专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明专利

JPH03269683A COLOR IDENTIFYING DEVICE 失效
公开(公告)号：JPH03269683A
公开(公告)日：1991-12-02
申请号：JP6943090
申请日：1990-03-19
申请人： OYO KEISOKU KENKYUSHO KK
发明人： SHIMIZU MASAO , KUWAJIMA SHIGEZUMI
IPC分类号： H04N7/18 , G06T7/00
摘要： PURPOSE:To color-identify the feature representation of input picture information automatically and at high speed by transferring an n-dimensional feature vector into an m-dimensional finding a histogram and moreover, classifying by the technique of a main component analysis. CONSTITUTION:An n-dimensional feature vector constituting circuit 41 executes statistic processing after converting picture signals R, G and B into the color difference signals of R-Y and B-Y and a Y signal. An n-dimension m- dimension mapping circuit 44 maps in m-dimensional feature space with a main component analysis technique based on a respective axis histogram and covariance matrix on an n-dimensional vector generated by a respective axis histogram generating circuit 42 and a covariance matrix generating circuit 43. Next, respective axis histogram generating circuits 451 to 45m generate the respective dimensional histograms of a m-dimensional feature vector. m Comparators 461 to 46m set threshold values on the m-dimension at every respec tive axis and classify. An encoder 47 puts classified colors together moreover and input picture information can be color-identified automatically and at high speed so that a feature may be represented most effectively.

12. 发明专利

JPH0326281A OPERATION DIAGNOSING DEVICE 失效
公开(公告)号：JPH0326281A
公开(公告)日：1991-02-04
申请号：JP16129989
申请日：1989-06-23
申请人： OYO KEISOKU KENKYUSHO KK
发明人： SEKI CHIKASHI , NAKAYAMA HATOO , KUWAJIMA SHIZUSUMI , SUZUKI TAKAHITO , MIYAKE ICHIJI , SHIBATA TSUTOMU
IPC分类号： A63B69/36 , G06T1/00
摘要： PURPOSE:To automatically execute the diagnosis and evaluation of operation while a real operational feeling is still remained by extracting required various data from the photographed move of an operational point for a person to be diagnosed and comparing the extracted data with the data of a comparison reference. CONSTITUTION:When an input means 21 inputs the data of swing photographed by a TV camera 100, a measuring means 22 extracts the data for the coordinates of the operational point to be the base of swing analysis from these input data by using picture processing technique. A calculating means 23 extracts and calculates data such as velocity, acceleration, angular velocity and angular acceleration, etc., for each operational point from the obtained coordinate data. Then, a data group is calculated to be matched with the comparison reference as the object of the comparison. A comparison reference holding means 24 holds the data of the plural comparison references and a comparing and deciding means 25 compares the extracted and calculated data with the data of the comparison references. A post-processing means 26 selects a diagnosed result for each selected comparison reference, which is held by the comparison reference holding means 24, and executes processing so that a sound output or picture display output can be executed. Then, an output means 27 outputs this result by a sound or picture display, etc.

13. 发明专利

JPH02101591A ADAPTIVE LEARNING TYPE GENERAL PURPOSE PICTURE MEASURING DEVICE 失效
公开(公告)号：JPH02101591A
公开(公告)日：1990-04-13
申请号：JP25567988
申请日：1988-10-11
申请人： AGENCY IND SCIENCE TECHN , OYO KEISOKU KENKYUSHO KK
发明人： OTSU NOBUYUKI , KUWAJIMA SHIGESUMI , KURITA TAKIO
IPC分类号： G06T7/00
摘要： PURPOSE:To realize measurement which is applicable to a use difficult to discriminate and decide and is strong against a disturbance factor at site by performing the feature extraction of two stages of a large number of extraction to make a basic feature into an initial feature and the extraction to linear-couple the initial features, and performing adaptive picture measurement by learning. CONSTITUTION:An object 100 image-picked up by a television camera 101 is segmented by a partial picture segment circuit 110, and becomes an image DP. The image DP is inputted to a matching circuit 120, and is matched within the range of a window signal generated by a window signal generation circuit 140. Correlation data CL having been matched is inputted to a counter circuit 130, and the outputs of the number of auto-correlation masks are counted by a counter, and count data is stored in a RAM 152. Thus, it is extracted as the initial feature to satisfy invariability in respect of parallel displacement and additivity in respect of a picture. A CPU 150 multivariate- analyzes plural pieces of data in the RAM 152 by a program stored in a RAM 151, and determines a parameter for the subsequent measurement. Then, the initial feature extracted from an unknown object is decided by this parameter, and a measured result is outputted.

14. 发明专利

JPH02101586A ADAPTIVE LEARNING TYPE GENERAL PURPOSE PICTURE MEASURING SYSTEM 失效
公开(公告)号：JPH02101586A
公开(公告)日：1990-04-13
申请号：JP25567888
申请日：1988-10-11
申请人： AGENCY IND SCIENCE TECHN , OYO KEISOKU KENKYUSHO KK
发明人： OTSU NOBUYUKI , KURITA TAKIO , KUWAJIMA SHIGESUMI
IPC分类号： G06T7/00
摘要： PURPOSE:To measure a picture adaptively to various kinds of applications by performing statistical feature extraction with a learning function by using a multivariate analyzing method according to an extracted initial feature. CONSTITUTION:Picture measurement can be considered to be the problem of feature extraction from the picture. As its basic condition, there are three items of 1) variability in respect of parallel displacement, 2) additivity in respect of the picture, 3) adaptive learnability. In geometrical feature extraction F1, a large number of general and basic features to satisfy the conditions 1 and 2 are extracted as the initial features for all screens. In the statistical feature extraction F1, the features optimum for various kinds of the application are extracted adaptively by learning by linear-coupling the initial features. Thus, the measurement based on two stages of the feature extraction satisfies the conditions 1 to 3 of the picture measurement, and the picture measurement can be performed adaptively for various kinds of the applications by the learning of high speed.

15. 发明专利

JPS62134775A IMAGE PROCESSING METHOD 失效
公开(公告)号：JPS62134775A
公开(公告)日：1987-06-17
申请号：JP27502485
申请日：1985-12-09
申请人： OYO KEISOKU KENKYUSHO KK
发明人： KUWAJIMA SHIGESUMI
IPC分类号： G06T1/00 , G06T3/00 , G06T7/60
摘要： PURPOSE:To easily set a window shape, and also to simplify the algorithm of an image processing, by executing the processing by giving a priority order to a window. CONSTITUTION:At the time of measuring a feature quantity by using plural pieces of windows consisting of a data group of a structure for showing a sub-set, from an image of a data group having an (n)-dimensional (an integer of n>=1) array structure, a priority order is given to the window, and also it is constituted so that the part which has been processed by a specified window is not processed by other window. For instance, in case of processing two pieces of objects A, B, a window 100 and 102 of a sub-set corresponding to A and B, respectively are set, and also the priority order of the window 100 is made higher than that of the window 102. Accordingly, window 102, the processing can be executed. In this way, by giving the priority order to the window, a shape limit of the window being in the priority order of a lower rank can be relaxed.

16. 发明专利

JP2002247441A OBJECT RECOGNITION METHOD AND AUTOMATIC PHOTOGRAPHING CAMERA APPARATUS USING IT 失效
公开(公告)号：JP2002247441A
公开(公告)日：2002-08-30
申请号：JP2001046158
申请日：2001-02-22
申请人： OYO KEISOKU KENKYUSHO KK , JAPAN BROADCASTING CORP
发明人： OKAMOTO HIROYUKI , SUZUKI TAKAHITO , KATO TAIICHIRO , TSUDA TAKAO , HATAKEYAMA SUKESATO , INOUE SEIKI , SHIMODA SHIGERU
IPC分类号： G03B15/00 , G06T1/00 , G06T7/60 , H04N5/232
摘要： PROBLEM TO BE SOLVED: To provide an object recognition method that can detect a position of a face of an object person at a high-speed with high accuracy and an automatic photographing camera apparatus that can automatically photograph a video image as photographed by a broadcast cameraman and employs the object recognition method. SOLUTION: Three-dimensional coordinates of a marker mounted on an object are measured, a position of a predetermined feature part of the object is estimated on the basis of the measured three-dimensional coordinate information of the marker, a detection window with a proper shape, size and position including the estimated position of the feature part is set, and the feature part of the object is detected in the detection window that is set.

17. 发明专利

JP2002199267A METHOD AND DEVICE FOR CONTROLLING PHOTOGRAPHING BY ROBOT CAMERA 失效
公开(公告)号：JP2002199267A
公开(公告)日：2002-07-12
申请号：JP2000392099
申请日：2000-12-25
申请人： OYO KEISOKU KENKYUSHO KK , JAPAN BROADCASTING CORP
发明人： OKAMOTO HIROYUKI , SUZUKI TAKAHITO , KATO TAIICHIRO , TSUDA TAKAO , INOUE SEIKI , SHIMODA SHIGERU
IPC分类号： H04N5/232 , H04N7/18
摘要： PROBLEM TO BE SOLVED: To provide a method and device for controlling photographing by a robot camera that enable efficient photographing of an object with high reliability as intended by a program producer. SOLUTION: The method includes a step where presence of a marker in detection areas provided in a photographing space is detected and a step where when the mark is detected in the detection area, an object is automatically photographed according to a preset camerawork.

18. 发明专利

JPH11270936A REFRIGERATING DEVICE 失效
公开(公告)号：JPH11270936A
公开(公告)日：1999-10-05
申请号：JP9385498
申请日：1998-03-24
申请人： OYO KEISOKU KENKYUSHO KK
发明人： KAWATOKO OSAMU , HIDAWA TAKESHI
IPC分类号： F25B1/00 , F25B47/02
摘要： PROBLEM TO BE SOLVED: To minimize the fluctuation of a suction pressure compared with conventional ON/OFF control by a method wherein the suction pressure of refrigerant gas, detected by a pressure sensor between a solenoid valve and a compressor, is controlled and a heater is controlled by the output of a defrosting timer through a daily timer. SOLUTION: A necessary objective pressure is set by the operating unit of an objective pressure setting device 13 at first. The objective pressure is transmitted to a control unit 14 immediately. On the other hand, the suction pressure of refrigerant gas, which is detected by a pressure sensor 12, is also transmitted to the control unit 14 immediately. According to the operations and the effect of a correcting program, a frequency control signal 19 from the control unit 14 is corrected stepwisely during operation through real time process. In this case, the control of a cooling capacity is effected by the stepwise correction of the frequency through real time process adding a negative feedback based on a difference between the set objective pressure and the suction pressure of the refrigerant gas, which is detected by the pressure sensor 12.

19. 发明专利

JP2863782B2 失效
公开(公告)号：JP2863782B2
公开(公告)日：1999-03-03
申请号：JP9848590
申请日：1990-04-13
申请人： OYO KEISOKU KENKYUSHO KK
发明人： KUWAJIMA SHIGEZUMI , NAKAYAMA HATOO , SEKI CHIKOSHI , SUZUKI TAKAHITO , MYAKE ICHIJI , SHIBATA TSUTOMU
IPC分类号： A63B69/36 , G06T1/00

20. 发明专利

JPH10294890A AUTOMATIC/MANUAL PHOTOGRAPHIC CAMERA SYSTEM 失效
公开(公告)号：JPH10294890A
公开(公告)日：1998-11-04
申请号：JP10303197
申请日：1997-04-21
申请人： JAPAN BROADCASTING CORP , OYO KEISOKU KENKYUSHO KK
发明人： KATO TAIICHIRO , YAMADA MITSUO , ABE KAZUO , ISHIKAWA AKIO , TSUDA TAKAO , NUMAZAWA JUNJI , SUZUKI TAKAHITO , OKAMOTO HIROYUKI , KUWABARA HIROYUKI
IPC分类号： H04N5/232
摘要： PROBLEM TO BE SOLVED: To attain automatic tracking photographing through natural, smooth and optimum camera work by providing functions for automatically recognizing an object from a wide angle image photographed by a sensor camera, controlling the drive of camera while following up measured three-dimensional(3D) spatial movement, and predicting the motion of object. SOLUTION: Video signals VDI photographed by two sensor cameras 100 are sent to a 3D position measuring instrument 300, the position information of object 1 in the 3D space is calculated from the 2D coordinate image data of object 1 detected by an object recognizing part and the position information of camera 200 for photographing, and this information is inputted to a data analyzer 500 as measured information PD. Then, a motion vector is found from the motion analytic information at the last time and this time and the next motion of object 1 is predicted and supplied to a camera work control part based on the motion analytic information such as time, azimuth angle, distance and speed. Then, based on the predictive information and the azimuth angle/image angle information of photographic camera, 200 at a current time point, the direction, moving amount and moving speed of camera 200 are determined.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式