JPH06319141A - Supervisory equipment - Google Patents

Supervisory equipment

Info

Publication number
JPH06319141A
JPH06319141A JP10794993A JP10794993A JPH06319141A JP H06319141 A JPH06319141 A JP H06319141A JP 10794993 A JP10794993 A JP 10794993A JP 10794993 A JP10794993 A JP 10794993A JP H06319141 A JPH06319141 A JP H06319141A
Authority
JP
Japan
Prior art keywords
image
processing
picture
ship
conversion
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.)
Pending
Application number
JP10794993A
Other languages
Japanese (ja)
Inventor
Eiji Osaki
英二 大崎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Toshiba Corp
Original Assignee
Toshiba Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Toshiba Corp filed Critical Toshiba Corp
Priority to JP10794993A priority Critical patent/JPH06319141A/en
Publication of JPH06319141A publication Critical patent/JPH06319141A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE:To make a supervision job efficient by using a geometrical correction device to apply geometrical correction to a picture picked up by an image pickup device and using a difference processing unit to apply multi-value conversion processing to the picture to extract an object from other undesired parts thereby compensating a disadvantage such as mis-recognition of a ship caused by radar wave scattering on a sea surface having been in existence in a conventional coast radar system. CONSTITUTION:A geometrical correction device 12 has an address conversion table and executes geometrical conversion processing by the method such as table lookup processing in which the table is divided into meshes for the conversion. A length different from a position on a picked-up picture is corrected to be equal through the processing. Then a difference discrimination device 14 executes, e.g. binarizing processing. The binarizing processing is used to express the geometrical correction picture in a histogram where the axis of ordinate is a frequency of occurrence and the axis of abscissa is a density, in which a notch between data expressing a sea area and data expressing a ship is sought. The notch is divided by an initialized threshold level. For example, the picture is converted into a binary picture in which a sea area is set to 0 and a ship is set to 1.

Description

【発明の詳細な説明】Detailed Description of the Invention

【0001】[0001]

【産業上の利用分野】本発明は、画像処理を施して、船
や人や車等の監視を行う監視装置に関するものであり、
特に港の船舶入出港を監視する上で必要とされる船舶の
接近を自動的に探知する監視装置に関する。
BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a surveillance device for subjecting a ship, a person, a car or the like to image processing,
In particular, the present invention relates to a monitoring device that automatically detects the approach of a ship, which is required to monitor the entry and exit of a ship at a port.

【0002】[0002]

【従来の技術】船舶入出港の監視の概念を図6に示す。
現在、港に入出港する所定トン数以上の船舶に対して港
湾内における停泊料金の徴収等を目的として、船名及び
入出港時刻を監視所から監視、記録を行っている。この
際、従来では、沿岸レーダを利用し、海上船舶の接近に
対する監視を行なっていた。
2. Description of the Related Art The concept of monitoring the arrival and departure of ships is shown in FIG.
At present, for the purpose of collecting berth charges for ships with a predetermined tonnage or more entering and leaving the port, the ship name and the time of arrival and departure are monitored and recorded from the monitoring station. At this time, conventionally, coastal radars have been used to monitor the approach of marine vessels.

【0003】ところが、沿岸レーダは、海面の波による
レーダ波散乱を原因とする誤認識が多く、このため、実
用上ほとんど使用不可能であった。したがって、実際に
は、監視員が直接目視による監視を行い、常時、領海を
監視し続けなければならず、しかも、防波堤や、小島な
どの特殊な場所での監視となるため、労働条件として非
常に厳しいものがあった。
However, coastal radars are often misrecognized due to radar wave scattering due to waves on the surface of the sea, which makes them practically unusable. Therefore, in reality, the observer must directly monitor the territorial waters by direct visual observation, and at a special place such as a breakwater or a small island, it is a very difficult working condition. There was a tough one.

【0004】[0004]

【発明が解決しようとする課題】以上説明したように、
従来の船舶入出港監視システムにおいて、まず、沿岸レ
ーダによる監視では海面によるレーダ波散乱のために実
用上ほとんど使用不可能であり、また、直接人間による
監視では監視員が常時、検知領域に集中しなければなら
ず、このため長時間の監視には限界があるという難点が
あった。
As described above,
In the conventional ship entry / departure monitoring system, first, coastal radar monitoring is practically unusable due to radar wave scattering from the sea surface, while direct human monitoring constantly concentrates on the detection area. Therefore, there is a problem that there is a limit to long-time monitoring.

【0005】本発明は、上記欠点を考慮してなされたも
ので、自動的に船舶の接近を検知し、船舶の接近を知ら
せる出力表示が示された時のみ、監視に集中すればよ
く、また、誤認を最少限に抑える監視装置を提供するこ
とを目的とする。
The present invention has been made in consideration of the above-mentioned drawbacks, and it suffices to concentrate on monitoring only when an approach display of a ship is automatically detected and an output display informing the approach of the ship is displayed. , It aims at providing the monitoring device which suppresses misidentification to the minimum.

【0006】[0006]

【課題を解決するための手段】監視領域を撮像する撮像
装置と、この撮像装置から取得した画像に幾何変換処理
を施し、この画像上の任意の場所における物理長を等し
くする幾何補正装置と、この幾何補正装置により取得し
た幾何補正画像を所定のスレッショルドでn個の信号に
区分けすることにより、前記幾何補正画像をn値化する
差分判断装置と、この差分判断装置から得られたn値画
像から、目的とする対象物の大きさを判別する判別装置
と、前記各装置の全体制御を行う制御装置とを具備する
ことを特徴とする監視装置を提供する。
An image pickup device for picking up an image of a surveillance area, and a geometric correction device for subjecting an image acquired from this image pickup device to geometrical conversion processing so as to equalize physical lengths at arbitrary locations on the image, A difference determination device for converting the geometric correction image into n signals by dividing the geometric correction image acquired by the geometric correction device into n signals at a predetermined threshold, and an n-valued image obtained from the difference determination device. Therefore, there is provided a monitoring device comprising a discriminating device for discriminating the size of a target object and a control device for controlling the respective devices as a whole.

【0007】[0007]

【作用】上記構成による監視装置では、撮像装置により
撮像された画像を、幾何補正装置により、幾何補正する
ため、監視する対象物と撮像装置との、画像上の距離の
誤差に影響されずに、対象物の接近を正確に検知するこ
とができる。
In the monitoring device having the above structure, the image captured by the image pickup device is geometrically corrected by the geometric correction device, and therefore, the error in the distance between the object to be monitored and the image pickup device is not affected. It is possible to accurately detect the approach of the object.

【0008】さらに、差分処理装置では、対象物を他の
不要部分から抽出するn値化処理を行い、そして、判別
装置では、このn値化処理の結果取得したn値画像にお
いて、縦、横方向への画像の足し込みをし、この縦と横
方向の大きさから対象物のサイズ判断を行うため、検知
領域内のより確実な検知が可能となる。
Further, the difference processing device performs an n-valued process for extracting the object from other unnecessary parts, and the discriminating device performs vertical and horizontal processing on the n-valued image obtained as a result of the n-valued process. Since the image is added in the direction, and the size of the object is determined based on the size in the vertical and horizontal directions, more reliable detection in the detection area becomes possible.

【0009】[0009]

【実施例】以下、本発明の実施例について、図面を参照
して詳細に説明する。本発明による監視装置の構成を表
すブロック図を図1に示す。撮像装置11は船舶の接近
を検知すべき海域を撮像する。この撮像装置11は、例
えばCCDカメラを用い、このCCDカメラから出力さ
れたNTSC信号は、赤、緑、青の三原色に分離され、
色濃度を例えば、8bitにA/D変換(アナログ・デ
ジタル変換)し、ディジタル濃淡画像として幾何補正装
置12に入力する。撮像装置11が撮像した画像の任意
の場所における海面上での長さと、実際の海面上におけ
る物理的な長さでは、撮像装置11からの距離によって
その大きさが異なるため、幾何補正装置12は、この補
正を行うものである。このとき、陸地などの検知領域外
の範囲は、あらかじめ、マスキングをしている。図2
に、この補正処理の概念を示す。また、図3にその変換
モデルを示し,以下で,幾何変換処理について詳細に説
明する。
Embodiments of the present invention will now be described in detail with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the monitoring device according to the present invention. The image pickup device 11 picks up an image of a sea area where the approach of a ship is to be detected. The image pickup device 11 uses, for example, a CCD camera, and the NTSC signal output from the CCD camera is separated into three primary colors of red, green, and blue.
The color density is A / D converted (analog / digital conversion) to, for example, 8 bits, and is input to the geometric correction device 12 as a digital grayscale image. Since the size of the image captured by the imaging device 11 on the sea surface at an arbitrary position and the actual physical length on the sea surface varies depending on the distance from the imaging device 11, the geometric correction device 12 , This correction is performed. At this time, areas outside the detection area, such as land, are masked in advance. Figure 2
Shows the concept of this correction processing. The transformation model is shown in FIG. 3, and the geometric transformation process will be described in detail below.

【0010】図3において、撮像装置11の視点Z0
ら撮像装置11の見込む範囲410〜490 は、海であ
るxy平面に投影した範囲411 〜491 で示される。
このxy平面への投影図411 〜491 を撮像し、ディ
ジタル画像412 〜492 とする。このとき、平面x2
2 に存在するディジタル画像上の1画素は、平面x1
1 の海面上の矩形領域に対応し、撮像装置11からの
距離の関数として物理長が変化している。
In FIG. 3, the range 41 0 to 49 0 that the image pickup apparatus 11 can see from the viewpoint Z 0 of the image pickup apparatus 11 is indicated by ranges 41 1 to 49 1 projected on the xy plane which is the sea.
The projection view 41 1-49 1 to this xy plane captured, the digital image 41 2-49 2. At this time, the plane x 2
One pixel on the digital image existing in y 2 is a plane x 1
The physical length changes as a function of the distance from the imaging device 11, corresponding to the rectangular area on the sea surface of y 1 .

【0011】幾何補正装置22での幾何変換処理は、ア
ドレス変換テーブルを準備し、これをメッシュ状に切
り、行と例を対応させて、変換を行なうテーブル・ルッ
クアップ処理の他、あるいは、直線上にある点を例え
ば、曲線f=ax3 +bx2 +cx+d(ただしa.
b.cは定数)上に変換する等の方法により幾何変換処
理を行う。これらの幾何変換処理により、撮像画像上の
場所によって異なる長さは補正され、等しくなる。
In the geometric conversion processing in the geometric correction device 22, an address conversion table is prepared, this is cut into a mesh shape, and a table and a lookup processing for performing conversion by correlating rows with examples, or straight lines. The point on the top is, for example, the curve f = ax 3 + bx 2 + cx + d (where a.
b. The geometric conversion process is performed by a method such as conversion to (c is a constant). By these geometric conversion processes, the lengths that differ depending on the location on the captured image are corrected and become equal.

【0012】次に、幾何補正装置12の出力画像は、差
分判断装置14へ入力され、2値化処理が行なわれる。
この2値化処理は、まず、図4に示すように幾何補正画
像(a)を縦軸を度数とし、横軸を濃度とするヒストグ
ラム(b)に表し、このヒストグラム(b)において、
海域を表現するデータと船舶を表現するデータとの間の
谷を探す。この谷を制御装置17にてあらかじめ、初期
設定された閾値A(threshold)で区切る。そ
して、例えば、このスレッショルドAにより区分された
海域部分のデータを0(黒)とし、船体部分を1(白)
として幾何補正画像(a)を黒と白の2色による2値画
像(c)に変換する。なお、図4の(c)は幾何補正画
像(a)を2値化処理した2値画像の切り出し図となっ
ている。ところが、季節、天候、時間帯によって太陽光
の海面上での反射状態から、画像処理に影響を与え、2
値化処理上で誤認識を発生させてしまう可能性があるた
め、検知領域設定装置13は、撮像装置11が海面上の
どのエリアへの船舶の入出港を検知するか、適当なエリ
アを設定するものである。これにより、海面上の時とと
もに変化する環境の変化を察知し、誤認識を大幅に減ら
すことができる。 また、2値化処理を行う上で、スレ
ッショルドAは環境の変化に対応して幾何補正画像
(a)から算出されたヒストグラム(b)より、自動的
に、例えば、蓄積したノウハウ、制御装置17による初
期設定に基づき適値を設定できるようにし、誤認識を避
ける。
Next, the output image of the geometric correction device 12 is input to the difference determination device 14 and binarized.
In this binarization processing, first, as shown in FIG. 4, the geometrically corrected image (a) is represented in a histogram (b) in which the vertical axis represents frequency and the horizontal axis represents density. In this histogram (b),
Find the valley between the data that represents the ocean and the data that represents the ship. The valley is divided by the controller 17 in advance by a threshold value A (threshold) that is initially set. Then, for example, the data of the sea area sectioned by this threshold A is set to 0 (black) and the hull section is set to 1 (white).
The geometrically corrected image (a) is converted into a binary image (c) with two colors of black and white. It should be noted that FIG. 4C is a cutout diagram of a binary image obtained by binarizing the geometrically corrected image (a). However, depending on the season, weather, and time of day, the reflection of sunlight on the sea surface may affect image processing.
Since there is a possibility that erroneous recognition may occur in the binarization process, the detection area setting device 13 sets an appropriate area to which area on the sea surface the imaging device 11 detects the entry / exit of a ship. To do. This makes it possible to detect changes in the environment that change over time on the sea surface and significantly reduce false recognition. Further, in performing the binarization process, the threshold A is automatically calculated from the histogram (b) calculated from the geometrically corrected image (a) corresponding to the change of the environment, for example, the accumulated know-how and the control device 17 Allows to set an appropriate value based on the initial setting by to avoid erroneous recognition.

【0013】次に、差分判断装置14の出力である2値
画像(c)は、船体判別装置15に入力される。ここで
は、前記2値画像(c)の「1」の部分が表現する船体
シルエットに対して、その外接長方形から海面上の高
さ、及び長さを求め所定サイズ以上の船舶であるかを判
断する。このとき、マストのような突起物による船舶サ
イズの誤判断を防ぐため、図5のように、縦及び横の一
方向で画像を切ったときの「1」の度数をカウントし、
グラフに表す。続いて、このカウント処理によって得た
グラフを所定のスレッショルドで切ることにより船舶の
サイズを決定する。図5においては、レベルα、βがそ
れぞれスレッショルドを表わし、このとき、abが船舶
の高さ、cdが船舶の長さを示している。これにより、
船舶サイズの情報を正確に得ることができる。
Next, the binary image (c) output from the difference determination device 14 is input to the hull determination device 15. Here, with respect to the hull silhouette represented by the portion "1" of the binary image (c), the height above the sea surface and the length are obtained from the circumscribed rectangle, and it is determined whether the ship is a predetermined size or more. To do. At this time, in order to prevent misjudgment of the ship size due to a projection such as a mast, as shown in FIG. 5, the frequency of “1” when the image is cut in one of the vertical and horizontal directions is counted,
It is shown in the graph. Subsequently, the size of the ship is determined by cutting the graph obtained by this counting process at a predetermined threshold. In FIG. 5, levels α and β respectively represent thresholds, where ab represents the height of the ship and cd represents the length of the ship. This allows
It is possible to accurately obtain information on the ship size.

【0014】出力表示装置16では、船体判別装置15
の判別結果に従い、例えば所定サイズ以上の船舶が港湾
を入出港した場合ブザーと船舶の進行方向を示す矢印を
点滅させ監視員に警告を行う。
In the output display device 16, the hull identification device 15
According to the determination result of (3), for example, when a ship of a predetermined size or larger enters or leaves the port, the buzzer and the arrow indicating the traveling direction of the ship are blinked to warn the monitoring staff.

【0015】なお、各装置で行われる撮像範囲の設定、
初期値設定、所定サイズの船舶の判断等の全体制御は、
制御装置17にて行う。上述してきた監視装置では、検
知のための処理に画像処理を用いているので、従来の沿
岸レーダにあった海面上のレーダ波散乱等による誤認識
を大幅に減らすことが可能となる。さらに、本装置では
画像処理に幾何補正装置を用いているため、遠近の距離
により生ずる画像処理上の誤差を補正することができ、
また、船舶サイズの判断には船体シルエットの縦、横方
向のカウント処理を用いているのでマスト等の突起物に
よる誤判断を回避することもできる。
It should be noted that the setting of the imaging range performed by each device,
Overall control such as initial value setting and determination of ships of a predetermined size
The control device 17 performs this. In the above-described monitoring device, since image processing is used for the detection process, it is possible to significantly reduce erroneous recognition due to radar wave scattering on the sea surface that is present in the conventional coastal radar. Further, since the geometric correction device is used for image processing in this device, it is possible to correct an error in image processing caused by a distance.
In addition, since the counting process in the vertical and horizontal directions of the hull silhouette is used for the determination of the vessel size, it is possible to avoid an erroneous determination due to a protrusion such as a mast.

【0016】なお、幾何補正画像(a)から算出された
ヒストグラム(b)は、例えばCCDカメラのちょっと
した絞り具合の違い、環境の変化からヒストグラムの平
均、分散の度合が微妙に変化してしまう。そこで、この
平均値、分散値を一定レベルに安定させるために濃度正
規化装置を設けてもよい。
In the histogram (b) calculated from the geometrically corrected image (a), for example, the degree of average and variance of the histogram slightly changes due to a slight difference in aperture of the CCD camera and changes in the environment. Therefore, a density normalization device may be provided to stabilize the average value and the dispersion value at a constant level.

【0017】また、撮像画像のノイズが激しい場合、画
像のノイズを除去するノイズ除去装置を設けることで、
さらに安定した画像を取得することができる。また、上
述した実施例では、2値画像(c)を得るためにヒスト
グラムの谷からスレッショルドを決めているが、何枚か
の撮像画像の平均値からそのスレッショルドの傾向を判
断することで、より安定した適正なスレッショルドを設
定することができる。
Further, when the noise of the picked-up image is severe, by providing a noise removing device for removing the noise of the image,
A more stable image can be acquired. Further, in the above-described embodiment, the threshold is determined from the valley of the histogram in order to obtain the binary image (c), but by determining the tendency of the threshold from the average value of several captured images, A stable and appropriate threshold can be set.

【0018】また、差分判断装置14では、濃度を2つ
の信号に区分けする2値化処理を行っているが、さら
に、例えば信号「0」、「1」、「2」の3値化処理を
考え、信号「1」のみをカウントしたものや、信号
「2」のみを換算し得られたグラフを識別することで、
目的とする対象物の大きさを検知することが可能であ
る。さらに、多値の場合でも同様にして実施することが
できる。
Further, although the difference judgment device 14 performs the binarization process for dividing the density into two signals, for example, the ternarization process of the signals “0”, “1”, “2” is further performed. In consideration, by identifying the one obtained by counting only the signal “1” or the graph obtained by converting only the signal “2”,
It is possible to detect the size of the target object. Further, even in the case of multiple values, it can be carried out in the same manner.

【0019】なお、上記実施例では、監視装置が監視す
る対象物として主に、船舶を例に上げ説明してきたが、
本発明は人や車等の検知にも適用できるものであり、船
舶の検知のみに限るものではない。
In the above embodiment, the ship has been mainly described as an object to be monitored by the monitoring device.
The present invention can be applied to detection of people, vehicles, etc., and is not limited to detection of ships.

【0020】[0020]

【発明の効果】本発明によれば、例えば港湾内を入出港
する船舶の検知を、画像処理にて行うため、従来、沿岸
レーダにあった海面によるレーダ波散乱を原因とする船
舶の誤認識を補完することができ、監視業務の効率化を
図ることが可能となる。
According to the present invention, for example, a vessel entering or leaving a harbor is detected by image processing. Therefore, the vessel is erroneously recognized due to radar wave scattering due to the sea surface, which has been present in coastal radar. Can be supplemented, and the efficiency of monitoring work can be improved.

【図面の簡単な説明】[Brief description of drawings]

【図1】本発明における船舶接近検知装置の構造を示す
ブロック図。
FIG. 1 is a block diagram showing the structure of a ship approach detection device according to the present invention.

【図2】幾何変換補正を表す図。FIG. 2 is a diagram showing geometric transformation correction.

【図3】幾何変換モデルを示す図。FIG. 3 is a diagram showing a geometric transformation model.

【図4】2値画像への変換モデルを示す図。FIG. 4 is a diagram showing a conversion model into a binary image.

【図5】縦横方向へのカウント処理を示す図。FIG. 5 is a diagram showing a count process in vertical and horizontal directions.

【図6】従来の入出港監視の概念を示す図。FIG. 6 is a diagram showing a concept of conventional port entry / exit monitoring.

【符号の説明】[Explanation of symbols]

11…撮像装置 12…幾何補正装置 13…検知領域設定装置 14…差分判断装置 15…判別装置 16…出力表示装置 17…制御装置 11 ... Imaging device 12 ... Geometric correction device 13 ... Detection area setting device 14 ... Difference determination device 15 ... Discrimination device 16 ... Output display device 17 ... Control device

Claims (2)

【特許請求の範囲】[Claims] 【請求項1】 監視領域を撮像する撮像装置と、この撮
像装置から取得した画像に幾何変換処理を施す幾何補正
装置と、この幾何補正装置により取得した幾何補正画像
を所定のスレッショルドでn個の信号に区分けすること
により、前記幾何補正画像をn値化する差分判断装置
と、この差分判断装置から得られたn値画像から、目的
とする対象物の大きさを判別する判別装置と、前記各装
置の全体制御を行う制御装置とを具備することを特徴と
する監視装置。
1. An image pickup device for picking up an image of a monitoring area, a geometric correction device for performing a geometric conversion process on an image obtained from this image pickup device, and n geometric correction images obtained by this geometric correction device at a predetermined threshold. A difference determination device that divides the geometrically corrected image into n-values by dividing the signal into signals, and a determination device that determines the size of the target object from the n-valued image obtained from the difference determination device; A monitoring device comprising: a control device for controlling the overall operation of each device.
【請求項2】 前記判別装置は、前記n値画像を縦及び
横方向で任意の信号をカウントし、このカウント処理し
た画像を所定のスレッショルドで区分けすることによ
り、目的とする対象物の大きさを判別することを特徴と
する請求項1記載の監視装置。
2. The size of the target object is determined by the discrimination device by counting arbitrary signals in the vertical and horizontal directions of the n-valued image and dividing the counted image by a predetermined threshold. The monitoring device according to claim 1, wherein the monitoring device discriminates
JP10794993A 1993-05-10 1993-05-10 Supervisory equipment Pending JPH06319141A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP10794993A JPH06319141A (en) 1993-05-10 1993-05-10 Supervisory equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP10794993A JPH06319141A (en) 1993-05-10 1993-05-10 Supervisory equipment

Publications (1)

Publication Number Publication Date
JPH06319141A true JPH06319141A (en) 1994-11-15

Family

ID=14472141

Family Applications (1)

Application Number Title Priority Date Filing Date
JP10794993A Pending JPH06319141A (en) 1993-05-10 1993-05-10 Supervisory equipment

Country Status (1)

Country Link
JP (1) JPH06319141A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0973543A (en) * 1995-09-06 1997-03-18 Toshiba Corp Moving object recognition method/device
JP2000353234A (en) * 1999-06-10 2000-12-19 Mitsubishi Space Software Kk Sea extraction processing method from satellite picture
JP2002501234A (en) * 1998-01-08 2002-01-15 シャープ株式会社 Human face tracking system
JP2002352340A (en) * 2001-05-30 2002-12-06 Hitachi Ltd Image monitoring device
JP2021072003A (en) * 2019-10-31 2021-05-06 りんかい日産建設株式会社 Warning device, warning method, and warning program for safe navigation

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0973543A (en) * 1995-09-06 1997-03-18 Toshiba Corp Moving object recognition method/device
JP2002501234A (en) * 1998-01-08 2002-01-15 シャープ株式会社 Human face tracking system
JP2000353234A (en) * 1999-06-10 2000-12-19 Mitsubishi Space Software Kk Sea extraction processing method from satellite picture
JP2002352340A (en) * 2001-05-30 2002-12-06 Hitachi Ltd Image monitoring device
JP2021072003A (en) * 2019-10-31 2021-05-06 りんかい日産建設株式会社 Warning device, warning method, and warning program for safe navigation

Similar Documents

Publication Publication Date Title
CN108806334A (en) A kind of intelligent ship personal identification method based on image
CN107578012B (en) Driving assistance system for selecting sensitive area based on clustering algorithm
CN109409283A (en) A kind of method, system and the storage medium of surface vessel tracking and monitoring
CN108229342B (en) Automatic sea surface ship target detection method
CN111123251B (en) Target object detection method and device of radar
CN110866926B (en) Infrared remote sensing image rapid and fine sea-land segmentation method
Bloisi et al. Camera based target recognition for maritime awareness
KR102257006B1 (en) Ship Collision Avoidance Autonomous Avoidance System using Deep Learning
CN113112540A (en) Method for positioning ship image target by using AIS (automatic identification system) calibration CCTV (continuous transmission television) camera in VTS (vessel traffic service) system
Kaido et al. Examination of automatic detection and tracking of ships on camera image in marine environment
CN111428573A (en) Infrared weak and small target detection false alarm suppression method under complex background
JPH06319141A (en) Supervisory equipment
CN103810487A (en) Method and system for target detection and identification of aerial ocean images
CN113657250A (en) Flame detection method and system based on monitoring video
JP2612662B2 (en) Intruder identification system
CN116665120A (en) Tornado formation recognition and early warning system and method based on video
CN114863373A (en) Offshore unmanned platform monitoring method and offshore unmanned platform
CN106980861A (en) A kind of ship method for quickly identifying based on fusion feature
CN112712454B (en) Automatic snapshot system of boats and ships black cigarette suitable for ship lock
JP2000125288A (en) Object tracking method and object tracking device
JP4686773B2 (en) Moving object recognition method and moving object recognition apparatus
CN102842196A (en) Infrared thermal imaging all-weather anti-pirate on-board alarming system
CN109886133A (en) A kind of ship detection method and system based on remote sensing image
JP2000353234A (en) Sea extraction processing method from satellite picture
CN101882224A (en) Method for reorganizing and identifying multiple images and image capturing and identifying system