JP2001256500A - System and method for judging target - Google Patents

System and method for judging target

Info

Publication number
JP2001256500A
JP2001256500A JP2000065142A JP2000065142A JP2001256500A JP 2001256500 A JP2001256500 A JP 2001256500A JP 2000065142 A JP2000065142 A JP 2000065142A JP 2000065142 A JP2000065142 A JP 2000065142A JP 2001256500 A JP2001256500 A JP 2001256500A
Authority
JP
Japan
Prior art keywords
object
image processing
processing
image
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
JP2000065142A
Other languages
Japanese (ja)
Other versions
JP3946927B2 (en
Inventor
Minoru Kikuchi
稔 菊池
Original Assignee
Toshiba Corp
株式会社東芝
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Toshiba Corp, 株式会社東芝 filed Critical Toshiba Corp
Priority to JP2000065142A priority Critical patent/JP3946927B2/en
Publication of JP2001256500A publication Critical patent/JP2001256500A/en
Application granted granted Critical
Publication of JP3946927B2 publication Critical patent/JP3946927B2/en
Application status is Expired - Fee Related legal-status Critical
Anticipated expiration legal-status Critical

Links

Abstract

PROBLEM TO BE SOLVED: To provide a target judging system with high performance by performing a processing at higher speed and improving processing precision even when multiple similar objects (object candidates) exist and also an environmental change is intense. SOLUTION: A target judging system for judging a target object by using a picture processing system is presented. This system is provided with a picture input system 20 for inputting picture data comprising the target object and simultaneously performing a plurality kind of picture processing systems 200 and 201 in parallel. An object judgement processing system 1 calculates respective featured values corresponding to the object candidates obtained by the picture processings of the picture processing systems and calculates an evaluation value and a synthetic evaluation value based on the featured values. A synthetic judgement part 30 judges and processes the object candidate with the largest value as the final target object from the synthetic evaluation value of the object candidates.

Description

【発明の詳細な説明】 DETAILED DESCRIPTION OF THE INVENTION

【0001】 [0001]

【発明の属する技術分野】本発明は、特に画像処理システムを利用して、目標対象物の監視や追従処理に必要な目標対象を判定するための目標判定システム及び判定方法に関する。 The present invention relates, especially by using the image processing system, and the target determination system and determination method for determining a target object necessary for monitoring and follow-up processing of the target object.

【0002】 [0002]

【従来の技術】従来、例えばミサイルの目標判定システムや監視システムでは、目標対象物の追従や監視処理を行なうために、当該目標対象物を特定するための目標判定システムが設けられている。 In conventional, for example a missile target system for determining and monitoring system, in order to perform follow-up and monitoring processing of the target object, the target determination system for identifying the target object is provided.

【0003】目標判定システムは、例えばカメラなどの撮像装置から得られた入力画像データを入力し、当該画像データから対象物候補を抽出し、最終的に目標対象物を特定する処理プロセスを実行する。 [0003] The goal decision system, for example by entering the input image data obtained from an imaging device such as a camera, to extract the object candidate from the image data, and finally executes the processing process of identifying the target object . 当該システムは、 The system,
画像処理システムを利用して、静止画像処理方式による輝度やコントラスト検出に基づいた対象物候補の抽出処理や、動画像処理(動ベクトル処理)方式による移動領域の検出に基づいた対象物候補の抽出処理を実行する。 Using an image processing system, the extraction of the still image extraction processing of the object candidate based on brightness and contrast detection by processing method, moving picture processing (motion vector processing) object candidate based on the detection of the moving region by method process to run.
要するに、目標判定システムは、各画像処理方式により、対象物候補の特徴量を抽出して、この特徴量に基づいて最終的な目標対象物の判定処理を実行している。 In short, the target determination system, by the image processing method extracts a feature amount of an object candidate is running determination processing of the final desired object on the basis of the feature quantity.

【0004】 [0004]

【発明が解決しようとする課題】従来の画像処理システムを利用した目標判定システムは、対象物の特徴が一元的でかつ計測値の大小比較で判定可能な場合には、比較的容易に対象候補から目標対象物を判定することができる。 [SUMMARY OF THE INVENTION The target determination system using a conventional image processing system, when characteristics of the object can be determined by magnitude comparison of centralized and and measurements, relatively easily candidate it is possible to determine the target object from.

【0005】しかしながら、特に目標対象物が野外に存在する場合には、多数の類似物体(対象物候補)が存在する可能性が高い。 However, especially when the target object is present in the field, there is a high possibility that a large number of similar objects (object candidate) is present. このため、各対象物候補毎に画像処理を行なうことは、処理量が増大化し、結果として判定処理の遅延化を招く。 Therefore, to perform the image processing for each object candidate, the processing amount is increased of, causing a delay of the result as the determination process. また、画像処理の種類を単純に増加させた場合も、処理量が増大化し、同様に処理の遅延化を招く。 Further, even when simply increasing the kinds of image processing, the processing amount is increased of, causing a delay of similarly treated. また、必ずしも処理精度が向上するとは限らない。 Furthermore, not always necessarily process accuracy is improved.

【0006】一方、野外では環境変化が激しい場合が多く、一元的な画像処理を適用した場合には、画像状況の変化、ノイズの増大などにより、一時的に対象候補を検出できない事態となる可能性が高い。 On the other hand, if the field of application where severe environmental change is large, centralized image processing, a change in image conditions, due to noise or the like increase, temporarily be a situation that can not detect an object candidate high sex. この結果として、 As a result of this,
連続的な判定処理では、処理が停止状態になったり、対象候補に対する十分な特徴量を抽出できない事態が発生する可能性が高い。 In a continuous determination process, the process or the stopped state, a situation can not be extracted sufficiently characteristic quantity for the target candidate is likely to occur.

【0007】そこで、本発明の目的は、多数の類似物体(対象物候補)が存在し、かつ環境変化が激しい場合でも、処理の高速化及び処理精度の向上を図ることにより、高性能の目標判定システム及び判定方法を提供することにある。 An object of the present invention, there are a number of similar objects (object candidate), and even when the environment changes severe, by improving the speed and processing accuracy of processing, high-performance goals and to provide a determination system and determination method.

【0008】 [0008]

【課題を解決するための手段】本発明は、画像処理システムを利用して目標対象物を判定する目標判定システムに関し、複数種の画像処理方式を同時、並列的に実行して、各画像処理方式により得られた対象物候補の特徴量を統合的に処理するシステムである。 Means for Solving the Problems The present invention utilizes an image processing system relates to the target determination system determines the target object, the image processing method of plural kinds simultaneously, run in parallel, each of the image processing the feature quantity of the resulting object candidate by scheme is integrally processing system. 具体的には、本発明は、目標対象物を含む画像データを入力し、複数種の画像処理方式により当該入力画像を処理する画像入力手段と、各画像処理方式の画像処理により得られた対象物候補に対応する各特徴量を算出する算出手段と、各画像処理方式に対応する各特徴量に基づいて、対象物候補の総合的評価値を求めて、最終的な目標対象物の判定処理を行なう判定処理手段とを有する目標判定システムである。 Target Specifically, the present invention inputs the image data including the target object, that an image input means for processing the input image by a plurality of kinds of image processing systems, obtained by image processing of the image processing method a calculating means for calculating feature quantity corresponding to the object candidates, based on the feature amount corresponding to each image processing method, seek a comprehensive evaluation value of the object candidates, the final target object determination process which is a target determination system and a determination processing section for performing.

【0009】このような構成であれば、例えば静止画像処理方式及び動画像処理(動ベクトル処理)方式のような複数種の処理方式を同時、並列に実行して、各処理方式により対象物候補の特徴量を得ることができる。 [0009] With such a constitution, for example, the still image processing method and a moving picture processing (motion vector processing) a plurality of types of processing schemes simultaneous like manner, performed in parallel, the object candidate by each processing method it can be obtained in the feature amount. 従って、対象物候補に対する特徴を多角的に捉えることが可能となり、環境変化などにより一部の処理結果が無効になるような事態でも、十分な特徴量を確保することができる。 Accordingly, multifaceted it becomes possible to capture the features with respect to the object candidates, even in a situation such as part of the processing result is invalid due to environmental changes, it is possible to secure a sufficient characteristic amount. また、複数種の処理方式を同時、並列に実行すれば、多数の対象物候補が存在する場合でも、結果として判定処理速度の低下を招くことはない。 Further, executing plural kinds of processing method simultaneously, in parallel, even if a large number of objects candidate exists, does not lead to a reduction in the determination processing speed as a result. さらに、各処理方式により得られた対象物候補の特徴量を、いわば統合的に処理して対象物候補の総合的評価値を得ることにより、最終的に目標対象物の判定精度を向上させることができる。 Further, the feature quantity of the resulting object candidate by each processing system, by obtaining a comprehensive evaluation value of the object candidate is treated as it were an integrated manner, ultimately improving the determination accuracy of the target object can.

【0010】 [0010]

【発明の実施の形態】以下図面を参照して、本発明の実施の形態を説明する。 Referring to DETAILED DESCRIPTION OF THE INVENTION Hereinafter drawings, an embodiment of the present invention.

【0011】(目標判定システムの構成)図1は、ディジタル画像処理システムを利用した目標判定システム1 [0011] (target determination System Configuration) FIG. 1 is a target determination system 1 utilizing digital image processing system
の構成を示すブロック図である。 It is a block diagram showing a configuration. 当該システム1は大別して、画像入力系20と、対象物判定処理システム10 The system 1 roughly comprises an image input system 20, the object determination process system 10
と、総合判定部30とから構成されている。 When, and a comprehensive determination unit 30.

【0012】画像入力系20は、複数種の画像処理方式による例えば静止画像処理部200及び動画像処理部(動ベクトル処理部)201を有する。 [0012] The image input system 20 has, for example, the still image processing unit 200 and the video processing unit by a plurality of types of image processing system (motion vector processing unit) 201. 画像入力系20 Image input system 20
は、入力画像に対して、異なる各画像処理を同時、並列に実行して、それぞれの画像処理データ(SD),(M Is the input image, by executing each of the different image processing simultaneously, in parallel, each of the image processing data (SD), (M
D)を生成する。 D) to generate. ここで、入力画像は、目標対象物を含む範囲をカメラなどの撮像装置(図示せず)により撮像された画像データである。 Here, the input image is an image data taken a range including a target object image pickup device such as a camera (not shown).

【0013】静止画像処理部200は、例えば2次元C [0013] the still image processing section 200, for example, 2-dimensional C
FAR(two dimensional ConstantFalse Alarm Rate) FAR (two dimensional ConstantFalse Alarm Rate)
処理方式などを利用した処理部であり、入力画像から輝度、コントラストの強い領域を検出して、画像処理データ(SD)として出力する。 A processing unit utilizing such processing method, the luminance from the input image, by detecting a strong area contrast, to output as the image processing data (SD). また、動画像処理部201 The moving picture processing unit 201
は、入力画像から移動ベクトル処理を実行して、移動領域を検出して、画像処理データ(MD)として出力する。 Executes a movement vector processing from the input image, by detecting the moving region, and outputs it as an image processing data (MD).

【0014】ここで、各画像処理により検出された領域は、セグメントとして定義する。 [0014] Here, the area detected by the image processing is defined as a segment. 各セグメントは、目標対象物、類似した対象物候補、及びそれらの背景のいずれかに属するものである。 Each segment target object, similar objects candidates, and those belonging to one of those background. 各画像処理データ(SD), Each image processing data (SD),
(MD)には、後述するセグメントの特徴量(Ua), The (MD), the feature amount of the segment to be described later (Ua),
(Ub)が含まれている。 (Ub) are included.

【0015】対象物判定処理システム10は、セグメント照合処理部100と、識別関数値計算部101と、傾斜相関処理部102とを有する。 The object determination processing system 10 includes a segment matching process section 100, a classification function value calculation unit 101, and an inclined correlation processing unit 102. セグメント照合処理部100は、画像入力系20から出力された画像処理データ(SD),(MD)を入力して、各画像処理方式毎に特徴量(Ua),(Ub)を抽出して出力する。 Segment matching process section 100, an image output from the image input system 20 processes data (SD), to input (MD), the feature quantity for each image processing method (Ua), and extracted (Ub) Output to. さらに、セグメント照合処理部100は、位置情報などに基づいてセグメント照合処理を実行し、各セグメントが同一対象物であるか否かを判定する機能を有する。 Furthermore, the segment matching processor 100 executes the segment matching process like based on positional information, each segment has a function of determining whether the same object.

【0016】識別関数値計算部101は、セグメント照合処理部100により与えられる特徴量(Ua),(U The classification function value calculation unit 101, feature amount given by the segment matching process section 100 (Ua), (U
b)及び所定の特徴量重み係数(ωa,ωb)を使用して、複数の対象物候補(セグメント)の識別関数値(評価値(V))を計算する。 b) and a predetermined feature amount weighting factors (.omega.a, using [omega] b), discriminant function values ​​of a plurality of objects candidate (segment) (evaluation value (V) to calculate the). ここで、特徴量重み係数(ω Here, the feature weighting factor (omega
a,ωb)は、目標対象物を最も的確に算出可能であるような予め設定された設定値である。 a, [omega] b) is a predetermined set value such that the target object is most accurately be calculated. 傾斜相関処理部1 Inclined correlation processing unit 1
02は、傾斜相関処理により複数フレームの評価値を割引ながら積算する処理であり、時系列要素を考慮した複数の対象物候補の総合評価値(CV)を求める機能を有する。 02, the inclination correlation process is a process for integrating while discounting the evaluation value of the plurality of frames has a function of determining when total evaluation values ​​of the plurality of objects candidates considering sequence element (CV).

【0017】総合判定部30は、複数の対象物候補の総合評価値(CV)を比較処理し、例えば相対的に最大値を示す総合評価値(CV)のセグメントを最終的に目標対象物であると判定する機能を有する。 The total determination unit 30, the overall evaluation value of the plurality of objects candidate (CV) and comparison processing, for example, overall evaluation value indicating the relative maximum value segments (CV) in the final target object It has the function of determining that there is.

【0018】(目標判定処理の手順)以下図1と共に、 [0018] (Procedure target determination processing) with the following Fig. 1,
図2から図5、及び図6のフローチャートを参照して、 Figures 2-5, and with reference to the flowchart of FIG. 6,
同実施形態のシステムの処理手順を説明する。 Describing a processing procedure of the system of the embodiment.

【0019】まず、カメラなどの撮像装置により、例えば図2(A)に示すような入力画像が画像入力系20に入力されて処理される。 Firstly, by an imaging device such as a camera, for example, the input image as shown in FIG. 2 (A) is inputted to the processing to the image input system 20. 画像入力系20は、前述したように、入力画像に対して異なる各画像処理を同時、並列に実行して、それぞれの画像処理データ(SD),(M Image input system 20, as described above, by executing each image processing different from the input image simultaneously, in parallel, each of the image processing data (SD), (M
D)を生成する(ステップS1)。 D) generating a (step S1). ここで、入力画像としては、対象物候補(T1),(T2)及び背景(A, Here, as the input image, the object candidate (T1), (T2) and background (A,
B)が含まれていると想定する。 B) is assumed to have been included.

【0020】セグメント照合処理部100は、画像入力系20から出力された画像処理データ(SD),(M The segment matching process section 100, the image processing data output from the image input system 20 (SD), (M
D)から、各画像処理方式毎に特徴量(Ua),(U From D), the feature quantity for each image processing method (Ua), (U
b)を抽出して出力する(ステップS2)。 b) extracting and the output (step S2). 具体的には、図2(B)に示すように、同図(A)に示す画像に対して、静止画像処理部200からの画像処理データ(SD)から、対象物候補(T1),(T2)及び背景(A,B)に対応する特徴量(Ua)を抽出する。 Specifically, as shown in FIG. 2 (B), the image shown in FIG. (A), the image processing data from the still image processing unit 200 from (SD), the object candidate (T1), ( T2) and to extract the background (a, feature amount corresponding to B) (Ua). また、図3(B)に示すように、同図(A)に示す画像に対して、動画像処理部201からの画像処理データ(M Further, as shown in FIG. 3 (B), the image shown in FIG. (A), the image processing data from the video processing section 201 (M
D)から、対象物候補(T1),(T2)及び背景(A,B)に対応する特徴量(Ub)を抽出する。 From D), the object candidate (T1), and extracts a feature value (Ub) corresponding to (T2) and background (A, B).

【0021】さらに、セグメント照合処理部100は、 Furthermore, the segment matching process section 100,
位置情報などに基づいてセグメント照合処理を実行し、 Run the segment matching process like based on position information,
各セグメントが同一対象物であるか否かを判定する(ステップS3)。 Each segment determines whether the identical object (step S3). ここでは、当該判定処理により、対象物候補(T1),(T2)及び背景(A,B)である各セグメントは、同一対象物ではないと判定される。 Here, by the determination process, the object candidate (T1), each segment is (T2) and background (A, B) is determined not to be the same object.

【0022】識別関数値計算部101は、図4に示すように、セグメント照合処理部100により与えられる特徴量(Ua),(Ub)及び所定の特徴量重み係数(ω The classification function value calculation unit 101, as shown in FIG. 4, feature amount given by the segment matching process section 100 (Ua), (Ub) and a predetermined feature amount weighting factor (omega
a,ωb)を使用して、複数の対象物候補(T1,T a, using [omega] b), a plurality of objects candidates (T1, T
2)の評価値(V1,V2)を計算する(ステップS Evaluation value of 2) (V1, V2) is calculated (steps S
4)。 4). ここで、背景(A,B)である各セグメントは、 Here, each segment is the background (A, B),
当該計算部101による評価値に基づいて、目標対象物から除外される。 Based on the evaluation value by the calculation unit 101 is excluded from the target object. さらに、傾斜相関処理部102は、複数の対象物候補(T1,T2)の評価値(V1,V2) Further, the inclined correlation processing unit 102, evaluation value of the plurality of objects candidates (T1, T2) (V1, V2)
から、時系列要素を考慮した総合評価値(CV1,CV From, when the total evaluation value in consideration of the series element (CV1, CV
2)を求める(ステップS5)。 Request 2) (step S5).

【0023】そして、総合判定部30は、複数の対象物候補の総合評価値(CV1,CV2)を比較処理し、相対的に最大値を示す総合評価値のセグメントを最終的に目標対象物であると判定する(ステップS6)。 [0023] Then, the overall judgment section 30 compares the process overall evaluation value of the plurality of objects candidate (CV1, CV2), a segment of overall evaluation value indicating the relative maximum value at the final desired object It determines that there is (step S6). ここでは、図5に示すように、相対的に大きい総合評価値(C Here, as shown in FIG. 5, a relatively large total evaluation value (C
V1)を示す対象物候補(T1)を、最終的に目標対象物(50)として判定する。 The object candidate (T1) indicating a V1) determines, as the final target object (50).

【0024】以上のように同実施形態によれば、入力画像に対して異なる複数種の画像処理方式を同時、並列に実行して、各処理方式により対象物候補の複数の特徴量を得ることができる。 According to the embodiment as described above, simultaneously a plurality of kinds image processing method which is different to the input image, performed in parallel, to obtain a plurality of features of the object candidate by each processing method can. 従って、同一の対象物候補の場合でも特徴を多角的に捉えることが可能となる。 Therefore, it is possible to capture the features multilaterally even for the same object candidates. これにより、環境変化などにより一部の処理結果が無効になるような事態でも、十分な特徴量を確保することができる。 Accordingly, even in a situation such as part of the processing result is invalid due to environmental changes, it is possible to secure a sufficient characteristic amount.
また、複数種の処理方式を同時、並列に実行することにより、多数の対象物候補が存在する場合でも、処理速度の高速化を図ることができる。 Further, a plurality of kinds of processing methods simultaneously, by executing in parallel, even if a large number of objects candidate exists, it is possible to increase the speed of processing speed. 従って、結果として目標対象物の判定処理速度の低下を招くことはない。 Therefore, it does not lead to a reduction in the determination processing speed of the target object as a result. さらに、各処理方式により得られた対象物候補の特徴量を、 Further, the feature quantity of the resulting object candidate by each processing method,
いわば統合的に処理して総合的評価値に基づいて目標対象物を判定するため、判定精度を向上させることができる。 To determine the target object based on the comprehensive evaluation value is treated as it were an integrated manner, it is possible to improve the determination accuracy.

【0025】 [0025]

【発明の効果】以上詳述したように本発明によれば、多数の類似物体(対象物候補)が存在し、かつ環境変化が激しい場合でも、処理の高速化及び処理精度の向上を図ることにより、高性能の目標判定システムを提供することにある。 According to the present invention as described in detail above, there are a number of similar objects (object candidate), and even when the environment changes severe, possible to improve the speed and processing accuracy of the processing Accordingly, to provide a high performance target determination system. 従って、本発明のシステムを、例えば野外に存在する目標対象物を追従するミサイルシステムや、環境変化の激しい野外に存在する対象物を監視する監視システムに適用すれば、確実に目標対象物を特定できるため、極めて有用である。 Thus, the system of the present invention, for example, a missile system which follows the target object existing in the field, when applied to a monitoring system for monitoring an object existing at the severe outdoor environmental changes, reliably identify the target object since it is possible, it is extremely useful.

【図面の簡単な説明】 BRIEF DESCRIPTION OF THE DRAWINGS

【図1】本発明の実施形態に関係する目標判定システムの要部を示すブロック図。 Block diagram showing a main part of the target determination system related to the embodiment of the present invention; FIG.

【図2】同実施形態に関係するセグメント照合処理部の処理を説明するための図。 Figure 2 is a diagram for explaining the processing of the segment matching process unit related to the embodiment.

【図3】同実施形態に関係するセグメント照合処理部の処理を説明するための図。 3 is a diagram for explaining the processing of the segment matching process unit related to the embodiment.

【図4】同実施形態に関係する識別関数値計算部の処理を説明するための図。 4 is a diagram for explaining the process of classification function value calculating unit related to the embodiment.

【図5】同実施形態に関係する総合判定部の処理を説明するための図。 5 is a diagram for explaining the processing of the comprehensive determination unit related to the embodiment.

【図6】同実施形態の判定処理の手順を説明するためのフローチャート。 FIG. 6 is a flowchart for explaining the procedure of determination processing of the embodiment.

【符号の説明】 DESCRIPTION OF SYMBOLS

1…目標判定システム 10…対象物判定処理システム 20…画像入力系 30…総合判定部 100…セグメント照合処理部 101…識別関数値計算部 102…傾斜相関処理部 200…静止画像処理部 201…動画像処理部(動ベクトル処理部) 1 ... target determination system 10 ... object determination processing system 20 ... image input system 30 ... comprehensive determination unit 100 ... segment matching process section 101 ... classification function value calculator 102 ... inclined correlation processing unit 200 ... the still image processing unit 201 ... video image processing unit (motion vector processing unit)

Claims (6)

    【特許請求の範囲】 [The claims]
  1. 【請求項1】 画像処理システムを利用して目標対象物を判定する目標判定システムであって、 目標対象物を含む画像データを入力し、複数種の画像処理方式により当該入力画像を処理する画像入力手段と、 前記各画像処理方式の画像処理により得られた対象物候補に対応する各特徴量を算出する算出手段と、 前記各画像処理方式に対応する各特徴量に基づいて、対象物候補の総合的評価値を求めて、最終的な目標対象物の判定処理を行なう判定処理手段とを具備したことを特徴とする目標判定システム。 1. An image processing system target determination system determines the target object by using an image inputting image data including the target object, it processes the input image by a plurality of kinds of image processing systems input means, a calculating means for calculating feature quantity wherein corresponding to each image processing method an image object candidate obtained by the process of, based on the characteristic amounts corresponding to the respective image processing method, the object candidate target determination system seeking a comprehensive evaluation value, characterized by comprising a determination processing means for performing determination processing of the final goal object.
  2. 【請求項2】 前記画像入力手段は、静止画像処理を実行する第1の画像処理方式、及び動画像処理を実行する第2の画像処理方式の各画像処理を同時、並列に実行させて、対象物候補の抽出結果を含む各画像処理結果を生成することを特徴とする請求項1記載の目標判定システム。 Wherein said image input means, the first image processing method for executing the still image processing, and each image processing of the second image processing method simultaneously, it is executed in parallel to perform the moving image processing, target determination system of claim 1, wherein generating a respective image processing results, including extraction result of the object candidate.
  3. 【請求項3】 前記算出手段は、前記各画像処理方式の画像処理により得られた各対象物候補が同一対象物であるか否かを判定するための照合処理を実行するセグメント照合処理手段を含むことを特徴とする請求項1記載の目標判定システム。 Wherein said calculating means, the segment matching processing means for executing a matching process for each object candidate obtained by the image processing of each image processing method to determine whether an identical object target determination system according to claim 1, comprising.
  4. 【請求項4】 前記判定処理手段は、前記セグメント照合処理手段により同一対象物であると照合された対象候補の評価値を、所定の特徴量重み係数を利用して算出する識別関数値計算手段を含むことを特徴とする請求項3 Wherein said determination processing unit, wherein the evaluation value of the candidate that is verified to be the same object by segment matching process unit, classification function value calculating means for calculating by using a predetermined feature quantity weight coefficient claim 3, characterized in that it comprises
    記載の目標判定システム。 The goal determination system described.
  5. 【請求項5】 前記判定処理手段は、複数の対象物候補の総合的評価値を比較し、相対的に最大値を示す総合的評価値に対応する対象物候補を最終的な目標対象物であると判定することを特徴とする請求項1記載の目標判定システム。 Wherein said determination processing means compares the overall evaluation value of the plurality of objects candidate objects candidate corresponding to the overall evaluation value indicating the relative maximum value at the final desired object target determination system of claim 1, wherein the determining that there.
  6. 【請求項6】 画像処理システムを利用して目標対象物を判定する目標判定システムに適用する判定方法であって、 目標対象物を含む画像データを入力し、複数種の画像処理方式により当該入力画像を処理するステップと、 前記各画像処理方式の画像処理により得られた対象物候補に対応する各特徴量を算出するステップと、 前記各画像処理方式の画像処理により得られた各対象物候補が同一対象物であるか否かを判定するための照合処理を実行するステップと、 前記照合処理ステップにより同一対象物であると照合された対象候補の評価値を、所定の特徴量重み係数を利用して算出するステップと、 前記評価値の傾斜相関処理により対象候補の総合的評価値を算出するステップと、 複数の対象物候補の前記総合的評価値を比較し、相対的 6. A determination method to be applied to the target determination system determines, using the image processing system of the target object, receives the image data including the target object, the input of a plurality of kinds of image processing systems processing the image, and calculating the respective feature amounts corresponding to the respective image processing method an image object candidates obtained by the processing of the respective object candidate obtained by the image processing of the image processing method a step but to execute the matching process for determining whether the same object, the evaluation value of the candidate that is verified to be the same object by the matching process step, a predetermined feature quantity weight coefficient comparing and calculating by utilizing the steps of calculating an overall evaluation value of a candidate by the inclined correlation processing of the evaluation value, the total evaluation values ​​of the plurality of objects candidates, the relative に最大値を示す総合的評価値に対応する対象物候補を最終的な目標対象物であると判定するステップとからなる手順を有することを特徴とする判定方法。 Determination method characterized by comprising the step consisting of determining that an object candidate is a final target object corresponding to the overall evaluation value indicating the maximum value.
JP2000065142A 2000-03-09 2000-03-09 Target determination system and determination method Expired - Fee Related JP3946927B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2000065142A JP3946927B2 (en) 2000-03-09 2000-03-09 Target determination system and determination method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2000065142A JP3946927B2 (en) 2000-03-09 2000-03-09 Target determination system and determination method

Publications (2)

Publication Number Publication Date
JP2001256500A true JP2001256500A (en) 2001-09-21
JP3946927B2 JP3946927B2 (en) 2007-07-18

Family

ID=18584722

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2000065142A Expired - Fee Related JP3946927B2 (en) 2000-03-09 2000-03-09 Target determination system and determination method

Country Status (1)

Country Link
JP (1) JP3946927B2 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012043447A (en) * 2001-11-05 2012-03-01 Nant Holdings Ip Llc Image capture and identification system and method
US8712193B2 (en) 2000-11-06 2014-04-29 Nant Holdings Ip, Llc Image capture and identification system and process
US8792750B2 (en) 2000-11-06 2014-07-29 Nant Holdings Ip, Llc Object information derived from object images
US8824738B2 (en) 2000-11-06 2014-09-02 Nant Holdings Ip, Llc Data capture and identification system and process
US9310892B2 (en) 2000-11-06 2016-04-12 Nant Holdings Ip, Llc Object information derived from object images

Cited By (80)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8948459B2 (en) 2000-11-06 2015-02-03 Nant Holdings Ip, Llc Image capture and identification system and process
US8712193B2 (en) 2000-11-06 2014-04-29 Nant Holdings Ip, Llc Image capture and identification system and process
US8718410B2 (en) 2000-11-06 2014-05-06 Nant Holdings Ip, Llc Image capture and identification system and process
US8774463B2 (en) 2000-11-06 2014-07-08 Nant Holdings Ip, Llc Image capture and identification system and process
US8792750B2 (en) 2000-11-06 2014-07-29 Nant Holdings Ip, Llc Object information derived from object images
US8798322B2 (en) 2000-11-06 2014-08-05 Nant Holdings Ip, Llc Object information derived from object images
US8798368B2 (en) 2000-11-06 2014-08-05 Nant Holdings Ip, Llc Image capture and identification system and process
US8824738B2 (en) 2000-11-06 2014-09-02 Nant Holdings Ip, Llc Data capture and identification system and process
US8837868B2 (en) 2000-11-06 2014-09-16 Nant Holdings Ip, Llc Image capture and identification system and process
US8842941B2 (en) 2000-11-06 2014-09-23 Nant Holdings Ip, Llc Image capture and identification system and process
US8849069B2 (en) 2000-11-06 2014-09-30 Nant Holdings Ip, Llc Object information derived from object images
US8855423B2 (en) 2000-11-06 2014-10-07 Nant Holdings Ip, Llc Image capture and identification system and process
US8861859B2 (en) 2000-11-06 2014-10-14 Nant Holdings Ip, Llc Image capture and identification system and process
US8867839B2 (en) 2000-11-06 2014-10-21 Nant Holdings Ip, Llc Image capture and identification system and process
US8873891B2 (en) 2000-11-06 2014-10-28 Nant Holdings Ip, Llc Image capture and identification system and process
US8885982B2 (en) 2000-11-06 2014-11-11 Nant Holdings Ip, Llc Object information derived from object images
US8885983B2 (en) 2000-11-06 2014-11-11 Nant Holdings Ip, Llc Image capture and identification system and process
US8923563B2 (en) 2000-11-06 2014-12-30 Nant Holdings Ip, Llc Image capture and identification system and process
US8938096B2 (en) 2000-11-06 2015-01-20 Nant Holdings Ip, Llc Image capture and identification system and process
US8948460B2 (en) 2000-11-06 2015-02-03 Nant Holdings Ip, Llc Image capture and identification system and process
US10089329B2 (en) 2000-11-06 2018-10-02 Nant Holdings Ip, Llc Object information derived from object images
US8948544B2 (en) 2000-11-06 2015-02-03 Nant Holdings Ip, Llc Object information derived from object images
US9014515B2 (en) 2000-11-06 2015-04-21 Nant Holdings Ip, Llc Image capture and identification system and process
US9014516B2 (en) 2000-11-06 2015-04-21 Nant Holdings Ip, Llc Object information derived from object images
US9014513B2 (en) 2000-11-06 2015-04-21 Nant Holdings Ip, Llc Image capture and identification system and process
US9014512B2 (en) 2000-11-06 2015-04-21 Nant Holdings Ip, Llc Object information derived from object images
US9014514B2 (en) 2000-11-06 2015-04-21 Nant Holdings Ip, Llc Image capture and identification system and process
US9020305B2 (en) 2000-11-06 2015-04-28 Nant Holdings Ip, Llc Image capture and identification system and process
US9025813B2 (en) 2000-11-06 2015-05-05 Nant Holdings Ip, Llc Image capture and identification system and process
US9025814B2 (en) 2000-11-06 2015-05-05 Nant Holdings Ip, Llc Image capture and identification system and process
US9031278B2 (en) 2000-11-06 2015-05-12 Nant Holdings Ip, Llc Image capture and identification system and process
US9031290B2 (en) 2000-11-06 2015-05-12 Nant Holdings Ip, Llc Object information derived from object images
US9036947B2 (en) 2000-11-06 2015-05-19 Nant Holdings Ip, Llc Image capture and identification system and process
US9036949B2 (en) 2000-11-06 2015-05-19 Nant Holdings Ip, Llc Object information derived from object images
US9036862B2 (en) 2000-11-06 2015-05-19 Nant Holdings Ip, Llc Object information derived from object images
US9036948B2 (en) 2000-11-06 2015-05-19 Nant Holdings Ip, Llc Image capture and identification system and process
US9046930B2 (en) 2000-11-06 2015-06-02 Nant Holdings Ip, Llc Object information derived from object images
US9087240B2 (en) 2000-11-06 2015-07-21 Nant Holdings Ip, Llc Object information derived from object images
US9104916B2 (en) 2000-11-06 2015-08-11 Nant Holdings Ip, Llc Object information derived from object images
US9110925B2 (en) 2000-11-06 2015-08-18 Nant Holdings Ip, Llc Image capture and identification system and process
US9116920B2 (en) 2000-11-06 2015-08-25 Nant Holdings Ip, Llc Image capture and identification system and process
US9135355B2 (en) 2000-11-06 2015-09-15 Nant Holdings Ip, Llc Image capture and identification system and process
US9141714B2 (en) 2000-11-06 2015-09-22 Nant Holdings Ip, Llc Image capture and identification system and process
US9148562B2 (en) 2000-11-06 2015-09-29 Nant Holdings Ip, Llc Image capture and identification system and process
US9154695B2 (en) 2000-11-06 2015-10-06 Nant Holdings Ip, Llc Image capture and identification system and process
US9154694B2 (en) 2000-11-06 2015-10-06 Nant Holdings Ip, Llc Image capture and identification system and process
US9152864B2 (en) 2000-11-06 2015-10-06 Nant Holdings Ip, Llc Object information derived from object images
US9170654B2 (en) 2000-11-06 2015-10-27 Nant Holdings Ip, Llc Object information derived from object images
US9182828B2 (en) 2000-11-06 2015-11-10 Nant Holdings Ip, Llc Object information derived from object images
US9235600B2 (en) 2000-11-06 2016-01-12 Nant Holdings Ip, Llc Image capture and identification system and process
US9244943B2 (en) 2000-11-06 2016-01-26 Nant Holdings Ip, Llc Image capture and identification system and process
US9262440B2 (en) 2000-11-06 2016-02-16 Nant Holdings Ip, Llc Image capture and identification system and process
US9288271B2 (en) 2000-11-06 2016-03-15 Nant Holdings Ip, Llc Data capture and identification system and process
US9311553B2 (en) 2000-11-06 2016-04-12 Nant Holdings IP, LLC. Image capture and identification system and process
US9311554B2 (en) 2000-11-06 2016-04-12 Nant Holdings Ip, Llc Image capture and identification system and process
US9311552B2 (en) 2000-11-06 2016-04-12 Nant Holdings IP, LLC. Image capture and identification system and process
US9310892B2 (en) 2000-11-06 2016-04-12 Nant Holdings Ip, Llc Object information derived from object images
US9317769B2 (en) 2000-11-06 2016-04-19 Nant Holdings Ip, Llc Image capture and identification system and process
US9324004B2 (en) 2000-11-06 2016-04-26 Nant Holdings Ip, Llc Image capture and identification system and process
US9330327B2 (en) 2000-11-06 2016-05-03 Nant Holdings Ip, Llc Image capture and identification system and process
US9330326B2 (en) 2000-11-06 2016-05-03 Nant Holdings Ip, Llc Image capture and identification system and process
US9330328B2 (en) 2000-11-06 2016-05-03 Nant Holdings Ip, Llc Image capture and identification system and process
US9336453B2 (en) 2000-11-06 2016-05-10 Nant Holdings Ip, Llc Image capture and identification system and process
US9342748B2 (en) 2000-11-06 2016-05-17 Nant Holdings Ip. Llc Image capture and identification system and process
US9360945B2 (en) 2000-11-06 2016-06-07 Nant Holdings Ip Llc Object information derived from object images
US9536168B2 (en) 2000-11-06 2017-01-03 Nant Holdings Ip, Llc Image capture and identification system and process
US9578107B2 (en) 2000-11-06 2017-02-21 Nant Holdings Ip, Llc Data capture and identification system and process
US9613284B2 (en) 2000-11-06 2017-04-04 Nant Holdings Ip, Llc Image capture and identification system and process
US9785859B2 (en) 2000-11-06 2017-10-10 Nant Holdings Ip Llc Image capture and identification system and process
US9785651B2 (en) 2000-11-06 2017-10-10 Nant Holdings Ip, Llc Object information derived from object images
US9805063B2 (en) 2000-11-06 2017-10-31 Nant Holdings Ip Llc Object information derived from object images
US9808376B2 (en) 2000-11-06 2017-11-07 Nant Holdings Ip, Llc Image capture and identification system and process
US9824099B2 (en) 2000-11-06 2017-11-21 Nant Holdings Ip, Llc Data capture and identification system and process
US9844467B2 (en) 2000-11-06 2017-12-19 Nant Holdings Ip Llc Image capture and identification system and process
US9844468B2 (en) 2000-11-06 2017-12-19 Nant Holdings Ip Llc Image capture and identification system and process
US9844469B2 (en) 2000-11-06 2017-12-19 Nant Holdings Ip Llc Image capture and identification system and process
US9844466B2 (en) 2000-11-06 2017-12-19 Nant Holdings Ip Llc Image capture and identification system and process
US10080686B2 (en) 2000-11-06 2018-09-25 Nant Holdings Ip, Llc Image capture and identification system and process
US10095712B2 (en) 2000-11-06 2018-10-09 Nant Holdings Ip, Llc Data capture and identification system and process
JP2012043447A (en) * 2001-11-05 2012-03-01 Nant Holdings Ip Llc Image capture and identification system and method

Also Published As

Publication number Publication date
JP3946927B2 (en) 2007-07-18

Similar Documents

Publication Publication Date Title
Javed et al. Tracking and object classification for automated surveillance
JP3481430B2 (en) Moving object tracking device
EP2619728B1 (en) An adaptable framework for cloud assisted augmented reality
US7940956B2 (en) Tracking apparatus that tracks a face position in a dynamic picture image using ambient information excluding the face
US7324670B2 (en) Face image processing apparatus and method
JP3944647B2 (en) Object measuring apparatus, the object measuring method, and a program
US5210799A (en) System and method for ranking and extracting salient contours for target recognition
US9965719B2 (en) Subcategory-aware convolutional neural networks for object detection
US7003135B2 (en) System and method for rapidly tracking multiple faces
US20040047494A1 (en) Method of detecting a specific object in an image signal
US8494234B1 (en) Video hashing system and method
KR100474848B1 (en) System and method for detecting and tracking a plurality of faces in real-time by integrating the visual ques
JP4166253B2 (en) Object detection apparatus, the object detecting method, and the object detecting program
US20140169663A1 (en) System and Method for Video Detection and Tracking
JP4177826B2 (en) Image processing apparatus and image processing method
US7376270B2 (en) Detecting human faces and detecting red eyes
Han et al. Employing a RGB-D sensor for real-time tracking of humans across multiple re-entries in a smart environment
JP4451307B2 (en) How to classify objects in the scene
CN1963839A (en) Detection method and apparatus of human
JP4564634B2 (en) Image processing method and apparatus and a storage medium
JP3801137B2 (en) Intruding object detecting apparatus
JP4479478B2 (en) Pattern recognition method and apparatus
JP4241763B2 (en) Person recognition apparatus and method
KR100734849B1 (en) Method for recognizing face and apparatus thereof
CN101887524B (en) Pedestrian detection method based on video monitoring

Legal Events

Date Code Title Description
A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20040830

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20040907

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20041020

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20041207

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20050202

A911 Transfer of reconsideration by examiner before appeal (zenchi)

Free format text: JAPANESE INTERMEDIATE CODE: A911

Effective date: 20050218

A912 Removal of reconsideration by examiner before appeal (zenchi)

Free format text: JAPANESE INTERMEDIATE CODE: A912

Effective date: 20050422

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20070322

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20070412

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20100420

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20110420

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20130420

Year of fee payment: 6

LAPS Cancellation because of no payment of annual fees