马在田院士个人主页

马在田院士个人主页: "一个诚实的科学家能做出受国际重视的成果是可以冲破人为障碍的。一切优秀的科研成果是迟早会被承认的。你可以用诚实的工作成果找到知音。借用李白的两句诗表达自己的感受，那就是“莫愁前路无知己，天下谁人不识君”。一切正直的科学家的成果是会受到被承认的时候，当然是有迟早之别的。"

马在田院士个人主页

马在田院士个人主页: "认识自我，追求优秀，在不断完善知识结构中成才"

看了马院士的院士寄语，深受感动，引用其中一句如下：

科学一流必须是国际的，没有国内国外之分。因此当代青年追求的优秀都应当与国际一流相比。为此中国才能赶上美国，否则永远是二流甚至是三流的。

马在田院士个人主页

马在田院士个人主页: "认识自我，追求优秀，在不断完善知识结构中成才"

看了马院士的院士寄语，深受感动，引用其中一句如下：

科学一流必须是国际的，没有国内国外之分。因此当代青年追求的优秀都应当与国际一流相比。为此中国才能赶上美国，否则永远是二流甚至是三流的。

关于湖南大学校歌

关于湖南大学校歌

麓山巍巍，湘水泱泱，
宏开学府，济济沧沧，
承朱张之绪，取欧美之长，
华与实兮并茂，兰与芷兮齐芳，
楚材蔚起，奋志安壤。
振我民族，扬我国光。

这是目前为止唯一一首感动我的校歌，大气和朴实并存，热血隐隐奔腾，正是湖湘文化千年延绵的气势和风骨。

温家宝看望钱学森季羡林等学者(组图)_新闻中心_新浪网

温家宝看望钱学森季羡林等学者(组图)_新闻中心_新浪网: "国之魂魄，民之肝胆，屹立东方，亿万斯年"

我不知道，我们国家的魂魄是否是一个真实的存在，现在看到的很多精英人士，大多悲观失望，部分投机取巧，随波逐流，只关心自己的下一碗饭在哪里，很难看到对同胞和祖国的担心和赤诚。

我不想成为悲观失望者的一员，我也不想成为一个只说不做的清谈客，然而，每当我面对一些现实，我发现自己确实在逃避，如很多我所厌恶着的精英一样。

“我自横刀向天笑，去留肝胆两昆仑”， 那样的气魄，是我所神往的，而现在的我，却不知我的这些技能，能怎样的帮助我的祖国，归，或不归？回去是否会让我的研究理想沉沦？ 我对自己的毅力没有把握，我也担心害怕，自己会受到伤害。生活不是那么简单的，我只是为了寻求一种简单，选择了做一名科学家的理想，走到今天，却发觉，科学家不能解决我对我的祖国命运的困惑。到处有洪涝，环境在被破坏， 很多人的生存权利没有得早足够的尊重，而我，什么也做不了。我有时候就是感觉人群像一个毒瘤在世界上扩散，把世界变成丑恶的牛棚，直到有一天无药可救，所谓的科学家们也不能阻止这个熵极大化的过程。

唯一的力量也许来自于孔夫子：知其不可而为之。

Borland Together Downloads

Borland Together Downloads

Good news, Borland provides us a very good development tool, it is the integration of Together (UML Modeling tool) and Eclipse ! We can model and automatically generate code and maintain code now!And this excellent tool is free!

By the way, Turbo C# provided by Borland is also integrated with Together now, and it is also free!

Cheers.

钟万勰院士治学之道 | 丁香园 - 医学、药学、生命科学专业人士�

钟万勰院士治学之道 | 丁香园 - 医学、药学、生命科学专业人士�: "钟万勰院士治学之道"

I just read this article. This scholar graduated from Tongji University. The most impressive sentences from this article are:

Keep on your idea and do not blindly follow other people, no matter she or he is a internationally famous guy. You will fall into difficulties many times, and in your academic life failures will be definitely more than successful cases. Monitor your own direction, keep on doing thing which excites you, and forget temporary gains and loss, you will be happy.

IFC Engine Series

IFC Engine Series

This dll is a library which can be called by Visual C++ or Visual Basic application and it is useful for developing my own IFC Viewer.

By the way, I found that I can parse XML using MATLAB directly.

dyll.pdf (application/pdf Object)

A paper about using interval to model geometrical tolerances.
dyll.pdf (application/pdf Object)

Sweets Building Products by sweets.com - Google 3D Warehouse

Sweets Building Products by sweets.com - Google 3D Warehouse

This webpage provides a lot of 3D models of buildings, which should be very useful for simulation of construction site for construction management.

Tongji

老校训：仰天地之正气，法古今之完人。


同济老校歌，铿锵有力
校歌歌词

好一片中华大地
不振兴工艺
真可惜 真可惜
同有耳目
同有手足
同有心思才力
不作工负了好教育
勤劳 诚毅
提携我中华国民
同舟共济 同舟共济
振兴工艺

好一片中华大地
不健康身体
真可惜 真可惜
同有心腹 同有肌肉
同有起居饮食
不学医负了好教育
慈爱 仁义
扶持我中华国民
同舟共济 同舟共济
健康身体

好一片中华大地
不格物穷理
真可惜 真可惜
同有头脑 同有智慧
同有星辰空气
不学理负了好教育
明彻 清晰
训练我中华国民
同舟共济 同舟共济
格物穷理


（注：此校歌创作于1927年）

Accuracy and Geometric Decomposition

Lack of automatic support for data collection and interpretation makes the laser scanning based bridge geometric data acquisition process prohibitive to ordinary bridge inspectors. First, even though from the technical data of a laser scanner bridge inspectors can know how accurate each point can be positioned, what are more useful for them are the accuracy of geometric features which can be extracted from dense point cloud such as how much uncertainty lies in the normal values of an extracted plane. Evaluation of those geometric features and extraction of high level uncertainty information require bridge inspectors to know how to do manual uncertainty analysis. In addition, that process is too complicated for on-site data evaluation to get a quick feedback about the data quality. Second, bridge inspectors need to manually analyze the relationship between the accuracy of single geometric features and the value generated based on them. Interestingly, accuracy constraints for a group of geometric features can have multiple solutions to achieve the same accuracy level for their corresponding inspection goal. So if bridge inspector can get a tool to show them the trade-off between the accuracy constraints to achieve specific accuracy requirement for an inspection goal so that they can have more alternatives on site and get more flexibility on site. Third, bridge inspectors need to interpret accuracy into a series of surveying strategies such as locate the scanners within 10 m from the target object.

Today's work

1. Finish the executive summary of the PhD Proposal

2. Search papers related to my research and read the paper from Carl Haas and a paper from Burcu (About the impact of new data collection technology on data collection and transfer process for timely construction management, Journal of Construction Engineering and Management)

3. Find a paper from Martin Fisher: Formalizing Product Model Transformations (This paper might be important for me to understand how to extend IFC bridge information model to support inspection goal decomposition since it transforms design centered model into a construction activity centered model through three mechanisms introduced by the authors, I can transform the IFC bridge model to a surveying activity centered model so that bridge inspection goal will be transformed into a series of measurement activities to generate inspection goal value: such as the value of the under clearance of a bridge, we can decompose it into measurement of the bottom surface of the super structure and the measurement of the top surface of the road underneath the bridge).

Idea:

From the bridge function(cross river or valley or another highway, we can navigate to the road underneath the bridge, and then from the attribute of the bridge such as how big vehicles are allowed to run on it we can simulate the process that the biggest allowed truck passing under the bridge and to see whether the bridge's under clearance is satisfactory). This reasoning process is transparent, because it is not just specify a limit value for the under clearance, it shows the design intent behind the under clearance limitation values.

Flash LADAR

Flash LARDAR is a new sensor. We can call it 3D camera since it can simultaneously collect thousands of 3D points like a camera can simultaneously record color and reflectivity information for thousands of pixels.

Professor Carl Haas at University of Toronto (University of Texas Austin previously) are trying to use this new technology for spatial management on the construction site. This new technique can collect accurate 3D information directly and avoid the limitation of digital camera which requires complicated model to reconstruct depth information from multiple photos.

Professor Haas is also trying to merge the information from CAD model with 3D point clouds to enhance the speed and accuracy rate of traditional computer vision technique since in CAD model there is prerequisite knowledge about the 3D scene. But how to formally represent those knowledge in 3D model so that computer can automatically interpret 3D semantic information from 3D CAD model is a problem. The representation in IFC (a paper of Professor Grundig at UT Berlin talks about this from the perspective of a surveyor) and the semantic web technology might be of use to formally capture semantic information from 3D CAD model so that we can automatically extract knowledge from 3D model and help computer vision algorithms to interpret 3D point clouds which only contains xyz value and generate intelligent point clouds.

Good future is coming:-)

ICES Presentation of Pingbo

My presentation slides about geometric defect detection of Bombardier track system is available from the following link:

http://www.ices.cmu.edu/censcir/participate/collaboration_event_archives.html

Specification Model and Inspection Planning for Automatic Inspection Goal Decomposition

The researches of Frank Boukamp and Chris Gordon can be combined together and serve as the foundation of my research, which is about geometric inspection goal decomposition.

Frank is modeling the specification so that the knowledge in construction site inspection specifications can be represented in a formal way so that computer can interpret the knowledge from the specification model automatically and use the knowledge to detect defects of a structure. Here, defect means the part of a structure violating the design specification.

From Frank's model, Chris can generate a list of inspection task for a specific project based on the context of the site, the preference of the user and the project schedule.

I can use Frank's model to generate a list of bridge inspection goals, then I match those project specific goal with a generic inspection goal defined by myself. The generic inspection goal will separate domain abstrct knowledge from specific case. For example, I want to know the under clearance of a specific bridge, but the knowledge it self does not have to be related with a specific bridge, we can just say we want to know the size of a empty space. Then we decompose the generic geometric inspection goal into a number of generic targets. Then I matching those generic targets back to the specific context and make those generic targets to be specific. For example, I decompose "measuring vertical space size" into "measure bottom surface of the solid object over the space" and "measure the top surface of the solid object below the space". The using the project specific information I will know that the solid object below the space is the top the highway below the bridge (which can be extracted from GIS system or bridge management system), and the object above the space is the super structure of the bridge. Then I extract these specific information and get the bottom surface of the above object(super structure) and the top surface of the below object (highway). Finally I calculate the vertical distance between these two surfaces and get the under clearance of a specific bridge.

From specific inspetion goal to generic inspection goal, from inspection goal to generic measurement target, then using the specific project information the generate specific measurement targets, the whole project is inspection goal decomposition and assembly which provide a automatic process for bridge inspection gaol acquisition.

Intelligent Point cloud for 3D data registration

If we can not recognize 3D objects from 3D point clouds, those point clouds are just a bunch of xyz coordinates. Today I found that for complicated environments like inside the vision group laboratory, even though there is only minor changes of the environment (walking of a student, movement of a small board), two scans can not be registered together accurately.

That's too bad, because we can never expect construction site will be clean and static. If we can not automatically recognize object from point clouds and separate noisy information from useful information, we can not register the 3D point clouds using traditional algorithms. Another thing is that if we want to detect the environment change, we can not directly register two model and get the differences between them, we must segment the point clouds into patches and do "patch-based matching" between two 3D models and find a transformation which can figure out "outlier patches", which is the actual differences between two scenarios.

Anyway, if we know in advance which point belongs to which object, computer and operate on a "object" level and utilize domain knowledge to reason about the scene and detect changes or find a data registration results making more sense(this is a wall, it will not change, that is a table, it could be moved), so we will avoid the problem caused by non-semantic approach: all points are viewed as the same thing(a point, nothing else!), and the algorithm simply trying to minimize the distance between points so that small changes in the scenario will influence the whole registration results and result in failure of 3D registration.

Presentation on CenSCIR seminar

Today I gave a talk on the graduate seminar of CenSCIR, which is a research center about the application of sensor network for infrastructure management. I talked about my Bombardier research project, which is about using laser scanning technology for civil engineering system geometric defect detection.

I got a lot of feedback from faculty members from other research areas and students from other disciplines, that is a very good experience.

Matt talked about the scanner height and asked whether the height of scanner matters, Omer said something about generate 3D depth information from two cameras instead of using a scanner.

Ideas about stuff organization

I really need to organize two groups of my stuffs from now on:

1. The programs I have written: I need to design an architecture for my codes now since I have accumulated a bunch of codes and it is time consuming to find some codes when I need them. If I designed a architecture, separate foundation classes and client codes, create a framework, then I will know which code I have already developed and which I need to implement for saving time for future research.

2. The documents of previous research. Since I have so many documents accumulated and I have put most of them in my weekly notes directories. I need to look over those documents and try to summarize them into technical reports so that I will get more sense about what I have done and where I am in the whole research process. Summarizing those stuffs will also provide me an opportunity to rethink about my research and save time for future research once I need some stuff which I have created. If I did not archive those stuffs, some of them may be lost and in them future I need to redo some work. That is too bad.

To do regarding these two tasks:

For code:
1. Create a functionality requirements of codes based on my understanding about the research.
2. Design an architecture based on the functionality requirements;
3. Place my previous codes to a proper place in the architecture, and improve program documentation when necessary, so in the future, other people need to use my code for their research will benefit from it;
4. Develop a to-develop list and start to work on my tool for research, and keep on updating the architecture when necessary, and accumulate code in a systematical way;

For stuffs:
1. look over previous research notes and classify them according to my "type_time_project_description" template;

2. Grouping related stuffs and develop a list of tentative research report titles. that is a framework for all the works I have done and want to do;

3. Give each report a proper code and manage all my stuffs according in the units of "report";

4. Continue my work according to the framework structured by a number of reports and accumulate the works in a systematical manner;

Geometric Decomposition: IFC? COmponent Based?

Chris Gordon used component-based approach to represent inspection goal for developing inspection plans, but I find that is not a valid approach for inspection goals involving multiple components such as under-clearance of a bridge.

Is IFC's geometric representation good enough for bridge component recognition from 3D point clouds? since I am thinking about a way to represent the relationship between primitives and semantically meaningful objects. IFC represent a component's geometry, so I think I can develop geometric template based on IFC's approach. And the use the semantic relationship in IFC to develop a valid representation for geometric inspection goal involving multiple bridge components.

Data Visualization

Finally I have reduced the size of my IABSE 2007 paper within 8 pages. Hopefully this will be my first paper published on a influential conference and a good start for my academic career.

So what is today's new idea? Well, yesterday I read some slides on the TRB web page. That presentation is talking about highway safety. One thing impressed me is that they are trying to visualize the safety status of highways: red means dangerous, white means pretty safe. I do not know any details about how they define the safety level of a section of highway, but I find that data visualization is such a simple and effective way for data interpretation and information management.

We can generate a map labeled by the accident rate, and another map labeled with the population density, the curvature of the road etc. Then we can compute the correlation of accidents and various factors using these labeled maps. In my mind, those maps are images and can be processed by any image processing techniques and pattern classification algorithms for data interpretation. I do not know whether this is data mining and knowledge discovery, but I think image processing will be a powerful tool for us to digest huge amount of data and find patterns and knowledge hiding behind them.

Accident map can have different views. We can classify the accidents into several categories according to a specified taxonomy, and we can even compare different taxonomy based on the generated image and its processing results: a better taxonomy will generate images which can explain existing phenomenons and predict some accident correctly. We can also have hierarchy of the visualization: high level taxonomy can generate high-level images shows high-level trends and sub-taxonomy can zoom in to a specific level and view the data in a specific perspective.

These maps will be very useful for accident reducing since people can use it to guide better transportation planning, drivers can use it to generate a "safer path" based on the start point and the target information. Transportation agencies can use it to manage transportation system maintenance and replacement, and they can also provide guidance to drivers so that keep the traffic on deteriorated highway at a low level.

Visualization, such a good idea!

The link of that presentation is:
http://www.trb.org/conferences/e-session/2007am.htm#DATA

Idea of today

Knowledge language for civil engineers so that people can formalize the drawings, engineering knowledge and construction documents to efficiently extract information from thousands of engineering documents with the help of existing knowledge.

Knowledge language represent the engineering knowledge, document are organized and labled using this language, then a knowledge engine will extract the knowledge or engineering data at a proper level of detail for engineers so that engineers can get what they want to know for making an important decision for bridge maintenance, for construction method selection, for construction schedule change management.

A new start

I met Huaiwei yesterday, and he talked about the trend of the science development and I am impressed by his ideas.

I have been focusing only on my own research topic and projects for such a long time and never care what is happening out there. However, as a scientist, it is not good to just work alone and just finish the work assigned by the boss, I must explore my own area and find my own passion. So from now on, I will post at least one new idea, or new discovery or new interesting thing to me, a new communication with others everyday. I need to actively communicate with other and outreach the outside world: organizations such as TRB, ACM are good place for me, so I will read the pulications actively and use the resources from these two organizations efficiently.

Today, I just wrap up everything of my past: finish the Bombardier report, finish editing my IABSE2007 paper, organize my notes and papers. In the next week, I will find one or two interesting books as a start point for my adventure.

As a scientist, I want to start at these points: first, classic mathematic logic; second, astronauts; third, geography; fourth, artificial intelligence.

Cheers, for my new start.

Diagnostics and Data Fusion of Robotic Sensors

One section of this paper talks about "geometric hashing" idea for object recognizing.