Kddi Corporation

Kokusai Denshin Denwa Kabushiki Kaisha

Kdd Corporation

Kddi R&d Laboratories, Inc.

Ryoichi Kawada

Shuichi Matsumoto

Atsushi Koike

Masahiro Wada

Osamu Sugimoto

Takahiro Hamada

Sei Naito

Atsushi Matsumura

Koki Uchiyama

Sung Jiae

Santi Saeyor

Hirosuke Asano

Yukiko Habu

Toshiaki Shimamura

Nobuhide Kotsuka

A server is disclosed for computing a score of an opinion that a message in a text file is expected to convey regarding a subject to be evaluated, wherein the message is written using literal strings and pictorial symbols. In this server, by the use of a pictorial-symbol dictionary memory storing a correspondence between designated pictorial-symbols to be rated and scores of opinions expressed by the respective pictorial-symbols, at least one of the used pictorial-symbols in the message which is coincident with at least one of the designated pictorial-symbols stored in the pictorial-symbol dictionary memory, is extracted from the message, at least one of the opinion scores which corresponds to the at least one extracted pictorial-symbol is retrieved within the pictorial-symbol dictionary memory, and an aggregate net opinion score for the message is calculated, based on an aggregate opinion score for the at least one extracted pictorial-symbol.

Server for automatically scoring opinion conveyed by text message containing pictorial-symbols

A sender produces a background video imagefrom a reference video imageand a depth mapand synthesizes the background video imagein a background buffer. A projection converting matrixfor synthesizing is calculated. A receiver receives the reference video image, the depth mapand the projection converting matrix. The receiver produces a free viewpoint video imageand a background video image. The background bufferis dynamically renewed. The free viewpoint video imageand the image in the background bufferare synthesized with each other, and the background video image in the concealed regions in the free viewpoint video image are complemented to obtain the complemented image

Concealed regions complementing system of free viewpoint video images

Picture having a band of 6 MHz is distributed to the set-top box (STB)via the compression encoder, the distribution server, and the network. The low-pass filterin the picture quality monitoring apparatusremoves high-frequency components of an inputted digital signal and inputs luminance signal, the band of which is limited to 4 MHz, into the PSNR calculator. The Y/C separatorseparates a luminance signal from NTSC analog composite signal, which are sent out from the set-top box. The separated luminance signal has a band of 4 MHz. The PSNR calculatorcalculates PSNR between the luminance signal from the low-pass filterand the luminance signal from the Y/C separator

Picture quality monitoring apparatus

Characteristic amounts in each small region of audio signals transmitted in the working system and the standby system are extracted by characteristic amount calculators--. A characteristic amount comparatorcompares the characteristic amounts and judges occurrence of fault of a fault. Characteristic amount difference calculators--, &#x2225;D&#x2225; comparator, and faulty system judging unitjudges the system having a fault. Majority decision processorand significance judging unitenhance the reliability of the judgement. Delay difference of audio signals between systems is roughly detected by sub-sampling audio signals of two systems and comparing them, and then accurately detected without sub-sampling. Delay difference between audio signals is adjusted by the detected delay difference.

Apparatus for fault detection for parallelly transmitted audio signals and apparatus for delay difference detection and adjustment for parallelly transmitted audio signals

A matching section performs motion estimation upon a predetermined processing unit of input video (p) by, e.g., an iterative gradient method. A motion vector (v) obtained by the iterative gradient method is obtained by the expression v=&#x3b1;&#xb7;&#x394;v+v(wherein vindicates an initial displacement motion vector and &#x394;v indicates a differential vector). A characteristic amount extraction section extracts a characteristic amount from the distribution of motion vectors obtained by the motion estimation. A parameter determination section determines a conversion parameter &#x3b1; applied to the next processing unit by the characteristic amount. If the characteristic amount is equal to or larger than a predetermined threshold, the conversion parameter &#x3b1; is determined to be larger (e.g., &#x3b1;=1). If the characteristic amount is smaller than the threshold, the conversion parameter &#x3b1; is determined to be smaller (e.g., &#x3b1;=0.1).

Image matching device and method for motion pictures

Characteristic amounts in each small region of audio signals transmitted in the working system and the standby system are extracted by characteristic amount calculators--. A characteristic amount comparatorcompares the characteristic amounts and judges occurrence of a fault. Characteristic amount difference calculators--, &#x2225;D&#x2225; comparator, and faulty system judging unitjudges the system having a fault. Majority decision processorand significance judging unitenhance the reliability of the judgment. Delay difference of audio signals between systems is roughly detected by sub-sampling audio signals of two systems and comparing them, and then accurately detected without sub-sampling. Delay difference between audio signals is adjusted by the detected delay difference.

A picture of 625/50 format is converted to a picture of 525/60 format by a format converter provided halfway of the transmission link (). By thinning scanning lines from the 625/50 format with a scanning line thinning means () on an input side of the transmission link () and then thinning fields from the format of 525/60 with a field (frame) thinning means () on an output side, the formats are matched with each other. After that, a picture quality characteristic amount is extracted by picture quality characteristic amount extracting portions (), () and transmitted to a central monitoring room (). A comparing means () of the central monitoring room () compares received picture quality characteristic amount so as to monitor a transmitted picture quality on a transmission link.

Transmitted picture quality monitoring apparatus

Picture quality characteristic amounts are extracted with a picture quality characteristic amount extractor and are transmitted to a central monitoring room to monitor a transmitted-picture quality. The picture quality characteristic amount extractor includes a pixel-position interchanger, an orthogonal transformer and a coefficient extractor. The picture quality characteristic amount extrator may further include a PN-series multiplier.

Transmitted-picture quality monitoring apparatus

This invention is intended to reduce a line rate of a monitoring line necessary for transmission of a picture feature without complicating a system. A video signal x(n, n) of each block is subjected to spread spectrum by multiplying the video signal x(n, n) by a PN sequences S(n, n) (in a step S). The resultant video signal is orthogonally transformed by DFT, DCT, WHT, or the like (in a step S). An amplitude component A=|X(S, S)| of an arbitrary component (S, S) in a coefficient X(S, S) obtained by the steps Sand Sis extracted (in a step S), and the extracted amplitude component is quantized with a step size M (in a step S). The picture feature F[i] is given as a residue obtained under a modulus Nof a quantized typical value obtained by the quantization (in the step S) (in a step S).

Picture feature extraction system and picture quality evaluation system

Feature quantities of a transmitted picture and a received picture are extracted from a first and second block-by-block feature quantity extraction parts which are provided on a transmitting and receiving sides, respectively. The extracted feature quantities are transmitted to a block degradation calculation part which compares the transmitted feature quantities and finds the degree of picture quality degradation for each block. Next, a median filter replaces the degree of picture quality degradation for the each block with a median of the degrees of picture quality degradation among the neighboring blocks of the each block. Then, a degraded block detection part compares the median with a predetermined threshold and detects a degraded block. Finally, a degraded region detection part removes an isolated degraded block and detects a degraded region. According to the invention, local picture quality degradation in a frame caused by transmission failure can be automatically detected with high accuracy.

Device for automatically detecting picture degradation

In a transmission chain having series-connected a TSC unit, an encoder, a transmission path, a decoder, and an up-converter, characteristic value extracting units are connected to input/output points A, B, C, and D of these transmission processing units respectively. Each characteristic value extracting unit extracts characteristics like an average value m and a variance &#x3c3;of luminance of a picture, for example. These characteristic values are transmitted to a central monitoring unit via a low-speed line. A characteristic value comparator compares the characteristic values. When a difference equal to or larger than a predetermined threshold value has occurred in the characteristic values, the characteristic value comparator decides that an abnormality has occurred in the image in transmission. According to the present invention, it is possible to provide an apparatus for assessing quality of a picture in transmission and an apparatus for remote-monitoring picture quality of a picture in transmission that are capable of assessing the picture quality of a transmission picture in high precision, during an actual transmission of the picture.

Apparatus for assessing quality of a picture in transmission, and apparatus for remote monitoring quality of a picture in transmission

Road area blocks of monitoring camera video data are extracted by a road area block extractor, and motion vectors are calculated by a motion vector calculator. A motion vector direction detector detects the directions of the motion vectors. In a normal state, the mean value &#x398; and the variance &#x3c3;of the directions &#x3b8; of the motion vectors are calculated and accumulated in a statistics memory. In detection of road obstructions, the directions of the motion vectors detected by the motion vector direction detector are transmitted to an abnormal motion vector degree Q calculator. An abnormal motion vector degree Q is calculated on the basis of the statistics accumulated in the statistics accumulated in the statistics memory. A comparator compares the abnormal motion vector degree Q with a threshold. When the abnormal motion vector degree Q is equal to or larger than the threshold, road obstructions are decided. Therefore, according to the present invention, a detection apparatus for road obstructions which is not easily affected by changes in brightness and color in an image and which is not easily adversely affected by the color of a running vehicle is provided.

Detection apparatus for road obstructions

A first characteristic value extracting unit extracts a characteristic value from a picture transmitted from a transmission side, and a second characteristic value extracting unit extracts a characteristic value from a picture received on a reception side. These extracted characteristic values are supplied to a central monitoring unit through low speed lines, respectively. In the central monitoring unit, an MSE (mean square error) is assessed from the data by an MSE assessing unit. The first and second characteristic value extracting units divide an input picture into blocks, subject the blocks to an orthogonal transformation, or subject the blocks to PN sequence multiplication before the orthogonal transformation, and extract and output orthogonal transformation coefficients. The MSE assessing unit determines the differences between corresponding coefficients on the transmission side and the reception side and squares the differences, adds the squared differences for every coefficients or every blocks, and assess an MSE based on the added values referred to a table. With this operation, the MSE can be effectively assessed using a smaller amount of extracted data (accordingly, slower speed lines can be used in the central monitoring unit).

Growing community of inventors

Saitama, Japan

Ryoichi Kawada