Berthold Klaus Paul Horn | |
---|---|
Born | |
Other names | Berthold K.P. Horn Berthold Horn |
Citizenship | United States |
Occupation(s) | Professor, researcher |
Relatives | Peter Horn (brother) |
Awards | Elected to the National Academy of Engineering Azriel Rosenfeld Award |
Academic background | |
Alma mater | University of Witwatersrand Massachusetts Institute of Technology |
Thesis | Shape from Shading: A Method for Obtaining the Shape of a Smooth Opaque Object from One View (1970) |
Doctoral advisor | Marvin Minsky |
Academic work | |
Doctoral students | Matthew T. Mason Marc Raibert Shahriar Negahdaripour |
Berthold Klaus Paul Horn (born December 8,1943) is an American scientist working in the field of artificial intelligence and computer vision. He is Professor of Electrical Engineering and Computer Science at Massachusetts Institute of Technology (MIT). He is also Principal Investigator at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. [1]
Horn is the author of two books and over 300 articles. His research is focused on Machine Vision,Computational Imaging,Suppressing Traffic Flow Instabilities and Indoor Navigation.
Horn was elected a member of the National Academy of Engineering in 2002 for contributions to computer vision,including the recovery of three-dimensional geometry from image intensities. [2] He received the Azriel Rosenfeld Award by IEEE in 2009. [3]
Horn was born in Teplice,German-occupied Czechoslovakia (currently in Czech Republic). His family emigrated from Germany to South Africa after World War II and Horn was brought up there. He joined the University of Witwatersrand in 1961 for his Bachelor of Science in Electrical Engineering studies. After completing his bachelor's degree in 1965,Horn taught Numerical Analysis at the university. During this time,he also worked as a consultant for the South African Navy to help them predict tides in the harbors. [4]
One of his Professors,Derek S. Henderson,who contributed significantly in bringing the first computer to the University of Witwatersrand was,at the time,working on bringing a more powerful computer to the university. In order to facilitate the process and arrange the required software and equipment,Henderson asked Horn to travel to the U.S. During the trip,he visited several universities,took the GSAT examination and decided to study at MIT for his master's degree and later Ph.D. After completing his Ph.D. in 1970,Horn traveled back to South Africa and briefly taught at the University of Witwatersrand. Later he moved back to the United States and started teaching at MIT. [4]
In 1970,he began teaching at MIT and continued teaching there for the next 4 decades,becoming associate professor in 1976 and Professor in 1984. In 1983,he was appointed as the Associate Editor of Computer Vision and Image Understanding. [5] He also serves on the editorial board of International Journal of Computer Vision. [6]
Horn was instrumental in the conversion to scalable,hinted outline format (Adobe Type 1) of Donald Knuth's Computer Modern fonts,The American Mathematical Society (AMS) fonts,LaTeX fonts,Michael Spivak's MathTime and MathTime Plus,as well as Charles Bigelow and Kris Holmes' Lucida Bright,Lucida Bright Expert and Lucida New Math fonts,all used in mathematical typesetting. [7] [8]
Most of Horn's research has been focused on machine vision,particularly so-called "physics-based" machine vision,going back to the beginnings of the field in the 1960s. His thesis entitled Shape from Shading:A Method for Obtaining the Shape of a Smooth Opaque Object from One View was one of his first works in this area. [9] Much of his work in the 1970s and 1980s is focused in this area on the topics of optical flow,photometric stereo as well as closed-form solutions of orientation problems of Photogrammetry. [10]
During the 1990s,Horn's research interest began including Computational Imaging,which is the creation of an image based on raw measurements that are not directly related to local brightness or density values,but nonetheless capture some information about spatial distribution of matter. Some of his early work in computed tomography (CT) led to methods for reconstructing from fan-beam scans, [11] [12] which do not lend themselves to the widely known Fourier-slice theorem used for parallel beam scans. Through time,his research in this area moved towards structured illumination microscopy (SIM) and high resolution X-ray imaging,including phase reconstruction. [13]
In 2013,Horn presented an algorithm at the IEEE Conference on Intelligent Transport Systems [14] for reducing the problem of phantom traffic jams. He and his team studied traffic congestion and proposed that avoiding tailgating could decrease traffic jams. Their research proposed that keeping an equal distance from the car in the front and the back can reduce congestion and decrease commute time. They named their method the bilateral control. The research was published later in the IEEE Transactions on Intelligent Transportation Systems. [15] The team developed an algorithm that dictates exactly how fast a vehicle should travel to avoid congestion. Horn proposed that their algorithm could be used to improve the cruise control systems on cars. [16] Their later research was funded by Toyota. [17] In this area,Horn is also working on improving vehicle safety and passenger comfort using inverse-time-to-contact (TTC) for control. [18]
In the late 2010s Horn research also began including the topic of indoor location by means of Fine-Time-Measurement of Round-Trip-Time of electromagnetic waves at Wifi frequencies as a possible source for turn-by-turn navigation for the visually impaired. [19]
Horn's first book LISP co-authored with Patrick Winston was published in 1981. It was a textbook written for students with no previous background in the computer language LISP. The book was divided in two parts;one dealt with the theory of the language and the second gave instance of practical use in the area of artificial intelligence. [20] A second version of the book was published in 1984 followed by a third version in 1989.
Horn's second book,Robot Vision was published in 1986. The book was an outgrowth of one of his courses at MIT and covered the recent research in the area of image processing,machine vision and pattern recognition. [21]
Horn co-edited with Michael J. Brooks,the 1989 book Shape from Shading,which explained how a three dimensional object may be recovered from shading in a two dimensional image of the object. The book was one of the first in its field to provide a comprehensive review of shape from shading. [22]
Computer vision tasks include methods for acquiring,processing,analyzing and understanding digital images,and extraction of high-dimensional data from the real world in order to produce numerical or symbolic information,e.g. in the forms of decisions. Understanding in this context means the transformation of visual images into descriptions of the world that make sense to thought processes and can elicit appropriate action. This image understanding can be seen as the disentangling of symbolic information from image data using models constructed with the aid of geometry,physics,statistics,and learning theory.
Gerald Jay Sussman is the Panasonic Professor of Electrical Engineering at the Massachusetts Institute of Technology (MIT). He has been involved in artificial intelligence (AI) research at MIT since 1964. His research has centered on understanding the problem-solving strategies used by scientists and engineers,with the goals of automating parts of the process and formalizing it to provide more effective methods of science and engineering education. Sussman has also worked in computer languages,in computer architecture,and in Very Large Scale Integration (VLSI) design.
Avinash C. Kak is a professor of Electrical and Computer Engineering at Purdue University who has conducted pioneering research in several areas of information processing. His most noteworthy contributions deal with algorithms,languages,and systems related to networks,robotics,and computer vision. Born in Srinagar,Kashmir,he did his Bachelors in BE at University of Madras and Phd in Indian Institute of Technology Delhi. He joined the faculty of Purdue University in 1971.
Thomas Shi-Tao Huang was a Chinese-born American computer scientist,electrical engineer,and writer. He was a researcher and professor emeritus at the University of Illinois at Urbana-Champaign (UIUC). Huang was one of the leading figures in computer vision,pattern recognition and human computer interaction.
Patrick Henry Winston was an American computer scientist and professor at the Massachusetts Institute of Technology. Winston was director of the MIT Artificial Intelligence Laboratory from 1972 to 1997,succeeding Marvin Minsky,who left to help found the MIT Media Lab. Winston was succeeded as director by Rodney Brooks.
Digital topology deals with properties and features of two-dimensional (2D) or three-dimensional (3D) digital images that correspond to topological properties or topological features of objects.
Azriel Rosenfeld was an American Research Professor,a Distinguished University Professor,and Director of the Center for Automation Research at the University of Maryland,College Park,Maryland,where he also held affiliate professorships in the Departments of Computer Science,Electrical Engineering,and Psychology,and a talmid chochom. He held a Ph.D. in mathematics from Columbia University (1957),rabbinic ordination (1952) and a Doctor of Hebrew Literature degree (1955) from Yeshiva University,honorary Doctor of Technology degrees from Linkoping University (1980) and Oulu University (1994),and an honorary Doctor of Humane Letters degree from Yeshiva University (2000);he was awarded an honorary Doctor of Science degree from the Technion. He was a Fellow of the Association for the Advancement of Artificial Intelligence (1990) and of the Association for Computing Machinery (1994).
HoloVID is a measuring instrument,originally developed by Mark Slater for the holographic dimensional measurement of the internal isogrid structural webbing of the Delta family of launch vehicles in 1981.
Object recognition –technology in the field of computer vision for finding and identifying objects in an image or video sequence. Humans recognize a multitude of objects in images with little effort,despite the fact that the image of the objects may vary somewhat in different view points,in many different sizes and scales or even when they are translated or rotated. Objects can even be recognized when they are partially obstructed from view. This task is still a challenge for computer vision systems. Many approaches to the task have been implemented over multiple decades.
In computer vision and computer graphics,3D reconstruction is the process of capturing the shape and appearance of real objects. This process can be accomplished either by active or passive methods. If the model is allowed to change its shape in time,this is referred to as non-rigid or spatio-temporal reconstruction.
Photometric stereo is a technique in computer vision for estimating the surface normals of objects by observing that object under different lighting conditions (photometry). It is based on the fact that the amount of light reflected by a surface is dependent on the orientation of the surface in relation to the light source and the observer. By measuring the amount of light reflected into a camera,the space of possible surface orientations is limited. Given enough light sources from different angles,the surface orientation may be constrained to a single orientation or even overconstrained.
Matthew Thomas Mason is an American roboticist and the former Director of the Robotics Institute at Carnegie Mellon University. Mason is a researcher in the area of robotic manipulation,and is the author of two highly cited textbooks in the field.
The International Conference on Computer Vision (ICCV) is a research conference sponsored by the Institute of Electrical and Electronics Engineers (IEEE) held every other year. It is considered to be one of the top conferences in computer vision,alongside CVPR and ECCV,and it is held on years in which ECCV is not.
In computer vision,the Azriel Rosenfeld Award,or Azriel Rosenfeld Life Time Achievement Award was established at ICCV 2007 in Rio de Janeiro to honor outstanding researchers who are recognized as making significant contributions to the field of Computer Vision over longtime careers. This award is in memory of the computer scientist and mathematician Prof. Azriel Rosenfeld.
William Eric Leifur Grimson is a Canadian-born computer scientist and professor at the Massachusetts Institute of Technology,where he served as Chancellor from 2011 to 2014. An expert in computer vision,he headed MIT's Department of Electrical Engineering and Computer Science from 2005 to 2011 and currently serves as its Chancellor for Academic Advancement.
Matti Kalevi Pietikäinen is a computer scientist. He is currently Professor (emer.) in the Center for Machine Vision and Signal Analysis,University of Oulu,Finland. His research interests are in texture-based computer vision,face analysis,affective computing,biometrics,and vision-based perceptual interfaces. He was Director of the Center for Machine Vision Research,and Scientific Director of Infotech Oulu.
Jan Johan Koenderink is a Dutch physicist and psychologist known for his researches on visual perception,computer vision,and geometry.
Sir John Michael Brady is an emeritus professor of oncological imaging at the University of Oxford. He has been a Fellow of Keble College,Oxford,since 1985 and was elected a foreign associate member of the French Academy of Sciences in 2015. He was formerly BP Professor of Information Engineering at Oxford from 1985 to 2010 and a senior research scientist in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) in Cambridge,Massachusetts,from 1980 to 1985.
Narendra Ahuja is an Indian-American computer scientist and the Donald Biggar Willett Professor Emeritus in Engineering at the University of Illinois at Urbana–Champaign. His research primarily concerns computer vision and pattern recognition.