IMAGE PROCESSING APPARATUS

• US 20020126875A1
• Filed: 05/04/2000
• Published: 09/12/2002
• Est. Priority Date: 03/31/1993
• Status: Active Grant

• Current Assignee: Hiroichi Egawa, Morito Shiohara, Satoshi Naoi
• Original Assignee: Hiroichi Egawa, Morito Shiohara, Satoshi Naoi
• Inventors: Shiohara, Morito, Egawa, Hiroichi, Naoi, Satoshi
• Granted Patent: US 6,430,303 B1
• Time in Patent Office: Days
• 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 extracting one or a plurality of objects, in the case where a plurality of stationary objects and a plurality of moving objects are contained together as a group of objects in one image, comprising:

an image-input unit (1) which inputs an image including a background and a plurality of said objects;

a background image extract unit (2) which extracts and stores said background;

a first average background extract unit (3) which extracts an image that includes one or a plurality of said stationary objects or moving objects each having a speed not higher than a predetermined first speed and also includes said background;

a second average background extract unit (4) which extracts an image that includes one or a plurality of said stationary objects or moving objects each having a speed not higher than a predetermined second speed and also includes said background;

a first difference-calculation processing unit (5) which calculates a difference value between an output from said background image extract unit (2) and either one of outputs from said first average background extract unit (3), and then generates a first speed image;

a second difference-calculation processing unit (6) which calculates a difference value between respective outputs from said first and second average background extract unit (3, 4), and then generates a second speed image; and

a third difference-calculation processing unit (7) which calculates a difference value between an output from said image-input unit (1) and either one of outputs from said first and second average background extract unit (3, 4), and then generates a third speed image.

2. An image processing apparatus as set forth in claim 1, wherein said apparatus further comprises a plurality of local-area characteristic-amount extract processing units which deal with outputs from said image-input unit (1), each of said plurality of local-area characteristic-amount extract processing units including:

a local-area determining unit (11) which allocates said outputs from said image-input unit (1) to each of a plurality of local areas;

a labeling processing unit (13) which separates at least one object.from each of said plurality of local areas, by labeling the same object existing in each of said plurality of local areas; and

a characteristic-amount calculating unit (14) which calculates a plurality of characteristic-amounts for the thus labeled object in said plurality of local areas.

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

said apparatus is operative to calculate a difference between said background and an average background image at a low speed, and to extract one or a plurality of connected areas from a difference image obtained by the thus calculated difference, wherein;

said apparatus is operative to produce each projection for each of said connected areas, and to calculate each position of the corresponding object in accordance with said each projection, and to calculate a plurality of characteristic-amounts, which at least include the value of a length and breadth of said object or the value of an area of said object, wherein;

said apparatus is operative to estimate a change in said each position of said object and also a change in said characteristic-amounts of said object for every sampling time in time series, and wherein;

said apparatus is operative to determine said object as a stationary object, in the case where both of the change in said position of said object and the change in said characteristic-amounts thereof are small.

4. An image processing apparatus as set forth in claim 2, wherein, said apparatus further comprises local-area characteristic-amount extract units (8, 9 and 10) which respectively have said local-area characteristic-amount extract processing units, corresponding to said local areas, for every speed image which is output from each of said difference-calculation processing units (5, 6 and 7).

5. An image processing apparatus as set forth in claim 2, wherein said apparatus comprises a locus calculation unit (20) having a list making unit (20-2), which detects an existence of said object in each of said plurality of local areas in time series, on the basis of an output from each of said plurality of local-area characteristic-amount extract processing units, and which makes out a list concerning the result of the detection.

6. An image processing apparatus as set forth in claim 5, wherein said locus-calculation unit (20) includes a character analyzing unit (20-1) for making a locus of the same moving object, on the basis of a character concerning the shape of said moving object, which is selected among said characteristic-amounts calculated by said characteristic-amount calculating unit (14).

7. An image processing apparatus as set forth in claim 5, wherein said apparatus is adapted to set a plurality of local areas which are to be processed, and to check whether or not said moving object passes through each of said local processed areas, and to calculate the locus of the same moving object, in accordance with the character concerning the shape of said moving object and the time when said moving object passes through each of said local processed areas, and to discriminate an abrupt change in the speed of said moving object and an abrupt change in the direction thereof, and to identify said moving object in said image.

8. An image processing apparatus as set forth in claim 5, wherein:

said apparatus is adapted to set a plurality of areas which are to be processed, in accordance with the size of a plurality of moving objects, and wherein;

said locus calculation unit (20) includes a list analyzing unit (20-3) for discriminating a locus of each of a plurality of small-scale cars in each of said local processed areas, and for recognizing a locus of the same moving object, even in the case where a large-scale car puts said plurality of small-scale cars out of sight.

9. An image processing apparatus as set forth in claim 6, wherein said apparatus is adapted to set a plurality of local areas which are to be processed, and to examine a periodicity as to whether or not said moving object passes through each of said local processed areas, and to examine a periodicity as to the character concerning the shape of said moving object, and to identify at least one flashing object.

10. An image processing apparatus for calculating a distance between two moving objects contained in one image, comprising:

an image-input unit (114) which inputs said image including a background and a plurality of objects;

a marker holding unit (110) which places a plurality of markers in said background;

a moving object extract unit (128) which extracts a plurality of moving objects;

a moving object/marker time-series table making unit (131) which traces said plurality of moving objects;

a marker extract unit (129) which extracts the markers existing between the two different moving objects; and

a distance measuring unit (113) which calculates said distance between said two moving objects, on the basis of the size of the thus extracted markers.

11. An image processing apparatus as set forth in claim 10, wherein a plurality of other markers, which are not connected with each other by said marker holding unit (110), are provided in said background, and wherein said apparatus further comprises:

a connected-area position/shape calculating unit (125) which calculates the size, the shape, and the number of said markers;

a marker dictionary unit (127) which has a marker dictionary for storing in advance the size and the shape of said markers; and

a marker collating unit (126) which collates the shape of the markers existing between the two different moving objects and also collates said marker dictionary, and wherein said apparatus is adapted to calculate the number of the markers which can be identified as true markers by a result of the collation in said marker collating unit (126), and to calculate said distance between said two moving objects.

12. An image processing apparatus as set forth in claim 11, wherein said apparatus is adapted to trace the the number of the markers existing between the two different moving objects, and to calculate said distance between said two moving objects.

14. An image processing apparatus as set forth in claim 13, wherein:

said connected-area position/shape calculating unit (125) is adapted to separate each of said connected areas into a plurality of connected components, and to obtain the value of a projection for every connected components;

wherein;

said connected-area position/shape calculating unit (125) is adapted to calculate the value of length and breadth in 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 (125) is adapted to finally-discriminate whether or not each of said connected areas has the rectangular shape.

15. An image processing apparatus as set forth in claim 13, wherein:

said connected-area position/shape calculating unit (125) is adapted to extract a contour in XY two-dimensional image in which a binary code processing is carried out and a color extract processing is carried out, and to obtain the maximum and minimum value in both of x-component and y-component of said contour and also the value of a length of circumference of said contour, and wherein;

said connected-area position/shape calculating unit (125) is adapted to compare said maximum and minimum value in both of said x-component and y-component and said value of said length of circumference with the value stored in advance, and to conclude that said contour has the rectangular shape, in the case where said maximum and minimum value in both of said X-component and Y-component and said value of said length of circumference conform to said value stored in advance.

13. An image processing apparatus for calculating a distance between two cars in the case where a plurality of cars are contained in one image as moving objects, comprising:

a marker holding unit (110) which draws a plurality of white lines which are perpendicular to the direction in which the cars move, at equal spaces between adjoining white lines, as a plurality of markers;

a marker dictionary unit (127) which has a marker dictionary for estimating in advance the 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 (124) which extracts some connected areas where the white lines are connected with each other, and labels said connected areas;

a connected-area position/shape calculating unit (125) which calculates the size and the shape of the thus labeled areas respectively corresponding to regions formed by said connected white lines, and then confirms the size of the white lines in said regions formed by said connected white lines and the size of the rectangular shape corresponding to each of the thus labeled areas, in accordance with the value of a length and breadth of the thus labeled areas;

a moving object/marker correlating unit (132) which traces a specified region formed by continuous white lines corresponding to said connected white lines; and

a distance measuring unit (113) which extracts the number of continuous white lines from the white lines confirmed by said connected-area position/shape calculating unit (125), and calculates said distance between said two moving objects on the basis of the total sum of spaces between said continuous white lines.