CN118205970A - Elevator user detection system and exposure control method - Google Patents

Abstract

The target value of the brightness used in the exposure control can be set appropriately according to the respective environments in the car and the hall, and the user in the car and the user in the hall can be detected accurately. The elevator user detection system according to one embodiment includes: a photometry window setting unit, a measuring unit, a target value determining unit, and an exposure control unit. The light measurement window setting means sets a light measurement window in the car or in a hall on the basis of an open/close state of a door of the car, on a captured image obtained from the camera. The measurement unit measures the brightness of the image in the photometric window as an index value. The target value determining unit determines a target value of the luminance based on the index value obtained by the measuring unit. The exposure control unit controls exposure of the camera so that the brightness of the image converges to the target value determined by the target value determination unit.

Description

Elevator user detection system and exposure control method

The present application is based on Japanese patent application 2022-200390 (application day: 12/15 of 2022) and enjoys priority of the application. The present application includes all of the contents of this application by reference thereto.

Technical Field

The embodiment of the invention relates to a user detection system of an elevator and an exposure control method.

Background

In general, when an elevator car arrives at a hall and opens, a door is closed after a predetermined time elapses. At this time, since the user of the elevator does not know when the car is closed, the user may hit a door during closing the door when riding the elevator from the hall to the car. In order to avoid collision of the door at the time of riding, there is a system that detects a user riding on the car using an image captured by a camera and reflects the detection result to the opening/closing control of the door. In addition, when a user gets on a car in the vicinity of a door, an accident of a door camera box being pulled into the door may occur when the door is opened. In order to prevent such a pull-in accident when closing the door, a camera may be used to capture an image.

The brightness of the car and hall of the elevator varies depending on the design and lighting environment. In particular, since the hall is susceptible to outdoor light at each floor, the brightness of each floor often varies. However, in general, in exposure control of a camera, photographing is always performed at a target value of the same brightness regardless of whether the car is a dark environment or a bright environment. In the hall, the same imaging is performed with the target value of the same brightness, both in a dark environment and in a bright environment. Therefore, if the target value of the luminance is set to a value suitable for a dark environment, overexposure may occur in a bright environment. In contrast, if the target value of the luminance is set to a value suitable for a bright environment, underexposure may occur in a dark environment.

For example, an environment in which the car is bright and the hall is dark is assumed. In this case, if the target value of the luminance is set to a value suitable for a bright environment, the imaging with the luminance suppressed is performed. Therefore, the image of the hall becomes unsuitable, and the detection accuracy of the hall is affected. On the other hand, if the target value of the luminance is set to a value suitable for a dark environment, the image in the car becomes inappropriate by suppressing the photographing of the darkness, and the detection accuracy in the car is affected. If the target value of the luminance is determined as the luminance between the car and the hall, the target value becomes a median image, and both the car and the hall affect the detection accuracy.

Disclosure of Invention

The present invention provides an elevator user detection system and an exposure control method, which can appropriately set a target value of brightness used in exposure control according to respective environments of an elevator car and a hall, and can accurately detect a user in the elevator car and a user in the hall.

The elevator user detection system according to one embodiment includes a photometric window setting unit, a measuring unit, a target value determining unit, and an exposure control unit. The light measurement window setting means sets a light measurement window in the car or in a hall on the basis of an open/close state of a door of the car, on a captured image obtained from the camera. The measurement unit measures the brightness of the image in the photometric window as an index value. The target value determining unit determines a target value of the luminance based on the index value obtained by the measuring unit. The exposure control unit controls exposure of the camera so that the brightness of the image converges to the target value determined by the target value determination unit.

Drawings

Fig. 1 is a diagram showing a configuration of a user detection system of an elevator according to an embodiment.

Fig. 2 is a view showing a configuration of an entrance peripheral portion in the car according to the embodiment.

Fig. 3 is a diagram showing a relationship between a captured image of a camera and a detection area of a hall in this embodiment.

Fig. 4 is a diagram showing a relationship between a captured image of a camera and a detection area in an elevator car in this embodiment.

Fig. 5 is a flowchart showing a user detection process of the image processing apparatus in this embodiment.

Fig. 6 is a diagram for explaining a coordinate system in real space in this embodiment.

Fig. 7 is a diagram showing a state in which the captured image in this embodiment is divided in block units.

Fig. 8 is a diagram showing an example of an image captured by normal exposure control.

Fig. 9 is a diagram showing an example of an image captured by normal exposure control.

Fig. 10 is a block diagram showing a functional configuration of the image processing apparatus according to this embodiment.

Fig. 11 is a view showing an example of a captured image before exposure control in this embodiment.

Fig. 12 is a diagram showing an example of a captured image before exposure control in this embodiment.

Fig. 13 is a view showing an example of a captured image after exposure control in this embodiment.

Fig. 14 is a view showing an example of a captured image after exposure control in this embodiment.

Fig. 15 is a diagram showing transition from the start to the end of exposure control in this embodiment.

Fig. 16 is a flowchart showing the operation of the exposure control process of the image processing apparatus according to this embodiment.

Detailed Description

Hereinafter, embodiments will be described with reference to the drawings.

The present invention is not limited to the following embodiments, but is merely an example. Variations that would be readily apparent to one of skill in the art are of course included within the scope of the disclosure. In order to make the description more clear, the dimensions, shapes, and the like of the respective portions may be schematically shown in the drawings by changing them with respect to the actual embodiments. In the drawings, corresponding elements are denoted by the same reference numerals, and detailed description thereof may be omitted.

Fig. 1 is a diagram showing a configuration of a user detection system of an elevator according to an embodiment. In this case, 1 car is taken as an example, but a plurality of cars are similarly configured.

A camera 12 is provided above the entrance of the car 11. Specifically, the camera 12 is provided in a door header plate 11a covering the upper portion of the doorway of the car 11, and the lens portion is tilted by a predetermined angle in the right downward direction or toward the hall 15 side or the inside of the car 11.

The camera 12 is a small-sized monitoring camera such as an in-vehicle camera, and has a wide-angle lens or a fisheye lens, and is capable of continuously capturing images of several frames (for example, 30 frames/second) per second. The camera 12 is activated when the car 11 reaches the hall 15 of each floor, for example, and captures images including the hall 15 in the car 11 or in the vicinity of the car door 13. The camera 12 may be always in operation during operation of the car 11.

The imaging range at this time is adjusted to L1+L2 (L1 > L2). L1 is an imaging range on the hall side, and has a predetermined distance from the car door 13 to the hall 15. L2 is an imaging range on the car side, and has a predetermined distance from the car door 13 to the car rear surface. The ranges L1 and L2 are ranges in the depth direction, and the range in the width direction (direction orthogonal to the depth direction) is at least larger than the lateral width of the car 11.

In each floor hall 15, a hall door 14 is provided so as to be openable and closable at an arrival opening of the car 11. The hall doors 14 engage with the car doors 13 to perform opening and closing operations when the car 11 arrives. The power source (door motor) is located on the car 11 side, and the hall door 14 is opened and closed only following the car door 13. In the following description, the hoistway door 14 is also opened when the car door 13 is opened, and the hoistway door 14 is also closed when the car door 13 is closed.

Each image (video) continuously captured by the camera 12 is analyzed and processed in real time by the image processing device 20. In fig. 1, the image processing device 20 is shown as being taken out of the car 11 for convenience, but in practice, the image processing device 20 is housed in the door lintel plate 11a together with the camera 12.

The image processing apparatus 20 includes a storage section 21, a control section 22, and a communication section 23. In addition, the elevator control device 30 may be provided with a part or all of the functions of the image processing device 20. The storage unit 21 is configured by a storage device such as a RAM, for example. The storage section 21 has a buffer area for sequentially storing images captured by the camera 12 and temporarily storing data necessary for processing by the control section 22. As the preprocessing of the captured image, the storage unit 21 may store an image subjected to the processing such as distortion correction, enlargement and reduction, and partial cutting. The storage unit 21 includes a target value storage unit 21a described later.

The control unit 22 is constituted by a microprocessor, for example. The control unit 22 includes a detection area setting unit 22a and a detection processing unit 22b as processing units related to a user detection function. The above-described components may be realized by software, hardware such as IC (Integrated Circuit), or a combination of software and hardware.

The detection area setting unit 22a sets at least one or more detection areas for detecting a user on the captured image obtained from the camera 12. In the present embodiment, a detection area E1 for detecting a user in the hall 15 and a detection area E2 for detecting a user near the entrance in the car 11 are set. Specifically, the detection area setting unit 22a includes the thresholds 18 and 47 in the floor surface 16 of the hall 15, and sets a detection area E1 (see fig. 3) having a predetermined distance L3 toward the hall 15. The detection area setting unit 22a sets a strip-shaped detection area E2 along the car threshold 18 in the vicinity of the entrance/exit of the floor surface 19 in the car 11 (see fig. 4).

The detection processing unit 22b detects a user or an object existing in the hall 15 by using the image in the detection area E1 from the door closing start to the full closing, and detects a user or an object existing near the car door 13 (entrance) in the car 11 by using the image in the detection area E2 from the door opening start to the full opening. The term "object" includes, for example, a user's clothing, luggage, and a moving body such as a wheelchair. In the following description, the term "detecting a user" is also intended to include "an object".

The control unit 22 includes a photometric window setting unit 22c, a luminance measuring unit 22d, a target value determining unit 22e, a target value setting unit 22f, and an exposure control unit 22g as exposure control functions for controlling exposure of the camera 12. In addition, the camera 12 may be provided with some of these functions. These functions are described in detail below with reference to fig. 10. The communication unit 23 is used for communication with an external device including, for example, the elevator control device 30. The communication unit 23 may be provided independently of the image processing apparatus 20.

The elevator control device 30 is constituted by a computer equipped with CPU, ROM, RAM or the like. The elevator control device 30 performs operation control of the car 11. The elevator control device 30 further includes a door opening/closing control unit 31.

The door opening/closing control unit 31 controls the opening/closing of the doors 13 of the car when the car 11 reaches the hall 15. Specifically, the door opening/closing control unit 31 opens the car door 13 when the car 11 reaches the hall 15, and closes the door after a predetermined time has elapsed. However, when the detection processing unit 22b detects a user of the hall 15 during the door closing operation of the car door 13 (from the door closing start to the full closing), the door opening/closing control unit 31 prohibits the door closing operation of the car door 13, and reopens the car door 13 in the full opening direction and maintains the door opening state. On the other hand, in the case where the detection processing unit 22b detects a user located near the door in the car 11 during the door opening operation of the car door 13 (during the period from the start of the door opening to the full opening), the door opening/closing control unit 31 prohibits the door opening operation of the car door 13, and the car door 13 is closed again in the full closing direction and the door closing state is maintained.

Fig. 2 is a view showing a configuration of the surrounding portion of the doorway in the car 11.

A car door 13 is provided to open and close an entrance of the car 11. In the example of fig. 2, a two-door double-open type car door 13 is shown, and two door panels 13a, 13b constituting the car door 13 are opened and closed in opposite directions along the front width direction (horizontal direction). The "front width" is the same as the entrance of the car 11.

Front posts 41a, 41b are provided on both sides of the entrance of the car 11, and surround the entrance of the car 11 together with the door lintel plate 11 a. The "front column" is also called an entrance column or an entrance frame, and a door camera for accommodating the car door 13 is generally provided on the rear surface side. In the example of fig. 2, when the car door 13 is opened, one door panel 13a is accommodated in a door box 42a provided on the rear surface side of the front column 41a, and the other door panel 13b is accommodated in a door box 42b provided on the rear surface side of the front column 41 b.

One or both of the front posts 41a and 41b are provided with a display 43, an operation panel 45 provided with a destination floor button 44, and the like, and a speaker 46. In the example of fig. 2, a speaker 46 is provided on the front pillar 41a, and a display 43 and an operation panel 45 are provided on the front pillar 41 b. Here, a camera 12 having a wide-angle lens is provided in a central portion of a door lintel plate 11a at an upper portion of an entrance of the car 11.

Fig. 3 is a diagram showing a relationship between a captured image of the camera 12 and the detection area E1 of the hall 15. The hall 15 is located at the upper side, and the car 11 is located at the lower side. In the figure, 16 denotes the floor surface of the hall 15, and 19 denotes the floor surface of the car 11. E1 represents a detection region.

The car door 13 has two door panels 13a, 13b that move in opposite directions to each other on the car threshold 47. Similarly, the hall door 14 has two door panels 14a, 14b that move in opposite directions relative to each other on the hall sill 18. The door panels 14a, 14b of the hoistway door 14 move in the door opening and closing direction together with the door panels 13a, 13b of the car door 13.

The camera 12 is provided at an upper portion of an entrance of the car 11. Therefore, when the car 11 opens in the hall 15, as shown in fig. 1, a predetermined range (L1) on the hall side and a predetermined range (L2) in the car are photographed. In the predetermined range (L1) on the hall side, a detection area E1 for detecting a user who is about to ride on the car 11 is set.

In real space, the detection area E1 has a distance L3 from the center of the entrance (front width) toward the hall (L3 is equal to or smaller than the imaging range L1 on the hall side). The lateral width W1 of the detection region E1 at the time of full-open is set to be equal to or greater than the lateral width W0 of the entrance (front face width). As shown by oblique lines in fig. 3, the detection area E1 is set to include the thresholds 18, 47 and to be other than dead corners of the door pocket 17a, 17 b. The size of the detection area E1 in the lateral direction (X-axis direction) may be changed in accordance with the opening/closing operation of the car door 13. The size of the detection area E1 in the longitudinal direction (Y-axis direction) may be changed in accordance with the opening/closing operation of the car door 13.

Fig. 4 is a diagram showing a relationship between a captured image of the camera 12 and the detection area E2 in the car 11. The hall 15 is located at the upper side, and the car 11 is located at the lower side. In the figure, 16 denotes the floor surface of the hall 15, and 19 denotes the floor surface of the car 11. E2 represents the detection area.

The detection area E2 is adjacent to a car threshold 47 provided on the floor surface 19 of the car 11. The detection area E2 is an area for detecting a user on a captured image, and is used to prevent an accident in which a user's hand or the like located near the car door 13 is pulled into the door dark boxes 42a, 42b when the door is opened.

The detection area E2 has a predetermined width L4 in a direction (Y-axis direction) orthogonal to the doorway, and is set to be strip-shaped along the longitudinal direction (X-axis direction) of the car threshold 47. The width L4 is substantially the same as the width in the Y-axis direction of the inner side surface 41a-1 of the front pillar 41a and the inner side surface 41b-1 of the front pillar 41 b. Since the car door 13 (door panels 13a, 13 b) moves on the car threshold 47, it is set outside the zone. That is, the detection area E2 is set to be adjacent to one side in the longitudinal direction of the car threshold 47 except for the car threshold 47. Thereby, the detection area E2 that is not affected by the opening and closing operation of the car door 13 can be set.

In the example of fig. 4, the car 11 is shown in a door-opened state, but the detection area E2 is preferably set on an image captured in a door-closed state. This is because the background on the hall 15 side is not shown in the captured image, and therefore the detection area E2 can be set with reference to only the structure in the car 11.

Fig. 5 is a flowchart showing the user detection processing of the image processing apparatus 20.

First, as an initial setting, a detection area setting process is performed by a detection area setting unit 22a of a control unit 22 provided in the image processing apparatus 20 (step S10). This detection area setting process is executed as follows, for example, when the camera 12 is set or when the setting position of the camera 12 is adjusted.

That is, the detection area setting unit 22a sets the detection area E1 having the distance L3 from the entrance to the hall 15 in the state where the car 11 is fully opened. As shown in fig. 3, the detection area E1 is set to include the thresholds 18, 47 and to exclude dead corners of the door pocket 17a, 17 b. In this case, in a state where the car 11 is fully opened, the detection area E1 has a lateral (X-axis direction) dimension W1 and a distance equal to or greater than a lateral width W0 of the doorway (front width).

The detection area setting unit 22a sets a strip-shaped detection area E2 along the longitudinal direction (X-axis direction) of the car threshold 47 in the vicinity of the entrance of the car 11 in a state where the car 11 is fully closed. As shown in fig. 4, the detection area E2 is set to be adjacent to one side in the longitudinal direction of the car sill 47 except on the car sill 47.

Here, if the car 11 arrives at the hall 15 of any floor (yes in step S11), the elevator control device 30 starts opening the door of the car 13 (step S12). At this time, the camera 12 provided at the upper part of the entrance of the car 11 photographs the predetermined range (L1) on the hall side and the predetermined range (L2) in the car at a predetermined frame rate (for example, 30 frames/second). The image processing device 20 acquires images captured by the camera 12 in time series, sequentially stores the images in the storage unit 21 (step S13), and simultaneously executes the following user detection processing in real time (step S14). In addition, as preprocessing of the captured image, distortion correction, enlargement and reduction, cutting out of a part of the image, and the like may be performed.

The user detection process is performed by the detection processor 22b of the controller 22 provided in the image processing apparatus 20. The detection processing unit 22b extracts images in the detection area E2 from a plurality of captured images obtained in time series by the camera 12, and detects the presence or absence of a user or an object near the entrance from these images.

Specifically, as shown in fig. 6, the camera 12 captures an image with an X-axis in a direction horizontal to the car door 13 provided at the entrance of the car 11, a Y-axis in a direction from the center of the car door 13 to the hall 15 (a direction perpendicular to the car door 13), and a Z-axis in a height direction of the car 11. In each image captured by the camera 12, a portion of the detection area E2 is compared in units of blocks, and a portion where a luminance change occurs is detected.

Fig. 7 shows an example in which a captured image is divided into a matrix in predetermined block units. An image obtained by dividing the original image into a grid of one side Wblock is referred to as a "block". In the example of fig. 7, the length of the blocks in the longitudinal and transverse directions is the same, but the lengths in the longitudinal and transverse directions may be different. The blocks may be uniformly sized over the entire image area, or may be unevenly sized such as having a shorter length in the vertical direction (Y-axis direction) of the image as the block goes up.

The detection processing unit 22b reads out the images held in the storage unit 21 one by one in time series, and calculates the average luminance value of the images for each block. At this time, the average luminance value of each block calculated when the first image is input is held as an initial value in a first buffer area, not shown, in the storage unit 21.

When the second and subsequent images are obtained, the detection processing unit 22b compares the average luminance value of each block of the current image with the average luminance value of each block of the previous image held in the above-described first buffer area. As a result, when there is a block having a luminance difference equal to or greater than the predetermined threshold in the current image, the detection processing unit 22b determines that the block is a moving block. When determining whether or not there is motion in the current image, the detection processing unit 22b stores the average luminance value of each block of the image in the first buffer area for comparison with the next image. In the same manner as described above, the detection processing unit 22b repeats the processing of determining whether or not there is motion while comparing the luminance values of the respective images in units of blocks in time series.

In the door opening operation, the detection processing unit 22b checks whether or not there is a moving block in the image in the detection area E2 set in the car 11. As a result, if there is a moving block in the image in the detection area E2, the detection processing unit 22b determines that there is a user or an object in the detection area E2.

Although the description has been made with the brightness change as an example of the detection method of the user, for example, an image taken when the car 11 is not in a person is stored as a reference image, and the reference image is compared with an image taken during the door opening operation to detect the presence or absence of the user or the object in the detection area E2.

If the presence of a user or an object is detected in the detection area E2 during the door opening operation of the car door 13 (during the period from the start of the door opening to the full opening of the door) (yes in step S15), a user detection signal is output from the image processing device 20 to the elevator control device 30. The door opening/closing control unit 31 of the elevator control device 30 receives the user detection signal to temporarily interrupt or re-close the door opening operation of the car door 13 (step S16). At this time, a user who is in the detection area E2, that is, a user who is riding a ladder near the entrance may be notified by broadcasting.

When a certain time has elapsed after the car door 13 is fully opened, the elevator control device 30 starts closing the car door 13 (step S17). In the door closing operation, the detection processing unit 22b detects the presence or absence of a user or an object (wheelchair or the like) present in the hall 15 using the captured image of the camera 12 (step S18). Specifically, the detection processing unit 22b compares the luminance values of the images sequentially obtained from the camera 12 in time series on a block-by-block basis, and determines that a user or an object is present in the detection area E1 if a moving block is present in the image in the detection area E1.

If the presence of a user or an object is detected in the detection area E1 during the door closing operation (during the period from the start of the door closing to the full door closing) (yes in step S19), a user detection signal is output from the image processing device 20 to the elevator control device 30. The door opening/closing control unit 31 of the elevator control device 30, upon receiving the user detection signal, prohibits the door closing operation of the car door 13, and maintains the door opening state (step S20).

Specifically, when the car door 13 is in the fully opened state, the door opening/closing control unit 31 starts the door opening time counting operation, and closes the door at a time when a predetermined time T (for example, 1 minute) is counted. When the user is detected during this period and the user detection signal is transmitted, the door opening/closing control unit 31 stops the counting operation, and the count value is cleared. Thereby, during the above-described time T, the door opening state of the car door 13 is maintained.

If a new user is detected during this period, the count value is again cleared, and the door opening state of the car door 13 is maintained during the time T. However, if the user arrives a plurality of times between the times T, it is preferable to set the allowable time Tx (for example, 3 minutes) because the situation that the car door 13 cannot be closed at all times cannot be sustained, and when the allowable time Tx has elapsed, the car door 13 is forcibly closed.

When the counting operation for the time T is completed, the door opening/closing control unit 31 closes the car door 13, and starts the car 11 to the destination floor (step S20).

(Exposure control)

In the normal exposure control, the target value of the luminance is fixed. Therefore, for example, if the target value of the luminance is set to a value suitable for a dark environment, overexposure may occur in a bright environment. In contrast, if the target value of the luminance is set to a value suitable for a bright environment, underexposure may occur in a dark environment.

Fig. 8 and 9 show an example of an image captured by normal exposure control. The hall 15 is located at the upper side, and the car 11 is located at the lower side. In the figure, 16 denotes the floor surface of the hall 15, and 19 denotes the floor surface of the car 11. P1 represents a user who is facing the car 11 from the hall 15, and P2 represents a user who is riding in the car 11.

Now, it is assumed that the interior of the car 11 is in a bright environment and the hall 15 is in a dark environment. If the target value of the brightness used in the exposure control is set to a value suitable for the dark environment of the hall 15, the exposure control is performed in a bright direction as a whole at the time of shooting. Therefore, as shown in fig. 8, the image in the car 11 may be captured brighter than necessary, and the user P2 in the car 11 may not be detected accurately due to overexposure. On the other hand, if the target value of the brightness is set to a value suitable for a bright environment in the car 11, exposure control is performed in a darker direction as a whole at the time of shooting. Therefore, as shown in fig. 9, the hall 15 may be photographed darker than necessary, and the user P1 of the hall 15 may not be correctly detected due to underexposure.

Therefore, in the present embodiment, by setting the target value of the brightness used in the exposure control to an appropriate value corresponding to the imaging environment, the detection accuracy of the user who uses the captured image is improved. Hereinafter, a specific configuration will be described.

Fig. 10 is a block diagram showing a functional configuration of the image processing apparatus 20. In the example of fig. 10, a configuration is shown in which the camera 12 is provided with a part of the exposure control function (the photometric window setting unit 22c, the luminance measuring unit 22d, and the exposure control unit 22 g).

(1) Detection region setting unit 22a and detection processing unit 22b

The detection area setting unit 22a sets detection areas E1 and E2 (see fig. 3 and 4) for detecting a user on the captured image of the camera 12. The detection processing unit 22b detects the presence or absence of a user or an object using the image in the detection area E2 during the door opening operation, and detects the presence or absence of a user or an object using the image in the detection area E1 during the door closing operation.

(2) Photometry window setting section 22c

The light measurement window setting unit 22c sets a light measurement window in the car 11 or the hall 15 according to the open/close state of the car door 13. The "photometry window" indicates a range in which the brightness is measured in the captured image, and is set to be a part or the whole of the hall 15 on the captured image when the car door 13 is fully opened, and to be a part or the whole of the car 11 on the captured image when the car door 13 is fully closed. The photometric window may be set in accordance with the detection areas E1 and E2.

The photometric window setting section 22c may be provided at either the inside or the outside of the camera 12. When the photometry window setting section 22c in the camera 12 is used, the image processing device 20 acquires information (position, size, weight, etc.) on the photometry window from the camera 12 via the communication section 23, and supplies the information to the brightness measuring section 22d.

(3) Brightness measuring unit 22d

The luminance measurement unit 22d measures the luminance of the image in the photometric window as an index value. Specifically, the luminance measurement unit 22d obtains an average luminance value of the image in the photometric window, and acquires the average luminance value as an index value. In the case of obtaining the average luminance value, the luminance value may be obtained by dividing the photometry window into blocks of an arbitrary size, for example, by increasing the weight of the luminance value of a portion susceptible to the outdoor light, and by weighting the luminance value for each block.

The brightness measuring section 22d may be provided at either the inside or the outside of the camera 12. When the brightness measuring unit 22d in the camera 12 is used, the image processing device 20 acquires information indicating the brightness of the image in the light metering window from the camera 12 via the communication unit 23 and supplies the information to the target value determining unit 22e.

(4) Target value determining unit 22e

The target value determining unit 22e determines a target value of the luminance used for exposure control based on the index value of the luminance measured by the luminance measuring unit 22 d. The method for determining the target value is as follows: (a) A method selected from a plurality of target values prepared in advance, and (b) a method using an equation for calculating a target value of brightness.

(A) Method for selecting from a plurality of target values

The target value storage unit 21a stores a plurality of target values including a target value set for a bright environment and a target value set for a dark environment.

Bright and dark environments

The target value determination unit 22e compares an index value indicating the brightness of the image in the measurement window with a preset threshold value. When the index value of the luminance is equal to or greater than the threshold value, that is, when the image is captured in a bright environment, the target value determination unit 22e selects the target value set for the bright environment from the target value storage unit 21a. On the other hand, when the index value of the luminance is lower than the threshold value, that is, when the image is captured in a dark environment, the target value determination unit 22e selects the target value set for the dark environment from the target value storage unit 21a. The threshold value may be changed when the light measurement window is set in the car 11 or when the light measurement window is set in the hall 15, or may be the same.

Further, a plurality of target values for a bright environment and a plurality of target values for a dark environment may be prepared in advance, and a target value corresponding to an index value of brightness may be selected stepwise from these target values by comparison with a plurality of threshold values.

Door state

The brightness in the hall 15 and the car 11 changes according to the door state (during door full open/close operation, door full close/open operation). In the target value storage unit 21a, a plurality of target values set for a bright environment and a dark environment are stored in consideration of such a door state. Information about the door status is obtained from the elevator controller 30.

When the index value indicating the brightness of the image in the measurement window is equal to or greater than the threshold value (in the case of a bright environment), the target value determination unit 22e selectively switches the target value according to the door state among the plurality of target values set for the bright environment. When the index value is lower than the threshold value (in the case of a dark environment), the target value determination unit 22e selectively switches the target value according to the door state among the target values set for the dark environment.

Floor information

The floor surface of the hall 15 of each floor may be different in color, wall color, and the like. The target value storage unit 21a stores a plurality of target values set for a bright environment and a dark environment, taking into account floor information including the color of the floor surface, the color of the wall, and the like. Floor information is obtained from the elevator control device 30.

When the index value indicating the brightness of the image in the measurement window is equal to or greater than the threshold value (in the case of a bright environment), for example, if the car 11 is on the 1 st floor, the target value determining unit 22e selects a target value corresponding to the color of the floor surface of the 1 st floor, the color of the wall, or the like, from among a plurality of target values set for the bright environment. When the index value is lower than the threshold value (in the case of a dark environment), the target value determination unit 22e selects a target value corresponding to the color of the floor surface of layer 1, the color of the wall, or the like, from among a plurality of target values set for the dark environment.

Time of day

At the time of morning, day, and night, the brightness of the hall 15 also changes because sunlight and illumination light are different. In addition, for example, when a glass window for gazing is used for the car 11, the brightness of the car 11 also changes depending on the time. The target value storage unit 21a stores a plurality of target values set for a bright environment and a dark environment, on the condition that the time is such. The time information is obtained from the elevator control device 30.

When the index value indicating the brightness of the image in the measurement window is equal to or greater than the threshold value (in the case of a bright environment), for example, if the brightness is the time of the morning, the target value determination unit 22e selects a target value corresponding to the time of the morning from among a plurality of target values set for the bright environment. When the index value is lower than the threshold value (in the case of a dark environment), the target value determination unit 22e selects a target value corresponding to the morning time among a plurality of target values set for the dark environment.

Weather of

For example, on sunny days, cloudy days, rainy days, the intensity of sunlight is different, and thus the brightness of the hall 15 is also changed. In addition, for example, when a glass window for gazing is used for the car 11, the brightness of the car 11 also changes depending on weather. The target value storage unit 21a stores a plurality of target values set for bright environments and dark environments in consideration of the influence of sunlight caused by such weather.

Weather information is obtained from the elevator control 30. When the index value indicating the brightness of the image in the measurement window is equal to or greater than the threshold value (bright state), for example, if the image is a sunny day, the target value determination unit 22e selects a target value corresponding to the sunny day from among a plurality of target values set for the sunny environment. When the index value is lower than the threshold value (in the case of a dark environment), the target value determination unit 22e selects a target value corresponding to a sunny day from among a plurality of target values set for the dark environment.

The target value may be selected on the condition of any one of the above door state, floor information, time, and weather, or a plurality of target values may be selected in combination.

(B) Method of using formula

The target value of the luminance is expressed by the following first order function.

y＝ax+b…(1)

Y is a target value of luminance, and x is the luminance (average luminance value) of the image within the measurement window. a is a coefficient for converting the brightness of an image obtained from the camera 12 into a register value necessary for image processing. b is an offset value, which takes a positive or negative value depending on the brightness of the image. For example, when the brightness of the image in the measurement window is equal to or higher than the threshold value (that is, when the image is captured in a bright environment), the offset value b takes a negative value. In the case where the brightness of the image within the measurement window is lower than the threshold value (i.e., in the case of an image captured in a dark environment), the offset value b takes a positive value.

Fig. 11 to 14 show specific examples.

Fig. 11 and 12 show captured images before exposure control, and fig. 13 and 14 show captured images after exposure control. PW1 in the figure represents a measurement window set in the floor surface 16 of the hall 15 when the door is fully opened, and PW2 represents a measurement window set in the floor surface 19 of the car 11 when the door is fully closed. The numerical value added to the side of the measurement window represents the brightness of the image, and for example, the numerical value is set to "0" to "100", and the smaller the numerical value is, the darker the numerical value is, and the larger the numerical value is, the brighter the state is. The numerical values themselves are added for convenience, and are different from actual values.

For example, assume that the threshold value is set to "50", and the offset value b is set to "20". In addition, for simplicity of explanation, the coefficient a is set to "1".

As shown in fig. 11, when the brightness of the image in the measurement window PW1 is measured at the time of opening the door, x is set to "90" and is set to the threshold value "50" or more. In this case, a negative offset value b is applied, and a target value y= "70" of luminance is calculated from the above expression (1). By performing exposure control using this target value y, it is possible to avoid the image of the hall 15 from becoming too dark (underexposure).

As shown in fig. 12, x is set to "20" and is lower than the threshold value "50" when the brightness of the image in the measurement window PW2 is measured at the time of closing the door. In this case, a positive offset value b is applied, and the target value y= "40" of luminance is calculated by the above expression (1). By performing exposure control using the target value y, it is possible to avoid the image in the car 11 from becoming too bright (overexposed).

In this case, the offset value b is used as an example, but the offset value b may be prepared for each of a plurality of thresholds, and the target value y of the luminance may be obtained by selectively using the offset values b based on the luminance of the image in the measurement window.

(5) Target value setting unit 22f and exposure control unit 22g

The target value setting unit 22f sets the target value of the luminance determined by the target value determining unit 22e to the camera 12. The exposure control unit 22g changes the target value of the brightness during operation to turn ON/OFF the automatic exposure. The term "automatic exposure" as used herein refers to exposure control (exposure control of the present invention) using a target value of brightness appropriately set according to the shooting environment. When the auto exposure is ON, the exposure control unit 22g performs exposure control based ON a target value corresponding to the brightness of the image in the measurement window. Specifically, the exposure control unit 22g adjusts the exposure time or gain of the camera 12 so that the brightness of the captured image converges to the target value.

The "exposure time" is a time during which the imaging element included in the camera 12 is exposed to light through the lens, and corresponds to an opening time of the shutter at the time of shooting. The longer the exposure time, the brighter the image can be obtained. The "gain" is a coefficient for increasing or decreasing the output value of the camera 12. If the gain value is increased, the output value of the camera 12 is also increased, so that a bright image can be obtained. Both the exposure time and the gain may be adjusted, or either may be adjusted. However, if the gain is increased, noise included in the image is also amplified, so if the image quality is considered, it is preferable to adjust the exposure time. In addition, if the exposure time is too long, the moving object is blurred, and therefore, it is preferable to limit the exposure time not to exceed a preset value.

The exposure control unit 22g may be provided in any of the inside and outside of the camera 12. When the exposure control unit 22g is provided in the camera 12, that is, if the camera 12 has an automatic exposure function, the target value of the brightness is directly set to the camera 12, and ON/OFF of the automatic exposure is set. When the exposure control unit 22g is external (when it is provided in the image processing apparatus 20), a parameter value related to exposure control, such as exposure time and gain, corresponding to a target value of brightness is set to the camera 12.

Here, as a trigger for setting target values of ON/OFF and brightness of the auto exposure, a door opening/closing control signal outputted from the elevator control device 30 as a control signal of the door is used. In addition to this, for example, a signal output from the car 11 when the floors are flat, a signal based on a manual operation, a time schedule based on a calendar or a clock (such as a time when outdoor light is easy to enter) may be used. Any one of them may be used, or a plurality of them may be combined.

When the door opening/closing control signal is used as a trigger signal, automatic exposure is performed at the time of full door opening and full door closing. At this time, automatic exposure may not be performed when the door is reopened in the door closing action. This is because there is no large change in the shooting environment when the camera is turned back on, and there is no need to measure the brightness of the image again. In addition, if the automatic exposure is performed at each re-opening, a time is required until the brightness of the image stabilizes, and there is a possibility that a delay occurs in the user detection process. In the same manner as in the case of re-closing the door during the door opening operation, since the photographing environment does not change greatly, the automatic exposure may not be performed.

(6) Communication unit 23

The communication unit 23 is configured to receive, from an external device, a target value of the luminance stored in advance in the target value storage unit 21a, a formula for selecting the target value, a threshold value, or the like, or transmit a detection result of a user to the external device.

Next, the exposure control function is described with reference to fig. 15 and 16. Fig. 15 is a diagram showing a transition from the start to the end of exposure control, and fig. 16 is a flowchart showing an operation of exposure control processing of the image processing apparatus 20. In the following, the control unit 22 of the image processing apparatus 20 includes each function related to the exposure control function. The processing of the flowchart shown in fig. 16 is executed by the control section 22 as a computer.

When receiving the door opening/closing control signal output from the elevator control device 30 when the door is fully opened or when the door is fully closed as the exposure control start signal (yes in step S21), the control unit 22 executes the following processing.

That is, first, the control unit 22 switches the photometric window into the hall 15 or the car 11 in cooperation with the door opening and closing of the car door 13 (step S22). Specifically, as shown in fig. 11 and 12, the control unit 22 sets the measurement window PW1 in a part of the hall 15 on the captured image when the door is fully opened, and sets the measurement window PW1 in a part of the car 11 on the captured image when the door is fully closed. The measurement window PW1 may be set to the entire floor surface of the hall 15, or may be set in correspondence with the detection area E1 shown in fig. 3. Similarly, the measurement window PW2 may be set to the entire floor surface in the car 11, or may be set in correspondence with the detection area E2 shown in fig. 4.

Hereinafter, a case will be described in which the measurement window PW1 is set in the hall 15 when the door is fully opened.

When measuring the brightness of the image in the photometric window PW1, the control unit 22 sets a gain or exposure time for brightness measurement in advance (step S23). This is because the exposure value of the camera 12 is kept in the state at the time of the last shooting, and therefore the state needs to be cleared, and the exposure value is adjusted for brightness measurement. The setting operation here is different from the automatic exposure performed in step S31 described later.

Here, the control unit 22 starts a first timer for brightness measurement (step S24). The control unit 22 measures the brightness of the image in the light measurement window PW1 (steps S25 to S26) until a predetermined time T1 (about 2 frames) is counted by the first timer. As described with reference to the example of fig. 15, when the time in which the gain or exposure time for brightness measurement is set in step S23 is T0, the period from T0 to T1 is the brightness measurement period, and corresponds to the time T1 counted by the first timer.

The reason why photometry is continued during the time T1 is that at least about 2 frames are required to obtain a stable image according to the gain or exposure time for brightness measurement set in the step S23. The first timer for brightness measurement is provided in the image processing apparatus 20 together with a second timer for automatic exposure, which will be described later.

When the counting of the time T1 is completed (yes in step S26), the control unit 22 acquires the brightness of the image measured in step S25 as an index value (step S27). Specifically, the control unit 22 obtains an average luminance value of the image within the photometric window PW1, and uses the average luminance value as an index value of luminance. The control unit 22 determines a target value used for exposure control based on the index value of the brightness, and sets the camera 12 (step S28). As described above, there are a method of selecting in advance from a plurality of target values and a method of using a formula for calculating a target value of luminance as a method of determining a target value.

Here, the control section 22 switches the auto exposure to ON (step S29). The control unit 22 starts a second timer for automatic exposure (step S30), and performs automatic exposure using the target value of brightness until a predetermined time T2 is counted by the second timer (steps S31 to S32). In the example of fig. 15, when the time when the luminance measurement period (time T1) has elapsed from T0 is T1, the period from T1 to T2 is an auto exposure period, and corresponds to the time T2 counted by the second timer. In the period from t1 to t2, the exposure time and the gain are controlled so that the brightness of the captured image of the camera 12 converges to the target value of the brightness set in step S28.

The automatic exposure is continued during the above-described time T2 because, as in the case of the brightness measurement, a time is required before the image is stabilized. In this case, if the target value is close to the index value of the luminance, the convergence time of the auto exposure is also short (about 2 frames), but if the target value is far from the index value of the luminance, the convergence time of the auto exposure is also long accordingly. Therefore, the time T2 is preferably set to be longer than the time T1 (T2 > T1).

When the counting of the time T2 is completed (yes in step S32), the control unit 22 turns off the auto exposure and prepares for the next auto exposure (step S33). For example, when the door is fully opened, the automatic exposure is performed in accordance with the brightness of the hall 15, and then when the door is fully closed, the automatic exposure is performed in accordance with the brightness of the car 11.

If the door is fully closed, a measurement window PW2 is set in the car 11, and the average luminance value of the image in the measurement window PW2 is obtained as an index value of the luminance in the same manner as described above, and a target value used for exposure control is determined based on the index value of the luminance. Thereby, the exposure time or gain is controlled so that the brightness of the captured image of the camera 12 converges to the target value.

As described above, according to the present embodiment, the light metering window is switched to the hall 15 or the car 11 in accordance with the opening and closing of the door, and a target value of the brightness suitable for the image in the light metering window is set. By performing exposure control using this target value, for example, when the hall 15 is in a bright environment, it is possible to avoid the image of the hall 15 from becoming excessively dark, and it is possible to accurately detect a user in the detection area E1 of the hall 15. In addition, in the case where the interior of the car 11 is a dark environment, it is possible to avoid excessively bright images in the car 11, and to accurately detect a user in the detection area E2 in the car 11.

According to at least one embodiment described above, it is possible to provide an elevator user detection system capable of appropriately setting a target value of brightness used for exposure control according to the respective environments in the car and the hall, and accurately detecting a user in the car and a user in the hall.

In addition, although several embodiments of the present invention have been described, these embodiments are presented as examples and are not meant to limit the scope of the invention. These novel embodiments can be implemented in various other modes, and various omissions, substitutions, 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 equivalent scope thereof.

Claims (7)

1. An elevator user detection system for detecting a user in an elevator car and a user in a hall located near an entrance of the elevator car by using an image of a camera provided in the elevator car, the elevator user detection system comprising:

A light measurement window setting unit that sets a light measurement window in the car or in the hall on a captured image obtained from the camera, according to an open/close state of a door of the car;

a measurement unit that measures, as an index value, the brightness of an image within the photometry window;

a target value determining unit that determines a target value of the luminance based on the index value obtained by the measuring unit; and

An exposure control unit that controls exposure of the camera so that the brightness of the image converges to the target value determined by the target value determination unit.

2. The elevator user detection system of claim 1, wherein,

The light metering window setting unit sets the light metering window in a part or the whole of the hall when the door is fully opened, and sets the light metering window in a part or the whole of the car when the door is fully closed.

3. The elevator user detection system of claim 1, wherein,

Comprising a storage unit for storing a plurality of target values set for a bright environment and a plurality of target values set for a dark environment,

The target value determining means compares the index value with a preset threshold value of brightness, and selects one of a plurality of target values set for the bright environment or a plurality of target values set for the dark environment based on the comparison result.

4. The elevator user detection system of claim 3, wherein,

The target value determining means selects one of a plurality of target values set for the dark environment or one of a plurality of target values set for the bright environment in consideration of any one or a combination of a door state, floor information, time, and weather.

5. The elevator user detection system of claim 1, wherein,

The target value determination unit uses an equation for calculating the target value from the index value.

6. The elevator user detection system of claim 1, wherein,

And a detection processing unit that detects a user in the car and a user located near the entrance of the car using an image of the camera that has performed exposure control at the target value, and reflects the detection result to the opening/closing control of the door.

7. An exposure control method for use in a system for detecting a user in an elevator car and a user in a hall located near an entrance of the elevator car by using an image of a camera provided in the elevator car, the exposure control method comprising,

A light measuring window is set in the car or in the hall on the shot image obtained from the camera at the time when the car is fully opened or fully closed,

After setting the photometry window, measuring the brightness of the image in the photometry window as an index value in a first period,

After a target value of brightness is determined based on the index value, exposure of the camera is controlled so that the brightness of the image converges to the target value during a second period.