JP2018163402A - Image processing system and marker - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing system and a marker which can precisely set a detection area even in the detection area having a complicated shape.SOLUTION: An image processing system comprises an image processing device having: imaging means 11 for picking up an image of a subject which includes one or more markers for setting a detection area capable of detecting the movement of a person or an object; detection means for detecting one or more markers 13 which can be rotated in the longitudinal direction with a rotation fulcrum as a reference, and has two sides extending from the rotation fulcrum, from a photographed image picked up by the imaging means; area setting means for setting an area which contains two sides each constituting one or more markers detected by the detection means as the detection area; and detection means for detecting the movement of the person or the object within the detection area set by the area setting means.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to an image processing system and a marker.

  In general, in an image sensor that detects the movement of a person or an object from an image captured by a camera, it is necessary to set a detection area that can detect the movement of the person or the object at the time of installation.

  As a method for setting the detection area, for example, there is a method in which an image taken at the time of installation is displayed on a display device, and the detection area is manually specified (set) on the display device. However, this method has a disadvantage that a display device for displaying an image taken at the time of installation is required, and the detection area is manually specified, which takes time.

  For this reason, a method has been devised in which a marker is set at a location that is a characteristic point of the detection area to set the detection area.

Japanese Patent No. 4140159 Japanese Patent No. 4858846

  However, the above-described method has a disadvantage in that a detection area having a complicated shape with many feature points cannot be set with high accuracy.

  The problem to be solved by the present invention is to provide an image processing system and a marker that can be accurately set even in a detection area having a complicated shape.

  An image processing system according to an embodiment includes an imaging unit that captures a subject including one or more markers for setting a detection area capable of detecting a motion of a person or an object, and a captured image captured by the imaging unit. A detecting means for detecting the one or more markers having two sides extending from the rotating fulcrum, and one or more detected by the detecting means. An area setting unit configured to set, as the detection area, an area including the two sides constituting the marker; and a detection unit configured to detect a movement of a person or an object in the detection area set by the area setting unit. .

FIG. 1 is a diagram illustrating a schematic configuration example of an image processing system according to the first embodiment. FIG. 2 is a diagram showing an appearance of the marker according to the embodiment. FIG. 3 is a diagram illustrating a case where the marker according to the embodiment is installed at a corner of the wall surface. FIG. 4 is another view showing the appearance of the marker according to the embodiment. FIG. 5 is still another view showing the appearance of the marker according to the embodiment. FIG. 6 is still another view showing the appearance of the marker according to the embodiment. FIG. 7 is still another view showing the appearance of the marker according to the embodiment. FIG. 8 is a diagram for explaining the difference between the marker shown in FIG. 2 and the marker shown in FIGS. FIG. 9 is a flowchart illustrating an example of a detection area setting process performed by the image processing apparatus according to the embodiment. FIG. 10 is a diagram for supplementarily explaining FIG. 9. FIG. 11 is another diagram for supplementarily explaining FIG. 9. FIG. 12 is still another diagram for supplementarily explaining FIG. FIG. 13 is still another diagram for supplementarily explaining FIG. FIG. 14: is a figure which shows the detection result of the outline edge component in the case of being painted with the single color regarding the marker which concerns on the embodiment. FIG. 15: is another figure which shows the detection result of the outline edge component in the case of being painted with the single color regarding the marker which concerns on the embodiment. FIG. 16 is a diagram illustrating a detection result of the contour edge component when the marker according to the embodiment is painted with a plurality of colors. FIG. 17: is another figure which shows the detection result of the outline edge component in the case of being painted with multiple colors regarding the marker which concerns on the embodiment. FIG. 18 is a diagram illustrating a schematic configuration example of an elevator system to which various functions realized by the image processing system according to the embodiment are applied. FIG. 19 is a diagram illustrating a schematic configuration example of an image processing system according to the second embodiment. FIG. 20 is a diagram for explaining the function of the marker designation direction determination unit according to the embodiment. FIG. 21 is a flowchart illustrating an example of a detection area setting process performed by the image processing apparatus according to the embodiment.

Hereinafter, embodiments will be described with reference to the drawings.
<First Embodiment>
FIG. 1 is a diagram illustrating a schematic configuration example of an image processing system according to the first embodiment.
As shown in FIG. 1, the image processing system includes a camera 11 (may be referred to as an “imaging unit”), an image processing device 12, a marker 13, and the like. ) To detect people or objects in a specific area.

  The camera 11 is a small surveillance camera such as an in-vehicle camera, and has a wide-angle lens and can continuously take several frames (for example, 30 frames / second) images per second.

  Each image (video) continuously captured by the camera 11 is analyzed in real time by the image processing device 12. Specifically, the image processing device 12 detects a person, an object, or the like (movement) based on a change in the luminance value of the image in a specific area.

  The marker 13 is used for setting a detection area in which the image processing apparatus 12 can detect a person, an object, or the like, thereby defining the detection area.

Here, the marker 13 will be described in detail with reference to FIG.
2A and 2B are views for explaining the structure of the marker 13 used for setting the detection area. FIG. 2A is a perspective view showing the appearance of the marker 13, and FIG. FIG. 2C is a side view showing the appearance of the marker 13 corresponding to FIG. 2A, FIG. 2C is another perspective view showing the appearance of the marker 13, and FIG. 2D is FIG. It is another side view which shows the external appearance of the marker 13 corresponding to.

  As shown in FIGS. 2A and 2B, the marker 13 includes a plurality of fan-shaped plate members (thick paper) 131a to 131c having both sides r1 and r2 (may be referred to as “radius”). The plate members 131a to 131c are connected to each other so as to be rotatable in the left-right direction by a shaft member 132 provided in the vicinity of the fan-shaped center point. That is, the shape of the marker 13 is also fan-shaped (or circular), and the central angle θ of the fan-shaped marker 13 is a plurality of fan-shaped plate members as shown in FIGS. It can be adjusted to an arbitrary angle by rotating part or all of 131a to 131c in the left-right direction.

  For example, as shown in FIG. 3A, when the marker 13 is placed (placed) in a place where the corner of the wall is an acute angle (for example, X degrees, where X is 0 ≦ X <90), the marker 13 is By rotating the plurality of fan-shaped plate members 131 in the left-right direction, the center angle θ is deformed to be (360-X) degrees.

  In addition, as shown in FIG. 3B, when the marker 13 is installed in a place where the corners of the wall surface are perpendicular, the marker 13 is centered by rotating a plurality of fan-shaped plate members 131 in the left-right direction. The angle θ is deformed so as to be 270 degrees.

  Further, as shown in FIG. 3C, when the marker 13 is installed in a place where the angle of the wall surface is an obtuse angle (for example, Y degrees, where Y is 90 <Y <180), the marker 13 has a plurality of sector shapes. By rotating the shaped plate member 131 in the left-right direction, the center angle θ is deformed so as to be (360−Y) degrees.

  The plurality of plate members 131a to 131c constituting the marker 13 are painted with a specific color. The specific color is, for example, a fluorescent color or the like, and is preferably a color that is generally used as a color of a floor surface or a wall surface.

  In FIG. 2, the plate members 131a to 131c are connected to each other so as to be rotatable in the left-right direction by a shaft member 132 provided in the vicinity of the fan-shaped center point. Each plate member 131a to 131c is provided with a concave depression in the vicinity of the center point on the upper surface of each plate member 131a to 131c, and a convex protrusion in the vicinity of the center point on the lower surface (position facing the concave depression). You may mutually connect so that rotation is possible in the left-right direction. Alternatively, each plate member 131a is provided by providing a convex protrusion in the vicinity of the center point on the upper surface of each plate member 131a to 131c and providing a concave recess in the vicinity of the center point on the lower surface (position facing the convex protrusion). To 131c may be connected to each other so as to be rotatable in the left-right direction.

  Moreover, the shape of the marker 13 is not limited to the shape shown in FIG. 2, For example, the following shapes may be sufficient.

  As shown in FIGS. 4A and 4B, the marker 13 is formed by stacking a plurality of fan-shaped plate members 131 so as to be rotatable in the left-right direction, and each plate member 131 is shown in FIG. Unlike the shape, it may have a stopper member 133 that protrudes upward or downward from both sides r1 and r2 of the sector shape. As shown in FIG. 4C, the stopper member 133 provided on the predetermined plate member 131 is in contact with the stopper member 133 provided on the opposing plate member 131 when the plate member 131 rotates in the left-right direction. Touch.

  As shown in FIGS. 5A and 5B, the marker 13 is formed by stacking a plurality of fan-shaped plate members 131 so as to be rotatable in the left-right direction. Unlike the shape shown, a convex protrusion 134 may be provided on the upper or lower surface of the sector shape. As shown in FIG. 5C, the protrusion 134 provided on the predetermined plate member 131 is in contact with the protrusion 134 provided on the opposing plate member 131 when the plate member 131 rotates in the left-right direction. Touch.

  As shown in FIGS. 6A and 6B, the marker 13 is configured by stacking a plurality of fan-shaped plate members 131 so as to be rotatable in the left-right direction. Unlike the shape of FIG. 5, it has a convex projection 135 provided on the upper or lower surface of the sector, and a sliding groove 136 provided along the sector arc and engaged with the projection 135. May be. As shown in FIG. 6C, the protrusion 135 provided on the predetermined plate member 131 is formed in the sliding groove 136 provided on the opposing plate member 131 when the plate member 131 rotates in the left-right direction. , And comes into contact with the opposing plate member 131 at the end of the sliding groove 136.

  As shown in FIG. 7, the marker 13 may be integrally formed so that a plurality of fan-shaped plate members 131 have a bellows shape.

  When the marker 13 has the shape shown in FIGS. 4 to 7, the following advantages can be obtained. Hereinafter, the above-described advantages will be described by comparing the shape shown in FIG. 2 with the shape shown in FIG. 4 with reference to FIG.

  In the case of the marker 13 having the shape shown in FIG. 2, a gap (gap) as shown in FIG. 8A may be formed when each plate member 131 is rotated in the left-right direction. According to this, there is a possibility that the accuracy of the process of detecting the edge of the marker 13 described later is lowered. On the other hand, in the case of the marker 13 having the shape shown in FIG. 4, the compactness (portability) is inferior to the shape shown in FIG. 2, but when each plate member 131 is rotated in the left-right direction, FIG. As shown in (b), since the stopper member 133 abuts on the corresponding stopper member 133, the possibility that the above-described gap is generated can be eliminated. According to this, it is possible to execute the process of detecting the edge of the marker 13, which will be described later, with higher accuracy than when a gap is generated.

  Here, the marker 13 having the shape shown in FIG. 4 has been described as a representative example, but the same advantage can be obtained with the marker 13 having the shape shown in FIGS.

  Moreover, in this embodiment, although the marker 13 was comprised with the some fan-shaped board member 131, it is not limited to this, The marker 13 may be comprised with the some triangular-shaped board member.

  Returning to the description of FIG. The image processing apparatus 12 includes a storage unit 121, a detection unit 122, a marker detection unit 123, a marker edge detection unit 124, an area setting unit 125, an area setting information storage unit 126, and the like.

  The storage unit 121 has a buffer area for sequentially storing images taken by the camera 11 and temporarily holding data necessary for the processing of the detection unit 122. The detection unit 122 detects a person or an object in the detection area based on a change in luminance value in the detection area in the captured image.

  The marker detection unit 123 detects (extracts) the marker 13 installed for setting (calibrating) the detection area on site as an initial setting from the image. In this embodiment, since it is assumed that the marker 13 is painted with a specific color such as a fluorescent color, the marker detection unit 123 has a hue / saturation corresponding to the specific color from the image. The marker 13 is detected by extracting the region.

  In this embodiment, since it is assumed that the shape of the marker 13 is a fan shape, the marker detection unit 123 extracts a shape close to a circle from the image using a known separability filter or the like. Thus, the marker 13 may be detected.

  Furthermore, when the marker 13 is painted so as to have a predetermined pattern (pattern), the marker detection unit 123 extracts the predetermined pattern using a known method such as pattern matching, so that the marker 13 is extracted. It may be detected.

  The marker edge detection unit 124 detects edges corresponding to both sides r1 and r2 of the marker 13 detected by the marker detection unit 123. More specifically, first, the marker edge detection unit 124 extracts the contour edge component of the marker 13 detected by the marker detection unit 123 by Sobel edge detection or the like. Thereafter, the marker edge detection unit 124 applies, for example, a Hough transform to the extracted contour edge component, and extracts only the straight line component of the extracted contour edge component, whereby both side portions r1, An edge corresponding to r2 is detected.

  Further, when the marker edge detection unit 124 detects two edges corresponding to both sides r1 and r2 of the marker 13, the intersection of the two detected edges is determined as the corner of the wall surface on which the marker 13 is installed (in other words, , The center point of the fan-shaped marker 13).

  The area setting unit 125 sets, as a detection area, an area including edges corresponding to both side parts r1 and r2 of the marker 13 detected by the marker edge detection unit 124. More specifically, an area defined by an extension line obtained by extending edges corresponding to both sides r1 and r2 of the marker 13 detected by the area setting unit 125 and the marker edge detection unit 124 is set as a detection area.

  The area setting information storage unit 126 stores area setting information indicating the detection area set by the area setting unit 125.

  Next, an example of the detection area setting process executed by the image processing apparatus 12 configured as described above will be described with reference to the flowchart of FIG.

  First, the image processing apparatus 12 acquires an image (hereinafter, referred to as “initial setting image”) shot with the marker 13 installed from the camera 11 (step S1). Here, it is assumed that the initial setting image shown in FIG.

  Subsequently, the marker detection unit 123 in the image processing device 12 detects the marker 13 in the initial setting image (step S2). In this case, three markers 13a to 13c are detected from the initial setting image shown in FIG.

  As described above, the marker 13 may be detected by extracting a region having a hue / saturation corresponding to the color of the marker 13 from the initial setting image, or a shape close to a circle is the initial setting image. It may be detected by extracting from.

Next, the marker edge detection unit 124 in the image processing apparatus 12 detects the contour edge components of the markers 13a to 13c detected by the marker detection unit 123 (step S3). In this case, as shown in FIG. 11, edges ea _{1 to} ea ₃ are detected from the marker 13a, edges eb _{1 to} eb ₃ are detected from the marker 13b, and edges ec _{1 to} ec ₃ are detected from the marker 13c. Is done.

After that, the marker edge detection unit 124 extracts only the straight line component from the detected contour edge components, and detects edges corresponding to both side parts r1 and r2 of the marker 13 (step S4). In this case, as shown in FIG. 12, the edges ea ₁ and ea ₂ are detected as edges corresponding to both sides from the marker 13a, and the edges eb ₁ and eb ₂ are detected as edges corresponding to both sides from the marker 13b. The edges ec ₁ and ec ₂ are detected as edges corresponding to both sides from the marker 13c.

Subsequently, the marker edge detection unit 124 detects the intersection of the edges corresponding to the extracted both sides r1 and r2 as the corner of the wall surface (step S5). In this case, as shown in FIG. 12, the intersection of the edges ea ₁ and ea ₂ corresponding to the marker 13a is detected as the corner C1 of the wall surface, and the intersection of the edges eb ₁ and eb ₂ corresponding to the marker 13b is detected on another wall surface. It is detected as a corner C2, and the intersection of the edges ec ₁ and ec ₂ corresponding to the marker 13c is further detected as a corner C3 of another wall surface.

  Next, the area setting unit 125 detects based on the edges corresponding to the both sides r1 and r2 of the marker 13 detected by the marker edge detection unit 124 and the corners of the wall surface detected by the marker edge detection unit 124. An area is set (step S6).

In this case, as shown in FIG. 13, the extension lines ea _{1 ′} and ea _{2 ′} respectively extending the edges ea ₁ and ea ₂ corresponding to both sides of the marker 13a in the direction opposite to the corner C1 of the wall surface, and the marker 13b Edge lines eb ₁ , eb _{2 ′} extending from edges eb ₁ , eb ₂ corresponding to both sides of the marker in the direction opposite to the corner C2 of the wall surface, and edges ec ₁ , ec ₂ corresponding to both sides of the marker 13c. Is defined as a detection area E1 by the areas defined by extension lines ec _{1 ′} and ec _{2 ′} respectively extending in the opposite direction to the corner C3 of the wall surface.

  Thereafter, the area setting unit 125 stores area setting information indicating the set detection area in the area setting information storage unit 126 (step S7), and ends the processing here.

  According to the first embodiment described above, since the marker detection unit 123, the marker edge detection unit 124, and the area setting unit 125 are provided, the detection area setting process using the marker 13 can be realized. Since the marker 13 has a structure in which the center angle θ can be adjusted to an arbitrary angle, it is possible to specify in which direction the detection area is set. That is, the number of markers can be reduced compared to a general method of recognizing a marker as one point and connecting the recognized points to set a detection area.

  In the present embodiment, the case where the marker 13 is painted in one color (single color) such as a fluorescent color has been described. However, in this case, the following inconvenience may occur.

  14 and 15, the marker 13 a on the left side in the drawing painted in the first color and the marker 13 b on the right side in the drawing painted in the second color different from the first color are various colors. It is a figure which shows the detection result of the contour edge component at the time of being installed in the floor surfaces F1 and F2 of various colors along the wall surface W of FIG.

  In the following, for convenience of explanation, not all the drawings shown in FIGS. 14 and 15 will be described, but only some partial drawings as representative examples will be described.

  As shown in the left diagram of FIG. 14A, when all of the wall surface W and the floor surfaces F1, F2 are colors different from the first and second colors, the marker edge detection unit 124 Both the contour edge components of the markers 13a and 13b painted with the second color can be detected with high accuracy (high intensity).

  On the other hand, when the wall surface W is the first color and the floor surfaces F1 and F2 are both different colors from the first and second colors, as shown in the central view of FIG. Although the detection unit 124 can accurately detect the contour edge component of the marker 13b painted with the second color, the wall W is the marker 13a of the contour edge component of the marker 13a painted with the first color. Cannot be detected with high accuracy. More specifically, an inconvenience that edges corresponding to both side parts r1 and r2 of the marker 13a cannot be detected with high accuracy may occur.

  However, in the case of the central view of FIG. 14A, the marker edge detection unit 124 can accurately detect an edge corresponding to the arc of the marker 13a. Edges corresponding to r1 and r2 can also be detected with some prediction.

  However, as shown in the central view of FIG. 15A, when all of the wall surface W and the floor surfaces F1 and F2 are in the first color, the marker edge detection unit 124 uses the marker painted in the first color. The edge component of 13a cannot be detected at all (or cannot be detected with high accuracy), and the edge cannot be detected by prediction as in the case of the central view of FIG. .

  According to this, the inconvenience that the area setting unit 125 cannot set the detection area or sets the detection area in the wrong place occurs.

  In order to eliminate such inconvenience, it is preferable that the marker 13 is painted with a plurality of colors instead of one color.

  16 and 17, the inner circle is painted with the first color and the outer circle is painted with the second color, the marker 13a on the left side of the figure, the inner circle is painted with the second color, and the outer circle is Detection result of contour edge component when marker 13b on the right side in the drawing painted in the first color is installed on floor surfaces H1, H2 of various colors along wall surface W of various colors FIG.

  As shown in FIGS. 16 and 17, when the markers 13a and 13b are painted in a plurality of colors, the contour edge components of the markers 13a and 13b are detected with high accuracy in any case. I understand.

  For example, even if the center view of FIG. 15A and the center view of FIG. 17A in which the colors of the wall surface W and the floor surfaces F1 and F2 are the same, the marker edge detection unit 124 has the contour of the marker 13a. The edge component can be accurately detected by the inner circle portion painted in the second color.

  Thus, by separately marking the marker 13 with a plurality of colors, the detection of the contour edge component by the marker edge detection unit 124 can be realized with higher accuracy, and the above-described inconvenience can be solved.

  In addition, although the case where the marker 13 is separately applied with a plurality of colors has been described here, the marker 13 may be applied with a color of a similar color but a different luminance value (lightness).

  Various functions realized by the image processing system according to the present embodiment may be applied to, for example, an elevator system illustrated in FIG. Below, the case where the various functions implement | achieved by an image processing system are applied to an elevator system is demonstrated.

  In FIG. 18, reference numeral 20 denotes an elevator (car), 21 denotes a car door, 22 denotes a landing door, and 23 denotes an elevator control device that controls opening and closing of the car door 21.

  In recent years, various techniques have been devised to prevent people and objects from being caught in the car door 21 of the elevator 20, and among them, there is an elevator system shown in FIG. 18. This elevator system photographs the vicinity of the car door 21 using the camera 11, and controls the opening / closing of the car door 21 based on the presence or absence of a user in the detection area set in the vicinity of the car door 21. I do. For example, when there is a user in the detection area, processing such as prohibiting the door closing operation of the car door 21 and maintaining the door open state is executed.

  In such an elevator system, it is necessary to set a detection area for each floor where the car 20 stops. However, if the shape of the three-way frame arranged around the landing door 22 is a complicated shape, maintenance is required. The worker displays the initial setting image on a terminal such as a tablet, manually sets the detection area, and sets the detection area. This is inconvenient because it is necessary to carry around a terminal such as a tablet and to manually specify the detection area.

  However, the functions realized by the above-described image processing system, in particular, the image processing apparatus 12 includes the marker detection unit 123, the marker edge detection unit 124, and the area setting unit 125, so that the detection area can be set using the marker 13. It becomes possible to set, and the inconvenience described above can be solved.

  In the image processing apparatus 12 shown in FIG. 18, as a function unique to the elevator system, a user closest to the car door 21 is detected based on a change in the luminance value of the image, and the detected user detects the car door. A function of determining whether or not there is an intention to get on the car 20 based on whether or not the vehicle is approaching 21 may be installed. Further, when it is determined that there is an intention to get into the car 20, a function of prohibiting the door closing operation of the car door 21 and maintaining the door open state may be further mounted.

<Second Embodiment>
Next, a second embodiment will be described. As shown in FIG. 19, the second embodiment is different from the first embodiment in that the image processing apparatus 12 further includes a marker designation direction determination unit 127. In addition, the part which has the same function as 1st Embodiment attaches | subjects the same code | symbol, and shall omit the detailed description.

  Further, in the present embodiment, the inner circle and the outer circle shown in FIGS. 16 and 17 are painted separately in the first and second colors instead of the marker 13 painted in the single color shown in FIGS. The case where the marker 13 is used is assumed.

  The marker designation direction determination unit 127 defines a place where the detection area is set based on the color of the inner circle (or the color of the outer circle) of the marker 13. More specifically, the marker designation direction determination unit 127 determines whether the detection area is set on both sides r1 and r2 of the marker 13 based on whether or not the inner circle color of the marker 13 is the first color. Whether or not the edge corresponding to the arc of the marker 13 is detected is determined using the corresponding edge as a boundary.

  In this embodiment, when the color of the inner circle of the marker 13 is the first color, the marker designation direction determination unit 127 determines that the place where the detection area is set is the marker as shown in FIG. If the edge corresponding to the arc of 13 is detected, and the color of the inner circle of the marker 13 is not the first color (the second color), the place where the detection area is set is shown in FIG. As shown in b), it is assumed that the edge corresponding to the arc of the marker 13 is not detected. However, this is merely an example, and when the color of the inner circle of the marker 13 is the first color, the place where the detection area is set is the side where the edge corresponding to the arc of the marker 13 is not detected. When the color of the inner circle of the marker 13 is not the first color, the place where the detection area is set may be the side where the edge corresponding to the arc of the marker 13 is detected.

  Here, an example of the procedure of the detection area setting process executed by the image processing apparatus 12 according to the second embodiment will be described with reference to the flowchart of FIG. In addition, the same code | symbol is attached | subjected about the process similar to the flowchart shown in FIG. 9, and the detailed description shall be abbreviate | omitted.

  After the processing of steps S1 to S5 described above is executed, the marker designation direction determination unit 127 determines whether or not the inner circle color of the marker 13 is the first color (step S11).

  When the inner circle of the marker 13 is the first color as a result of the process of step S11 (YES in step S11), the marker designation direction determination unit 127 uses the edge corresponding to the arc of the marker 13 where the detection area is set Is detected, the determination result is notified to the area setting unit 125 (step S12), and the process proceeds to step S14 described later.

  On the other hand, if the inner circle of the marker 13 is not the first color as a result of the processing in step S11 (NO in step S11), the marker designation direction determination unit 127 corresponds to the arc of the marker 13 where the detection area is set. It is determined that the detected edge is not detected, and the determination result is notified to the area setting unit 125 (step S13).

  Subsequently, the area setting unit 125 determines edges corresponding to both sides r1 and r2 of the marker 13 detected by the marker edge detection unit 124, corners of the wall surface detected by the marker edge detection unit 124, and marker designation direction determination. The detection area is set based on the location (side) where the detection area determined by the unit 127 is set (step S14).

  Thereafter, the process of step S7 described above is executed, and the process here ends.

  In the present embodiment, the marker designation direction determination unit 127 defines the location where the detection area is set, but conversely, even if the location where the detection area is not set, that is, the location excluded from the detection area, is defined. good.

  According to the second embodiment described above, the marker designation direction determination unit 127 is further provided so that the hollow area can be set as the detection area as shown in FIG. Become. Further, by using a combination of the marker 13 whose inner circle is painted with the first color and the marker 13 whose inner circle is painted with the second color, a detection area is formed on the floor surface and the hollow area at a time. Can be set, that is, detection areas can be set at various locations at once.

  According to at least one embodiment described above, it is possible to provide an image processing system and a marker that can be accurately set even in a detection area having a complicated shape.

  In addition, although some embodiment of this invention was described, these embodiment is shown as an example and is not intending limiting the range of invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

  DESCRIPTION OF SYMBOLS 11 ... Camera, 12 ... Image processing apparatus, 13 ... Marker, 121 ... Memory | storage part, 122 ... Detection part, 123 ... Marker detection part, 124 ... Marker edge detection part, 125 ... Area setting part, 126 ... Area setting information storage part .

Claims (12)

Imaging means for photographing a subject including one or more markers for setting a detection area capable of detecting the movement of a person or an object;
Detecting means for detecting the one or more markers having two sides that are rotatable in the left-right direction with reference to a rotation fulcrum from a captured image photographed by the imaging means;
Area setting means for setting, as the detection area, an area including each of the two sides constituting one or more markers detected by the detection means;
An image processing system comprising: detection means for detecting movement of a person or an object in the detection area set by the area setting means. The marker is
The image processing system according to claim 1, wherein the image processing system has a fan shape with the two sides as both side portions and the rotation fulcrum as a center point. The detection means includes
Detecting a contour edge component of the detected marker;
Detecting two straight edge components corresponding to the both sides from the detected contour edge component;
The image processing system according to claim 2, wherein an intersection of the two detected linear edge components is detected as the center point. The area setting means includes
The detected two linear edge components are extended in a direction opposite to the position where the center point is detected, and an area defined by an extension line obtained thereby is set as the detection area. The image processing system according to claim 3. The marker is
The inner circle portion centering on the center point is painted with a first color, and the outer circle portion is painted with a second color different from the first color. Image processing system.   6. The image processing system according to claim 5, further comprising marker designation direction determination means for designating an area for setting the detection area based on a color of an inner circle portion of the marker. The marker designation direction determination means includes
When the color of the inner circle part of the marker is the first color, the edge corresponding to the arc of the detected contour edge components after setting the two detected linear edge components as a boundary line Determine that there is a region to set the detection area on the side where the component exists,
When the color of the inner circle portion of the marker is the second color, the edge corresponding to the arc of the detected contour edge components, with the two detected linear edge components as a boundary line The image processing system according to claim 6, wherein it is determined that there is an area for setting the detection area on a side where no component exists. A marker used when setting a detection area for detecting the movement of a person or an object,
A plurality of fan-shaped plate members;
A shaft member provided in the vicinity of the center point of each plate member,
Each of the plate members is connected to the shaft member so as to be rotatable in the left-right direction,
A marker characterized in that the central angle of a sector formed by each plate member can be adjusted to an arbitrary angle by rotating a part or all of each plate member in the left-right direction. It further comprises a stopper member protruding upward or downward from both sides of each plate member,
The marker according to claim 8, wherein each stopper member comes into contact with a stopper member provided on an opposing plate member when each plate member rotates in the left-right direction. A convex protrusion on the upper or lower surface of each plate member;
9. The marker according to claim 8, wherein each protrusion comes into contact with a protrusion provided on an opposing plate member when each plate member rotates in the left-right direction. A protrusion provided on the upper or lower surface of each plate member;
A sliding groove that is provided along the fan-shaped arc of each plate member, and that engages with the protrusion,
The protrusions move in the sliding grooves provided in the opposing plate members when the plate members rotate in the left-right direction, and the opposing plate members at the ends of the sliding grooves. The marker according to claim 8, which abuts against the marker.   The marker according to claim 8, wherein each of the plate members is integrally formed to have a bellows shape.

Images