视觉不变量是指那些对于尺度变化、物体移动、旋转、放射、透视变化仍保持不变的特征。
Visual invariants are those changes in scale, moving, rotating, radiation, the perspective changes remain invariant feature.
视觉是人类最完善的感知系统，基于视觉不变量的平面目标识别方法近年来得到广泛的关注。
Vision is the best perception system of human. Vision invariants for planar object recognition catch our attention.
大脑的结构不是固定不变的，如果没有图像需要处理，那么大脑视觉皮层将会重组并拥有新的功能。
The architecture of the brain is not fixed, and without images to process, the visual cortex can reorganize for new functions.
建立仿射不变的形状相似性度量是模式识别、计算机视觉和图象理解领域中的基本问题之一。
Establishing affine invariant similarity measure of shapes is one of the basic problems in pattern recognition, computer vision and image understanding domains.
但有一点不变，就是反映真实！而视觉真实是绘画的深层基础，也是最终目的。
A little bit, invariable, be true report! And the visual reality is the deep foundation of the painting, is also ultimate purpose.
针对这个问题，提出了一种基于双重交比不变的线结构光视觉传感器的标定方法，设计了相应的标定靶标。
To address this problem, a method basing on the invariance of double cross ratio is proposed for calibrating structured-light-stripe vision sensor, and the calibration target is designed.
实验结果证明，该算法在基本保持视觉效果不变的情况下，极大地提高了虚拟地形场景的绘制速度。
The experiment results indicate that this scheme may attain a much higher frame rate in rendering the virtual terrain scene, as well as maintain the visual quality.
不变矩的几何变换不变性特点，使其在模式识别、计算机视觉和图像重构中被广泛使用。
For geometric invariance of the invariant moment, it has been used in pattern recognition, computer vision and image reconstruction.
图像不变量特征的提取与构造是模式识别和计算机视觉领域中的关键技术之一。
Extracting or construction of the invariant features is one of the key technologies in the field of pattern recognition and computer vision.
交比是和射影变换有关的一个基本不变量，利用交比不变性的计算来揭示场景的本质特征也是计算机视觉研究的一个热点。
To discover intrinsic properties of a scene by using the computation of cross ratio invariance has been one of the most hot research areas in computer vision fields.
如何提取图像的不变性特征，构造一个高效率的分类识别系统一直是计算机视觉研究领域的一项热门课题。
How to extract invariable features of images and construct a efficient system of classification and recognition is always a hot spot in the field of computer vision.
通过实验验证该方法具有尺度不变特性，适用于尺度变化较大的视觉系统。
It is proved to be scale invariant by experiments and can be applied to the vision system with significant scale changes.
实验证明，该方法具有良好的平移、缩放、旋转和镜像不变性，得到的检索结果能很好地符合人的视觉感受。
Experiment results show that this method can keep good invariance under translation, rotation, scale and mirror, and the retrieved results match human visual perception very well.
本文以射影变换下的复比不变性为理论基础，设计了一种可基于形状信息进行视觉识别的灰度人工路标。
Based on invariance of the cross-ratio in projective transformation, this paper designed a gray artificial landmark for vision-based recognition by shape information.
提出了一种新型拓扑地图；该地图用激光的扇区特征和视觉的比例不变特征来联合表示节点。
A novel topological map is proposed in this paper, and its nodes are represented with the visual scale-invariant features and the beam features of the laser range finder.
基于交比不变性原理和一维靶标点共线的特点，提出了一种多视觉传感器全局校准方法。
Based on the invariance of cross-ratio and the collinear property of all points for one dimensional target, a global calibration method of multi-vision sensor system is proposed.
投影不变量具有与视点和摄像机内外参数无关等优点，正逐渐成为计算机视觉研究的常用工具。
Projective invariants are independent of viewpoints, intrinsic and extrinsic camera parameters and common used in computer vision gradually.
纹理分析是图像处理和机器视觉中的一个基本要素，而如何获得其中的纹理旋转不变性描述则是其中的重要环节。
Texture analysis is a basic issue in image processing and computer vision, and how to attain the rotation-invariant texture characterization is a key problem.
该地图用激光的扇区特征和视觉的比例不变特征来联合表示节点。
A novel topological map is proposed in this paper, and its nodes are represented with the visual scale-invariant features and the beam features of the laser range finder.
仿射变换下的点模式匹配和参数估计是计算机视觉中的重要研究课题，其关键是寻找对仿射变换不变的不变量。
Matching and parameter estimation of two point-patterns under an affine transform is a very important research topic in the field of computer vision.
仿射变换下的点模式匹配和参数估计是计算机视觉中的重要研究课题，其关键是寻找对仿射变换不变的不变量。
Matching and parameter estimation of two point-patterns under an affine transform is a very important research topic in the field of computer vision.
应用推荐