Image processing apparatus

• US 6,430,303 B1
• Filed: 05/04/2000
• Issued: 08/06/2002
• Est. Priority Date: 03/31/1993
• Status: Expired due to Fees

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Egawa, Hiroichi, Shiohara, Morito, Naoi, Satoshi
• Primary Examiner(s): CHANG, JON CARLTON
• Application Number:
  US09/564,535
• Publication Number:
  US 20020126875A1
• Time in Patent Office: 824 Days
• Field of Search: 382/104, 382/106, 348/148, 348/149, 340/937, 701/117
• US Class Current: 382/104
• CPC Class Codes: G06T 7/254 involving subtraction of images

Abstract

An image processing apparatus for extracting the specified objects has a background image extract unit for extracting a background; a first average background extract unit which extracts an image that includes a plurality of stationary and moving objects each having a speed not higher than a predetermined first speed and also the background; a second average background extract unit which extracts an image that includes the stationary and moving objects each having a speed not higher than a predetermined second speed and also the background; a first difference-calculation processing unit which calculates a difference between an output from the background image extract unit and an output from the first average background extract unit as a first speed image; a second difference-calculation processing unit which calculates a difference value between two outputs from the first and second average background extract units as a second speed image; and a third difference-calculation processing unit which calculates a difference value between an original image and either one of outputs from the first and second average background extract units as a third speed image.

Claims

1. An image processing apparatus for calculating a distance between two moving objects contained in time series images which are captured at different sampling times, comprising:

an image-input unit which inputs said image including a background and a plurality of objects;

a marker holding unit which records location information of a plurality of markers in said background;

a moving object extract unit which extracts a plurality of moving objects;

a moving object/marker time-series table making unit which creates a time-series table of said plurality of moving objects and said markers, each existing between two different moving objects;

a marker extract unit which extracts the markers existing between two different moving objects; and

a distance measuring unit which calculates a distance between two different moving objects, on the basis of respective sizes of the extracted markers existing therebetween.

2. An image processing apparatus as set forth in claim 1, wherein:

a plurality of markers, which are not connected with each other, are provided in said background by said marker holding unit; and

said apparatus further comprises;

a connected-area position/shape calculating unit which calculates a size, a shape, and a number of said markers;

a marker dictionary unit which has a marker dictionary for storing in advance the size and the shape of said markers; and

a marker collating unit which collates said marker dictionary and discriminates whether or not a portion of a marker calculated by said connected-area position/shape calculating unit is a marker which overlaps a moving object, and

wherein said apparatus is adapted to determine a number of the markers which can be identified as a result of the collation in said marker collating unit, and to calculate said distance between said two moving objects.

3. An image processing apparatus as set forth in claim 2, wherein said apparatus is adapted to track a number of markers existing between two different moving objects, and to calculate said distance between the two different moving objects.

4. An image processing apparatus for calculating a distance between two cars in a case where a plurality of cars are contained in a time series of images which are captured at different sampling times as moving objects, comprising:

a marker holding unit which locates a plurality of white lines which are perpendicular to a direction in which the cars move, with equal spaces between adjacent white lines, as a plurality of markers;

a marker dictionary unit which has a marker dictionary for providing in advance a value of a length and breadth of each of said white lines, and also storing in advance said value of said length and breadth thereof;

a connected-area extract unit which extracts some areas which are obtained by continuous white lines existing at positions overlapped with each of said moving objects, and labels said extracted areas with a common label;

a connected-area position/shape calculating unit which calculates a size and a shape of the labeled areas respectively corresponding to regions formed by said continuous white lines, and confirms the size of the white lines in said regions formed by said continuous white lines and the size of shape corresponding to each of the thus labeled areas, in accordance with the value of a length and breadth of each of the white lines;

a moving object/marker correlating unit which tracks a specified region formed by said continuous white lines; and

a distance measuring unit which extracts a number of said continuous white lines from the white lines confirmed by said connected-area position/shape calculating unit, and calculates said distance between said two moving objects on the basis of a total sum of spaces between said continuous white lines.

5. An image processing apparatus as set forth in claim 4,

wherein said connected-area position/shape calculating unit is adapted to separate each of said connected areas into a plurality of connected components, and to obtain a value of a projection for each of the connected components,

wherein said connected-area position/shape calculating unit is adapted to calculate a value of length and breadth for each of said connected areas, and to compare a product of the value of said length and the value of said breadth with a total sum of the value of each projection, and

wherein said connected-area position/shape calculating unit is adapted to discriminate whether each of said connected areas has a rectangular shape.

6. An image processing apparatus as set forth in claim 4, wherein said connected-area position/shape calculating unit is adapted to extract a contour from a two-dimensional image in which binary code processing is carried out and color extraction processing is carried out, and to obtain a maximum and minimum value in x-component and y-component directions of said contour and also the value of a length of a circumference of said contour, and

wherein said connected-area position/shape calculating unit is adapted to compare said maximum and minimum value and said value of said length of circumference with values stored in advance, and to conclude that said contour has the rectangular shape, in a case where said maximum and minimum value and said value of said length of circumference conform to said values stored in advance.

7. An image processing apparatus as recited in claim 6, wherein said image processor performs one of determining distances between the objects, determining locations of the objects and determining sizes of the objects.