JPH09282452A - Monitor - Google Patents
MonitorInfo
- Publication number
- JPH09282452A JPH09282452A JP8114411A JP11441196A JPH09282452A JP H09282452 A JPH09282452 A JP H09282452A JP 8114411 A JP8114411 A JP 8114411A JP 11441196 A JP11441196 A JP 11441196A JP H09282452 A JPH09282452 A JP H09282452A
- Authority
- JP
- Japan
- Prior art keywords
- value
- image
- day
- luminance
- night
- 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
- Image Analysis (AREA)
Abstract
Description
【０００１】[0001]
【発明の属する技術分野】本発明は、撮像装置によって
撮影した画像から対象物を認識して監視する画像処理技
術を用いた監視装置に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a monitoring device using an image processing technique for recognizing and monitoring an object from an image taken by an imaging device.
【０００２】[0002]
【従来の技術】屋外等で終日稼働が要求される画像処理
技術を用いた監視装置では、監視カメラ等の撮像装置で
撮影した画像を背景差分等の画像処置技術を用いて対象
物の特徴を抽出し、それに基づいて対象物を認識して監
視するようにしている。2. Description of the Related Art In a surveillance device using an image processing technique which is required to be operated all day outdoors, an image taken by an image pickup device such as a surveillance camera is used to detect the characteristics of an object by using image processing techniques such as background subtraction. It extracts and recognizes and monitors the object based on it.
【０００３】この場合、画像の輝度平均値は昼間と夜間
とでは大きく異なるため、撮影した画像から昼夜の判定
を行い、その判定結果に基づいて昼と夜とで異なる画像
処理技術を用いて対象物の監視を行っている。昼夜の判
定方法としては、画像全体の輝度平均値を求め、この輝
度平均値の大きさから判断している。In this case, since the average brightness value of the image is significantly different between daytime and nighttime, the imaged image is used to determine whether it is daytime or nighttime. Based on the determination result, different image processing techniques are used for daytime and nighttime. I am monitoring things. As a method for determining day and night, the average brightness value of the entire image is obtained, and the average brightness value is used for the determination.
【０００４】[0004]
【発明が解決しようとする課題】ところが、従来の画像
全体の輝度平均値による昼夜の判定方法では、周囲の環
境などによって対象物が影響を受けやすい場所や地域で
は、判定精度が低下するという不都合が生じる。However, in the conventional day / night determination method based on the average luminance value of the entire image, the determination accuracy is lowered in a place or area where the object is easily affected by the surrounding environment. Occurs.
【０００５】また、昼と早朝・薄暮とで異なる２値化閾
値（固定値）を設定して画像を２値化処理し、対象物を
認識する場合、早朝・薄暮時のような輝度平均値が急激
に変化する時間帯では、２値化閾値が低すぎるとノイズ
を抽出したり、逆に高すぎると対象物を認識できないと
いった不都合が生じる。When the object is recognized by binarizing the image by setting different binarization thresholds (fixed values) for daytime and early morning / dusk, the average brightness value for early morning / dusk is set. In a time zone in which a sharp change occurs, if the binarization threshold is too low, noise is extracted, and conversely, if it is too high, an object cannot be recognized.
【０００６】本発明は、このような従来の課題を解決す
るためになされたもので、画像から昼夜を判定する際の
判定精度を向上させ、かつ早朝・薄暮時のような輝度平
均値が急変する時間帯でも対象物を精度よく認識して監
視することができる画像処理技術を用いた監視装置を提
供することを目的とする。The present invention has been made in order to solve such a conventional problem, improves the determination accuracy when determining the day and night from an image, and changes the average luminance value in the early morning and dusk suddenly. It is an object of the present invention to provide a monitoring device using an image processing technique capable of accurately recognizing and monitoring an object even in a time zone in which it is operated.
【０００７】[0007]
【課題を解決するための手段】本発明による監視装置の
第１の発明は、撮像装置で撮影した画像を入力する画像
入力手段と、この画像内の特定の指定領域の輝度平均値
を求める輝度検出手段と、指定領域の輝度平均値から昼
夜の判定を行う昼夜判定手段と、昼夜判定手段での判定
結果に基づいて昼間時と夜間時とで異なる画像処理技術
を用いて画像から対象物を認識する認識手段とを備え
る。According to a first aspect of the present invention, there is provided an image input means for inputting an image photographed by an image pickup device, and a luminance for obtaining an average luminance value of a specific designated area in the image. The detection means, the day and night determination means for determining the day and night from the brightness average value of the designated area, and the image processing technique that is different between daytime and nighttime based on the determination result by the daytime determination means And a recognition means for recognizing.
【０００８】第１の発明によれば、画像の全体領域では
なく特定の指定領域の輝度平均値から昼夜の判定を行
い、この判定結果に基づいて昼夜で異なる画像処理技術
を用いて対象物を認識する。従って、指定領域を適切に
設定すれば指定領域以外は昼夜の判定の対象とならない
ため、対象物に対する周囲の環境の影響を低減させるこ
とができ、それによって昼夜の判定精度が向上するの
で、対象物の認識精度および監視精度の向上を図ること
ができる。According to the first aspect of the invention, day and night are determined based on the luminance average value of a specific designated area rather than the entire area of the image, and based on the result of the determination, the object is detected using different image processing techniques day and night. recognize. Therefore, if the designated area is set appropriately, the target other than the designated area will not be the target of day and night judgment, so it is possible to reduce the influence of the surrounding environment on the object, which improves the accuracy of day and night judgment. It is possible to improve the recognition accuracy and the monitoring accuracy of the object.
【０００９】本発明による監視装置の第２の発明は、撮
像装置で撮影した画像を入力する画像入力手段と、画像
内の特定の指定領域の輝度平均値および輝度分散値を求
める輝度検出手段と、指定領域の輝度平均値および輝度
分散値の２次元的な分布位置から昼夜の判定を行う昼夜
判定手段と、昼夜判定手段での判定結果に基づいて昼間
時と夜間時とで異なる画像処理技術を用いて画像から対
象物を認識する認識手段とを備える。A second invention of the monitoring device according to the present invention is image input means for inputting an image photographed by an image pickup device, and luminance detection means for obtaining a luminance average value and a luminance dispersion value of a specific designated area in the image. , A day / night judging means for judging day / night from a two-dimensional distribution position of the average brightness value and the brightness dispersion value of a designated area, and an image processing technique which differs between daytime and nighttime based on the judgment result by the day / night judging means. And a recognition means for recognizing the target object from the image.
【００１０】第２の発明によれば、指定領域によって昼
夜の判定を行い、しかも輝度平均値および輝度分散値の
２つの情報から昼夜の判定を行うので、さらなる判定精
度の向上を図ることができる。According to the second aspect of the invention, the day and night are determined by the designated area, and the day and night are determined from the two pieces of information of the luminance average value and the luminance dispersion value, so that the determination accuracy can be further improved. .
【００１１】本発明による監視装置の第３の発明は、第
１または第２の発明における昼夜判定手段が、昼間から
夜間への変化を検出する第１の判定基準と、夜間から昼
間への変化を検出する第２の判定基準とを備えるように
構成されている。According to a third aspect of the monitoring apparatus of the present invention, the day / night determining means in the first or second aspect of the invention has a first criterion for detecting a change from daytime to nighttime and a change from nighttime to daytime. And a second criterion for detecting
【００１２】第３の発明によれば、早朝時（明け方）と
薄暮時（夕暮れ）とで異なる判断基準を用いることによ
って昼夜の判定精度の向上を図ることができる。According to the third aspect of the invention, it is possible to improve the day / night determination accuracy by using different determination criteria for early morning (dawn) and dusk (dusk).
【００１３】本発明による監視装置の第４の発明は、第
１または第２の発明における昼夜判定手段が、撮像装置
の露出情報を補助情報として用いて昼夜の判定を行うよ
うに構成されている。According to a fourth aspect of the monitoring apparatus of the present invention, the day / night determining means in the first or second aspect is configured to determine the day / night by using the exposure information of the image pickup device as auxiliary information. .
【００１４】第４の発明によれば、昼夜の切り替え付近
（早朝・薄暮）では撮像装置の絞りは解放となり、シャ
ッタ速度は最低となるので、この情報を用いることによ
って昼間で輝度分散値が大きくなったときの誤判定を低
減することができる。According to the fourth aspect of the invention, the aperture of the image pickup device is opened near the switching between day and night (early morning / dusk) and the shutter speed becomes the minimum. Therefore, by using this information, the luminance dispersion value becomes large during the daytime. It is possible to reduce the erroneous determination when it becomes.
【００１５】本発明による監視装置の第５の発明は、撮
像装置で撮影した画像を入力する画像入力手段と、この
画像内の特定の指定領域の輝度平均値および輝度分散値
を求める輝度検出手段と、指定領域の輝度平均値から昼
と早朝・薄暮とを判定してそれらに適した２値化閾値を
決定する閾値決定手段と、２値化閾値を用いて画像を２
値化処理し２値化画像を得る２値化処理手段と、２値化
画像から対象物を認識する認識手段とを備える。A fifth aspect of the monitoring apparatus according to the present invention is image input means for inputting an image photographed by an image pickup device, and luminance detecting means for obtaining an average luminance value and a luminance dispersion value of a specific designated area in the image. And a threshold value determining unit that determines daytime, early morning and dusk from the average luminance value of the designated area and determines a binarization threshold value suitable for them, and an image is displayed using the binarization threshold value.
A binarization processing unit that performs a binarization process to obtain a binarized image and a recognition unit that recognizes an object from the binarized image are provided.
【００１６】第５の発明によれば、指定領域内のデータ
で昼と早朝・薄暮との判定を行うので、指定領域を適切
に設定すれば対象物に対する周囲の環境の影響を低減さ
せて判定精度の向上を図ることができる。また、輝度平
均値および輝度分散値の２つの情報から判定を行うの
で、判定精度の向上を図ることができる。According to the fifth aspect of the invention, the data in the designated area is used to determine whether it is daytime, early morning, or twilight. Therefore, if the designated area is set appropriately, the influence of the surrounding environment on the object can be reduced. The accuracy can be improved. Moreover, since the determination is performed based on the two pieces of information of the average luminance value and the luminance dispersion value, the determination accuracy can be improved.
【００１７】本発明による監視装置の第６の発明は、第
５の発明における閾値決定手段が、早朝・薄暮と判定し
た場合は、輝度平均値および輝度分散値の２次元的な分
布位置から補正輝度平均値を求め、この補正輝度平均値
から２値化閾値を決定するように構成されている。In a sixth aspect of the monitoring apparatus according to the present invention, when the threshold value determining means in the fifth aspect determines early morning / dusk, correction is made from the two-dimensional distribution position of the average luminance value and the luminance dispersion value. The brightness average value is obtained, and the binarization threshold value is determined from the corrected brightness average value.
【００１８】第６の発明によれば、輝度平均値が急変す
る早朝・薄暮のような時間帯では２値化閾値を自動的に
可変するので、最適な２値化閾値で２値化画像を得るこ
とができる。According to the sixth aspect of the invention, the binarization threshold is automatically varied in a time zone such as early morning or dusk when the average luminance value changes abruptly. Obtainable.
【００１９】本発明による監視装置の第７の発明は、第
６の発明における閾値決定手段が、補正輝度平均値から
２値化閾値を決定する際に過去の２値化閾値に対して設
定した範囲内で決定するように構成されている。In a seventh aspect of the monitoring apparatus according to the present invention, when the threshold value determining means in the sixth aspect determines the binarization threshold value from the corrected luminance average value, it is set with respect to the past binarization threshold value. It is configured to determine within a range.
【００２０】第７の発明によれば、過去の２値化閾値を
考慮して今回の２値化閾値を決定するので、輝度平均値
の急激な変動に対しても２値化閾値を安定化できる。According to the seventh aspect of the invention, the current binarization threshold value is determined in consideration of the past binarization threshold value, so that the binarization threshold value is stabilized even when the brightness average value changes abruptly. it can.
【００２１】本発明による監視装置の第８の発明は、第
５の発明における閾値決定手段が、撮像装置の露出情報
を補助情報として昼と早朝・薄暮との判定を行うように
構成されている。According to an eighth invention of the monitoring device of the present invention, the threshold value determining means in the fifth invention is configured to determine whether it is daytime, early morning or twilight by using the exposure information of the image pickup device as auxiliary information. .
【００２２】第８の発明によれば、昼夜の切り替え付近
である早朝・薄暮時では、撮像装置の絞りが解放とな
り、シャッタ速度が最低となるので、この情報を用いる
ことにより不要な２値化閾値の変動を低減することがで
きる。According to the eighth invention, the aperture of the image pickup device is opened and the shutter speed becomes the lowest at the time of early morning / dusk, which is near the switching between day and night, so that unnecessary binarization is performed by using this information. It is possible to reduce the fluctuation of the threshold value.
【００２３】本発明による監視装置の第９の発明は、第
１の発明における輝度検出手段が、複数の小領域からな
る指定領域の輝度平均値を、各小領域毎に求めた輝度平
均値の代表値とするように構成されている。According to a ninth aspect of the monitoring apparatus of the present invention, the luminance detecting means in the first aspect of the present invention calculates the average luminance value of a designated area composed of a plurality of small areas for each small area. It is configured to be a representative value.
【００２４】また、本発明による監視装置の第１０の発
明は、第２または５の発明における輝度検出手段が、複
数の小領域からなる指定領域の輝度平均値および輝度分
散値を、各小領域毎に求めた輝度平均値および輝度分散
値の代表値とするように構成されている。According to a tenth aspect of the monitoring apparatus of the present invention, the luminance detecting means according to the second or fifth aspect of the present invention uses the luminance average value and the luminance variance value of a designated area consisting of a plurality of small areas for each small area. It is configured to be a representative value of the brightness average value and the brightness dispersion value obtained for each.
【００２５】第９または第１０の発明によれば、指定領
域の代表値として各小領域の中間値、または最小値、ま
たは最大値以外の平均値等を選択すれば、指定領域内の
ノイズ成分を低減することができ、輝度平均値の精度を
高めることができる。According to the ninth or tenth aspect of the invention, the noise component in the designated area can be selected by selecting an average value other than the minimum value or the maximum value of each small area as the representative value of the designated area. Can be reduced, and the accuracy of the brightness average value can be improved.
【００２６】[0026]
（実施の形態１）図１は、本発明の実施の形態１による
監視装置のブロック図である。この装置は対象物の認識
を昼と夜とで異なる認識方法を用いて行うもので、昼夜
の判定精度を向上させることによって対象物の認識方法
の選択精度を向上させ、それによって対象物の監視精度
の向上を図るものである。(Embodiment 1) FIG. 1 is a block diagram of a monitoring apparatus according to Embodiment 1 of the present invention. This device recognizes objects by using different recognition methods for day and night.It improves the accuracy of day / night determination, thereby improving the accuracy of object recognition method selection, and thereby monitoring the objects. This is intended to improve accuracy.
【００２７】図１において、画像入力部１は屋外に設置
した監視カメラ等の撮像装置（図示せず）によって撮影
した画像を、監視画像として取り込み、内部の画像メモ
リに一時的に記憶するものである。In FIG. 1, an image input section 1 is for taking in an image taken by an image pickup device (not shown) such as a surveillance camera installed outdoors, as a surveillance image, and temporarily storing it in an internal image memory. is there.
【００２８】輝度検出部２は画像メモリに記憶した監視
画像の中から予め定めた指定領域内の各画素の輝度を求
め、その総和を指定領域内の画素数で割った値を輝度平
均値として求め、さらに各画素の輝度分布から輝度分散
値を求めるものである。The brightness detection unit 2 obtains the brightness of each pixel in a predetermined specified area from the monitor image stored in the image memory, and divides the sum by the number of pixels in the specified area to obtain a brightness average value. Then, the luminance dispersion value is obtained from the luminance distribution of each pixel.
【００２９】図２に、画像メモリに記憶した監視画像の
全体領域Ｅ１と指定領域Ｅ２との関係を示す。従来は実
線で示す全体領域Ｅ１の各画素の輝度から輝度平均値を
求めて昼夜の判定を行っていたが、本実施の形態では、
一点鎖線で示す指定領域Ｅ２の輝度平均値、または輝度
平均値と輝度分散値とから昼夜の判定を行っている。監
視カメラは固定されているので、指定領域Ｅ２を適切に
設定すれば、指定領域Ｅ２以外の画素は昼夜の判定の対
象とならないため、対象物に対する周囲の環境の影響を
低減させることができ、昼夜の判定精度の向上を図るこ
とができる。FIG. 2 shows the relationship between the entire area E1 of the monitor image stored in the image memory and the designated area E2. Conventionally, the brightness average value is obtained from the brightness of each pixel of the entire region E1 indicated by the solid line to determine whether it is day or night, but in the present embodiment,
Day / night determination is performed based on the average luminance value of the designated area E2 indicated by the alternate long and short dash line, or the average luminance value and the luminance dispersion value. Since the surveillance camera is fixed, if the designated area E2 is appropriately set, the pixels other than the designated area E2 are not the target of the day / night determination, so that the influence of the surrounding environment on the object can be reduced. It is possible to improve the day / night determination accuracy.
【００３０】また、図に破線で示すように、指定領域Ｅ
２内を複数の小領域Ｅ３に分割した場合は、各小領域Ｅ
３毎に輝度平均値および輝度分散値を求め、その中から
代表値を定めて指定領域Ｅ２の輝度平均値および輝度分
散値とする。代表値としては中間値、最小値、または最
大値以外の平均等がある。これにより指定領域Ｅ２内の
ノイズを低減することができる。Further, as indicated by a broken line in the figure, the designated area E
2 is divided into a plurality of small areas E3, each small area E
The brightness average value and the brightness dispersion value are obtained for each of the three, and the representative value is determined from them to be the brightness average value and the brightness dispersion value of the designated area E2. The representative value includes an average value other than the intermediate value, the minimum value, or the maximum value. As a result, noise in the designated area E2 can be reduced.
【００３１】昼夜判定部３は輝度検出部２で求めた輝度
平均値、または輝度平均値と輝度分散値とから昼夜の判
定を行うものである。輝度平均値から昼夜判定する場合
は、輝度平均値と予め定めた判定閾値とを比較し、輝度
平均値が判定閾値より大きければ昼間と判定し、小さけ
れば夜間と判定する。輝度平均値および輝度分散値から
昼夜判定する場合は、輝度平均値および輝度分散値の２
次元的な分布位置から判定する。これらの詳細について
は後述する。The day / night judging section 3 judges the day and night from the brightness average value obtained by the brightness detecting section 2, or the brightness average value and the brightness dispersion value. In the case of day / night determination based on the average brightness value, the average brightness value is compared with a predetermined determination threshold value. If the average brightness value is larger than the determination threshold value, it is determined to be daytime, and if smaller than that, it is determined to be nighttime. When determining the day and night from the brightness average value and the brightness variance value, 2 of the brightness average value and the brightness variance value is used.
Determine from the dimensional distribution position. Details of these will be described later.
【００３２】昼間用認識部４ａおよび夜間用認識部４ｂ
は昼夜判定部３での判定結果に基づいて、昼間と夜間と
で異なる画像処理技術を用いて画像入力部１に記憶され
ている監視画像の画像処理を行い、対象物を認識する。
昼間の場合は、昼間用認識部４ａによって例えば背景差
分、フレーム差分、エッジ抽出によるパターンマッチン
グ等により対象物の認識を行う。夜間の場合は、夜間用
認識部４ｂによって例えば対象が車両であればヘッドラ
イト部分のパターンマッチングにより対象物である車両
を認識する。Daytime recognition unit 4a and nighttime recognition unit 4b
On the basis of the determination result of the day / night determination unit 3, image processing of the monitoring image stored in the image input unit 1 is performed by using different image processing techniques for daytime and nighttime, and the target object is recognized.
In the daytime, the object recognition is performed by the daytime recognition unit 4a by, for example, background difference, frame difference, pattern matching by edge extraction, or the like. In the case of nighttime, the nighttime recognition unit 4b recognizes the vehicle that is the object by pattern matching of the headlight portion if the object is a vehicle, for example.
【００３３】出力部５は昼間用認識部４ａおよび夜間用
認識部４ｂで生成したデータを通信回線を介して中央の
監視装置（図示せず）に伝送する。例えば、対象物が通
行人であればその人数を伝送し、自動車であればその通
過台数を伝送する。The output unit 5 transmits the data generated by the daytime recognition unit 4a and nighttime recognition unit 4b to a central monitoring device (not shown) via a communication line. For example, if the object is a passerby, the number of people is transmitted, and if it is a car, the number of passing vehicles is transmitted.
【００３４】次に、昼夜判定部３における昼夜判定の詳
細について説明する。図３は、昼間から夜間にかけての
各時刻における輝度平均値の変化を示すグラフ図であ
る。この図から明らかなように、時刻ＴＭで輝度平均値
が判定閾値ＴＨより小さくなるので、時刻ＴＭ以前は昼
間と判定し、以後は夜間と判定する。Next, the details of the day / night determination in the day / night determination section 3 will be described. FIG. 3 is a graph showing changes in the average brightness value at each time from daytime to nighttime. As is clear from this figure, since the brightness average value becomes smaller than the determination threshold value TH at time TM, it is determined to be the daytime before the time TM and thereafter the nighttime.
【００３５】なお、各時刻毎の輝度平均値を取ると変動
が激しいので、所定時間毎の平均を取ることで時間的に
平滑化すれば、図４に示すように、急激な変動が少なく
なり昼夜の境界付近での判定のバラツキが低減するの
で、昼夜処理の切り替えが安定化する。It should be noted that when the luminance average value at each time point is taken, the change fluctuates greatly. Therefore, if the luminance is averaged at a predetermined time for smoothing in time, the sudden change becomes small as shown in FIG. Since the variation in the determination near the day / night boundary is reduced, the switching of the day / night processing is stabilized.
【００３６】次に、輝度平均値および輝度分散値から昼
夜判定を行う場合は、図５に示すように、各時刻におけ
る輝度平均値および輝度分散値の２次元的な分布位置を
座標上にプロットする。図において、黒丸は昼間の各時
刻におけるデータであり、白丸は夜間の各時刻における
データである。Next, in the case of making the day / night determination from the brightness average value and the brightness dispersion value, as shown in FIG. 5, the two-dimensional distribution positions of the brightness average value and the brightness dispersion value at each time are plotted on the coordinates. To do. In the figure, black circles are data at each time of day, and white circles are data at each time of night.
【００３７】次いで、座標上に判定関数Ｆを描く。この
判定関数Ｆは輝度平均値をｘ座標、輝度分散値をｙ座標
とすれば「ｙ＝ａｘ−ｂ」（ａ，ｂは正の定数）と表せ
る。データが判定関数Ｆの直線よりも低輝度平均値側
（図で左側）に位置する場合は夜間と判定し、高輝度平
均値側（図で右側）に位置する場合は昼間と判定する。
従って、例えば対象物が自動車である場合に、ヘッドラ
イトによって輝度平均値が明るくなっても輝度分散値が
大きければ夜間と判定する。このように輝度平均値と輝
度分散値とを利用して昼夜を判定するので、精度の高い
昼夜判定を行うことができる。Then, a decision function F is drawn on the coordinates. This determination function F can be expressed as "y = ax-b" (a and b are positive constants) when the luminance average value is the x coordinate and the luminance dispersion value is the y coordinate. When the data is located on the low luminance average value side (left side in the figure) of the straight line of the determination function F, it is determined to be night, and when it is located on the high luminance average value side (right side in the figure), it is determined to be daytime.
Therefore, for example, when the object is an automobile, even if the brightness average value is brightened by the headlight, if the brightness dispersion value is large, it is determined to be night. Since day and night are determined using the brightness average value and the brightness variance value in this manner, highly accurate day and night determination can be performed.
【００３８】なお、早朝時の昼夜判定と、薄暮時の昼夜
判定とを精度よく行うために、図６に示すように、昼間
から夜間への移行を検出する判定閾値ＴＨDNと、夜間か
ら昼間への移行を検出する判定閾値ＴＨNDとの２つの判
定閾値を設定して判定するようにしてもよい。As shown in FIG. 6, a judgment threshold value THDN for detecting the shift from daytime to nighttime and a nighttime to daytime determination are provided in order to accurately perform daytime determination at early morning and daytime determination at dusk. The determination may be performed by setting two determination thresholds, that is, a determination threshold THND for detecting the shift of the.
【００３９】また、輝度平均値および輝度分散値から昼
夜判定を行う場合も、図７に示すように、昼間から夜間
への移行を検出する判定関数ＦDNと、夜間から昼間への
移行を検出する判定関数ＦNDとの２つの判定関数を用い
て判定するようにしてもよい。Also, in the case of making the day / night judgment from the brightness average value and the brightness variance value, as shown in FIG. 7, the judgment function FDN for detecting the shift from the daytime to the night and the shift from the nighttime to the daytime are detected. The determination may be performed using two determination functions such as the determination function FND.
【００４０】（実施の形態２）図８は、本発明の実施の
形態２による監視装置のブロック図である。この装置は
２値化閾値によって原画像または背景画像などを２値化
処理し、得られた２値化画像から対象物を認識するもの
で、とくに早朝・薄暮時のような輝度平均値が急変する
時間帯では、２値化閾値を自動的に可変し、最適な２値
化閾値で２値化画像を得ることによって対象物の監視精
度の向上を図るものである。(Second Embodiment) FIG. 8 is a block diagram of a monitoring apparatus according to a second embodiment of the present invention. This device binarizes an original image or a background image with a binarization threshold value and recognizes an object from the binarized image obtained. In particular, the average brightness value changes abruptly during early morning and twilight. In the period of time during which the threshold value is changed, the binarization threshold value is automatically changed, and the binarized image is obtained with the optimum binarization threshold value to improve the monitoring accuracy of the object.
【００４１】図８において、画像入力部１１は屋外に設
置した監視カメラ等の撮像装置（図示せず）によって撮
影した画像を、監視画像として取り込み、内部の画像メ
モリに一時的に記憶する。In FIG. 8, the image input unit 11 takes in an image taken by an image pickup device (not shown) such as a surveillance camera installed outdoors, as a surveillance image, and temporarily stores it in an internal image memory.
【００４２】輝度検出部１２は画像メモリに記憶した監
視画像の中から予め定めた指定領域Ｅ２（図２）の各画
素の輝度を求め、その総和を指定領域Ｅ２の画素数で割
って輝度平均値を求める。また、指定領域Ｅ２の各画素
の輝度分布から指定領域Ｅ２の輝度分散値を求める。The brightness detection unit 12 obtains the brightness of each pixel in a predetermined designated area E2 (FIG. 2) from the monitor image stored in the image memory, divides the sum by the number of pixels in the designated area E2, and averages the brightness. Find the value. Further, the luminance dispersion value of the designated area E2 is obtained from the luminance distribution of each pixel of the designated area E2.
【００４３】指定領域Ｅ２を複数の小領域Ｅ３に分割し
た場合は、各小領域Ｅ３毎に輝度平均値および輝度分散
値を求め、その中から代表値を決めて指定領域Ｅ２の輝
度平均値および輝度分散値とする。このように監視領域
を指定することによって指定領域Ｅ２以外の画素は判定
の対象としないことにより、周囲の環境の影響を低減さ
せることができる。これらのことは前述した輝度検出部
２と同様である。When the designated area E2 is divided into a plurality of small areas E3, a luminance average value and a luminance dispersion value are obtained for each small area E3, and a representative value is determined from the obtained luminance average value and the luminance average value of the designated area E2. The luminance variance value. In this way, by designating the monitoring area, pixels other than the designated area E2 are not targeted for determination, so that the influence of the surrounding environment can be reduced. These are the same as those of the brightness detection unit 2 described above.
【００４４】閾値決定部１３は輝度検出部１２で求めた
輝度平均値および輝度分散値から２値化閾値を決定す
る。２値化閾値としては、昼間用の閾値（固定値）と、
早朝・薄暮用の閾値（可変値）とがある。２値化閾値の
決定方法の詳細については後述する。The threshold value determining unit 13 determines a binarization threshold value from the average luminance value and the luminance dispersion value obtained by the luminance detecting unit 12. As the binarization threshold, a daytime threshold (fixed value),
There are thresholds (variable values) for early morning and dusk. Details of the method of determining the binarization threshold will be described later.
【００４５】２値化処理部１４はこうして決定した２値
化閾値によって画像メモリに記憶されている監視画像を
２値化して２値化画像を得る。２値化閾値は、原画像の
２値化、背景差分後の２値化、フレーム差分後の２値
化、微分後の２値化などに用いる。The binarization processing unit 14 binarizes the monitor image stored in the image memory by the binarization threshold value thus determined to obtain a binarized image. The binarization threshold value is used for binarization of the original image, binarization after background difference, binarization after frame difference, binarization after differentiation, and the like.
【００４６】認識部１５は２値化処理部１４で得た２値
化画像からパターンマッチングなどによって対象物を認
識し、これに基づいて対象物に関するデータを生成す
る。出力部１６は認識部１５で生成したデータを通信回
線を介して中央の監視装置（図示せず）に伝送する。例
えば、対象物が通行人であればその人数を計数し、対象
物が車両であればその台数を計数し、それぞれ通信回線
を介して中央の監視装置に伝送する。The recognition unit 15 recognizes an object by pattern matching or the like from the binarized image obtained by the binarization processing unit 14, and generates data on the object based on this. The output unit 16 transmits the data generated by the recognition unit 15 to a central monitoring device (not shown) via a communication line. For example, if the object is a passerby, the number of people is counted, and if the object is a vehicle, the number is counted and transmitted to the central monitoring device via the respective communication lines.
【００４７】次に、閾値決定部１３における２値化閾値
の決定方法について説明する。図９は、昼間から夜間に
かけての各時刻における輝度平均値の変化を示すグラフ
図である。輝度平均値が輝度上限値ＢＵより大きい場合
は昼間と判定して昼間用の２値化閾値を決定し、輝度平
均値が輝度下限値ＢＬより小さい場合は早朝・薄暮用の
下限２値化閾値を決定する。Next, a method of determining the binarized threshold value in the threshold value determination unit 13 will be described. FIG. 9 is a graph showing a change in the average luminance value at each time from daytime to nighttime. When the brightness average value is larger than the brightness upper limit value BU, it is determined to be daytime and the binarization threshold value for daytime is determined. When the brightness average value is smaller than the brightness lower limit value BL, the lower limit binarization threshold value for early morning / dusk. To decide.
【００４８】輝度平均値が上限値ＢＵと下限値ＢＬとの
間の領域ＢＲ内に位置する場合は、早朝・薄暮時と判定
し、以下に述べる手順によって２値化閾値を決定する。
なお、各時刻毎の輝度平均値を取ると変動が激しいの
で、所定時間毎の平均を取ることで時間的に平滑化すれ
ば、図１０に示すように急激な変動が少なくなる。When the average brightness value is located in the area BR between the upper limit value BU and the lower limit value BL, it is determined that it is early morning and twilight, and the binarization threshold value is determined by the procedure described below.
It should be noted that when the luminance average value is taken at each time point, there is a large variation, so if the averaging is performed every predetermined time for temporal smoothing, abrupt changes are reduced as shown in FIG.
【００４９】図１１は、各時刻における輝度平均値およ
び輝度分散値の２次元的な分布位置を座標上にプロット
した図である。図の右上位置は晴れの昼間のデータであ
り、その下の位置は曇りの昼間のデータである。図の左
下に移行するにつれて夕闇が深まったときのデータとな
る。FIG. 11 is a diagram in which the two-dimensional distribution positions of the brightness average value and the brightness dispersion value at each time are plotted on the coordinates. The upper right position in the figure is the data for sunny daytime, and the position below it is the data for cloudy daytime. The data becomes when the dusk deepens as it moves to the lower left of the figure.
【００５０】次いで、座標上に上限関数ＦＵと下限関数
ＦＬとを描く。この関数ＦＵ，ＦＬは輝度平均値をｘ座
標、輝度分散値およびｙ座標とすれば、上限関数ＦＵは
「ｙ＝−ｃｘ＋ｄ」、下限関数ＦＬは「ｙ＝−ｃｘ＋
ｅ」（ｅ＜ｄ）と表せる。データが上限関数ＦＵと下限
関数ＦＬとの間に位置するときは、各データ毎に２値化
閾値を決定するために、図１２に示すように、上限関数
ＦＵおよび下限関数ＦＬと平行にデータＤを通過する関
数ＦＤを想定する。この関数ＦＤは「ｙ＝−ｃｘ＋ｆ」
（ｅ＜ｆ＜ｄ）と表せる。そして、輝度分散値が０のと
きの関数ＦＤ上の輝度平均値を補正輝度平均値ＢＤとす
る。Next, the upper limit function FU and the lower limit function FL are drawn on the coordinates. In the functions FU and FL, if the luminance average value is the x coordinate, the luminance dispersion value, and the y coordinate, the upper limit function FU is “y = −cx + d” and the lower limit function FL is “y = −cx +”.
e ”(e <d). When the data is located between the upper limit function FU and the lower limit function FL, in order to determine the binarization threshold value for each data, as shown in FIG. 12, the data is parallel to the upper limit function FU and the lower limit function FL. Assume a function FD passing through D. This function FD is “y = −cx + f”
It can be expressed as (e <f <d). Then, the luminance average value on the function FD when the luminance dispersion value is 0 is set as the corrected luminance average value BD.
【００５１】次いで、図１３に示すように、輝度平均値
と２値化閾値との関係を示す閾値算出関数Ｆthを用いて
補正輝度平均値ＢＤから２値化閾値ＴＨＤを決定する。
補正輝度平均値ＢＤは輝度平均値の上限値ＢＵと下限値
ＢＬとの間の可変領域ＢＲ内に位置し、決定される２値
化閾値ＴＨＤは昼間用の２値化閾値ＴＨＵと早朝・薄暮
用の下限２値化閾値ＴＨＬとの間を線形に変動するよう
に設定されている。こうして求めた２値化閾値ＴＨＤに
より２値化処理部１４で画像を２値化処理して２値化画
像を得る。Next, as shown in FIG. 13, a binarization threshold value THD is determined from the corrected brightness average value BD using a threshold value calculation function Fth indicating the relationship between the brightness average value and the binarization threshold value.
The corrected brightness average value BD is located in the variable region BR between the upper limit value BU and the lower limit value BL of the brightness average value, and the determined binarization threshold value THD is the binarization threshold value THU for daytime and early morning / dusk. It is set so as to linearly fluctuate between the lower limit binarization threshold value THL for. The binarization processing unit 14 binarizes the image using the binarization threshold value THD thus obtained to obtain a binarized image.
【００５２】なお、過去の２値化閾値を考慮するため、
図１４に示すように、過去の２値化閾値（図の黒丸）に
対して閾値変動有効領域ＴＨＲを設定し、今回求めた２
値化閾値ＴＨＤが有効領域ＴＨＲ内にある場合はそのま
ま決定し、有効領域ＴＨＲの上限値ＴＨＲＵを上回った
場合はこの上限値を２値化閾値と決定し、下限値ＴＨＲ
Ｌを下回った場合はこの下限値を２値化閾値と決定す
る。これによって輝度平均値の急激な変動を抑えること
ができる。Since the past binarization threshold is taken into consideration,
As shown in FIG. 14, the threshold variation effective region THR is set with respect to the past binarization threshold value (black circle in the figure), and the presently obtained 2
If the binarization threshold value THD is within the effective area THR, it is determined as it is. If it exceeds the upper limit value THRU of the effective area THR, this upper limit value is determined as the binarization threshold value, and the lower limit value THR is determined.
When it is less than L, this lower limit value is determined as a binarization threshold value. This makes it possible to suppress a sudden change in the average luminance value.
【００５３】また、輝度平均値の急激な変動を抑える他
の方法としては、図１５に示すように、過去の２値化閾
値が昼間用の２値化閾値ＴＨＵであったとすると、今回
の２値化閾値は第１の閾値算出関数Ｆth１から算出す
る。次いで、算出した２値化閾値が夜間用の２値化閾値
ＴＨＬになると、次からは第２の閾値算出関数Ｆth２か
ら算出する。算出した２値化閾値が昼間用の２値化閾値
ＴＨＵになるまで閾値算出関数Ｆth２を使用する。以後
はこの繰り返しである。Further, as another method for suppressing the abrupt change of the average luminance value, if the past binarization threshold is the daytime binarization threshold THU as shown in FIG. The threshold value threshold value is calculated from the first threshold value calculation function Fth1. Next, when the calculated binarization threshold becomes the nighttime binarization threshold THL, it is calculated from the second threshold calculation function Fth2 from then on. The threshold calculation function Fth2 is used until the calculated binarization threshold becomes the binarization threshold THU for daytime. Hereinafter, this is repeated.
【００５４】この場合、可変領域は閾値算出関数Ｆth１
のときの可変領域ＢＲ１（輝度平均値ＢＬ１〜ＢＵ１）
と、閾値算出関数Ｆth２のときの可変領域ＢＲ２（輝度
平均値ＢＬ２〜ＢＵ２）との２つの可変領域が設定され
る。In this case, the variable region is the threshold value calculation function Fth1.
Variable region BR1 (average brightness values BL1 to BU1)
And a variable region BR2 (luminance average value BL2 to BU2) when the threshold value calculation function Fth2 is set.
【００５５】なお、前述の実施の形態では、昼夜の判
定、あるいは昼と早朝・薄暮との判定を監視画像のみか
ら行うようにしたが、昼夜の切り替え付近である早朝・
薄暮時は監視カメラの絞りが解放となり、シャッタ速度
が最低となるので、この情報を補助情報として用いるこ
とにより、不要な２値化閾値の変動を低減することがで
きる。In the above-mentioned embodiment, the judgment of day and night or the judgment of day and early morning / dusk is made only from the monitoring image.
Since the diaphragm of the surveillance camera is opened and the shutter speed becomes the lowest at dusk, by using this information as auxiliary information, unnecessary fluctuations in the binarization threshold can be reduced.
【００５６】[0056]
【発明の効果】本発明によれば、対象物の認識を昼夜で
異なる認識方法を用いて行う場合、指定領域によって昼
夜の判定を行うようにしたので、指定領域を適切に設定
することによって対象物に対する周囲の環境の影響を低
減させることができ、判定精度の向上を図ることができ
る。また、昼夜の判定を輝度平均値および輝度分散値の
２つの情報から行うようにしたので、さらなる判定精度
の向上を図ることができる。これにより対象物の監視精
度の向上が図れる。According to the present invention, when the object recognition is performed by using different recognition methods for day and night, the day and night are determined according to the designated area. Therefore, the target area can be appropriately set. The influence of the surrounding environment on the object can be reduced, and the determination accuracy can be improved. In addition, since the determination of day and night is made based on the two pieces of information of the luminance average value and the luminance dispersion value, it is possible to further improve the determination accuracy. As a result, the accuracy of monitoring the object can be improved.
【００５７】また、本発明によれば、２値化閾値によっ
て原画像等を２値化処理し、得られた２値化画像から対
象物を認識する場合、早朝・薄暮のような輝度平均値が
急変する時間帯では２値化閾値を自動的に可変するよう
にしたので、昼間時および早朝・薄暮時のいかなる時間
帯でも対象物の認識精度を向上させることができ、これ
により対象物の監視精度の向上を図ることができる。Further, according to the present invention, when the original image or the like is binarized by the binarization threshold value and the object is recognized from the obtained binarized image, the average brightness value such as early morning and dusk is obtained. Since the binarization threshold is automatically changed in the time zone when the sudden change occurs, it is possible to improve the recognition accuracy of the object at any time of daytime and early morning / dusk. It is possible to improve the monitoring accuracy.
【図１】本発明の実施の形態１による監視装置のブロッ
ク図である。FIG. 1 is a block diagram of a monitoring device according to a first embodiment of the present invention.
【図２】監視画像の全体領域、指定領域および小領域を
示す図である。FIG. 2 is a diagram showing an entire area, a designated area, and a small area of a surveillance image.
【図３】輝度平均値の変化を示すグラフ図である。FIG. 3 is a graph showing a change in average luminance value.
【図４】図３に示す輝度平均値の変化を時間的に平滑化
したグラフ図である。FIG. 4 is a graph diagram in which changes in the average luminance value shown in FIG. 3 are temporally smoothed.
【図５】各時刻における輝度平均値および輝度分散値の
２次元的な分布位置をプロットした図で、黒丸は昼間の
データ、白丸は夜間のデータである。FIG. 5 is a diagram in which the two-dimensional distribution positions of the average luminance value and the luminance dispersion value at each time are plotted, where the black circles represent daytime data and the white circles represent nighttime data.
【図６】輝度平均値の変化を示すグラフ図で、２つの判
定閾値によって昼夜を判定するためのグラフ図である。FIG. 6 is a graph showing a change in average luminance value and is a graph for judging day and night by two judgment threshold values.
【図７】各時刻における輝度平均値および輝度分散値の
２次元的な分布位置をプロットした図で、２つの判定関
数によって昼夜を判定するための図である。FIG. 7 is a diagram in which two-dimensional distribution positions of a luminance average value and a luminance dispersion value at each time are plotted, and is a diagram for determining day and night by two determination functions.
【図８】本発明の実施の形態２による監視装置のブロッ
ク図である。FIG. 8 is a block diagram of a monitoring device according to a second embodiment of the present invention.
【図９】輝度平均値の変化を示すグラフ図である。FIG. 9 is a graph showing a change in luminance average value.
【図１０】図９に示す輝度平均値の変化を時間的に平滑
化したグラフ図である。FIG. 10 is a graph diagram in which changes in the average luminance value shown in FIG. 9 are smoothed with time.
【図１１】各時刻における輝度平均値および輝度分散値
の２次元的な分布位置をプロットした図である。FIG. 11 is a diagram in which two-dimensional distribution positions of a brightness average value and a brightness dispersion value at each time are plotted.
【図１２】早朝・薄暮時のデータから補正輝度平均値を
求めるための説明図である。FIG. 12 is an explanatory diagram for obtaining a corrected luminance average value from data in early morning and twilight.
【図１３】輝度平均値と２値化閾値との関係を表す閾値
算出関数を示す図である。FIG. 13 is a diagram showing a threshold value calculation function representing a relationship between a brightness average value and a binarization threshold value.
【図１４】過去の２値化閾値を考慮して２値化閾値を決
定するための説明図である。FIG. 14 is an explanatory diagram for determining a binarization threshold in consideration of a past binarization threshold.
【図１５】過去の２値化閾値を考慮して２値化閾値を決
定するための説明図である。FIG. 15 is an explanatory diagram for determining a binarization threshold in consideration of a past binarization threshold.
１ 画像入力部 ２ 輝度検出部 ３ 昼夜判定部 ４ａ 昼間用認識部 ４ｂ 夜間用認識部 ５ 出力部 １１ 画像入力部 １２ 輝度検出部 １３ 閾値決定部 １４ ２値化処理部 １５ 認識部 １６ 出力部 Ｅ１ 全体領域 Ｅ２ 指定領域 Ｅ３ 小領域 DESCRIPTION OF SYMBOLS 1 Image input unit 2 Luminance detection unit 3 Day / night determination unit 4a Daytime recognition unit 4b Nighttime recognition unit 5 Output unit 11 Image input unit 12 Luminance detection unit 13 Threshold value determination unit 14 Binarization processing unit 15 Recognition unit 16 Output unit E1 Whole area E2 Designated area E3 Small area
Claims (10)
入力手段と、 前記画像内の特定の指定領域の輝度平均値を求める輝度
検出手段と、 前記指定領域の輝度平均値から昼夜の判定を行う昼夜判
定手段と、 前記昼夜判定手段での判定結果に基づいて昼間時と夜間
時とで異なる画像処理技術を用いて前記画像から対象物
を認識する認識手段と、を備えることを特徴とする監視
装置。1. An image input unit for inputting an image photographed by an image pickup device, a luminance detecting unit for obtaining an average luminance value of a specific designated area in the image, and a day / night determination based on an average luminance value of the designated area. And a recognition unit that recognizes an object from the image by using different image processing techniques for daytime and nighttime based on the determination result by the daytime determination unit. Monitoring equipment.
入力手段と、 前記画像内の特定の指定領域の輝度平均値および輝度分
散値を求める輝度検出手段と、 前記指定領域の輝度平均値および輝度分散値の２次元的
な分布位置から昼夜の判定を行う昼夜判定手段と、 前記昼夜判定手段での判定結果に基づいて昼間時と夜間
時とで異なる画像処理技術を用いて前記画像から対象物
を認識する認識手段と、を備えることを特徴とする監視
装置。2. An image input unit for inputting an image photographed by an image pickup device, a luminance detecting unit for obtaining a luminance average value and a luminance dispersion value of a specific designated region in the image, and a luminance average value of the designated region and The day and night determination means for determining the day and night from the two-dimensional distribution position of the brightness dispersion value, and the object from the image by using different image processing techniques for the daytime and the nighttime based on the determination result by the day and night determination means A monitoring device comprising: a recognition unit that recognizes an object.
を検出する第１の判定基準と、夜間から昼間への変化を
検出する第２の判定基準とを備えることを特徴とする請
求項１または２記載の監視装置。3. The day / night determination means comprises a first determination criterion for detecting a change from daytime to nighttime, and a second determination criterion for detecting a change from nighttime to daytime. The monitoring device according to 1 or 2.
補助情報として用いて昼夜の判定を行うように構成され
ていることを特徴とする請求項１または２記載の監視装
置。4. The monitoring device according to claim 1, wherein the day / night determining means is configured to determine the day / night by using the exposure information of the image pickup device as auxiliary information.
入力手段と、 前記画像内の特定の指定領域の輝度平均値および輝度分
散値を求める輝度検出手段と、 前記指定領域の輝度平均値から昼と早朝・薄暮とを判定
してそれらに適した２値化閾値を決定する閾値決定手段
と、 前記２値化閾値を用いて前記画像を２値化処理し２値化
画像を得る２値化処理手段と、 前記２値化画像から対象物を認識する認識手段と、を備
えることを特徴とする監視装置。5. An image input means for inputting an image photographed by an image pickup device, a luminance detecting means for obtaining a luminance average value and a luminance dispersion value of a specific designated area in the image, and from the luminance average value of the designated area. Threshold value determining means for determining daytime, early morning and twilight, and determining a binarization threshold value suitable for them, and a binary value for binarizing the image using the binarization threshold value to obtain a binarized image A monitoring apparatus comprising: a digitization processing unit; and a recognition unit that recognizes an object from the binarized image.
た場合、輝度平均値および輝度分散値の２次元的な分布
位置から補正輝度平均値を求め、この補正輝度平均値か
ら２値化閾値を決定することを特徴とする請求項５記載
の監視装置。6. The threshold value determining means obtains a corrected brightness average value from a two-dimensional distribution position of the brightness average value and the brightness dispersion value, and binarizes the corrected brightness average value when it is determined that it is early morning or twilight. The monitoring device according to claim 5, wherein a threshold value is determined.
値化閾値を決定する際に過去の２値化閾値に対して設定
した範囲内で決定することを特徴とする請求項６記載の
監視装置。7. The threshold value determining means calculates 2 from the corrected average brightness value.
7. The monitoring device according to claim 6, wherein when the binarization threshold value is determined, the binarization threshold value is determined within a range set for the past binarization threshold value.
補助情報として昼または早朝・薄暮の判定を行うことを
特徴とする請求項５記載の監視装置。8. The monitoring device according to claim 5, wherein the threshold value determining means determines whether it is daytime, early morning or twilight by using exposure information of the image pickup device as auxiliary information.
指定領域の輝度平均値を各小領域毎に求めた輝度平均値
の代表値とするように構成されていることを特徴とする
請求項１記載の監視装置。9. The brightness detecting means is configured to use a brightness average value of a designated area composed of a plurality of small areas as a representative value of the brightness average values obtained for each small area. The monitoring device according to item 1.
る指定領域の輝度平均値および輝度分散値を、各小領域
毎に求めた輝度平均値および輝度分散値の代表値とする
ように構成されていることを特徴とする請求項２または
５記載の監視装置。10. The brightness detecting means is configured to use a brightness average value and a brightness dispersion value of a designated area composed of a plurality of small areas as a representative value of the brightness average value and the brightness dispersion value obtained for each small area. The monitoring device according to claim 2, wherein the monitoring device is provided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP11441196A JP3550874B2 (en) | 1996-04-12 | 1996-04-12 | Monitoring device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP11441196A JP3550874B2 (en) | 1996-04-12 | 1996-04-12 | Monitoring device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH09282452A true JPH09282452A (en) | 1997-10-31 |
| JP3550874B2 JP3550874B2 (en) | 2004-08-04 |
Family
ID=14637026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP11441196A Expired - Fee Related JP3550874B2 (en) | 1996-04-12 | 1996-04-12 | Monitoring device |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP3550874B2 (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008165743A (en) * | 2006-12-29 | 2008-07-17 | Alpine Electronics Inc | Day and night image discriminating method, and device |
| JP2010109859A (en) * | 2008-10-31 | 2010-05-13 | Mitsubishi Electric Corp | Monitoring image processing apparatus |
| US7805000B2 (en) | 2000-05-01 | 2010-09-28 | Minolta Co., Ltd. | Image processing for binarization of image data |
| US7916169B2 (en) | 2007-06-07 | 2011-03-29 | Denso Corporation | Face image capture apparatus |
| JP2011123726A (en) * | 2009-12-11 | 2011-06-23 | Mitsubishi Electric Corp | Image processing device for monitoring |
| JP2012043403A (en) * | 2010-08-19 | 2012-03-01 | Sharp Corp | Feature point extraction method, feature point extraction device, program and recording medium |
| JP2013120412A (en) * | 2011-12-06 | 2013-06-17 | Samsung Techwin Co Ltd | Object detection device, monitoring camera and object detection method |
| JP2014157453A (en) * | 2013-02-15 | 2014-08-28 | Omron Corp | Image processing apparatus, image processing method, and image processing program |
| WO2015001878A1 (en) * | 2013-07-03 | 2015-01-08 | クラリオン株式会社 | Approaching-object detection system and vehicle |
| JP5976198B2 (en) * | 2013-03-26 | 2016-08-23 | 株式会社日立国際電気 | Number counting device and number counting method |
| JP2017142764A (en) * | 2016-02-09 | 2017-08-17 | 株式会社リコー | Information processing apparatus, information processing method, and information processing program |
| WO2019031802A1 (en) * | 2017-08-07 | 2019-02-14 | 주식회사 다본다 | System and method for compensating for image quality for each brightness section |
| KR20190055479A (en) * | 2017-11-15 | 2019-05-23 | 주식회사 아이피엘 | Sytem for marker recognition and method therefor |
| CN111684455A (en) * | 2018-02-09 | 2020-09-18 | 索尼公司 | Recognition device, recognition method, and program |
| EP3667614A4 (en) * | 2018-03-19 | 2021-04-21 | Hitachi Construction Machinery Co., Ltd. | Monitor device and trolley-type vehicle |
-
1996
- 1996-04-12 JP JP11441196A patent/JP3550874B2/en not_active Expired - Fee Related
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7805000B2 (en) | 2000-05-01 | 2010-09-28 | Minolta Co., Ltd. | Image processing for binarization of image data |
| JP2008165743A (en) * | 2006-12-29 | 2008-07-17 | Alpine Electronics Inc | Day and night image discriminating method, and device |
| US7916169B2 (en) | 2007-06-07 | 2011-03-29 | Denso Corporation | Face image capture apparatus |
| JP2010109859A (en) * | 2008-10-31 | 2010-05-13 | Mitsubishi Electric Corp | Monitoring image processing apparatus |
| JP2011123726A (en) * | 2009-12-11 | 2011-06-23 | Mitsubishi Electric Corp | Image processing device for monitoring |
| US8971632B2 (en) | 2010-08-19 | 2015-03-03 | Sharp Laboratories Of America, Inc. | System for feature detection for low contrast images |
| JP2012043403A (en) * | 2010-08-19 | 2012-03-01 | Sharp Corp | Feature point extraction method, feature point extraction device, program and recording medium |
| JP2013120412A (en) * | 2011-12-06 | 2013-06-17 | Samsung Techwin Co Ltd | Object detection device, monitoring camera and object detection method |
| JP2014157453A (en) * | 2013-02-15 | 2014-08-28 | Omron Corp | Image processing apparatus, image processing method, and image processing program |
| JP5976198B2 (en) * | 2013-03-26 | 2016-08-23 | 株式会社日立国際電気 | Number counting device and number counting method |
| JPWO2014156733A1 (en) * | 2013-03-26 | 2017-02-16 | 株式会社日立国際電気 | Number counting device and number counting method |
| US9811745B2 (en) | 2013-07-03 | 2017-11-07 | Clarion Co., Ltd. | Approaching-object detection system and vehicle |
| JP2015014819A (en) * | 2013-07-03 | 2015-01-22 | クラリオン株式会社 | Approaching object detection system and vehicle |
| WO2015001878A1 (en) * | 2013-07-03 | 2015-01-08 | クラリオン株式会社 | Approaching-object detection system and vehicle |
| JP2017142764A (en) * | 2016-02-09 | 2017-08-17 | 株式会社リコー | Information processing apparatus, information processing method, and information processing program |
| WO2019031802A1 (en) * | 2017-08-07 | 2019-02-14 | 주식회사 다본다 | System and method for compensating for image quality for each brightness section |
| KR20190055479A (en) * | 2017-11-15 | 2019-05-23 | 주식회사 아이피엘 | Sytem for marker recognition and method therefor |
| CN111684455A (en) * | 2018-02-09 | 2020-09-18 | 索尼公司 | Recognition device, recognition method, and program |
| EP3751512A4 (en) * | 2018-02-09 | 2021-04-07 | Sony Corporation | Recognition device, recognition method, and program |
| US11438517B2 (en) | 2018-02-09 | 2022-09-06 | Sony Corporation | Recognition device, a recognition method, and a program that easily and accurately recognize a subject included in a captured image |
| EP3667614A4 (en) * | 2018-03-19 | 2021-04-21 | Hitachi Construction Machinery Co., Ltd. | Monitor device and trolley-type vehicle |
| US11468685B2 (en) | 2018-03-19 | 2022-10-11 | Hitachi Construction Machinery Co., Ltd. | Monitor device and trolley type vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| JP3550874B2 (en) | 2004-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7209832B2 (en) | Lane recognition image processing apparatus | |
| JP3307335B2 (en) | Vehicle region detection device and vehicle region verification method | |
| JP3083918B2 (en) | Image processing device | |
| US6037976A (en) | Method and apparatus for determining ambient conditions from an image sequence, such as fog, haze or shadows | |
| JP3816887B2 (en) | Apparatus and method for measuring length of vehicle queue | |
| US20060215882A1 (en) | Image processing apparatus and method, recording medium, and program | |
| JPH09282452A (en) | Monitor | |
| JPH08166221A (en) | Vehicle recognizing device for night | |
| JPH07302328A (en) | Method for extracting area of moving object based upon background difference | |
| CN111860120A (en) | Automatic shielding detection method and device for vehicle-mounted camera | |
| CN111046741A (en) | Method and device for identifying lane line | |
| US20190095761A1 (en) | Vicinity supervising device and method for supervising vicinity of vehicle | |
| KR101026778B1 (en) | Vehicle image detection apparatus | |
| JP3294468B2 (en) | Object detection method in video monitoring device | |
| JPH11278182A (en) | Fog status detection device for vehicle | |
| KR100801989B1 (en) | Recognition system for registration number plate and pre-processor and method therefor | |
| JP2001067484A (en) | Stereo monitor device for vehicle's outside | |
| JP6825299B2 (en) | Information processing equipment, information processing methods and programs | |
| JPH0337356B2 (en) | ||
| JP2004208209A (en) | Device and method for monitoring moving body | |
| JP3567114B2 (en) | Image monitoring apparatus and image monitoring method | |
| JP3390122B2 (en) | Vehicle white line detection device | |
| JPH11219493A (en) | Method for processing traffic information | |
| JP2007257242A (en) | White line recognition device | |
| JP3175509B2 (en) | Road white line detector |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20040105 |
|
| A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20040113 |
|
| A521 | Written amendment |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20040304 |
|
| 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: 20040330 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20040412 |
|
| R150 | Certificate of patent or registration of utility model |
Free format text: JAPANESE INTERMEDIATE CODE: R150 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20090514 Year of fee payment: 5 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100514 Year of fee payment: 6 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20100514 Year of fee payment: 6 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20110514 Year of fee payment: 7 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20120514 Year of fee payment: 8 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20130514 Year of fee payment: 9 |
|
| FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20140514 Year of fee payment: 10 |
|
| LAPS | Cancellation because of no payment of annual fees |