JP2000125288A5 - - Google Patents

Download PDF

Info

Publication number
JP2000125288A5
JP2000125288A5 JP1998289864A JP28986498A JP2000125288A5 JP 2000125288 A5 JP2000125288 A5 JP 2000125288A5 JP 1998289864 A JP1998289864 A JP 1998289864A JP 28986498 A JP28986498 A JP 28986498A JP 2000125288 A5 JP2000125288 A5 JP 2000125288A5
Authority
JP
Japan
Prior art keywords
detected
area
object tracking
detection
types
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
JP1998289864A
Other languages
Japanese (ja)
Other versions
JP2000125288A (en
JP4302801B2 (en
Filing date
Publication date
Application filed filed Critical
Priority to JP28986498A priority Critical patent/JP4302801B2/en
Priority claimed from JP28986498A external-priority patent/JP4302801B2/en
Publication of JP2000125288A publication Critical patent/JP2000125288A/en
Publication of JP2000125288A5 publication Critical patent/JP2000125288A5/ja
Application granted granted Critical
Publication of JP4302801B2 publication Critical patent/JP4302801B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Description

【特許請求の範囲】
【請求項1】
少なくとも2以上の画像の比較を行うことにより画像中の物体を検出し、検出された物体を追跡する物体追跡方法において、
前記検出された物体の検出領域の形状または面積の少なくともいずれかに基いて、検出物体を複数の種類に分類し、該複数の種類に分類された検出物体から、追跡すべき物体を選択し、該選択された物体を追跡対象物体として追跡することを特徴とする物体追跡方法。
【請求項2】
請求項1記載の物体追跡方法において、
前記検出物体の領域の形状に基いて検出物体の種類を分類する方法は、検出物体の領域の外接矩形の横の長さと縦の長さとの比率によって分類することを特徴とする物体追跡方法。
【請求項3】
請求項1記載の物体追跡方法において、
前記検出物体の領域の形状に基いて検出物体の種類を分類する方法は、検出物体の領域の縦の長さによって分類することを特徴とする物体追跡方法。
【請求項4】
請求項3記載の物体追跡方法において、
前記検出物体の領域の投影ヒストグラムを計算する投影ヒストグラム計算ステップを設け、前記投影ヒストグラム計算ステップによって算出した投影ヒストグラムの最大値を前記検出物体の領域の縦の長さとすることを特徴とする物体追跡方法。
【請求項5】
請求項記載の物体追跡方法において、
前記検出領域の形状に基づいて検出物体の種類を分類する方法は、前記検出物体の領域の投影ヒストグラムの値が所定のしきい値以上の大きさの連続する投影画素数によって分類することを特徴とする物体追跡方法。
【請求項6】
請求項3記載の物体追跡方法において、
前記検出物体の領域の投影ヒストグラムを計算する投影ヒストグラム計算ステップを設け、投影ヒストグラムの値が所定のしきい値以上の大きさの連続する投影画素数によって、前記検出物体の領域の種類を更に分類することを特徴とする物体追跡方法。
【請求項7】
請求項1記載の物体追跡方法において、
前記検出物体の領域の面積に基いて検出物体の種類を分類する方法は、検出物体の領域の外接矩形の面積と検出物体の領域の面積との比率によって分類することを特徴とする物体追跡方法。
【請求項8】
請求項1乃至請求項7記載の少なくとも1つの物体追跡方法において、
前記複数の種類に分類された検出物体少なくとも1つの種類の検出物体を特定の物体として検出し、前記検出した特定の物体を除外した検出物体を追跡対象物体として追跡することを特徴とする物体追跡方法。
【請求項9】
請求項1乃至請求項8記載の少なくとも1つの物体追跡方法において、
前記複数の種類に分類された検出物体の情報を複数フレームにわたって記憶し、それぞれの検出物体毎に前記複数フレームの情報に基いて、前記それぞれの検出物体の種類を再度分類することを特徴とする物体追跡方法。
【請求項10】
カメラと、該カメラからの入力信号を画像信号に変換する画像入力インターフェース手段と、該変換された画像信号と追跡対象物体の写っていない基準背景画像との画素毎の輝度値の差を求めその差分値の大きい領域を侵入物体として検出する検出手段と、CPUと、メモリとを有し、前記の画像信号から追跡対象物体を抽出することによって物体追跡を行う物体追跡装置において、
前記検出手段によって検出された検出領域の形状または面積の少なくともいずれかに基いて検出領域を複数の種類に分類する手段を有し、追跡対象物体を追跡することを特徴とする物体追跡装置。
【請求項11】
請求項10記載の物体追跡装置において、
前記複数の種類に分類された検出領域の少なくとも1つの種類の検出領域を物体追跡対象から除外することを特徴とする物体追跡装置。
【請求項12】
請求項10または請求項11記載の物体追跡装置において、
前記複数の種類に分類された検出物体の情報をそれぞれ複数フレームにわたって記憶する手段と、該記憶手段が記憶したそれぞれの検出物体毎の複数フレームの情報に基いて、前記それぞれの物体を再度複数の種類に再度分類することを特徴とする物体追跡装置。
【請求項13】
カメラと、該カメラが撮像した画像を入力する画像入力I/Fと、該画像入力I/Fから入力された画像を蓄積する画像メモリと、物体追跡監視装置の動作のプログラムを記憶しているプログラムメモリと、該プログラムメモリに保持されている前記プログラムに従って前記物体追跡装置を動作させるCPUと、前記画像メモリに蓄積された画像の解析を行うワークメモリと、少なくとも音、可視光、振動のいずれかを表示し、人体または補助動物が感知可能な信号を発生する警告表示手段と、監視モニタと、前記ワークメモリの解析結果に対応して前記CPUの指示によって前記警告表示手段に警告を表示させる信号を伝達する出力I/Fと、前記ワークメモリの解析結果に対応して前記CPUの指示によって前記監視モニタに表示させる画像を送る画像出力I/Fと、前述の構成要素同士を接続するデータバスを有する物体追跡装置において、
前記カメラより得られた入力画像と対象物体の写っていない基準背景画像との画素毎の輝度値の差分を計算する差分処理手段と、該差分処理手段によって計算された輝度値の差分が所定のしきい値以上の画素を物体の存在する画素とし、該物体の存在する画素の領域を検出する物体検出手段と、該物体検出手段によって検出された検出物体の領域の外接矩形の形状が横長で、かつ、検出物体の領域の面積が外接矩形領域の面積に占める割合に基いて検出物体を分類する第1の分類手段と、前記検出物体の領域の縦方向の大きさに基いて検出物体を分類する第2の分類手段と、該検出領域内の物体の存在する画素に対して縦方向の投影ヒストグラムを計算する縦方向投影ヒストグラム計算手段と、該縦方向投影ヒストグラム計算手段によって計算された投影ヒストグラムから所定の最大の大きさよりも大きい投影画素を求める連続投影画素算出手段と、該連続投影画素算出手段によって算出された連続する投影画素数に基いて検出物体を分類する第3の分類手段とを設け、前記第1の分類手段及び第2の分類手段及び第3の分類手段によって、追跡対象以外の検出物体を除外することによって誤検出を低減することを特徴とする物体追跡装置。
【請求項14】
請求項1から請求項13記載の物体追跡方法または物体追跡装置において、
前記複数の種類に分類する検出物体の1つの種類が波であることを特徴とする物体追跡方法。
[Claims]
[Claim 1]
In an object tracking method in which an object in an image is detected by comparing at least two or more images and the detected object is tracked.
Based on at least one of the shape or area of the detection area of the detected object, the detected object is classified into a plurality of types, and the object to be tracked is selected from the detected objects classified into the plurality of types. object tracking method characterized by tracking the selected object as the tracking target object.
2.
In the object tracking method according to claim 1,
The method of classifying the type of the detected object based on the shape of the region of the detected object is an object tracking method characterized by classifying by the ratio of the horizontal length and the vertical length of the circumscribed rectangle of the region of the detected object.
3.
In the object tracking method according to claim 1,
The method for classifying the types of detected objects based on the shape of the region of the detected object is an object tracking method characterized by classifying according to the vertical length of the region of the detected object.
4.
In the object tracking method according to claim 3,
An object tracking characterized in that a projection histogram calculation step for calculating the projection histogram of the region of the detected object is provided, and the maximum value of the projection histogram calculated by the projection histogram calculation step is the vertical length of the region of the detection object. Method.
5.
In the object tracking method according to claim 1,
The method of classifying the types of detected objects based on the shape of the detection area is characterized in that the value of the projection histogram of the area of the detection object is classified by the number of continuous projected pixels having a size equal to or larger than a predetermined threshold value. Object tracking method.
6.
In the object tracking method according to claim 3,
A projection histogram calculation step is provided to calculate the projection histogram of the region of the detection object, and the types of the region of the detection object are further classified according to the number of continuous projection pixels in which the value of the projection histogram is larger than a predetermined threshold value. An object tracking method characterized by doing so.
7.
In the object tracking method according to claim 1,
The method of classifying the type of the detected object based on the area of the area of the detected object is an object tracking method characterized by classifying by the ratio of the area of the circumscribing rectangle of the area of the detected object to the area of the area of the detected object. ..
8.
In at least one object tracking method according to claim 1 to 7.
Detection object classified into the plurality of types Object tracking characterized in that at least one type of detection object is detected as a specific object, and the detection object excluding the detected specific object is tracked as a tracking target object. Method.
9.
In at least one object tracking method according to claim 1 to 8.
The feature is that the information of the detected objects classified into the plurality of types is stored over a plurality of frames, and the types of the respective detected objects are reclassified for each detected object based on the information of the plurality of frames. Object tracking method.
10.
The difference in brightness value for each pixel between the camera, the image input interface means for converting the input signal from the camera into an image signal, and the converted image signal and the reference background image in which the tracked object is not shown is obtained. In an object tracking device having a detection means for detecting an area having a large difference value as an intruding object, a CPU, and a memory, and tracking the object by extracting the object to be tracked from the image signal.
An object tracking device comprising means for classifying a detection area into a plurality of types based on at least one of the shape or area of the detection area detected by the detection means, and tracking an object to be tracked.
11.
In the object tracking device according to claim 10,
Object tracking apparatus characterized by excluding at least one type of the detection area of the detection area are classified into the plurality of types from the object tracked.
12.
In the object tracking device according to claim 10 or 11.
Based on the means for storing the information of the detected objects classified into the plurality of types over a plurality of frames and the information of a plurality of frames for each detected object stored by the storage means, the respective objects are stored again in a plurality of frames. An object tracking device characterized by reclassifying into types.
13.
It stores a camera, an image input I / F for inputting an image captured by the camera, an image memory for storing an image input from the image input I / F, and an operation program of an object tracking and monitoring device. A program memory, a CPU that operates the object tracking device according to the program stored in the program memory, a work memory that analyzes an image stored in the image memory, and at least any of sound, visible light, and vibration. A warning display means that generates a signal that can be detected by a human body or an auxiliary animal, a monitoring monitor, and a warning display means that displays a warning according to an instruction from the CPU in response to an analysis result of the work memory. Data that connects the above-mentioned components to the output I / F that transmits a signal, the image output I / F that sends an image to be displayed on the monitoring monitor according to the instruction of the CPU in response to the analysis result of the work memory, and the data that connects the above-mentioned components. In an object tracking device with a bus
A difference processing means for calculating the difference in brightness value for each pixel between the input image obtained from the camera and the reference background image in which the target object is not captured, and the difference in brightness value calculated by the difference processing means are predetermined. The pixels above the threshold value are defined as the pixels in which the object exists, and the object detecting means for detecting the region of the pixel in which the object exists and the circumscribing rectangular shape of the region of the detected object detected by the object detecting means are horizontally long. In addition, the first classification means for classifying the detected object based on the ratio of the area of the detected object area to the area of the circumscribing rectangular area, and the detected object based on the vertical size of the detected object area. A second classification means for classifying, a vertical projection histogram calculation means for calculating a vertical projection histogram for a pixel in which an object exists in the detection region, and a projection calculated by the vertical projection histogram calculation means. A continuous projection pixel calculation means for obtaining projection pixels larger than a predetermined maximum size from a histogram, and a third classification means for classifying detected objects based on the number of continuous projection pixels calculated by the continuous projection pixel calculation means. The object tracking device is characterized in that false detection is reduced by excluding detected objects other than the tracking target by the first classification means, the second classification means, and the third classification means.
14.
In the object tracking method or object tracking device according to claim 1 to 13.
An object tracking method characterized in that one type of detected object classified into the plurality of types is a wave.

JP28986498A 1998-10-12 1998-10-12 Object tracking method and object tracking apparatus Expired - Fee Related JP4302801B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP28986498A JP4302801B2 (en) 1998-10-12 1998-10-12 Object tracking method and object tracking apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP28986498A JP4302801B2 (en) 1998-10-12 1998-10-12 Object tracking method and object tracking apparatus

Publications (3)

Publication Number Publication Date
JP2000125288A JP2000125288A (en) 2000-04-28
JP2000125288A5 true JP2000125288A5 (en) 2005-11-24
JP4302801B2 JP4302801B2 (en) 2009-07-29

Family

ID=17748757

Family Applications (1)

Application Number Title Priority Date Filing Date
JP28986498A Expired - Fee Related JP4302801B2 (en) 1998-10-12 1998-10-12 Object tracking method and object tracking apparatus

Country Status (1)

Country Link
JP (1) JP4302801B2 (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3997062B2 (en) * 2001-05-30 2007-10-24 株式会社日立製作所 Image monitoring device
GB2411229B (en) 2003-07-22 2006-04-12 Hitachi Int Electric Inc Object tracking method and object tracing apparatus
JP2006311099A (en) * 2005-04-27 2006-11-09 Matsushita Electric Ind Co Ltd Device and method for automatic tracking
JP4691570B2 (en) * 2008-02-29 2011-06-01 東芝テリー株式会社 Image processing apparatus and object estimation program
JP5759170B2 (en) * 2010-12-27 2015-08-05 キヤノン株式会社 TRACKING DEVICE AND ITS CONTROL METHOD
US10282622B2 (en) 2016-12-09 2019-05-07 Hitachi Kokusai Electric Inc. Marine intrusion detection system and method
CN111382627B (en) * 2018-12-28 2024-03-26 成都云天励飞技术有限公司 Method for judging peer and related products
JP6896307B1 (en) * 2020-07-28 2021-06-30 株式会社サイバーウェア Image judgment method and image judgment device

Similar Documents

Publication Publication Date Title
US6678413B1 (en) System and method for object identification and behavior characterization using video analysis
US6816184B1 (en) Method and apparatus for mapping a location from a video image to a map
US6404455B1 (en) Method for tracking entering object and apparatus for tracking and monitoring entering object
US7916944B2 (en) System and method for feature level foreground segmentation
US7123745B1 (en) Method and apparatus for detecting moving objects in video conferencing and other applications
JP5836095B2 (en) Image processing apparatus and image processing method
US20060170769A1 (en) Human and object recognition in digital video
US7982748B2 (en) Vehicle surroundings monitoring apparatus
JP6764481B2 (en) Monitoring device
US20090067716A1 (en) Robust and efficient foreground analysis for real-time video surveillance
EP2851841A2 (en) System and method of alerting a driver that visual perception of pedestrian may be difficult
JP2007310705A (en) Vehicle periphery monitoring device
US20150169980A1 (en) Object recognition device
JP2000125288A5 (en)
JP6991045B2 (en) Image processing device, control method of image processing device
US9064158B2 (en) Vehicle surroundings monitoring device
CN112101134B (en) Object detection method and device, electronic equipment and storage medium
WO2018110377A1 (en) Video monitoring device
JP3736836B2 (en) Object detection method, object detection apparatus, and program
JPH05300516A (en) Animation processor
JP2002218443A (en) Intruding object detecting method for automatically determining threshold for intruding object detection and intruding object monitor
JP2014006820A (en) Vehicle periphery monitoring device
Tupper et al. Pedestrian proximity detection using RGB-D data
JP2007280151A (en) Image analyzer, image analytical method, and program
JP2000082146A (en) Moving image processor