There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

I have developed "tennis elbow" from lugging this book around the past four weeks, but it is worth the pain, the effort, and the aspirin. It is also worth the (relatively speaking) bargain price. Including appendixes, this book contains 894 pages of text. The entire panorama of the neural sciences is surveyed and examined, and it is comprehensive in its scope, from genomes to social behaviors. The editors explicitly state that the book is designed as "an introductory text for students of biology, behavior, and medicine," but it is hard to imagine any audience, interested in any fragment of neuroscience at any level of sophistication, that would not enjoy this book. The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or

Principles of Neural Science

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Contoulet-based features have been paid much attention in image processing applications such as image enhancement,
edge detection, image fusion and image retrieval. In this paper, we present a novel approach which takes advantage of
the multi-scale and multi-directional properties of the Contourlet transform to extract features of real-world rough
surface texture. These features are effectively used for 3D surface texture classification and fusion. The classification
scheme based on these features achieves good results even for those test samples not included in the training data sets.
Three-dimensional surface texture fusion based on Contourlet can successfully preserve original texture patterns and
retain the significant features of input images, which can generate fusion images under arbitrary illumination directions.

Contourlet features for 3D surface texture classification and fusion

Simultaneous Localization and Mapping (SLAM) has always been a hot topic in the field of intelligent mobile robots in recent years. The existing SLAM algorithms have been developed relatively maturely under the assumption of static environment, and have achieved good performance. However, assuming a static environment limits the application of SLAM in dynamic scenarios to a certain extent. To solve the problems existing in the application of robots in dynamic scenes, this paper proposes a semantic SLAM system for dynamic scenes. We add depth information to adjust the contour of semantic segmentation results and combine it with an improved optical flow-based examination of moving consistency to form a dynamic detection algorithm that classifies feature points into three categories. Different types of features are selected according to different robot tasks, which weakens the effect of dynamic objects on the camera pose estimation and makes full use of static features to improve the localization accuracy of the robot in dynamic scenes. Meanwhile, a semantic octree map constructed from the static scene is generated, which can be used for advanced tasks. We set up experiments on the TUM RGB-D dataset. Compared with ORB-SLAM2, our system achieves up to 97.43% improvement in dynamic scenes and also outperforms four other advanced dynamic SLAM systems. Experiments show that our system reduces the pose estimation error of the camera in dynamic scenes to different degrees and improves the localization accuracy of the camera.

Visual Semantic SLAM Based on Examination of Moving Consistency in Dynamic Scenes

Procedural texturing is a powerful way to add details to the surface of rendered objects. The Worley basis function of Cellular Texture is the most popular one and widely used to create various kinds of solid textures. However, most applications are implemented over 2D textures, which do not present varied illumination and viewpoint information. We present a method for creating surface height maps based on cellular textures and relighting them on 3D scenes. Furthermore, we implement our algorithm on GPU and show real-time relighting performance under arbitrary lighting directions.

GPU-Based 3D Cellular Surface Texture Relighting

Visual-Inertial initialization aims at estimating key parameters for Visual-Inertial Simultaneous Localization And Mapping (VI-SLAM) systems. However, most existing methods put more emphasis on making all estimations jointly consistent whereas ignoring the influence of gravity estimation on accelerometer bias estimation, resulting in unreliable parameter estimation. This hinders the performance of VI-SLAM under challenging environments. In this paper, we propose a novel stereo visual-inertial initialization method in a coarse-to-fine manner to estimate the system parameters accurately. Concretely, our method consists of four stages: 1) The stereo visual tracking with a track-then-verify strategy to generate robust matches for reliable vision-only state estimation; 2) The IMU preintegration with Euler integration for preprocessing raw IMU data and obtaining the inertial-only state estimation; 3) Loosely-coupled visual-inertial alignment for coarse-level parameter estimation with polar-based gravity estimation; 4) Tightly-coupled nonlinear visual-inertial optimization for fine-level parameter estimation. Comparative experiments on the EuRoC dataset show that our method achieves highly competitive performance against the state-of-the-art methods in gyroscope bias, accelerometer bias, and gravity direction estimation.

Junyu Dong

Papers

Contourlet features for 3D surface texture classification and fusion

Visual Semantic SLAM Based on Examination of Moving Consistency in Dynamic Scenes

GPU-Based 3D Cellular Surface Texture Relighting

Robust Initialization for Stereo Visual-Inertial SLAM with Polar-Based Gravity Estimation