗颗粒的,粗粒度 [?]
  42. collision-less  无碰撞 [?]
  43. commercial off-the-shelf  现货 [?]
  44. commodity n. 商品,货物,日用品 [?]
  45. compelling adj. 引人入胜的 [?]
  46. complication n. 复杂,混乱 [?]
  47. comprehensive adj. 所有的 [?]
  48. compromise n. 妥协,危及,损害,连累 [?]
  49. concise adj. 简明的,简练的 [?]
  50. congestion n. 拥塞,塞车 [?]
  51. consecutive adj. 连续不断的 [?]
  52. consecutive adj. 连续不断的 [?]
  53. constellation n. 星座(卫星) [?]
  54. contaminated adj. 被污染的 [?]
  55. converge v. 会聚,收敛 [?]
  56. counterpart v. 对应物,配对物 [?]
  57. covariance n. 协方差 [?]
  58. crawl v. 爬行,爬虫(数据) [?]
  59. criteria n. 标准,尺度 [?]
  60. criterion n. 标准,原则 [?]
  61. crop v. 裁剪,剪短 [?]
  62. dashed line  虚线 [?]
  63. de-facto  事实上,实际上(没有规定但实际上...) [?]
  64. dedicated adj. 专注的 [?]
  65. deduce v. 推演,推算 [?]
  66. delicate adj. 精致的,微妙的 [?]
  67. depict v. 描写,叙述 [?]
  68. depict v. 描写,画,如...所示 [?]
  69. derive v. 推导,得到 [?]
  70. deterministic adj. 决定性的 [?]
  71. diameter n. 直径 [?]
  72. disarm v. 解除...武装 [?]
  73. discontinued adj. 停产的 [?]
  74. discrete adj. 离散的 [?]
  75. discrimination n. 辨别力,识别力 [?]
  76. disparity n. 不同,差异,视差(parallax) [?]
  77. distinctive adj. 独特的,特别的 [?]
  78. disturbance n. 骚动,动乱 [?]
  79. diverge v. 偏离,分叉,发散 [?]
  80. dodge v. 闪开,躲开,避开 [?]
  81. dominate v. 支配,控制 [?]
  82. dozens n. 若干 [?]
  83. drone n. 无人机 [?]
  84. edibility n. 可实用性 [?]
  85. elaborate adj. 复杂的,详尽的 [?]
  86. elbow n. 肘 [?]
  87. eliminate v. 排除,除去 [?]
  88. eliminate v. 消除,消灭 [?]
  89. embellish v. 美化,文章润色 [?]
  90. emit v. 发射 [?]
  91. emulate v. 仿真 [?]
  92. enforce v. 强制,坚持 [?]
  93. enumeration n. 枚举,列举 [?]
  94. equivalence n. 等价,对等 [?]
  95. erroneously adv. 错误地,不正确地 [?]
  96. evaluation metric  评价指标,评估尺度 [?]
  97. exclusively adv. 仅仅,专门地 [?]
  98. exhaustive adj. 详尽的,全面的 [?]
  99. explicit adj. 清楚的,明白的 [?]
  100. eyebrow n. 眉毛 [?]
  101. facade n. (建筑物的)正面,立面 [?]
  102. facilitate v. 促进,促使 [?]
  103. feasible  可行的,行得通的 [?]
  104. formulate v. 用公式表示 [?]
  105. fraction n. 分数,小数部分 [?]
  106. fraction n. 碎片,分数 [?]
  107. gesticulate v. 打手势 [?]
  108. government-subsidized adj. 政府补贴的 [?]
  109. grasp v. 抓取,抓住 [?]
  110. gyroscope n. 陀螺仪 [?]
  111. hinder v. 阻碍,阻止 [?]
  112. hip n. 髋 [?]
  113. imformative adj. 提供有用信息的 [?]
  114. immediate adj. 立即的,立刻的 [?]
  115. imply v. 暗示,包含 [?]
  116. incompatibility n. 不兼容 [?]
  117. inconsistency n. 不一致,矛盾 [?]
  118. incure v. 招致,招受 [?]
  119. inevitable adj. 不可避免的 [?]
  120. inference n. 推断,推理 [?]
  121. infinite adj. 极大的,无限的 [?]
  122. inherent adj. 固有的,内在的 [?]
  123. inpaint v. 修补,填充 [?]
  124. instantaneous adj. 立即的,立刻的 [?]
  125. intensity n. 亮度 [?]
  126. interpretability n. 可解释性,可解读性 [?]
  127. intuitively adv. 直观地 [?]
  128. involved adj. 有关的,复杂的 [?]
  129. irritation n. 愤怒 [?]
  130. jointly adv. 连带地 [?]
  131. laborious adj. 耗时费力的,辛苦的 [?]
  132. leverage v. 依靠,使用 [?]
  133. leverage v. 对...施加影响 [?]
  134. limb n. 肢,四肢 [?]
  135. maturity n. 成熟 [?]
  136. medicinal adj. 有疗效的 [?]
  137. methodology n. 方法,研究方法 [?]
  138. metric n. 度量,指标 [?]
  139. minimalistic adj. 极简化的 [?]
  140. modality n. 形态,形式 [?]
  141. monochrome n. 黑白照片,灰度图像 [?]
  142. nature n. 特性,特点 [?]
  143. necessitate v. 使...成为必须,使需要 [?]
  144. noise-free adj. 无噪声的 [?]
  145. nominally adv. 名义上地 [?]
  146. novel adj. 新颖的,与众不同的 [?]
  147. novelty n. 新颖,创新 [?]
  148. occluded by...  被...阻塞 [?]
  149. occlusion n. 阻塞,吸留 [?]
  150. off-the-shelf  现货供应的 [?]
  151. omit v. 忽略 [?]
  152. optoisolatd adj. 光电耦合的 [?]
  153. outperform v. 胜过,比...好 [?]
  154. outperform v. 超过,胜过 [?]
  155. panchromeatic adj. 全色的 [?]
  156. paradigm n. 模型(正式) [?]
  157. parallax n. 视差 [?]
  158. parameterization n. 参数化 [?]
  159. patrol n. 巡逻 [?]
  160. payload n. 装载量,负载 [?]
  161. pedestrian n. 行人,路人 [?]
  162. percentile n. 百分数 [?]
  163. photoelectron n. 光电子 [?]
  164. piecemeal adj. 零散的 [?]
  165. pillar n. 柱子 [?]
  166. pilot v. 驾驶 [?]
  167. pipeline n. 流程,管线 [?]
  168. plethora n. 过多,过剩 [?]
  169. poisoning n. 中毒 [?]
  170. pole n. 杆,电线杆 [?]
  171. postpon v. 延期,推迟 [?]
  172. preintegrated adj. 预先整合的 [?]
  173. prerequisite n. 前提,先决条件 [?]
  174. presence n. 存在,出现 [?]
  175. presence n. 存在,出现 [?]
  176. prevalence n. 流行 [?]
  177. priori adj. 先验的 [?]
  178. prohibitely expensive adj. 价格高得离谱的 [?]
  179. promising adj. 有希望的,有前途的 [?]
  180. propagate v. 传播,宣传 [?]
  181. propeller n. 推进器 [?]
  182. proportional adj. 成比例的 [?]
  183. proprietary adj. 专卖的,专利的 [?]
  184. qualitative adj. 质量的,定性的 [?]
  185. quantitative adj. 定量的 [?]
  186. realistic adj. 现实的,实际的 [?]
  187. reconnaissance n. 侦查 [?]
  188. recursive adj. 递归的,循环的 [?]
  189. regulatory adj. 管理的,监管的 [?]
  190. reproducibility n. 重复性,复现性 [?]
  191. requisite n. 必须的事物,先决条件 [?]
  192. retention n. 保留,保持 [?]
  193. retrieval n. 检索 [?]
  194. road grader n. 压路机 [?]
  195. sacrifice n. 牺牲 [?]
  196. saliency n. 显著性 [?]
  197. salient adj. 显著的,突出的 [?]
  198. scenario n. 场景 [?]
  199. sector n. 行业 [?]
  200. self-contained adj. 独立的,自主的 [?]
  201. sensor-agnostic adj. 传感器未知的 [?]
  202. skeletal adj. 骨架的,骨骼的 [?]
  203. skyrocket v. 飞涨,猛涨 [?]
  204. soldering n. 焊锡 [?]
  205. specification n. 规范,规格,说明书 [?]
  206. spider v. 爬虫 [?]
  207. spuriou adj. 虚假的,伪造的 [?]
  208. state-of-the-art  最新的 [?]
  209. status quo  现状,维持现状 [?]
  210. subdivide v. 再分,细分 [?]
  211. substitute into  代入... [?]
  212. suitability n. 适合 [?]
  213. synchronize v. 同步 [?]
  214. synonyms n. 同义词 [?]
  215. synthesize v. 人工合成 [?]
  216. synthesized adj. 合成的 [?]
  217. synthetic adj. 人造的,人工的 [?]
  218. tabular adj. 表格的,列成表的 [?]
  219. tackle v. 处理 [?]
  220. tedious adj. 冗长的 [?]
  221. telemetry n. 遥测,测控 [?]
  222. temporal adj. 时间的 [?]
  223. temporally adv. 时间上的 [?]
  224. temporally synchronized  时间同步的 [?]
  225. thereafter adv. 之后,此后,以后 [?]
  226. thesis n. 论文(学位论文),区别于paper [?]
  227. thorough adj. 彻底的 [?]
  228. thrust v. 刺,塞 [?]
  229. tilde n. 波浪号 [?]
  230. topographic adj. 地形的 [?]
  231. tradeoff n. 权衡,折中,取舍 [?]
  232. trajectory n. 轨迹,弹道 [?]
  233. trivial adj. 不重要的,琐碎的 [?]
  234. trivial adj. 不重要的,琐碎的 [?]
  235. ubiquitous adj. 十分普遍的 [?]
  236. unprecedented adj. 前所未有的 [?]
  237. utilization n. 使用,利用 [?]
  238. utilize v. 使用,利用 [?]
  239. vacuum v. 用吸尘器清扫 [?]
  240. vague adj. 含糊的,不明确的 [?]
  241. vaguely adv. 模糊地 [?]
  242. valuable adj. 有用的,重要的 [?]
  243. vibrant adj. 充满生机的 [?]
  244. wire n. 线,电线 [?]
  245. wrist n. 手腕 [?]
↑ return to top ↑

Expressions

  1. ... achieve very high resolution imagery at low cost 以低成本实现了很高地表分辨率的影像
  2. ... are detailed in part 3. ...在第三部分进行了详细描述
  3. ... are summarized in Table 1 ...总结如表1
  4. ... bridge the ... gap between ... and ... ...架起了...和...之间的...的桥梁
  5. ... can introduce errors ...可以引入误差
  6. ... can provide better accuracy than ... and much lower resources utilization than ... 相比于...和...,...可以提供更好的精度和更低的资源利用
  7. ... contains most of common daily scenes in which a person usually appear ... 包含了一个人通常出现在日常生活中的大多数场景
  8. ... excessive amounts of motion blur will be captured. 会捕捉到大量的运动模糊
  9. ... extremely complex and expensive 尤其复杂与昂贵
  10. ... fill a gap between in introductory-level robotics courses and extensible drone platforms for education ... 填补入门级机器人技术课程与可扩展无人机教育平台之间的空白
  11. ... gives the most efficient performance, although it makes a significant sacrifice in overall accuracy, as well as robustness on challenging trajectories. ... 提供最有效的性能,尽管它在整体精度上做出了重大牺牲以及牺牲了在具有挑战性的轨迹上的鲁棒性。
  12. ... has a large overlap with ... 与...有很大重叠
  13. ... has received a high degree of attention and research efforts over the last years. ... 在过去的几年里受到了高度的关注和研究。
  14. ... is depicted in Figure 7. ...在图7中进行了说明
  15. ... is not optimized for real-time operation ...并没有针对实时运行进行优化
  16. ... is provided in Figure 9 ...如图9所示
  17. ... is the first commercial microsatellite that can produce sub-meter GSD imagery and video when combined with ground-based image processing systems. ...是第一颗商业微纳卫星,当与地面图像处理系统结合时,可以产生亚米级地表分辨率的图像和视频。
  18. ... is the ideal resolution to detect activity that impacts the global economic landscape ...是用于探测影响全球经济活动的理想的地表分辨率
  19. ... large pixels to collect many photoelectrons 用于手机很多光电子的大像素
  20. ... many are specific to a certain type of hardware or are limited to a particular environment. ...许多都针对于特定类型的硬件或仅限于特定环境
  21. ... relaxes the pointing stability required by ... ...缓解了由...带来的对指向稳定性的要求
  22. ... resolutions grater than 1m GSD 优于1m的地表分辨率
  23. ... run at a very high frame rate 以一个比较高的帧率运行
  24. ... seems to be a trivial detail but turns out rather crucial. ...似乎是一个不重要的细节但事实上却很重要
  25. ... squeeze very high-performance into a very small form factor(mass and volume) ... 将非常高的性能压缩到非常小的形状因子(质量和体积)
  26. ... suffer from an inherent lack of scale information ...面对尺度信息的先天缺乏情况
  27. ... uniform pixels responses across all three sensors 在所有三个传感器中统一像素响应
  28. ... use the absolute trajectory RMSE as the error metric for our experiments ...用绝对轨迹RMSE作为实验的误差度量
  29. ... we do not cover the algorithm in depth 我们不深入讨论算法
  30. ... which is the foundation of benchmarking the accuracy of different algorithms ...是衡量不同算法准确性的基础
  31. ... which leaves many open issues ...留下许多悬而未决/待解决的问题
  32. ... without incurring motion blur or smear into the imagery 不会引起图像的运动模糊或模糊
  33. A map is necessary to localize, but one must localize to create a map. - chicken and egg problem 地图对于定位来说是必须的,但同时又需要定位才能创建地图-鸡生蛋蛋生鸡的问题。
  34. A real-time requirement meant a slight reduction in accuracy in exchange for constant time assumption. 实时性要求意味着用不变的时间假设来交换精度的轻微降低。
  35. A study of ... was conducted to determine the overall accuracy of WorldView ortho products. 为了确定WorldView正射产品的总体精度,一个...研究被进行了。
  36. Absolute Trajectory Error(ATE) 绝对轨迹误差
  37. Absolute geolocation accuracy is a measure of the location of an object, as it appears in a product, with respect to its true location on the Earth. 绝对地理定位精度是指对影像中出现的某个物体的位置与其在地球上真实位置的测量。
  38. Accuracy and robustness can be improved with additional computation, but on systems with limited resources, finding the right balance between the computing requirements can be challenging. 通过额外的计算可以提高精度和鲁棒性,但对于资源有限的系统,在计算需求之间找到正确的平衡点可能是一项挑战。
  39. Achieving both high temporal resolution and high spatial resolution has been very hard/difficult to achieve. 实现高时间分辨率和高空间分辨率一直是非常困难的。
  40. Although the assumption holds for some robotic applications. 尽管这种假设适用于一些机器人应用。
  41. Among motion based approaches 在基于运动的方法中...
  42. As robots become more common, they also become more accessible and easier to develop. 随着机器人越来越普遍,它们也变得更容易获取和开发。
  43. As the segment contours are high-gradient areas, the keypoints falling in this intersection have to be removed. 由于线段轮廓是高梯度区域,因此必须删除落在这些区域上的特征点。
  44. Because of both practical and theoretical benefits, 由于实际与理论上的好处...
  45. Because of the advantages and disadvantages of both methods, we consider that they are complementary and therefore their combined used is an effective way of achieving accurate tracking and mapping. 由于这两种方法的优缺点,我们认为它们是互补的,因此它们的结合使用是实现精确跟踪和建图的有效途径。
  46. Because the segment contours usually become high-gradient areas, salient point features tend to appear. We do not consider the features in such contour areas. 由于线段轮廓通常成为高梯度区域,因此会出现显著的点特征。我们不考虑这些边缘区域的特征。
  47. CE90 is the circular error at the 90th percentile. This means that a minimum of 90 percent of the points measured has a horizontal error less than the stated CE90 value. CE90是第90百分位处的圆误差。这意味着至少90%的测量点的平面误差小于规定的CE90值。
  48. CPU and memory load CPU与内存负载
  49. Due to the power and payload constraints of aerial platforms, state estimation algorithms must provide these qualities under the computational constraints of embeded haraware. 由于空中平台的功率和有效载荷的限制,状态估计算法必须在嵌入式硬件的计算限制下提供这些特性。
  50. Early approaches to tackle this issue ... 解决这个问题的早期方法...
  51. Figure best viewed in electronic format. 以电子格式查看图片有最好效果。
  52. For a single camera, 3D points that are in the same direction but at different distances are projected to the same 2D point, which leads to the scale ambiguity. When a second camera with a constant transformation relative to the first one is added, the scale ambiguity is eliminated. 对于单摄像机,同一方向不同距离的三维点都会投影到同一个二维点上,导致尺度不确定。当添加相对于第一个相机具有恒定变换的第二个相机时,消除了这种尺度不确定。
  53. For an individual control point, the geolocation error is measured by calculating the difference between the observed location in the product and the known, surveyed location. 对于单个控制点,通过计算产品中观测位置与已知测量位置之间的差异来测量地理位置误差。
  54. Furthermore, we have compared our system against the original ORB-SLAM2 to quantify the improvement of our approach in dynamic scenes. 此外,我们还将我们的系统与原始的ORB-SLAM2进行了比较,以量化我们的方法在动态场景中的改进。
  55. Geolocation accuracy is determined by comparing a known, surveyed location (typically a ground control point), to the corresponding photo-identifiable feature in an image product.  地理定位精度是通过将已知的测量位置(通常是地面控制点)与图像产品中相应的照片可识别特征进行比较来确定的。
  56. Geolocation accuracy is driven by the sensors and models used in the imagery collection system and by terrain displacement when the image pixels are projected to a surface on the Earth. 地理定位精度由图像采集系统中使用的传感器和模型决定,也受图像像素投影到地球表面时的地形位移影响。
  57. Geolocation accuracy of ortho products is determined by creating ortho products over sites that contain a dense network of surveyed ground control points.  正射产品的地理定位精度是通过在包含已测地面控制点密集网络的场地上创建正射产品来确定的。
  58. However, the trained models cannot be applied for arbitrary configurations, and re-training is often more resource intensive than applying a conventional calibration approach. In addition, the failure case analysis and analytical estimation of the limits of operations are highly challenging for black box deep learning approaches. 然而这些训练好的模型并不能适用于任意的硬件配置环境,并且重新训练一个网络通常比应用常规校准方法更耗费资源。此外,对于黑箱的深度学习方法来说,故障案例分析和操作限制的分析估计是非常具有挑战性的。
  59. If a camera is the only sensor used, the system has no way of knowing scale. It is impossible with only one image to tell the scale of an object. 如果摄像机是唯一使用的传感器,则系统无法知道尺度信息。只有一幅图像是不可能分辨出物体的尺度大小的。
  60. In order to accomplish this accurately and efficiently 为了精确与高效地完成...
  61. In order to localize, one needs a map. In order to create a map, one must localize. 为了定位,需要一张地图,而要创建地图,又必须要定位。
  62. In order to satisify regulatory requirements... 为了满足监管要求...
  63. In our case 在我们的情况中
  64. In our experiments, we observed a common problem that... 在我们的实验中,我们观察到了一个场景的问题...
  65. In this work, we conducted a survey of ... 在这项工作中,我们对...进行了调查
  66. In words, xxx aims to find the x that minimizes the sum of covariance weighted visual and inertial residuals. 也就是说,xxx的目标是找到最小化协方差加权视觉和惯性数据残差之和的x。
  67. Inequality holds for any weighted mean of the two points. 不等关系对于任意两个点的加权平均仍然成立。
  68. It implies that the image-matching based on grey correlation is sensitive to the image grey feature, which indicates that the more similar the reffered band with the test band, the better the evaluation results. 它说明了基于灰度相关的影像匹配对于影像的灰度特征很敏感,也就是说参考波段与待配准波段越相似,评价的结果就越好。
  69. It is important that sensors used be low cost with simple calibration requirements. 重要的是,使用的传感器应该使用成本低且校准要求简单。
  70. It is trivial for humans to make this distinction. 对于人类而言做这种判别是很简单(微不足道)的。
  71. Landmarks are detected and compared with a map to localize the robot while at the same time newly detected landmarks are added to that map. 检测地标并与地图进行比较以定位机器人,同时将新检测到的地标添加到地图中。
  72. Multivariate Gaussian Model 多变量高斯模型
  73. Nonlinear Least Square(NLLS) problem 非线性最小二乘问题
  74. On the other hand our SVS fully exploits the fact that... 另一方面,我们的SVS方法充分证实了...这样一个事实
  75. Products have a pointing accuracy of a 5 meters CE90, meaning that 90 percent of all WorldView Basic and Standard products will achieve a horizontal accuracy of 5 meters or better. 产品的指向精度为5米CE90,这意味着90%的WorldView基本和标准产品将达到5米或更好的平面精度。
  76. Relative Error(RE) 相对误差
  77. The WorldView-1 horizontal accuracy versus time is provided in Figure 3. WorldView-1平面精度与时间的关系如图3所示。
  78. The above transformation estimation can be defined as a finite search problem by discretization of the possible parameter space into equal bins. 通过对可能的参数空间进行离散化成相等的区域,上面的变换估计可以被定义为一个有限搜索问题。
  79. The affine transformation matrix between frames does not account for the roll and pitch of the camera out of the image plane. 帧之间的仿射变换矩阵不考虑相机相对于图像平面的滚动和俯仰。
  80. The comparison against the state of the art shows that DynaSLAM achieves in most cases the highest accuracy. 与最新的SLAM比较表明,DynaSLAM在大多数情况下达到了最高的精度。
  81. The error between the location of the projected pixel and the GCP is the error for that point.  投影像素的位置和GCP之间的差异就是该点的误差。
  82. The ground control points are used for accuracy testing purposes and are not used to correct the position of the image. The difference in the location of feature representing the control point in the image, and actual location of the control point is measured in the image. This difference is the error for that pixel. The errors for all the control points in the image are measured and these errors are used to calculate the accuracy of the image.  地面控制点仅用于精度评价,并不用于校正图像位置。控制点的实际位置以及影像中表示该控制点的特征位置之间的差异被测量,这个差异就作为该像素的定位误差。最后图像中所有控制点的误差都被测量,基于这些误差来计算图像的精度。
  83. The high barrier to entry prevents many students from taking these courses and being exposed to the field. 很高的入门门槛阻碍了学生选择这些课程以及了解该领域。
  84. The horizontal and vertical axes are error in the East and North directions, respectively, both in units of meters. 水平与竖直坐标轴分别表示东和北方向上的误差,单位都是米。
  85. The majority of robots still lack even the most basic forms of autonomy. 大多数机器人甚至还缺乏最基本的自动形式。
  86. The motivation of this paper is to address this deficiency by performing a comprehensive evaluation of publicly-available VIO algorithms on hardware configurations that are typical of flying robot systems. 本文的目的是通过在飞行机器人系统的典型硬件配置上对公开可用的VIO算法进行综合评估来解决这一缺陷。
  87. The outline of the paper is the following 论文的提纲如下
  88. The remainder of this paper will present the details of each of these principles. 本文的其余部分将详细介绍这些原则。
  89. The rest of the letter is structured as follows ... 这篇letter的其余部分结构如下...
  90. The rest of the tutorial is structed as follows. 本教程的其余部分结构如下。
  91. The rest of this thesis is dedicated to explaining the details ... 这篇论文的其余部分致力于解释...的细节
  92. The subscript i indicates... 下标i表示...
  93. The system acquires multiple images of the same location on the ground while collecting data in a "push-frame" approach. 该系统采用“推帧”方式采集数据,同时采集地面同一位置的多幅图像。
  94. There is no free lunch in visual state estimation. 在视觉状态估计中没有免费的午餐。
  95. These limitations block the evaluation and improvement of methods. 这些限制了方法的评估与进步。
  96. They paint an accurate picture of obstacles faced by real, situated robots. 他们准确地描绘了真实的情形下机器人所面临的障碍。
  97. This is obviously not the case if we use the difference as an error metric directly. 如果我们直接使用差分作为误差度量,显然不是我们期望的结果。
  98. This iteration converges to a local optimum. 这个迭代收敛到局部极值。
  99. This phenomenon significantly reduced the performance and robustness of the matching. To handle this issue we introduce a pre-processing step 这个现象显著降低了匹配的性能与鲁棒性。为了解决这个问题,我们引入一个预处理步骤...
  100. This section outlines the stages of this program. 本部分列出了该程序的主要阶段。
  101. This survey of available systems shows that existing platforms do not satisfy all of the educational goals. 对现有系统的调查表明,现有的平台并不能满足所有的教育目标。
  102. Though semi-automatic methods may yield very accurate calibration, these approaches are very time consuming and the calibration results highly depend on the skills of the operators. 虽然半自动方法可能产生非常精确的校准结果,但这些方法非常耗时,校准结果高度依赖于操作员的技能。
  103. To address the first problem 为了说明第一个问题
  104. To benefit the reproducibility of related research, we release our implementation of the methods in this tutorial to the public. 为了方便相关研究的重复工作,我们将这篇文章中我们方法的实现(代码)公开了。
  105. To handle the merging problem of... 为了解决这个出现的...问题
  106. To our best knowledge 据我们所知
  107. To quantify the improvements of... 为了量化...的提升
  108. To this end 为了达到这个目的
  109. To this end, ... 为了这个目的
  110. Two commonly used error metrics are the absolute trajectory error(ATE) and the relative error(RE). 两种常用的误差度量是绝对轨迹误差(ATE)和相对误差(RE)。
  111. Univariate Gaussian Model 单变量高斯模型
  112. VO/VIO is able to provide robust state estimate for other tasks, such as control and planing, and therefore is widely used in robotic applications. VO/VIO能够为控制和规划等其它任务提供鲁棒的状态估计,因此在机器人应用中得到了广泛的应用。
  113. We are following that to be consistent in notation. 我们遵循它以在表达记法上保持一致。
  114. We can find strengths and limitations in both methods, hense the motivation for their combined use. 我们可以发现这两种方法的优点和局限性,这也是将它们结合使用的动机。
  115. We can see "raw" estimation from VINS-Mono is in a different reference frame as the groundtruth, and therefore cannot be directly compared. 我们可以看到VINS-Mono直接的估计结果与真实在不同的参考坐标系中,因此它们不能够直接比较。
  116. When a map is not available and building one is not feasible, it is impossible to know a robot's exact location, so a best guess pose estimate can be maintained along with a measure of uncertainty. 当地图不可用且构建地图不可行时,就不可能知道机器人的准确位置,因此我们可以通过测量不确定程度来维持一个最优的位姿估计猜测。
  117. abnormal action detection 异常行为检测
  118. accuracy specifications 精度参数(指标)
  119. accuracy stability over time 精度的时间稳定性
  120. accurate depth with detailed texture and color information can be obtained in parallel from the scene 携带纹理和颜色的精确的深度信息可以从场景中并行地获得
  121. adopt a structure from motion (SfM) method 采用SfM的方法
  122. aerospace-grade 航空级
  123. approaches can be methodologically divided into two main categories 这些方法可以主要被分为两类
  124. assess accuracy 精度评价
  125. baseline for comparison 用于比较的基准方法
  126. canonical model 经典模型
  127. compromise between computational cost and accuracy 计算成本与精度的折中
  128. computational overload 计算负担
  129. conduct the experiments 做实验
  130. constellation of many satellites 多个卫星的星座
  131. discrete parameterization 离散参数化
  132. divide and conquer 分而治之
  133. downlink&uplink 下传与上传
  134. drive up 抬高
  135. dynamic changes in the motion and in the environment 运动与环境中的动态变化
  136. evaluate the method 评价这个方法
  137. even-distributed 均匀分布的
  138. expensive high quality sensors 昂贵的高质量传感器
  139. fair and thorough performance measurement 公正彻底的性能衡量
  140. fault tolerance 容错性
  141. give depth information rapidly and accurately 快速准确地给出深度信息
  142. ground robots 地面机器人
  143. ground sample distance(GSD) 地表采样距离,对应中文的地表分辨率
  144. high accurate ground control points 高精度地面控制点
  145. high spatial resolution 高空间分辨率
  146. high temporal resolution 高时间分辨率
  147. highly active field of research 高度活跃的研究领域
  148. highly dynamic scenes 高动态场景
  149. horizontal error/accuracy 平面误差/精度
  150. image domain 影像域,影像坐标系
  151. imagery 在论文中对应于“影像”的抽象概念,image是图片,像片的意思
  152. in the literature 在相关文献中
  153. include but are not limited to 包括但不限于
  154. inherent inability to measure scale 测量尺度的先天能力缺陷
  155. intractable to deal with 很难对付(或处理)的
  156. irrelevant correspondences 不相关的对应匹配
  157. is primarily driven by 主要由...影响
  158. it should be emphasized that... 需要强调的是...
  159. latent variable 隐变量
  160. line & sample 行、列
  161. linear push-broom satellite 线阵推扫卫星
  162. low-dynamic scenes 低动态场景
  163. methods to deal with noise and uncertainty 处理噪声与不确定的方法
  164. misalignment 未配准、未对齐
  165. more robust performance 更鲁棒的性能
  166. noise introduced by ... 由...引入的噪声
  167. non-convex optimization 非凸优化
  168. not well investigated in previous vision tasks 在以前的视觉任务中没有得到很好的研究
  169. orbital dynamics 轨道动力学
  170. ordinary people 普通人
  171. original image 原始影像
  172. photoelectron integration time 光电子积分时间
  173. pointing capability and pointing stability 指向能力与指向稳定性
  174. poorly triangulated visual features 三角化不良的视觉特征
  175. pose estimation accuracy 位姿估计精度
  176. problems we encountered are described in ... 在...描述了我们所遇到的问题
  177. quantitative evaluation 定量评价
  178. raw camera and Lidar sensor streams 原始相机与Lidar数据流
  179. registered image 配准的影像
  180. registration error 配准误差
  181. reliable information 可靠的信息
  182. represented by ... 由...表示
  183. resource constained system 资源受限的系统
  184. rigorous corresponding relationship 严密的对应关系
  185. salient points matching 静态点匹配
  186. scale ambiguity 尺度不确定性
  187. significant burden 显著的负担
  188. static scenarios 静态场景
  189. sub-meter GSD 亚米级地表分辨率
  190. sub-pixel accuracy 亚像素精度
  191. take into account 考虑
  192. terrain-induced offset 地形引起的偏移
  193. the accuracy was consistent regardless of the platforms 无论平台如何,精度都是一致的
  194. the challenges and complexity associated with robotics in the real world 现实世界中与机器人相关的挑战和复杂性
  195. their measurements have highly diverse characteristics, which makes the efficient exploitation of the multimodal data challenging 它们的观测数据特性差异很大,这使得有效发掘这些数据成为挑战
  196. this step may have a direct impact on the quality of the object based alignment algorithm 这个步骤可能对于基于目标的配准算法质量有直接的影响
  197. time-delay integration(TDI) CCD array 时延积分CCD阵列
  198. trade-offs between error and computational resources 错误和计算资源之间的权衡
  199. tune 调整,调参等,tune parameters
  200. variants or extensions of... ...的变种或延伸扩展
  201. vertical accuracy performance meets the 5 meter accuracy specification 垂直精度性能满足5米精度规范
  202. vertical error/accuracy 高程误差/精度
  203. visual interpretation 视觉解译
  204. vital role 关键角色
  205. we address the extrinsic calibration problem as a registration task 我们将外参标定问题作为一个配准任务
↑ return to top ↑