Xinguo Yu

A framework of timestamp replantation for panorama video surveillance

This paper presents a framework to automatically replant timestamps for panorama video surveillance. The system mainly comprises six modules: 1) timestamp localization; 2) image registration; 3) timestamp pixel recovery; 4) color correction; 5) timestamp recognition; and 6) panorama video generation. The proposed framework first develops a method to localize the timestamp by employing the method of locating digital video clocks. Then, a fast and novel method is developed to recover the pixels covered by timestamps. The proposed method has fast speed because a fast image translation estimation procedure is introduced based on the PTZ camera motion estimation and global histogram-based image matching. Moreover, a hybrid color correction method by combining region matching with the gamma correction and the linear correction is presented. To plant timestamps accurately, a timestamp recognition procedure is developed by adopting the time recognition method for digit video clocks. Experimental results show that the proposed approach can accurately remove timestamps in real time, the recovered frames are visually consistent with the real scene, and the performance of color correction for panorama video is visually acceptable.

Extraction of Implicit Quantity Relations for Arithmetic Word Problems in Chinese

The extraction of implicit quantity relations is one of critical steps of building the machine solver for solving arithmetic word problems. Extracting implicit quantity relations is a challenge research problem as partial problem of natural language understanding, which has no mature solution method. To address this challenge, the existing work in the extraction of quantity relations mainly relies on creating problem solving framework and extracting system of linear equations. However, these existing methods can solve the relatively simple problems due to they have no methods to extract implicit quality relations. This paper proposes a novel method for extracting implicit quantity relations, which is achieved by the process of Chinese phrase parse, classification and instantiation method of required general implicit quantity relations with semantic models. A set of experiments were conducted to classify the arithmetic word problems, and an example was taken to illustrate the proposed method of identifying general implicit quantity relations. The experimental results demonstrate that the proposed method is effective in extracting implicit quantity relations.

An Automatic Timestamp Replanting Algorithm for Panorama Video Surveillance

Timestamp replanting is required when we want to remove timestamps in individual videos and to plant a timestamp into their merged panorama video. This paper presents a preliminary automatic timestamp replanting algorithm for producing panorama surveillance video. Timestamp replanting is a challenge problem because localization, removal, and recognition of timestamp are three difficulty tasks. This paper develops methods to attack the difficulties to finish the tasks. First, it presents a novel localization procedure which first localizes second-digit by using a pixel secondly-periodicity method. And then it localizes timestamp via extracting all digits of timestamp. Second, it adopts a homography-based method to conduct timestamp removal. Third, it presents a digit-sequence recognition method to recognize second-digit and online template matching to recognize the other digits. Experimental results show that the algorithm can accurately localize timestamp in a very low computing cost and that the performances of replanting are visually acceptable.

An algorithm for timestamp removal for panorama video surveillance

This paper presents an algorithm for removing the timestamp of a video surveillance before it is merged to form a panorama surveillance video. Timestamp localization and timestamp pixel recovery are two challenging tasks for developing timestamp removal algorithm. This paper presents a novel localization procedure which first localizes the second-digit by using a pixel secondly-periodicity method. And then it develops a procedure for timestamp removal. Experimental results show that the algorithm can accurately localize timestamp in a very low computing cost and that the performance of timestamp removal is visually acceptable.

Understanding Plane Geometry Problems by Integrating Relations Extracted from Text and Diagram

Understanding problems is a critical and hard step for solving plane geometry problems. This paper presents a method for understanding plane geometry problems by integrating the information from text and diagram two modalities. Then high-confidence geometric relations are extracted for problem understanding through integrating the information separately extracted from text and diagram. And this paper also presents a function that can visually encode the extracted relations into the diagram to interactively present the visual effects of problem understanding results. The geometric relations are mined from the diagram after visual primitives are detected. The syntax-semantics (S\( ^{2} \)) model method is adopted to extract geometric relations from the text. And an integration process is used to couple the information from text and diagram to obtain the high-confidence geometric relations. The experimental results show that the proposed method can mine geometric relations in high accuracy and it can understand some problems that cannot be understood by using text only or by using diagram only.

Automatic Problem Understanding from Circuit Schematics

This paper presents an algorithm for understanding problems from circuit schematics in exercise problems in physics at secondary school. This paper models the problem understanding as a problem of extracting a set of relations that can be used to solve problems with enough information. The challenges lie in not only analyzing the circuit schematics but also extracting the proper relations for a given exercise problem. To face these challenges a novel approach is proposed to detect circuit nodes with their current flows to extract the current equations for nodes. And the other novel approach is proposed to extract voltage equations of independent loops. The proposed approach was tested with a dataset collected from the text books and the exam papers for the students at secondary schools. Experimental results show that the effect of recognition and analysis we designed delivers promising result, and our approach can be adapted to more complex electrical circuit analysis.

Extracting Plücker Line and Their Relations for 3D Reconstruction of Indoor Scene

The structure line is an important clue for understanding indoor space. Unfortunately, in the context of indoor scene, very little structural data is available due to occlusion. To address this issue, this paper proposes to extract structural lines and analyze their relations to obtain the structure lines, which are continuous, anti-occlusion, able to reconstruct indoor space. In this paper, Plucker line is used to express the lines in 3D indoor scene. And then it studies the properties and the benefits of using Plucker line. For the first time, a new strategy is suggested to maintain the integrity of indoor space, which uses the extracted high confidence lines to infer the properties of other lines. Experimental results show that our methods have many advantages in obtaining a complete 3D interior structure line, which resists most occlusion in near ground.

Machine Solving on Hypergeometric Distribution Problems

Hypergeometric distribution is one of the most important mathematical models in probabilistic subjects, and also an integral part of the intelligent tutoring system based on automatic machine solving. In this paper, we propose a set of solutions to automatically solve the Hypergeometric distribution problems. Our method combines the syntactic and semantic information of the subject, establishes the matching rule between the topic narration and the type template, and implement the problem solving by establishing the solution formula corresponding to the topic, as well as extracting and complementing the corresponding problem data. Experiments conducted on a dataset which collected from the Internet and College Entrance Examination questions over the years demonstrate the feasibility of our method.

Extracting Algebraic Relations from Circuit Images Using Topology Breaking Down and Shrinking

Extracting algebraic relations from a given circuit image is still a challenge task due to the complex topology of considered circuit. This paper presents an approach for extracting algebraic relations from circuit images through producing a set of atomic topologies from the complex topology of a given circuit. In which, algebraic relations, in form of a set of equations involving voltage, current and resistance relations from atomic topologies that is obtained by an iteratively operation of transforming a complex series/parallel connection into a series of atomic connection topology breaking down and shrinking. The extracted algebraic relations can be used to solve the exercise problem described by the circuit. Experimental results on 20 exercise problems show that the proposed algorithm can obtain a complete set of algebraic relations that can be used to solve the given problem. Further experiments conducted on a dataset of 200 scanned circuit images from the text books and exam papers demonstrate the proposed algorithm is the robustness and effectiveness.

China-Finland EduCloud Platform Towards Innovative Education

Education for innovation development is emphasized looking at the future of education. Cloud computing is regarded as the key trigger and enabling technology to advance innovative education. This paper specifies an intelligent Cloud-based platform for innovative education under the term of EduCloud. We give an overview and discuss the challenges facing future education, especially in the cases of China and Finland. We define innovative education and EduCloud-relevant concepts. We give an overview of Cloud computing and present EduCloud platform. We also describe current practices and initiatives in innovative education in the China-Finland arena.