JP2020143941A - Object monitoring system having distance-measuring device - Google Patents
Object monitoring system having distance-measuring device Download PDFInfo
- Publication number
- JP2020143941A JP2020143941A JP2019039071A JP2019039071A JP2020143941A JP 2020143941 A JP2020143941 A JP 2020143941A JP 2019039071 A JP2019039071 A JP 2019039071A JP 2019039071 A JP2019039071 A JP 2019039071A JP 2020143941 A JP2020143941 A JP 2020143941A
- Authority
- JP
- Japan
- Prior art keywords
- filter
- distance
- monitoring area
- computer device
- pixels
- 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
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 104
- 238000005259 measurement Methods 0.000 claims abstract description 48
- 230000005856 abnormality Effects 0.000 claims description 24
- 238000001514 detection method Methods 0.000 abstract description 13
- 238000012545 processing Methods 0.000 abstract description 13
- 230000002159 abnormal effect Effects 0.000 abstract description 5
- 238000000034 method Methods 0.000 description 15
- 238000012935 Averaging Methods 0.000 description 7
- 230000001186 cumulative effect Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000001914 filtration Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000003321 amplification Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Abstract
Description
本発明は、測距装置を有する物体監視システムに関し、特に物体監視システムのフィルタ処理に関する。 The present invention relates to an object monitoring system having a distance measuring device, and more particularly to filtering of the object monitoring system.
物体までの距離を測定する測距装置として、光の飛行時間に基づき距離を出力するＴＯＦ（time of flight）カメラが知られている。ＴＯＦカメラは、所定周期で強度変調した参照光を対象空間に照射し、参照光と対象空間からの反射光との間の位相差に基づき対象空間の測距値を出力する位相差方式を採用するものが多い。ＴＯＦカメラの利用も想定された物体検知技術としては、下記の文献が公知である。 As a distance measuring device that measures the distance to an object, a TOF (time of flight) camera that outputs a distance based on the flight time of light is known. The TOF camera adopts a phase difference method that irradiates the target space with reference light whose intensity is modulated in a predetermined cycle and outputs the distance measurement value of the target space based on the phase difference between the reference light and the reflected light from the target space. There are many things to do. The following documents are known as an object detection technique that is expected to use a TOF camera.
特許文献１には、ＴＯＦカメラ等で撮像した検知エリアの撮像画像と、検知エリアの背景画像との背景差分画像を生成し、背景差分画像において前景画素をグルーピングし、前景画素の画素数がオブジェクト判定画素数以下の前景領域をノイズと判定することが記載されている。 In Patent Document 1, a background difference image between a captured image of a detection area captured by a TOF camera or the like and a background image of the detection area is generated, foreground pixels are grouped in the background difference image, and the number of pixels of the foreground pixels is an object. It is described that the foreground region equal to or less than the number of determination pixels is determined to be noise.
ＴＯＦカメラの距離空間の中に定めた監視領域内の物体有無の判定を行う場合、ＴＯＦカメラの測距値にはバラツキがあるため、物体が監視領域の遠方面から僅かに侵入した状態では、監視領域内と判定される画素が離散的になることがある。また、ＴＯＦカメラは、サチュレーション、露光不足、イメージセンサの画素故障等といった測距異常を示す画素を発生させることもある。このような測距値のバラツキ、測距異常等を発生させる測距装置を用いて監視領域内の物体有無を判定する場合、判定安定化のために距離画像に対してフィルタ処理を行うことが想定される。 When determining the presence or absence of an object in the monitoring area defined in the metric space of the TOF camera, the distance measurement value of the TOF camera varies, so if the object slightly invades from a distant side of the monitoring area, Pixels determined to be in the monitoring area may be discrete. In addition, the TOF camera may generate pixels that indicate distance measurement abnormalities such as saturation, underexposure, and pixel failure of the image sensor. When determining the presence or absence of an object in the monitoring area using a distance measuring device that causes such variations in distance measurement values and abnormal distance measurement, it is necessary to filter the distance image to stabilize the judgment. is assumed.
しかし、従来の画像処理フィルタ、例えば収縮フィルタ、平均化フィルタ、中間値フィルタ等では、フィルタサイズに対して監視領域内と判定される画素数が少ない場合、監視領域内に物体有りと判定できないことがある。例えば収縮フィルタは、図１１Ａに示すように対象画素周辺の３×３の画素値が全て１のときに１を出力する。収縮フィルタで期待される一般的な効果は規定サイズ以下のノイズや細かな凹凸を削除することであるが、収縮フィルタを距離画像に適用して監視領域内の物体検知を行う場合、３×３の画素群の測距値が全て監視領域内に無いと、監視領域内に物体が侵入したと判定できない。 However, with conventional image processing filters such as shrinkage filters, averaging filters, median filters, etc., if the number of pixels determined to be within the monitoring area is small relative to the filter size, it cannot be determined that there is an object in the monitoring area. There is. For example, the contraction filter outputs 1 when all the 3 × 3 pixel values around the target pixel are 1, as shown in FIG. 11A. The general effect expected of a shrink filter is to remove noise and fine irregularities smaller than the specified size, but when applying the shrink filter to a distance image to detect an object in the monitoring area, 3x3 If all the distance measurement values of the pixel group are not within the monitoring area, it cannot be determined that an object has entered the monitoring area.
また平均化フィルタは、図１１Ｂに示すように対象画素周辺の３×３の画素値の平均値を出力する。平均化フィルタで期待される一般的な効果は急峻に変化する領域を滑らかにすることであるが、平均化フィルタを距離画像に適用して監視領域内の物体検知を行う場合、物体が背景の距離と平均化されてしまうと、監視領域内に物体が侵入したと判定できなくなる。 Further, the averaging filter outputs an average value of 3 × 3 pixel values around the target pixel as shown in FIG. 11B. A common effect expected with an averaging filter is to smooth out rapidly changing areas, but when an averaging filter is applied to a distance image to detect an object in the surveillance area, the object is in the background. If it is averaged with the distance, it cannot be determined that an object has entered the monitoring area.
さらに中間値フィルタは、図１１Ｃに示すように対象画素周辺の３×３の画素値の中間値（例えば５番目の値）を出力する。中間値フィルタで期待される一般的な効果はスパイク的なノイズの除去であり、滑らかさは平均化フィルタと比べて若干劣るものの、エッジ部のぼけが抑えられる。中間値フィルタを距離画像に適用して監視領域内の物体検知を行う場合、３×３の画素群のうち５個以上の画素が監視領域内と判定されないと、監視領域内に物体が侵入したと判定できない。 Further, the intermediate value filter outputs an intermediate value (for example, the fifth value) of 3 × 3 pixel values around the target pixel as shown in FIG. 11C. A common effect expected with an intermediate filter is the removal of spike-like noise, which is slightly inferior to the averaging filter in smoothness but reduces edge blur. When an intermediate value filter is applied to a distance image to detect an object in the monitoring area, if 5 or more pixels in the 3x3 pixel group are not determined to be in the monitoring area, an object has entered the monitoring area. Cannot be determined.
そこで、測距値のバラツキ、測距異常等を発生させる測距装置を用いた物体監視システムにおいて、物体検知の安定性を高めたフィルタ処理が求められている。 Therefore, in an object monitoring system using a distance measuring device that causes variations in distance measurement values, distance measurement abnormalities, and the like, there is a demand for filter processing that enhances the stability of object detection.
本開示の一態様は、対象空間の距離画像を生成する測距装置と、対象空間の中に定めた監視領域内の物体有無を距離画像に基づき判断するコンピュータ装置と、を備える物体監視システムであって、コンピュータ装置は、距離画像において、特定の配置関係にある第１個数の隣接画素群の中で、監視領域内と判定した画素数が、１以上で第１個数未満である第２個数以上と判定された場合に、監視領域内に物体有りと判定するフィルタを備える、物体監視システムを提供する。 One aspect of the present disclosure is an object monitoring system including a distance measuring device that generates a distance image of the target space and a computer device that determines the presence or absence of an object in the monitoring area defined in the target space based on the distance image. Therefore, in the distance image, the computer device has a second number of pixels determined to be in the monitoring area among the first number of adjacent pixel groups having a specific arrangement relationship, which is 1 or more and less than the first number. Provided is an object monitoring system including a filter for determining that there is an object in the monitoring area when the above is determined.
本開示の一態様によれば、従来の画像処理フィルタでは物体検知が難しい場合でも物体検知が可能になる。また、測距異常の画素があっても本開示のフィルタのみで判定を継続できる。 According to one aspect of the present disclosure, it is possible to detect an object even when it is difficult to detect the object with a conventional image processing filter. Further, even if there are pixels with abnormal distance measurement, the determination can be continued only by the filter of the present disclosure.
以下、添付図面を参照して本開示の実施形態を詳細に説明する。各図面において、同一又は類似の構成要素には同一又は類似の符号が付与されている。また、以下に記載する実施形態は、特許請求の範囲に記載される発明の技術的範囲及び用語の意義を限定するものではない。 Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In each drawing, the same or similar components are given the same or similar reference numerals. In addition, the embodiments described below do not limit the technical scope of the invention and the meaning of terms described in the claims.
図１は本実施形態における物体監視システム１のブロック図である。物体監視システム１は、測距装置１０及びコンピュータ装置２０を備えている。測距装置１０及びコンピュータ装置２０は、有線又は無線のネットワークを介して相互に通信可能に接続されるか、又は、バス接続等により一体化して構成されてもよい。 FIG. 1 is a block diagram of the object monitoring system 1 in the present embodiment. The object monitoring system 1 includes a distance measuring device 10 and a computer device 20. The distance measuring device 10 and the computer device 20 may be connected to each other so as to be able to communicate with each other via a wired or wireless network, or may be integrally configured by a bus connection or the like.
測距装置１０は、ＴＯＦカメラ、レーザスキャナ等で構成され、対象空間の距離画像を順次生成する。測距装置１０は、入出力部１１、発光撮像制御部１２、照射部１３、受光部１４、Ａ／Ｄ変換部１５、及び距離画像生成部１６を備えている。入出力部１１は、種々の設定値等の入力、距離画像や強度画像等の出力等を行う。発光撮像制御部１２は、入力した設定値に基づき照射部１３の発光及び受光部１４の撮像を制御する。 The distance measuring device 10 is composed of a TOF camera, a laser scanner, and the like, and sequentially generates distance images of the target space. The distance measuring device 10 includes an input / output unit 11, a light emitting image pickup control unit 12, an irradiation unit 13, a light receiving unit 14, an A / D conversion unit 15, and a distance image generation unit 16. The input / output unit 11 inputs various set values and outputs, outputs a distance image, an intensity image, and the like. The light emission imaging control unit 12 controls the light emission of the irradiation unit 13 and the imaging of the light receiving unit 14 based on the input set value.
照射部１３は、強度変調した参照光を発光する光源、参照光を対象空間に照射するための拡散板やＭＥＭＳミラー等のスキャナ機構等を備えている。受光部１４は、対象空間からの反射光を集光する集光レンズ、特定波長の反射光のみを透過する光学フィルタ、反射光を受光する受光素子等を備えている。受光部１４は、参照光の発光タイミングに対し、例えば０°、９０°、１８０°、２７０°だけ位相をずらした４種類の露光タイミングで受光を繰返し、位相毎に電荷量Ｑ1−Ｑ4を蓄積していく。 The irradiation unit 13 includes a light source that emits intensity-modulated reference light, a diffuser plate for irradiating the target space with reference light, a scanner mechanism such as a MEMS mirror, and the like. The light receiving unit 14 includes a condensing lens that collects the reflected light from the target space, an optical filter that transmits only the reflected light of a specific wavelength, a light receiving element that receives the reflected light, and the like. The light receiving unit 14 repeats light reception at four types of exposure timings that are out of phase by, for example, 0 °, 90 °, 180 °, and 270 ° with respect to the emission timing of the reference light, and the amount of charge Q 1 −Q 4 for each phase. Will accumulate.
Ａ／Ｄ変換部１５は、蓄積した電荷量Ｑ1−Ｑ4を増幅してＡ／Ｄ変換し二値化した値で出力する。また増幅した際に飽和を検出した場合には、これを示す値（ビット）を出力する。 A / D converter 15 outputs at amplifies the charge amount Q 1 -Q 4 accumulated converted A / D binarized values. If saturation is detected during amplification, a value (bit) indicating this is output.
距離画像生成部１６は、電荷量Ｑ1−Ｑ4に基づいて参照光と反射光との位相差を画素毎に求め、各画素の位相差から測距値を算出して距離画像を生成する。位相差Ｔｄ及び測距値Ｌの算出式の一例を下記に示す。下記式において、ｃは光速であり、ｆは参照光の変調周波数である。 Distance image generating unit 16 obtains each pixel a phase difference between the reference light and the reflected light based on the electric charge amount Q 1 -Q 4, and generates a distance image by calculating the distance value from the phase difference of each pixel .. An example of the calculation formulas for the phase difference Td and the distance measurement value L is shown below. In the following equation, c is the speed of light and f is the modulation frequency of the reference light.
また距離画像生成部１６は、電荷量Ｑ1−Ｑ4に基づいて、Ａ／Ｄ変換部１５の出力に電荷量の飽和が検出されている場合、一般にサチュレーション発生と判断し、測距値として特異値（例えば９９９９）を出力することもできる。また、距離画像生成部１６は、電荷量Ｑ1−Ｑ4のいずれもが規定値より小さいと判断される場合には、露光不足と判断し、測距値として特異値（例えば９９９８）を出力することもできる。 The distance image generation unit 16 based on the charge amount Q 1 -Q 4, if the saturation charge amount in the output of the A / D converter 15 is detected, typically determines that the saturation occurs, as a distance measurement value It is also possible to output a singular value (for example, 9999). The distance image generation unit 16, when it is determined that none of the charge amount Q 1 -Q 4 is less than the specified value, it is determined that underexposure, outputs the singular values (e.g. 9998) as a distance measurement value You can also do it.
距離画像生成部１６は、電荷量Ｑ1−Ｑ4のいずれも同じ値である場合、画素故障発生と判断し、測距値として特異値（例えば９９９７）を出力することもできる。また、電荷量Ｑ1、Ｑ3の和と電荷量Ｑ2、Ｑ4の和との差分をスケール調整して求めた精度情報が所定閾値を超える場合には、精度異常と判断し、特異値（例えば９９９６）を出力することもできる。精度情報の詳細については特願２０１８−１１２６６５号を参照されたい。なお、他の実施形態において、これら異常の検出や特異値への置換動作については、電荷量Ｑ1−Ｑ4のＡ／Ｄ変換値をコンピュータ装置２０へ送信し、コンピュータ装置２０側で判定してもよい。 Distance image generation unit 16, if the same value both in the charge amount Q 1 -Q 4, and determines that the pixel failure, can output the singular values (e.g. 9997) as a distance measurement value. Further, when the accuracy information obtained by subtracting the scaled with the sum of the charge amount Q 1, Q 3 and the sum of the charge amount Q 2, Q 4 exceeds a predetermined threshold value, it is determined that inexact, singular value (For example, 9996) can also be output. For details of accuracy information, refer to Japanese Patent Application No. 2018-112665. Note that in another embodiment, for the replacement operation for these anomalies detected and singular values, an A / D conversion value of the charge amount Q 1 -Q 4 is transmitted to the computer device 20 determines in the computer device 20 side You may.
測距装置１０はさらに、強度画像生成部１７を備えていてもよい。強度画像生成部１７は、距離画像内の各画素について電荷量Ｑ1−Ｑ4の関係に基づき受光強度Ｉを算出し、距離画像に対応した強度画像を順次生成する。受光強度Ｉの算出式の一例を下記に示す。 The distance measuring device 10 may further include an intensity image generation unit 17. Intensity image generating unit 17, for each pixel in the distance image based on the relationship of the charge amount Q 1 -Q 4 calculates the received light intensity I, sequentially generates an intensity image corresponding to the distance image. An example of the calculation formula of the light receiving intensity I is shown below.
コンピュータ装置２０は、ＣＰＵ（central processing unit）、ＲＡＭ（random access memory）、ＡＳＩＣ（application specific integrated circuit）、ＦＰＧＡ（field-programmable gate array）等で構成され、対象空間の中に定めた監視領域内の物体有無を距離画像に基づき判断する。コンピュータ装置２０は、入出力部２１、設定メモリ２２、フィルタ判定部２３、信号出力部２４、及び表示部２５を備えている。 The computer device 20 is composed of a CPU (central processing unit), a RAM (random access memory), an ASIC (application specific integrated circuit), an FPGA (field-programmable gate array), etc., and is within a monitoring area defined in the target space. The presence or absence of an object is determined based on the distance image. The computer device 20 includes an input / output unit 21, a setting memory 22, a filter determination unit 23, a signal output unit 24, and a display unit 25.
入出力部２１は、距離画像、強度画像等の入力、種々の設定値の出力等を行う。設定メモリ２２は、監視領域データ、種々のフィルタ設定値、撮像モード等を記憶している。監視領域データは、測距装置１０の対象空間における三次元位置として設定され、距離画像の各画素が眺望する監視領域の距離範囲テーブルに変換されて記憶される。フィルタ設定値は、監視領域内の物体有無を判定するフィルタに関する設定値であり、例えばフィルタ形状、判定閾値、後述する他の設定値を含む。撮像モードは、測距装置の発光撮像に関する設定値であり、例えば参照光の発光量、露光時間、絞り値等を含む。 The input / output unit 21 inputs a distance image, an intensity image, and the like, outputs various set values, and the like. The setting memory 22 stores monitoring area data, various filter setting values, an imaging mode, and the like. The monitoring area data is set as a three-dimensional position in the target space of the distance measuring device 10, is converted into a distance range table of the monitoring area in which each pixel of the distance image is viewed, and is stored. The filter setting value is a setting value relating to a filter for determining the presence or absence of an object in the monitoring area, and includes, for example, a filter shape, a determination threshold value, and other setting values described later. The image pickup mode is a set value related to light emission imaging of the distance measuring device, and includes, for example, a light emission amount of reference light, an exposure time, an aperture value, and the like.
フィルタ判定部２３は、距離画像をフィルタ処理して監視領域内の物体有無を判定する。本例のフィルタは、特定の配置関係にあるＭ個（Ｍは整数）の隣接画素群の中で、監視領域内と判定した画素数が、１以上でＭ個未満であるＮ個以上（Ｎは整数）と判定された場合に、監視領域内に物体有りと判定する。 The filter determination unit 23 filters the distance image to determine the presence or absence of an object in the monitoring area. In the filter of this example, among the M (M is an integer) adjacent pixel group having a specific arrangement relationship, the number of pixels determined to be in the monitoring area is N or more (N) which is 1 or more and less than M. Is an integer), it is determined that there is an object in the monitoring area.
信号出力部２４は、監視領域内に物体有りとフィルタ判定された場合に、物体検知信号２６を外部へ出力する。物体検知信号２６は、例えば監視領域に侵入した作業者の安全を確保するため、作業者から隔離するロボット、工作機械等の危険源の動力停止信号として使用される。 The signal output unit 24 outputs the object detection signal 26 to the outside when the filter determines that there is an object in the monitoring area. The object detection signal 26 is used as a power stop signal for a danger source such as a robot or a machine tool that is isolated from the worker, for example, in order to ensure the safety of the worker who has entered the monitoring area.
表示部２６は、種々の設定画面、距離画像、強度画像等を表示する。後述するが、本例の表示部２６は、距離画像、強度画像等の対象空間の画像上に、監視領域内か否か、測距異常の種別、フィルタの判定結果等の画素状況を重ねた画像を表示する。 The display unit 26 displays various setting screens, distance images, intensity images, and the like. As will be described later, the display unit 26 of this example superimposes pixel conditions such as whether or not it is within the monitoring area, the type of ranging abnormality, and the determination result of the filter on the image of the target space such as the distance image and the intensity image. Display the image.
図２はフィルタ処理の具体例を説明する距離画像の状態を示す図である。画素領域３１は、設定された監視領域を眺望する画素であることを示し、これら画素の測距値が距離範囲テーブルの範囲内である場合には、監視領域内と判定される。図２では、物体３０の一部が監視領域に侵入した場合を想定している。なお、距離画像３２は、画素領域３１内において監視領域内と判定した４つの画素３２ａ−３２ｄと、測距異常を示す１つの画素３２ｅと、を含んでいる。理解を容易にするため、図２は距離画像３２の一部のみを示し、また物体３０は距離画像３２上で表現していることに留意されたい。 FIG. 2 is a diagram showing a state of a distance image for explaining a specific example of the filtering process. The pixel area 31 indicates that the pixels are for viewing the set monitoring area, and when the distance measurement values of these pixels are within the range of the distance range table, it is determined to be within the monitoring area. In FIG. 2, it is assumed that a part of the object 30 has invaded the monitoring area. The distance image 32 includes four pixels 32a-32d determined to be in the monitoring area in the pixel area 31, and one pixel 32e indicating an abnormality in distance measurement. Note that for ease of understanding, FIG. 2 shows only a portion of the distance image 32 and the object 30 is represented on the distance image 32.
本例のフィルタ３３は、３×３のＭ＝９個の隣接画素群の中で、監視領域３１内に侵入したと判定した画素数がＮ＝４個以上と判定された場合に、監視領域３１内に物体有りと判定する。一般にフィルタ処理は、注目画素を隣接画素群の中心部の画素位置とし、注目画素を含む隣接画素群の値を用いて判定を行う。フィルタ３３を距離画像３２に適用し、監視領域３１内に物体有りと判定される注目画素が１画素でもあった場合には、物体検知信号が出力される。例えば図２に示すように、対象画素３２ａ−３２ｄの４つの画素を夫々注目画素とした場合には、いずれも監視領域３１内と判定した画素数が４個以上となるため、監視領域３１内に物体有りと判定される（図２の右側にフィルタ判定結果を示す。）。距離画像３２内に測距異常を示す画素３２ｅがあっても同様のフィルタ判定結果が得られるため、本例のフィルタ３３のみで判定を継続できる。 The filter 33 of this example is a monitoring area when it is determined that the number of pixels determined to have entered the monitoring area 31 is N = 4 or more in a group of 3 × 3 M = 9 adjacent pixels. It is determined that there is an object in 31. Generally, in the filter processing, the pixel of interest is set as the pixel position at the center of the adjacent pixel group, and the determination is made using the value of the adjacent pixel group including the pixel of interest. When the filter 33 is applied to the distance image 32 and there is at least one pixel of interest in the monitoring area 31 that is determined to have an object, an object detection signal is output. For example, as shown in FIG. 2, when each of the four pixels of the target pixels 32a-32d is set as the pixel of interest, the number of pixels determined to be in the monitoring area 31 is 4 or more, and therefore the inside of the monitoring area 31. It is determined that there is an object in (the filter determination result is shown on the right side of FIG. 2). Since the same filter determination result can be obtained even if there is a pixel 32e indicating an abnormality in distance measurement in the distance image 32, the determination can be continued only by the filter 33 of this example.
対照的に、従来の画像処理フィルタ、例えば収縮フィルタ、中間値フィルタでは、監視領域３１内と判定した画素数がフィルタ内に９個又は５個以上ないため、実際には監視領域３１内に物体３０が侵入していても物体検知できない。また平均化フィルタの場合も対象画素３２ａ−３２ｄ以外の周辺画素の測距値が平均値計算上支配的になるため、物体検知できない可能性が高い。従って、本例のフィルタ３３によれば、従来の画像処理フィルタでは物体検知が難しい場合でも物体検知が可能になる。 In contrast, in a conventional image processing filter, for example, a shrinkage filter or an intermediate value filter, the number of pixels determined to be in the monitoring area 31 is not 9 or 5 or more in the filter, so that an object is actually in the monitoring area 31. Even if 30 is invading, the object cannot be detected. Also, in the case of the averaging filter, since the distance measurement values of the peripheral pixels other than the target pixels 32a-32d are dominant in the average value calculation, there is a high possibility that the object cannot be detected. Therefore, according to the filter 33 of this example, it is possible to detect an object even when it is difficult to detect the object with the conventional image processing filter.
図３はフィルタ処理の変形例を説明する図である。図３では、再帰反射材４０が物体３０の先端の一部に付いている場合を想定している。再帰反射材４０によってサチュレーションが発生するため、距離画像３２は、監視領域３１内と判定した３つの画素３２ａ−３２ｃに加えて、測距異常を示す６つの画素４０ａ−４０ｆも含んでいる。 FIG. 3 is a diagram illustrating a modified example of the filtering process. In FIG. 3, it is assumed that the retroreflective material 40 is attached to a part of the tip of the object 30. Since saturation is generated by the retroreflective material 40, the distance image 32 includes six pixels 40a-40f indicating an abnormality in distance measurement in addition to the three pixels 32a-32c determined to be within the monitoring area 31.
本例のフィルタ３３は、監視領域３１内と判定した画素数に、サチュレーション等の測距異常を示す画素数も含めた画素数がＮ＝４個以上かを判定する点で、前述のフィルタとは異なる。監視領域３１内と判定した３つの画素３２ａ−３２ｃ、及び、測距異常を示す６つの画素４０ａ−４０ｆの計９つの画素を夫々注目画素とした場合には、いずれも監視領域３１内と判定した画素数に、サチュレーション等の測距異常を示す画素数も含めた画素数が４個以上あるため、監視領域３１内に物体有りと判定される（図３の右側にフィルタ判定結果を示す。）。 The filter 33 of this example is different from the above-mentioned filter in that it determines whether the number of pixels determined to be in the monitoring area 31 includes the number of pixels indicating a distance measurement abnormality such as saturation and N = 4 or more. Is different. When a total of nine pixels, the three pixels 32a-32c determined to be in the monitoring area 31 and the six pixels 40a-40f indicating a distance measurement abnormality, are each set as the pixel of interest, they are all determined to be in the monitoring area 31. Since the number of pixels is 4 or more including the number of pixels indicating an abnormality in distance measurement such as saturation, it is determined that there is an object in the monitoring area 31 (the filter determination result is shown on the right side of FIG. 3). ).
対照的に、測距異常の画素数を含めないフィルタでは、監視領域３１内と判定した画素数が３個しかないため、フィルタ判定閾値がＮ＝４個の場合には監視領域３１内に物体有りと判定できない。このように測距異常を示す画素数も含めてフィルタ判定を行うことにより、今回例示したような先端部に再帰反射材が付いている物体をよりいち早く、また、より安全サイドに判定することが可能になる。 In contrast, in a filter that does not include the number of pixels with abnormal distance measurement, the number of pixels determined to be within the monitoring area 31 is only 3, so when the filter determination threshold is N = 4, an object is within the monitoring area 31. Cannot be determined to be present. By performing the filter judgment including the number of pixels indicating an abnormality in distance measurement in this way, it is possible to judge an object having a retroreflective material at the tip as illustrated this time more quickly and on the safer side. It will be possible.
図８は約２ｍ先の物体を眺望する画素が出力した測距値のバラツキを示している。ショットノイズ、暗電流ノイズ、熱雑音等の不可避なランダムノイズの影響を受けるため、ＴＯＦカメラの各画素の測距値のバラツキは正規分布的に分布することが知られている。これは、物体が監視領域の遠方面上に丁度ある場合、これを眺望する各画素は、監視領域内と判定する判定確率がほぼ０．５であることを意味する。図９は平均がμで偏差σのバラツキを持つ測距値の正規分布及びその累積分布確率Ｆ（ｘ）を示している。μが監視領域の遠方面の距離とした場合、判定確率に対応する累積分布確率Ｆ（ｘ）は０．５であり、物体が監視領域の遠方面より侵入している距離が大きくなるほど、判定確率に対応する累積分布確率Ｆ（ｘ）は大きくなる。 FIG. 8 shows the variation in the distance measurement value output by the pixel that looks at the object about 2 m away. It is known that the variation in the distance measurement value of each pixel of the TOF camera is normally distributed because it is affected by unavoidable random noise such as shot noise, dark current noise, and thermal noise. This means that when the object is exactly on the far side of the monitoring area, each pixel looking at the object has a determination probability of being within the monitoring area of about 0.5. FIG. 9 shows a normal distribution of distance measurement values having an average of μ and a variation of deviation σ and a cumulative distribution probability F (x) thereof. When μ is the distance of the far side of the monitoring area, the cumulative distribution probability F (x) corresponding to the judgment probability is 0.5, and the larger the distance that the object invades from the far side of the monitoring area, the more the judgment. The cumulative distribution probability F (x) corresponding to the probability increases.
図４はフィルタ処理の他の変形例を説明する図である。図９に示しているが、仮に測距値が偏差σのバラツキを持ち、物体が監視領域の遠方面から０．２５σに相当する距離分侵入していると、物体を眺望する各画素が監視領域内と判定する判定確率は０．６となる。従って各距離画像において、監視領域内と判定する画素の状況は、図４に示すように離散的になる。この状況下において、３×３のＭ＝９個、Ｎ＝４個のフィルタを適用した場合のフィルタ処理後のフィルタ判定確率を考える。物体を眺望する各画素が監視領域内と判定される判定確率をｐとし、フィルタ処理後のフィルタ判定確率をＰとした場合、フィルタ判定確率Ｐは、判定確率ｐの試行をＭ回行ってＮ回以上成功する確率を計算する下記の二項分布の式から求められ、フィルタ判定確率Ｐは０．７３３となる。 FIG. 4 is a diagram illustrating another modification of the filtering process. As shown in FIG. 9, if the distance measurement value has a variation of deviation σ and the object invades from a distant side of the monitoring area by a distance corresponding to 0.25σ, each pixel viewing the object monitors. The determination probability of determining that the area is within the region is 0.6. Therefore, in each distance image, the status of the pixels determined to be within the monitoring region becomes discrete as shown in FIG. Under this circumstance, consider the filter determination probability after the filter processing when 3 × 3 M = 9 and N = 4 filters are applied. When the judgment probability that each pixel viewing the object is determined to be in the monitoring area is p and the filter judgment probability after the filter processing is P, the filter judgment probability P is N by performing the trial of the judgment probability p M times. It is obtained from the following binomial distribution formula that calculates the probability of success more than once, and the filter determination probability P is 0.733.
＜方式１＞
フィルタ判定確率を高めるため、方式１のフィルタ３３は、時系列に生成したＱ個の距離画像ｎ、ｎ−１、ｎ−２にわたって監視領域内と判定した画素数の合計又は測距異常を示す画素数も含めた画素数の合計が、１以上でＭ×Ｑ個未満であるＬ個以上かを判定する時間フィルタである点で、前述のものとは異なる。例えば図４に示すように、過去３回（時間フィルタ定数Ｑ＝３個）の距離画像ｎ、ｎ−１、ｎ−２にわたって３×３のＭ＝９×３＝２７個、Ｎ＝４×３＝１２個の時間フィルタを適用した場合、フィルタ判定確率Ｐ１が０．９５７まで向上する。従って、物体検知の安定性が高まる。
<Method 1>
In order to increase the filter determination probability, the filter 33 of the method 1 indicates the total number of pixels determined to be within the monitoring area or the distance measurement abnormality over the Q distance images n, n-1, and n-2 generated in time series. It differs from the above in that it is a time filter for determining whether the total number of pixels including the number of pixels is 1 or more and L or more, which is less than M × Q. For example, as shown in FIG. 4, 3 × 3 M = 9 × 3 = 27, N = 4 × over the past 3 times (time filter constant Q = 3) distance images n, n-1, n-2. When 3 = 12 time filters are applied, the filter determination probability P1 is improved to 0.957. Therefore, the stability of object detection is improved.
＜方式２＞
さらにフィルタ判定確率を高めるため、方式２のフィルタ３３は、時系列に生成したＱ個の距離画像ｎ、ｎ−１、ｎ−２にわたって１度でも監視領域内と判定した画素数又は測距異常を示す画素数も含めた画素数がＮ個以上かを判定する点で、前述のものとは異なる。例えば図４に示すように、過去３回の距離画像ｎ、ｎ−１、ｎ−２にわたって３×３のＭ＝９個、Ｎ＝４個の時間フィルタを適用した場合、１画素の判定確率ｐが０．６から０．９３６へ向上するため、フィルタ判定確率Ｐ２が０．９９９９まで向上する。従って、物体検知の安定性がさらに高まる。
<Method 2>
In order to further increase the filter determination probability, the filter 33 of the method 2 has the number of pixels or distance measurement abnormality determined to be within the monitoring area even once over the Q distance images n, n-1, and n-2 generated in time series. It differs from the above in that it determines whether the number of pixels including the number of pixels indicating the above is N or more. For example, as shown in FIG. 4, when a 3 × 3 M = 9 and N = 4 time filters are applied over the past three distance images n, n-1, and n-2, the judgment probability of one pixel is determined. Since p is improved from 0.6 to 0.936, the filter determination probability P2 is improved to 0.9999. Therefore, the stability of object detection is further enhanced.
判定確率の向上度は、フィルタ処理する距離画像が多い程高くなる。因みに、時間フィルタ定数Ｑ＝１０個の場合、フィルタ判定確率Ｐ１は０．９９７まで向上し、フィルタ判定確率Ｐ２は１−１．６Ｅ−１８まで向上する。 The degree of improvement in the determination probability increases as the number of distance images to be filtered increases. Incidentally, when the time filter constants Q = 10, the filter determination probability P1 is improved to 0.997, and the filter determination probability P2 is improved to 1-1.6E-18.
前述のフィルタに応じて、コンピュータ装置２０は下記項目の少なくとも１つを設定する手段を備えているとよい。設定手段としては、設定ソフトウェア、設定ボタン等がある。
（１）フィルタ形状（フィルタサイズ：Ｍ、画素群の配置関係等。図５に一例を示す）
（２）フィルタ判定閾値：Ｎ、Ｌ
（３）測距異常を示す画素数を含めるか否か
（４）時間フィルタ定数：Ｑ
（５）使用するフィルタの選択
（６）撮像モード（参照光の発光量、露光時間、絞り値等）
上記項目の設定により、物体検知サイズ、フィルタ判定確率等の調整が可能になるため、使用目的、設置環境等に応じたフレキシブルな物体検知が可能となる。
Depending on the above-mentioned filter, the computer device 20 may be provided with means for setting at least one of the following items. Setting means include setting software, setting buttons, and the like.
(1) Filter shape (filter size: M, pixel group arrangement, etc. An example is shown in FIG. 5)
(2) Filter judgment threshold: N, L
(3) Whether to include the number of pixels indicating an abnormal distance measurement (4) Time filter constant: Q
(5) Selection of filter to be used (6) Imaging mode (emission amount of reference light, exposure time, aperture value, etc.)
By setting the above items, it is possible to adjust the object detection size, filter judgment probability, etc., so that flexible object detection according to the purpose of use, installation environment, etc. is possible.
またコンピュータ装置２０は、測距異常を示す画素数を含めてフィルタ判定を行う場合、監視領域内に物体有りと判定した理由としては、物体の侵入と測距異常、さらにこの測距異常は、サチュレーション、露光不足、画素故障、精度故障等と複数に分類される場合もあり、監視領域内に物体有りと判定した判定理由を通知する手段を備えるとよい。通知手段としては、通知メール、通知音、通知ランプ等がある。 Further, when the computer device 20 performs the filter determination including the number of pixels indicating the distance measurement abnormality, the reason why it is determined that there is an object in the monitoring area is that the object invades and the distance measurement abnormality, and further, this distance measurement abnormality is It may be classified into a plurality of categories such as saturation, underexposure, pixel failure, accuracy failure, etc., and it is preferable to provide a means for notifying the reason for determining that there is an object in the monitoring area. Notification means include notification mail, notification sound, notification lamp, and the like.
図６はフィルタの判定理由の選定アルゴリズムを説明する図である。フィルタ処理において判定理由を選定するアルゴリズムとしては、フィルタ内で最も多く見られる種別を選定する方法がある。種別としては、侵入、サチュレーション、露光不足、画素故障、精度異常等がある。図６では、距離画像が、監視領域内と判定した３つの画素３２ａ−３２ｃと、サチュレーションを示す２つの画素５０ａ−５０ｂと、露光不足を示す１つの画素５０ｃと、を含んでいる場合を想定している。測距異常を示す画素数も含めるフィルタ３３を注目画素３２ｂに適用して監視領域内に物体有りと判定された場合、フィルタ内で最も多い種別が「侵入」であるため、フィルタ３３の判定理由は「侵入」が選定される。また、注目画素からの距離が遠い程小さくなる重みを加味した加重平均の高い理由を選定する方法や、判定理由に優先順位を付けておき、最も高い優先順位の理由を選定する方法もある。 FIG. 6 is a diagram illustrating an algorithm for selecting a filter determination reason. As an algorithm for selecting the reason for judgment in the filter processing, there is a method of selecting the type most often seen in the filter. Types include intrusion, saturation, underexposure, pixel failure, and accuracy error. In FIG. 6, it is assumed that the distance image includes three pixels 32a-32c determined to be in the monitoring area, two pixels 50a-50b indicating saturation, and one pixel 50c indicating underexposure. are doing. When the filter 33 including the number of pixels indicating an abnormality in distance measurement is applied to the pixel of interest 32b and it is determined that there is an object in the monitoring area, the most common type in the filter is "intrusion", so the reason for determining the filter 33. Is selected as "intrusion". Further, there is also a method of selecting a reason having a high weighted average in consideration of a weight that becomes smaller as the distance from the pixel of interest becomes farther, or a method of prioritizing the judgment reason and selecting the reason of the highest priority.
一方、物体監視システムとして監視領域内に物体有りと判定した理由は、フィルタ判定が物体有りと判定した同一の距離画像の全てのフィルタ判定の理由を対象とするのが一般である。従って、各フィルタ処理のフィルタ判定の理由は複数になる場合や、さらにそれらの種別が異なる場合がある。 On the other hand, the reason why the object monitoring system determines that there is an object in the monitoring area is generally that the filter determination targets all the reasons for the filter determination of the same distance image determined to have the object. Therefore, there may be a plurality of reasons for the filter determination of each filter processing, or the types thereof may be different.
また、注目画素毎にフィルタ判定の理由が複数で異なる場合、主たる理由を選定して通知する方が、ユーザには使い勝手が良い場合もある。物体監視システムとして監視領域内に物体有りと判定した主たる判定理由を選定するアルゴリズムとしては、最も多い判定理由を選定する方法や、判定理由に優先順位を付けておき、最も高い優先順位の判定理由を選定する方法等がある。一例として「侵入」を優先順位の最高位にしておくことで、例えば再帰反射材の付いた物体が侵入し、サチュレーションと判定したフィルタが３つ、物体侵入と判定したフィルタが１つであった場合も、「侵入」を監視領域内に物体有りと判定した主たる判定理由として通知することになり、ユーザに対して、より現実的な理由の選択が可能になる。 Further, when a plurality of reasons for filter determination are different for each pixel of interest, it may be more convenient for the user to select and notify the main reason. As an algorithm for selecting the main judgment reason for determining that there is an object in the monitoring area as an object monitoring system, a method of selecting the most judgment reason or a priority is given to the judgment reason, and the judgment reason of the highest priority is given. There is a method of selecting. As an example, by setting "intrusion" to the highest priority, for example, an object with a retroreflective material invaded, and there were three filters judged to be saturation and one filter judged to be object intrusion. In this case as well, the "intrusion" is notified as the main reason for determining that there is an object in the monitoring area, and the user can select a more realistic reason.
さらにコンピュータ装置２０は、監視領域内か否か（未侵入、侵入）、測距異常の種別（サチュレーション、露光不足、画素故障、精度異常等）、フィルタの判定結果、及びフィルタの判定理由のうち少なくとも１つの画素状況を対象空間の画像上に重ねて表示する手段を備えていてもよい。表示手段としては、液晶ディスプレイ等がある。図７は、対象空間の強度画像３４上に画素状況を重ねた画像を示している。このような画素状況を重ねた画像は、物体監視システムを設置した時の初期の画像状況、改善処置の効果、監視領域への物体侵入検知のテスト等の確認を効果的に行うことができ、さらには物体検知した際の原因究明にも役立つ。 Further, the computer device 20 includes whether or not it is within the monitoring area (non-intrusion, intrusion), the type of ranging abnormality (saturation, underexposure, pixel failure, accuracy abnormality, etc.), the filter determination result, and the filter determination reason. A means for displaying at least one pixel situation on the image in the target space may be provided. As a display means, there is a liquid crystal display or the like. FIG. 7 shows an image in which the pixel situation is superimposed on the intensity image 34 of the target space. An image in which such pixel conditions are superimposed can effectively confirm the initial image condition when the object monitoring system is installed, the effect of improvement measures, the test of detecting the intrusion of an object into the monitoring area, and the like. Furthermore, it is useful for investigating the cause when an object is detected.
本開示のフィルタは、測距値のバラツキを低減するのと等価な効果を有している。図８に示す正規分布的に分布する測距値のバラツキの幅は統計学的に偏差σで表せるが、測距装置としては、この偏差σが小さい方が良いことは言うまでもない。図９は平均がμで偏差σのバラツキを持つ測距値の正規分布及びその累積分布確率Ｆ（ｘ）を示している。監視領域の遠方面の距離がμとして、物体が監視領域の遠方面上に丁度ある場合、これを眺望する画素の測距値に対する判定閾値ｘにμを適用した場合には、μ以下と判定される判定確率が０．５であることを示している。同様に、判定閾値ｘにμ−σを適用した場合にはμ−σ以下と判定される判定確率は０．１６となり、判定閾値ｘにμ＋σを適用した場合にはμ＋σ以下と判定される判定確率は０．８４となる。即ち判定確率が０．１６から０．８４となる判定確率の幅は２σとなる。 The filter of the present disclosure has an effect equivalent to reducing the variation in the distance measurement value. The width of the variation of the distance measurement values distributed in the normal distribution shown in FIG. 8 can be statistically expressed by the deviation σ, but it goes without saying that it is better for the distance measurement device to have a small deviation σ. FIG. 9 shows a normal distribution of distance measurement values having an average of μ and a variation of deviation σ and a cumulative distribution probability F (x) thereof. When the distance of the far side of the monitoring area is μ and the object is just on the far side of the monitoring area, it is judged to be μ or less when μ is applied to the judgment threshold value x for the distance measurement value of the pixel viewing this. It shows that the judgment probability to be made is 0.5. Similarly, when μ-σ is applied to the judgment threshold x, the judgment probability of being judged to be μ-σ or less is 0.16, and when μ + σ is applied to the judgment threshold x, the judgment is judged to be μ + σ or less. The probability is 0.84. That is, the range of the judgment probability from 0.16 to 0.84 is 2σ.
本開示のフィルタによる測距バラツキの低減効果を考えるに当たって、一例としてＭ＝９個のフィルタとし、９個の対象画素は同じ距離にある物体を測距し、同じバラツキ分布特性：累積分布確率Ｆ（ｘ）を持ち、同じ判定閾値ｘで判定されるものとする。このときＮ＝１からＮ＝８の夫々の場合において、適用する判定閾値ｘとその時のフィルタ判定確率Ｐは、下記の二項分布の式で求められる。 In considering the effect of reducing the distance measurement variation by the filter of the present disclosure, as an example, M = 9 filters are used, 9 target pixels measure an object at the same distance, and the same variation distribution characteristic: cumulative distribution probability F. It is assumed that it has (x) and is determined by the same determination threshold value x. At this time, in each case of N = 1 to N = 8, the determination threshold value x to be applied and the filter determination probability P at that time are obtained by the following binomial distribution equation.
図１０は判定閾値ｘと本開示のフィルタの判定確率の関係を、夫々のＮに対して追加したものである。個々の画素の累積分布確率Ｆ（ｘ）のグラフに対し、Ｎ＝１からＮ＝７のフィルタ判定確率の立ち上がりは急峻になることが分かる。さらに、各グラフについて前述の判定確率０．１６、判定確率０．８４、さらに判定確率０．５となる判定確率ｘを纏めたものが下記の表である。表には、急峻さの指標として、判定確率０．１６と０．８４となる判定確率の差、及び、単画素と比較した偏差σの比率が加えられている。 FIG. 10 shows that the relationship between the determination threshold value x and the determination probability of the filter of the present disclosure is added to each N. It can be seen that the rise of the filter determination probability from N = 1 to N = 7 is steep with respect to the graph of the cumulative distribution probability F (x) of each pixel. Further, the following table summarizes the above-mentioned determination probabilities 0.16, determination probabilities 0.84, and determination probabilities x such that the determination probabilities are 0.5 for each graph. In the table, as an index of steepness, the difference between the judgment probabilities of 0.16 and 0.84 and the ratio of the deviation σ compared with the single pixel are added.
いずれのＮであっても、判定確率が０．１６から０．８４となる判定閾値の幅は１σ前後であり、本開示のフィルタが単画素の測距値のバラツキを半分程度に低減したのと等価的な効果を有することが分かる。 Regardless of which N, the width of the judgment threshold value at which the judgment probability is 0.16 to 0.84 is around 1σ, and the filter of the present disclosure reduces the variation of the distance measurement value of a single pixel by about half. It can be seen that it has an effect equivalent to.
前述のコンピュータ装置２０の構成要素は、ＣＰＵ等で実行されるプログラムとして構成してもよい。斯かるプログラムは、コンピュータ読取り可能な非一時的記録媒体、例えばＣＤ−ＲＯＭ等に記録して提供できる。 The components of the computer device 20 described above may be configured as a program executed by a CPU or the like. Such a program can be provided by recording on a computer-readable non-temporary recording medium such as a CD-ROM.
本明細書において種々の実施形態について説明したが、本発明は、前述の実施形態に限定されるものではなく、以下の特許請求の範囲に記載された範囲内において種々の変更を行えることを認識されたい。 Although various embodiments have been described herein, it is recognized that the present invention is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims described below. I want to be.
１ 物体監視システム
１０ 測距装置
１１ 入出力部
１２ 発光撮像制御部
１３ 照射部
１４ 受光部
１５ Ａ／Ｄ変換部
１６ 距離画像生成部
１７ 強度画像生成部
２０ コンピュータ装置
２１ 入出力部
２２ 設定メモリ
２３ フィルタ判定部
２４ 信号出力部
２５ 表示部
２６ 物体検知信号
３０ 物体
３１ 監視領域
３２ 距離画像
３２ａ−３２ｄ 監視領域内と判定した画素
３２ｅ 測距異常を示す画素
３３ フィルタ
３４ 強度画像
４０ 再帰反射材
４０ａ−４０ｆ 測距異常を示す画素
５０ａ−５０ｂ サチュレーションを示す画素
５０ｃ 露光不足を示す画素
1 Object monitoring system 10 Distance measuring device 11 Input / output unit 12 Emission imaging control unit 13 Irradiation unit 14 Light receiving unit 15 A / D conversion unit 16 Distance image generation unit 17 Intensity image generation unit 20 Computer device 21 Input / output unit 22 Setting memory 23 Filter judgment unit 24 Signal output unit 25 Display unit 26 Object detection signal 30 Object 31 Monitoring area 32 Distance image 32a-32d Pixels determined to be within the monitoring area 32e Pixels indicating distance measurement abnormality 33 Filter 34 Strength image 40 Retroreflective material 40a- 40f Pixel showing distance measurement abnormality 50a-50b Pixel showing saturation 50c Pixel showing underexposure
Claims (10)
前記コンピュータ装置は、前記距離画像において、特定の配置関係にある第１個数の隣接画素群の中で、前記監視領域内と判定した画素数が、１以上で前記第１個数未満である第２個数以上と判定された場合に、前記監視領域内に物体有りと判定するフィルタを備えることを特徴とする物体監視システム。 An object monitoring system including a distance measuring device that generates a distance image of a target space and a computer device that determines the presence or absence of an object in a monitoring area defined in the target space based on the distance image.
In the distance image, the computer device has a second number of pixels determined to be within the monitoring region among the first number of adjacent pixel groups having a specific arrangement relationship, which is 1 or more and less than the first number. An object monitoring system including a filter that determines that there is an object in the monitoring area when it is determined that the number of objects is equal to or greater than the number of objects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2019039071A JP7306840B2 (en) | 2019-03-04 | 2019-03-04 | Object monitoring system with rangefinder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2019039071A JP7306840B2 (en) | 2019-03-04 | 2019-03-04 | Object monitoring system with rangefinder |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2020143941A true JP2020143941A (en) | 2020-09-10 |
| JP7306840B2 JP7306840B2 (en) | 2023-07-11 |
Family
ID=72353543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2019039071A Active JP7306840B2 (en) | 2019-03-04 | 2019-03-04 | Object monitoring system with rangefinder |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP7306840B2 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5040116A (en) * | 1988-09-06 | 1991-08-13 | Transitions Research Corporation | Visual navigation and obstacle avoidance structured light system |
| JP2006099749A (en) * | 2004-08-31 | 2006-04-13 | Matsushita Electric Works Ltd | Gesture switch |
| JP2014006727A (en) * | 2012-06-25 | 2014-01-16 | Omron Corp | Motion sensor and object action detection method |
| JP2014035304A (en) * | 2012-08-09 | 2014-02-24 | Sanyo Electric Co Ltd | Information acquisition device and object detection apparatus |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6804949B2 (en) | 2016-11-28 | 2020-12-23 | パイオニア株式会社 | Controls, measuring devices, and computer programs |
-
2019
- 2019-03-04 JP JP2019039071A patent/JP7306840B2/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5040116A (en) * | 1988-09-06 | 1991-08-13 | Transitions Research Corporation | Visual navigation and obstacle avoidance structured light system |
| JP2006099749A (en) * | 2004-08-31 | 2006-04-13 | Matsushita Electric Works Ltd | Gesture switch |
| JP2014006727A (en) * | 2012-06-25 | 2014-01-16 | Omron Corp | Motion sensor and object action detection method |
| JP2014035304A (en) * | 2012-08-09 | 2014-02-24 | Sanyo Electric Co Ltd | Information acquisition device and object detection apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| JP7306840B2 (en) | 2023-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109564382B (en) | Imaging device and imaging method | |
| JP4727388B2 (en) | Intrusion detection device | |
| US8735792B2 (en) | Optoelectronic sensor | |
| US10455149B2 (en) | Image processing apparatus, image processing apparatus control method, image pickup apparatus, and image pickup apparatus control method | |
| TWI393980B (en) | The method of calculating the depth of field and its method and the method of calculating the blurred state of the image | |
| EP2445192A2 (en) | Scene based non-uniformity correction for infrared detector arrays | |
| JP4815190B2 (en) | Intrusion detection device | |
| CN110596727A (en) | Distance measuring device for outputting precision information | |
| JP2010164463A (en) | Laser three-dimensional image measuring device | |
| CN113570582B (en) | Camera cover plate cleanliness detection method and detection device | |
| JP2010124028A (en) | Monitoring apparatus | |
| US10755389B2 (en) | Image processing apparatus, image processing method, and medium | |
| JP2020143941A (en) | Object monitoring system having distance-measuring device | |
| CN112014858A (en) | Distance image generating device for correcting distance measurement abnormality | |
| US11039096B2 (en) | Image processing device, image processing method and storage medium | |
| JP2018159685A (en) | Distance measuring device | |
| CN111343418B (en) | Object monitoring system with distance measuring device | |
| JP5160495B2 (en) | Welding workpiece shape measuring device and program thereof | |
| JP2015143657A (en) | Stereo camera system for vehicle | |
| JP6985872B2 (en) | Vehicle peripheral monitoring device and peripheral monitoring method | |
| JP2008241434A (en) | Distance image generation device | |
| JP6934981B1 (en) | Image processing device | |
| JP2020013291A (en) | Object detecting system and object detecting program | |
| WO2022168903A1 (en) | Abnormality detection device, abnormality detection method, and program | |
| US20230345142A1 (en) | Three-dimensional-measurement device and three-dimensional-measurement method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20220114 |
|
| A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20221130 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20230110 |
|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20230306 |
|
| TRDD | Decision of grant or rejection written | ||
| A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20230530 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20230629 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 7306840 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |