JPS62159084A - Method for detecting man - Google Patents
Method for detecting manInfo
- Publication number
- JPS62159084A JPS62159084A JP61002426A JP242686A JPS62159084A JP S62159084 A JPS62159084 A JP S62159084A JP 61002426 A JP61002426 A JP 61002426A JP 242686 A JP242686 A JP 242686A JP S62159084 A JPS62159084 A JP S62159084A
- Authority
- JP
- Japan
- Prior art keywords
- luminance
- image information
- detected
- person
- pixel
- 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
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
Description
【発明の詳細な説明】
この発明は検出領裟に人が存在するかどうかを検出でき
るようにした人を検出する方法に関するものである。DETAILED DESCRIPTION OF THE INVENTION The present invention relates to a method for detecting a person that is capable of detecting whether or not a person is present in a detection area.
例えば、特定領域に進入した人を検出する手段として、
１１１Ｊ６図に示すような装置が用いられている。図に
おいて、＋１＋は床面、（２ａ）は床面（１１から所定
の高さのところに設電されたＸＴｖカメラで（以下カメ
ラと略称する）、所定の面積（ｌａ）の画 ′像を撮像
できる撮像角度（２ａｌ）を備えている。（４ａ）はカ
メラ（２ａ）で撮像した画像情報をディジタル情報に変
換して記憶する’！１の画像記憶部、（５ａ）は第１の
画像より所定の時間後にカメラ（２ｍ）で撮像した画像
情報をディジタル情報に変換して記憶する第２の画像記
憶部、（６ａ）は第１の画像情報と′第２の画イ象情報
とを比較して処理する比較処理部で、第１の画像情報と
第２の画像情報との差を画像情報のすべての画素を走査
して比較し、第１の画像情報に対する第２の画像情報の
変化を検出すると、変化位置を座標で指示する信号を出
力する。（）ａ）は比較処理部（６ａ）の座標信号によ
る変化部分が、限定領域（ユａ）に進入した人であるか
どうがを判断する判定処理部で、゛検出した座標の輝度
を所定の輝度を閾値とした設定値と比較し、人に対応し
た値であると所定の信号を出力する。上記（４ａ）〜（
７ａ）で処理装置（８ａ）が形成される。１９１１−を
判定処理部（７ａ）の信号を受けて動作する出力装置で
、例えば警報器等である。叫は出力装置（９）の動作を
モニタするモニタ装置で、例えばテレビ受像機である。For example, as a means of detecting a person entering a specific area,
A device as shown in Figure 111J6 is used. In the figure, +1+ is the floor surface, and (2a) is the XTv camera (hereinafter referred to as camera) installed at a predetermined height from the floor surface (11), which captures an image of a predetermined area (la). It is equipped with an imaging angle (2al) at which an image can be taken. (4a) is an image storage unit of '!1 that converts the image information taken by the camera (2a) into digital information and stores it, and (5a) is an image storage unit for storing the first image. A second image storage unit (6a) converts the image information captured by the camera (2m) into digital information and stores it after a predetermined time; A comparison processing unit that performs comparison processing scans and compares the difference between the first image information and the second image information by scanning all pixels of the image information, and compares the difference between the first image information and the second image information. When a change is detected, it outputs a signal indicating the changed position in coordinates. ()a) determines whether the changed part according to the coordinate signal of the comparison processing unit (6a) is a person who has entered the limited area (Ya). The determination processing unit compares the brightness of the detected coordinates with a set value using a predetermined brightness as a threshold, and outputs a predetermined signal if the value corresponds to a person. Above (4a) to (
7a) forms a processing device (8a). 1911- is an output device that operates upon receiving a signal from the determination processing unit (7a), and is, for example, an alarm device. The monitor is a monitor device that monitors the operation of the output device (9), such as a television receiver.
このような第６図のものは、カメラ（２ａ）で限定ｆｌ
ｌＨ（ｌａ）に全く人が存在しない情景を撮像したｇｒ
Ｊｌの画像情報ｆ第１の画像記憶部（４ａ）に記憶し、
所定の時間間隔で限定＠域（１ａ）を撮像したｖ；２の
画像情報を第２０画像記憶部（５ａ）に記憶し、記憶さ
れた第１０画像情報と第２の画像情報とを座標構成され
た各画素について走査して変化を検出し、検出した変化
の輝度を照合することにより、隈定頒［（ｌａ）に進入
した人を検出する。In this case, the camera (2a) has a limited fl
gr that captured a scene with no people present at lH(la)
Jl image information f is stored in the first image storage unit (4a),
The image information of v;2 obtained by imaging the limited @ area (1a) at a predetermined time interval is stored in the 20th image storage unit (5a), and the stored 10th image information and the second image information are configured in coordinates. By scanning each pixel that has been detected and detecting a change, and comparing the brightness of the detected change, a person who has entered the area is detected.
つぎに動作について＊’／図のフローチャートを用いて
説明する。ステップ６υで！ｌの画像情報を第１の画像
記憶部（４ａ）に記憶する。この％１の画像情報は限定
幅域（ｌａ）に全く人が存在しない情景のものであるの
で、複数個の画素からなる画像情報の座標には１例えば
画素と座標の関係を示す！９図に曲線３υで示す輝度分
布となる。つき゛にステップ□□□で第２の画像情報を
’！２の画像記憶部（５ａ）に記憶し、ステップ關で第
１の画像情報と第２の画像情報とを全画素に亘って比較
する。この比較は横軸＝ｉ （１） 、縦軸？ （Ｊ）
としたとき、例えば第８図のような順序で行われ、％１
の画像情報に対する第２の画像情報の輝度の差を検出す
る。ステップ關で検出された輝度は、ステップ霞で所定
の閾値以上の差があるか否かの判定処理がステップＩ５
１で二値化処理され、ステップ槌で閾値を超えたもので
あると人と判断して検出信号を出力する。Next, the operation will be explained using the flowchart shown in *'/. At step 6υ! 1 image information is stored in the first image storage section (4a). Since this image information of %1 is of a scene in which there are no people at all in the limited width area (la), the coordinates of the image information consisting of a plurality of pixels are 1, for example, indicating the relationship between pixels and coordinates! The brightness distribution is shown by curve 3υ in Figure 9. Next, step □□□ to get the second image information! The first image information and the second image information are compared over all pixels in each step. This comparison is horizontal axis = i (1), vertical axis? (J)
For example, it is performed in the order shown in Figure 8, and %1
A difference in brightness between the second image information and the second image information is detected. In step I5, a determination process is performed to determine whether or not the brightness detected at the step has a difference of more than a predetermined threshold value at the step haze.
1, it is binarized, and a step mallet determines that it exceeds the threshold and outputs a detection signal.
ここで、′第２の画像情報を得るときに限定幅域（１ａ
）にゴミや人等か存在すると、第２の画像記憶部（５１
Ｌ）には第５図に示すように、ゴミα９に対応した輝度
をもつ画素と、人＠に対応した輝度金もつ画素が生じる
。したがって、ステップ（財）で行われる第１の画像情
報と第２の画像情報との比較では、第９図に曲線（イ）
で示す輝度分布となる。これによって、曲線（財）と所
定の幅で輝度が小さい値の曲線（２１ｍ ）との輝度の
差を閾値として閾値より小さい値の輝度を有するものを
検出する。Here, when obtaining the second image information, the limited width area (1a
), the second image storage unit (51
As shown in FIG. 5, in L), a pixel having a brightness corresponding to dust α9 and a pixel having a brightness gold corresponding to a person @ are generated. Therefore, in the comparison between the first image information and the second image information performed in step (goods), the curve (a) shown in FIG.
The brightness distribution is shown as . As a result, the difference in brightness between the curve (goods) and a curve (21m) having a predetermined width and a small brightness value is used as a threshold to detect a curve having a brightness value smaller than the threshold.
従来の人を検出する方法は以上のように行われるので、
閾値より小さい輝度すなわち画素の濃度が所定の値を超
えると人として検出するので、人以外でも所定の濃度で
あると人として検出する検出誤りが発生するという問題
点があった。The conventional method of detecting people is performed as described above.
If the luminance is lower than the threshold value, that is, the density of a pixel exceeds a predetermined value, it is detected as a person, so there is a problem in that a detection error occurs in which a person other than a person is detected as a person if the pixel has a predetermined density.
この発明は、上記のような問題点を解消するためになさ
れたもので１人と人以外のものとを区別して検出誤りを
防止できるようにした人の検出方法？得ることを目的と
する。This invention was made in order to solve the above-mentioned problems, and is a method for detecting a person that can distinguish between one person and something other than a person and prevent detection errors. The purpose is to obtain.
この発明に係る大全検出する方法は、所定の輝度の範囲
の閾値を超えた輝度全盲する画素の濃度から、人の頭部
と人の衣服とを検出し、頭部と衣服とのそれぞれの画素
の間隔が所定の距離であると人として検出するようにし
たものである。The total detection method according to the present invention detects a person's head and clothing from the density of pixels whose brightness exceeds a threshold in a predetermined brightness range, and detects each pixel of the head and clothing. If the distance between the two is a predetermined distance, the person is detected as a person.
この発明における人を検出する方法は、人の頭部の画素
濃度と衣服の画素濃度及び頭部の画素と衣服の画素との
距離から人を検出するので、人と床上に置かれた荷物や
ゴミ等とを区別する。The method of detecting a person in this invention detects a person based on the pixel density of the person's head, the pixel density of the clothes, and the distance between the pixels of the head and the pixels of the clothes. Distinguish from garbage, etc.
以下、この発明の実施例を図について説明する。 Embodiments of the present invention will be described below with reference to the drawings.
＠１．図において、（１１（ｌａ ） ｆ９１ （１０
１は従来のものと同様である。（２）は床（１）から所
定の高さのところに設置された赤外線カメラ（以下カメ
ラと略称する）で、所定の撮像範囲（２ａ）を有し撮像
した画像を画像情報として送出できるものである。（３
１はカメラ（２；の撮像範囲を照射できるように配電さ
れた複数個の赤外線照射器で、それぞれ所定の照射範囲
（３ａ）を備えており、限定饋［（ｌａ）では床（１１
面から所定の高さのものにすべて照射できるようにされ
ている。（４１はカメラ（２）で撮像した画像情報をデ
ィジタル化した第１の画像信号として記憶する第１の画
像記憶部、（５１は′Ｉ！ｒＪ１の画像を撮像した後、
所定の時間間隔で搬像された％２の画像情報をディジタ
ル化して記憶する第２の画像記憶部、（６）は’！ｌの
画像情報と第２の画像情報とを比較する比較処理部でｑ
ＩＪｌの画像情報と第２の画像情報との輝度全画像情報
のすべての画素を走査して比較し、第１の画像情報に対
する第２の画像情報の変化を検出すると、変化位置を座
標で指示するとともに検出した座標の輝度を所定の閾値
と比較して比較した値に応じた信号を出力する。（７）
は比較値を判定する判定処理部で比較処理部（６１の比
較信号による変化部の輝度と変化部相互間の距離から人
と判定し、人を判定した場合には検出信号を出力する。@1. In the figure, (11(la) f91 (10
1 is the same as the conventional one. (2) is an infrared camera (hereinafter referred to as a camera) installed at a predetermined height from the floor (1), which has a predetermined imaging range (2a) and can send out the captured image as image information. It is. (3
Reference numeral 1 designates a plurality of infrared irradiators distributed with power so as to illuminate the imaging range of the camera (2), each having a predetermined irradiation range (3a).
It is designed to irradiate all objects at a predetermined height from the surface. (41 is a first image storage unit that stores the image information captured by the camera (2) as a digitized first image signal, (51 is a first image storage unit that stores the image information captured by the camera (2) as a first image signal; (51 indicates that after capturing the image of 'I!rJ1,
The second image storage section (6) which digitizes and stores %2 image information transferred at predetermined time intervals is '! q in the comparison processing unit that compares the image information of l and the second image information.
Scans and compares all pixels of the brightness total image information of the IJl image information and the second image information, and when a change in the second image information with respect to the first image information is detected, the change position is indicated by coordinates. At the same time, the brightness of the detected coordinates is compared with a predetermined threshold value, and a signal corresponding to the compared value is output. (7)
is a determination processing unit that determines a comparison value, and the comparison processing unit (61) determines that it is a person based on the brightness of the changing portions and the distance between the changing portions based on the comparison signal, and outputs a detection signal when it determines that it is a person.
つぎに動作について！２図のフローチャートを甲いて説
明する。限定領域Ｃ１ａ）に人の進入検出に、照射器（
３１から赤外線を照射し、カメラ（２；の始動によって
開始される。ステップ５Ｄで限定領ｖｃ（１ａ）に人が
花屋しない情景をカメラ（２１で撮像し、第１の画像情
報を第１の画像記憶部（４１に記憶する。Next, let's talk about the operation! This will be explained with reference to the flowchart in Figure 2. An irradiator (
The process starts by emitting infrared rays from 31 and starting the camera 2. In step 5D, the camera 21 captures an image of a scene where there are no people in the limited area VC (1a), and the first image information is transferred to the first The image is stored in the image storage unit (41).
つぎに、ステップ（至）で第２の画像情報を第２の画像
記憶部（６１に記憶し、ステップ−で第１の画像情報と
第２の画像情報との輝度差を第３図に示すように画素ご
とに比較処理部（６）で検出し、検出した輝度差を有す
る画素の輝度が所定の輝度範囲を閾値としたとき、閾値
より輝度が大きいか小さいかの照合をするとともに対応
したそれぞれの画素の座標信号を出力する。Next, in step (to), the second image information is stored in the second image storage unit (61), and in step -, the luminance difference between the first image information and the second image information is shown in FIG. The comparison processing unit (6) detects each pixel as follows, and when the luminance of the pixel having the detected luminance difference is set to a predetermined luminance range as a threshold, it is checked whether the luminance is greater or less than the threshold, and the corresponding processing is performed. Outputs the coordinate signal of each pixel.
ここで、第１の画像情報は限定６ｉＪｔ（ｌａ）に人が
存在しない情景であるので、はぼ一定の輝度分布の画素
となり１例えば第４図にＪ−０，Ｉ＝Ｏ〜ＥＮＤ座標と
輝度との関係を示す曲線？ηのような輝度を示すとき、
この曲線（財）より所定の値（ＴＨｌ）だけ輝度か小さ
く曲線■Ｄとほぼ平行な曲線（２１＆）と、曲線（２）
より所定の値（ＴＨ２）だけ輝度が大きく曲線ｃ２Ｄと
ほぼ平行な曲線（２１ｂ ）とで形成され輝度の範囲’
！’Ｍｌ ＋ ＴＨ２−ＴＨを閾値として設定されてい
る。Here, since the first image information is a scene in which there are no people in the limit 6iJt(la), it becomes pixels with an almost constant brightness distribution.For example, in FIG. A curve showing the relationship with brightness? When exhibiting a luminance like η,
A curve (21 &) that is almost parallel to curve ■D and a curve (2) whose luminance is smaller by a predetermined value (THl) than this curve (goods).
The brightness range is greater by a predetermined value (TH2) and is formed by the curve c2D and the almost parallel curve (21b).
! 'Ml + TH2-TH is set as the threshold value.
第２の画像情報を撮像するとき、限定＠域（１ａ）にゴ
ミと人とが存在すると、第２の画像記憶部（６）には第
５図に示すように、ゴミ０に対応した輝度をもつ画素と
人（２）に対応した輝度をもつ画素が生じる。したがっ
て、ステップ（財）とステップ（至）で行われる各画素
の輝度と閾値との比較で、ゴミと人とを検出したときの
輝度分布ｆ′ｉ第４図に曲線（イ）で示すように現われ
る。第４図において、斜線で示した部分は閾値を超えた
ものを示し、（ａ）と山）は閾値より小さい輝度で（ａ
）と（ｄ）は閾値より大きい輝度を示している。このこ
とから、（ｂ）は人の頭部に対応した輝度で（ｃ）と（
ｄ）とは人の肩に対応した衣服の輝度で、（ｂ）〜（ｄ
）の輝度は座標で連結されている。When capturing the second image information, if there are dust and people in the limited @ area (1a), the second image storage unit (6) will have a luminance value corresponding to 0 dust as shown in FIG. A pixel with a luminance corresponding to the person (2) and a pixel with a luminance corresponding to the person (2) are generated. Therefore, by comparing the brightness of each pixel with the threshold value in step (goods) and step (end), the brightness distribution f′i when garbage and people are detected is as shown by the curve (a) in Figure 4. appears in In Fig. 4, the shaded area indicates the area exceeding the threshold, and (a) and the peak) indicate the luminance lower than the threshold.
) and (d) indicate luminance greater than the threshold. From this, (b) is the brightness corresponding to the human head, and (c) and (
d) is the brightness of clothing corresponding to a person's shoulders, and (b) to (d)
) are connected by coordinates.
このような輝度の変化をｇｒＩ３図及びステップ（至）
（至）で全画素について検出し、ステップ（至）で輝度
の小さい画素と輝度の大きい画素との座標上の距離から
人を検出し、検出信号を出力する。This kind of brightness change is shown in grI3 diagram and step (to)
In step (to), all pixels are detected, and in step (to), a person is detected from the coordinate distance between a pixel with low brightness and a pixel with high brightness, and a detection signal is output.
上記実施例においては、限定ｍ域に赤外線を照射し赤外
線カメラで撮像する場合について説明したが、近赤外線
と近赤外カメラを用いると、検出精変をさらに向上する
ことを期待できる。In the above embodiment, a case has been described in which infrared rays are irradiated to a limited m range and images are taken with an infrared camera, but it can be expected that the detection precision will be further improved by using near infrared rays and a near infrared camera.
以上のように、この発明によれば、限定ｍ域を撮像した
ｖ；１の画像情報と第２の画像情報とｆ画素嵐位で比較
して輝度の変化を検出し、輝度が変化した画像を所定範
囲の輝度を閾値と比較して人の頭部に対応した濃度の第
１の画素と人の衣服に対応したｆＪＩＪ２の画素とを検
出し、第１の画素と第２０画素とが連結されていると人
として検出するので、検出誤りを防止することができる
。As described above, according to the present invention, a change in brightness is detected by comparing the image information of v; 1 and the second image information captured in the limited m region at the f pixel height, and the image in which the brightness has changed is detected. A first pixel with a density corresponding to a person's head and a pixel of fJIJ2 corresponding to a person's clothing are detected by comparing the luminance of a predetermined range with a threshold value, and the first pixel and the 20th pixel are connected. Since it is detected as a person if it is detected, detection errors can be prevented.
第１図〜第４図はそれぞれこの発明の一実施例を示すも
ので、第１図は構成図、％２図は動作を示すフローチャ
ート、ｆＩＩ２３図は走査順序を示す座標図、第４図は
輝度分布図、第５図は画像情報を示す図、第６ｖｌＪ−
第９図はそれぞれ従来のものを示すもので、第６図は構
成図、第７図は動作を示すフローチャート、第８図は走
査順序を示す座標図、第９図は輝度分布図である。
図において、（２１は赤外線カメラ、（４）は第１の画
像記憶部、（６）ｄ％２の画像記憶部、（６）は比較処
理部、（７）は判定処理部である。
なお、各図中、同一符号は同−又は相当部分を示す。Figures 1 to 4 each show an embodiment of the present invention. Figure 1 is a configuration diagram, Figure %2 is a flowchart showing the operation, Figure fII23 is a coordinate diagram showing the scanning order, and Figure 4 is a diagram showing the scanning order. Brightness distribution diagram, Figure 5 is a diagram showing image information, Figure 6vlJ-
FIG. 9 shows the conventional apparatus, and FIG. 6 is a block diagram, FIG. 7 is a flowchart showing the operation, FIG. 8 is a coordinate diagram showing the scanning order, and FIG. 9 is a brightness distribution diagram. In the figure, (21 is an infrared camera, (4) is a first image storage unit, (6) is a d%2 image storage unit, (6) is a comparison processing unit, and (7) is a determination processing unit. , in each figure, the same reference numerals indicate the same or corresponding parts.
Claims (1)
１の画像情報と人が存在する上記限定領域を上記検出器
で撮像した第２の画像情報とを画像情報の画素ごとに比
較してそれぞれの画素の輝度の変化を検出し、変化した
上記画素の輝度を所定の範囲の輝度を有する閾値と比較
して上記閾値より小さい輝度を有する第１の画素と上記
閾値より大きい輝度を有する第２の画素とにそれぞれ区
分し、上記第１の画素と上記第２の画素とが上記画像情
報の同一の座標上にあると人として検出することを特徴
とする人を検出する方法。Compare the first image information of the detector which has imaged a scene where no person is present in the limited area and the second image information which has imaged the limited area where a person is present by the detector, pixel by pixel of the image information. A change in the brightness of each pixel is detected, and the changed brightness of the pixel is compared with a threshold value having a brightness in a predetermined range to determine whether a first pixel has a brightness smaller than the threshold value and a second pixel has a brightness larger than the threshold value. A method for detecting a person, characterized in that the first pixel and the second pixel are located on the same coordinates of the image information, and the person is detected as a person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP61002426A JPH0776791B2 (en) | 1986-01-07 | 1986-01-07 | How to detect a person |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP61002426A JPH0776791B2 (en) | 1986-01-07 | 1986-01-07 | How to detect a person |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPS62159084A true JPS62159084A (en) | 1987-07-15 |
| JPH0776791B2 JPH0776791B2 (en) | 1995-08-16 |
Family
ID=11528927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP61002426A Expired - Lifetime JPH0776791B2 (en) | 1986-01-07 | 1986-01-07 | How to detect a person |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH0776791B2 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0552933A (en) * | 1991-08-29 | 1993-03-02 | Japan Radio Co Ltd | System and device for measuring position of traveling object |
| US20140168033A1 (en) * | 2012-08-24 | 2014-06-19 | Tencent Technology (Shenzhen) Company Limited | Method, device, and system for exchanging information |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS57139649A (en) * | 1981-02-23 | 1982-08-28 | Mitsubishi Electric Corp | Device for detecting waiting passenger in transport facilities |
| JPS5983079A (en) * | 1982-11-02 | 1984-05-14 | Nec Corp | Object detector |
| JPS60100076A (en) * | 1983-11-04 | 1985-06-03 | Toppan Printing Co Ltd | Inspecting apparatus for color mark omission |
| JPS60231193A (en) * | 1984-05-01 | 1985-11-16 | Honda Motor Co Ltd | Vehicular view field monitoring system |
-
1986
- 1986-01-07 JP JP61002426A patent/JPH0776791B2/en not_active Expired - Lifetime
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS57139649A (en) * | 1981-02-23 | 1982-08-28 | Mitsubishi Electric Corp | Device for detecting waiting passenger in transport facilities |
| JPS5983079A (en) * | 1982-11-02 | 1984-05-14 | Nec Corp | Object detector |
| JPS60100076A (en) * | 1983-11-04 | 1985-06-03 | Toppan Printing Co Ltd | Inspecting apparatus for color mark omission |
| JPS60231193A (en) * | 1984-05-01 | 1985-11-16 | Honda Motor Co Ltd | Vehicular view field monitoring system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0552933A (en) * | 1991-08-29 | 1993-03-02 | Japan Radio Co Ltd | System and device for measuring position of traveling object |
| US20140168033A1 (en) * | 2012-08-24 | 2014-06-19 | Tencent Technology (Shenzhen) Company Limited | Method, device, and system for exchanging information |
Also Published As
| Publication number | Publication date |
|---|---|
| JPH0776791B2 (en) | 1995-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2633694B2 (en) | Person detection device | |
| US11869273B2 (en) | Object recognition with removal of event as noise when the event is detected for a group of pixels exceeding a threshold | |
| JP4004634B2 (en) | Face image eye position detection apparatus and method | |
| JPH0620243B2 (en) | Image processing system | |
| JP2009088801A (en) | Motionlessness deciding method and device for photograph object | |
| JPS62159084A (en) | Method for detecting man | |
| JP3081396B2 (en) | Image processing device | |
| JP4208269B2 (en) | Foreign matter contamination inspection method and system | |
| JP2554102B2 (en) | Slit optical detector | |
| JPH057363A (en) | Picture monitoring device | |
| JP6866182B2 (en) | Bed positioning device | |
| JP6847708B2 (en) | Bed positioning device | |
| JPH0514898A (en) | Image monitor device | |
| JP2503613B2 (en) | Abnormality monitoring device | |
| JP4230287B2 (en) | Motion detection device | |
| JPH0783474B2 (en) | Automatic tracking imaging device | |
| KR102349424B1 (en) | Personal identification apparatus using face recongintion | |
| JP3086309B2 (en) | Object detection system | |
| JPH0567984B2 (en) | ||
| JPH0520564A (en) | Fire detector using image processing | |
| JPH06223187A (en) | Image type human body detecting device | |
| JP2003323621A (en) | Image processor and protrusion detecting method for the image processor and its program | |
| JPH0729015A (en) | Picture recognition device | |
| JP3270508B2 (en) | Infrared imaging device | |
| JP2833021B2 (en) | Vehicle detection device |