JP2018123646A - Periphery monitoring system for work machine - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a periphery monitoring system for work machine capable of adjusting object detection performance by object detection means by an operator or the like, as needed.SOLUTION: A periphery monitoring system for work machine includes: an object detection section which detects a predetermined object in the periphery of a work machine; a notification section which notifies a user that an object is detected when the object is detected by the object detection section; and an operation section provided in the periphery of an operation seat of the work machine, where the object detection section changes sensitivity that detects the object according to a predetermined operation to the operation section.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a work machine periphery monitoring system.

  Peripheral monitoring system for a work machine comprising: an object detection unit that detects a predetermined object (for example, a person) around the work machine; and a notification unit that notifies when a predetermined object is detected by the object detection unit Is known (see, for example, Patent Document 1).

JP 2014-181508 A

  However, when there are a wide variety of surrounding environments, such as work machines, the object detection performance depends on the surrounding environment, resulting in false detections, omissions, etc., resulting in incorrect notifications or omissions. There is a possibility.

  In view of the above problems, an object of the present invention is to provide a work machine periphery monitoring system in which an operator or the like can adjust the object detection performance of the object detection means as necessary.

In order to achieve the above object, in one embodiment of the present invention,
An object detection unit for detecting a predetermined object around the work machine;
A notification unit for notifying that the object has been detected when the object is detected by the object detection unit;
A first operating portion provided around a cockpit of the work machine,
The object detection unit changes sensitivity of detecting the object in accordance with a predetermined operation on the first operation unit.
A work machine peripheral monitoring system is provided.

  According to the above-described embodiment, it is possible to provide a work machine periphery monitoring system in which an operator or the like can adjust the object detection performance of the object detection unit as necessary.

It is a figure which shows an example of the working machine with which the periphery monitoring system which concerns on this embodiment is mounted. It is a figure which shows an example of a structure of the periphery monitoring system which concerns on this embodiment. It is a figure which shows an example of the image for monitoring displayed on a display apparatus. It is a figure which shows an example of the display mode in which the area | region (detection object area | region) in which the detection target in the through image displayed on a display apparatus and a peripheral image is included is emphasized. It is a flowchart which shows roughly the 1st example of the process by a periphery monitoring system (person detection part). It is a figure which shows an example of the through image displayed on a display apparatus at the time of the detection miss of a detection target, and the time of an erroneous detection. It is a figure which shows an example of the peripheral image displayed on a display apparatus at the time of the detection miss of a detection target, and the time of an erroneous detection. It is a flowchart which shows roughly the 2nd example of the process by a periphery monitoring system (person detection part). It is a flowchart which shows roughly the 3rd example of the process by a periphery monitoring system (person detection part). It is a flowchart which shows roughly the 4th example of the process by a periphery monitoring system (person detection part). It is a figure which shows the other example of a structure of the periphery monitoring system which concerns on this embodiment. It is a figure which shows an example of the through image displayed on a display apparatus according to the process of FIG. It is a figure which shows the other example of the through image displayed on a display apparatus according to the process of FIG.

  Hereinafter, embodiments for carrying out the invention will be described with reference to the drawings.

  First, with reference to FIG. 1, the working machine in which the periphery monitoring system 100 (refer FIG. 2) which concerns on this embodiment is mounted is demonstrated.

  FIG. 1 is a diagram illustrating an example of a work machine on which the periphery monitoring system 100 according to the present embodiment is mounted, and is specifically a side view of an excavator.

  Note that the periphery monitoring system 100 according to the present embodiment may be mounted on a work machine other than an excavator, for example, a wheel loader, an asphalt finisher, or the like.

  The shovel according to the present embodiment includes a lower traveling body 1, an upper revolving body 3 that is mounted on the lower traveling body 1 so as to be able to swivel via a turning mechanism 2, a boom 4, an arm 5, and a bucket 6 as working devices. And a cabin 10 on which the operator is boarded.

  The lower traveling body 1 includes, for example, a pair of left and right crawlers, and each crawler is self-propelled by being hydraulically driven by a traveling hydraulic motor (not shown).

  The upper swing body 3 rotates with respect to the lower traveling body 1 by being driven by a swing hydraulic motor, an electric motor (both not shown) or the like.

  The boom 4 is pivotally attached to the center of the front part of the upper swing body 3 so that the boom 4 can be raised and lowered. An arm 5 is pivotally attached to the tip of the boom 4 and a bucket 6 is vertically attached to the tip of the arm 5. It is pivotally attached so that it can rotate. The boom 4, the arm 5, and the bucket 6 are hydraulically driven by a boom cylinder 7, an arm cylinder 8, and a bucket cylinder 9, respectively.

  The cabin 10 is a cockpit where an operator is boarded, and is mounted on the front left side of the upper swing body 3.

  The excavator according to the present embodiment includes a controller 30, an imaging device 40, a screen operation unit 44, a display device 50, and an audio output device 52 as components related to the periphery monitoring system 100.

  The controller 30 is a control device that performs drive control of the shovel. The controller 30 is mounted in the cabin 10.

  The imaging device 40 is attached to the upper part of the upper swing body 3 and images the periphery of the excavator. The imaging device 40 includes a rear camera 40B, a left side camera 40L, and a right side camera 40R.

  The rear camera 40 </ b> B is attached to the upper part of the rear end of the upper swing body 3 and images the rear of the upper swing body 3.

  The left side camera 40L is attached to the upper left end of the upper swing body 3 and images the left side of the upper swing body 3.

  The right side camera 40R is attached to the upper right end of the upper swing body 3 and images the right side of the upper swing body 3.

  The screen operation unit 44 (an example of the first operation unit and the second operation unit) is provided around the cockpit in the cabin 10, specifically, at a position that can be easily operated by an operator seated in the cockpit. Various operations on the screen displayed on the display device 50 are performed. The screen operation unit 44 may have any configuration as long as various operations on the screen displayed on the display device 50 are possible. For example, the screen operation unit 44 may be a touch panel that is integrally mounted on a display area of a liquid crystal display as the display device 50, or a touch pad, a click wheel, a joystick, etc. provided separately from the display device 50. The operation device may be used. Hereinafter, the screen operation unit 44 will be described on the assumption that it is a touch panel that is integrated with the display device 50.

  The display device 50 (an example of a notification unit) is provided in the vicinity of the cockpit in the cabin 10, specifically, at a position that can be easily seen by an operator sitting on the cockpit, and the controller 30 (specifically, will be described later). Various image information to be notified to the operator is displayed under the control of the display control unit 302). The display device 50 is, for example, a liquid crystal display.

  The audio output device 52 is provided around the cockpit in the cabin 10 and outputs various types of audio information notified to the operator under the control of the controller 30. The audio output device 52 is, for example, a speaker or a buzzer.

  Next, a specific configuration of the periphery monitoring system 100 according to the present embodiment will be described with reference to FIG.

  FIG. 2 is a block diagram illustrating an example of the configuration of the periphery monitoring system 100 according to the present embodiment.

  The periphery monitoring system 100 monitors the entry of a predetermined object (in this embodiment, a person) into a predetermined range around the excavator, and outputs a warning when a predetermined object is detected. The periphery monitoring system 100 includes a controller 30, an imaging device 40, a display device 50, and an audio output device 52.

  The controller 30 performs various control processes in the periphery monitoring system 100. The controller 30 may be realized by arbitrary hardware, software, or a combination thereof. The controller 30 is mainly configured by a microcomputer including a CPU, RAM, ROM, I / O, and the like. The controller 30 includes, for example, a human detection unit 301, a display control unit 302, and an alarm output unit 303 as functional units realized by executing various programs stored in the ROM on the CPU.

  As described above, the imaging device 40 includes the rear camera 40B, the left camera 40L, and the right camera 40R. The rear camera 40B, the left side camera 40L, and the right side camera 40R are mounted on the upper part of the upper revolving unit 3 so that the optical axis is obliquely downward, and includes an image in the vertical direction including the ground in the vicinity of the shovel to the far side of the shovel. It has a range (angle of view). The rear camera 40B, the left side camera 40L, and the right side camera 40R output a captured image and transmit it to the controller 30 every predetermined period (for example, 1/30 second) during operation of the excavator.

  The screen operation unit 44 transmits a signal related to the operation state of the screen of the display device 50 by the operator to the controller 30.

  The display device 50 displays a captured image (through image) of the imaging device 40, a peripheral image (for example, a viewpoint conversion image described later) generated by the controller 30 (display control unit 302) based on the captured image of the imaging device 40, and the like. To do. In addition, the display device 50 displays a captured image of the imaging device 40 including a person detected by a human detection unit 301 described later or a peripheral image generated based on the captured image under the control of the display control unit 302 described later. By displaying, it is possible to notify an operator or the like that a person has been detected by the person detection unit 301.

  The audio output device 52 outputs an alarm sound under the control of the controller 30 (alarm output unit 303).

  The human detection unit 301 (an example of an object detection unit) is configured to search for a person within a predetermined area around the excavator, for example, a predetermined distance D1 (for example, 5 meters) from the excavator, based on the captured image captured by the imaging device 40. Detect. The human detection unit 301 recognizes a person in the captured image by arbitrarily applying various known image processing methods, machine learning-based classifiers, and the like, and recognizes the actual position of the recognized person (person recognized from the excavator). Distance D, etc.) can be specified. For example, the human detection unit 301 has an extraction function for extracting a target image for identification processing from a captured image of the imaging device 40, and a candidate image included in the extracted target image is an object to be detected (in the case of the present embodiment, a person). Detecting the person who is the detection target using the identification function that identifies whether the image is a detection target image corresponding to, and the tracking function that tracks the identification result in time series and outputs the final detection result Good.

  Specifically, the human detection unit 301 uses the extraction function to provide a simple feature based on a local luminance gradient or edge, a geometric feature based on Hough transform, and the area of a region divided based on the luminance. Alternatively, the target image for identification processing may be extracted by image processing with a relatively small amount of calculation for extracting features and the like regarding the aspect ratio. The target image is an image portion (a part of the captured image) that is a target of subsequent image processing, and includes a detection target candidate image. A candidate image is an image portion (part of a captured image) that is determined to be highly likely to be a detection target image.

  Further, the human detection unit 301 uses an identification function to perform image recognition processing using an image feature quantity typified by HOG (Histograms of Oriented Gradients) feature quantity and a known classifier generated by machine learning, etc. Whether the candidate image is the detection target image is identified by the image processing with a relatively large calculation amount.

  When the identification result regarding the same detection target for a predetermined number of consecutive times satisfies the predetermined condition by the tracking function (for example, the person of the same person in four of the six consecutive identification results) When the image is identified as an image), it is determined that the corresponding candidate image is the detection target image (that is, a person as a detection target object is detected at the corresponding three-dimensional position).

  The human detection unit 301 includes a plurality of (three in the present embodiment) sensitivity-specific person detection units 3011 to 3013 (an example of a sensitivity-specific object detection unit) having different sensitivities for detecting a detection target (person). The sensitivity for detecting the detection target (person) is the highest in the sensitivity-specific person detection unit 3013 among the sensitivity-specific person detection units 3011 to 3013, the sensitivity-specific person detection unit 3012 is the next highest, and the sensitivity-specific person detection unit 3011 is the lowest. In other words, the probability that the detection target (person) is missed is the lowest in the sensitivity-specific person detection unit 3013, the sensitivity-specific person detection unit 3012 is the next lowest, and the sensitivity-specific person detection unit 3011 is the highest. On the other hand, if the sensitivity to detect the detection target (person) increases, there is a high possibility that an object that is not the detection target (person) will be erroneously detected as the detection target. The probability of the person-by-sensitivity detection unit 3011 is the lowest, the person-by-sensitivity detection unit 3012 is the next lowest, and the person-by-sensitivity detection unit 3013 is the highest. The human detection unit 301 detects a person as a detection target by any one of a plurality of sensitivity-specific human detection units 3011 to 3013 having different sensitivity for detecting the detection target.

  The difference between the sensitivities of detecting the detection targets of the sensitivity-specific human detection units 3011 to 3013 can be realized, for example, by generating a discriminator used in the above-described discrimination function by a different machine learning method. . Specifically, when the discriminator used by the sensitivity-specific person detection unit 3011 is generated by machine learning, it is included in the teacher image rather than the penalty when the object to be detected included in the teacher image cannot be detected. On the premise that the penalty when the object that is not the detection target is erroneously detected as the detection target is set to a large value, the total penalty for the entire teacher image may be optimized. On the other hand, when the discriminator used in the sensitivity-specific person detection unit 3013 is generated by machine learning, it is a detection target rather than a penalty when an object that is not a detection target included in the teacher image is erroneously detected as a detection target. On the assumption that the penalty when the object cannot be detected is set to a large value, the total penalty for the entire teacher data may be optimized. When the classifier used by the sensitivity-specific person detection unit 3012 is machine-learned, a penalty when an object that is not a detection target included in the teacher image is erroneously detected as a detection target and an object that is the detection target can be detected. On the premise that the penalty is set to the same value, the total penalty for the entire teacher data may be optimized so as to be minimized. As a result, sensitivity-specific person detection units 3011 to 3013 having different sensitivities for detecting the detection target are generated.

  In addition, the human detection unit 301 has a plurality of sensitivity-specific human detection units 3011 to 3013 having different sensitivities for detecting a detection target, but by changing parameters that affect the sensitivity continuously or stepwise. The mode of changing the sensitivity may be used. The human detection unit 301 detects a person as a predetermined object to be monitored, but may detect other predetermined objects, such as a vehicle.

  The display control unit 302 displays various information images on the display device 50 according to various operations by the operator. For example, the display control unit 302 causes the display device 50 to display a captured image (through image) of the imaging device 40 (rear camera 40B, left camera 40L, right camera 40R) in accordance with a predetermined operation by the operator. Further, for example, the display control unit 302 generates a peripheral image based on the captured image of the imaging device 40 in accordance with a predetermined operation by the operator, and causes the display device 50 to display the peripheral image. Specifically, the display control unit 302 performs a known viewpoint conversion process based on the captured images of the rear camera 40B, the left camera 40L, and the right camera 40R as the peripheral images, thereby generating a viewpoint converted image (virtual viewpoint). The image viewed from the above is generated and displayed on the display device 50. Further, when displaying the peripheral image on the display device 50, the display control unit 302 also shows the shovel image schematically representing the shovel in order to clearly indicate the relative positional relationship with respect to the shovel of the imaging range of the imaging device 40 that appears in the peripheral image. Display on the display device 50. That is, the display control unit 302 generates and displays a monitoring image including a shovel image and a peripheral image arranged around the shovel image in accordance with the relative positional relationship between the shovel and the imaging range of the imaging device 40. It is displayed on the device 50. Hereinafter, the monitoring image displayed on the display device 50 will be described with reference to FIG.

  FIG. 3 is a diagram illustrating an example of a monitoring image displayed on the display device 50. As shown in FIG. 3, on the horizontally long rectangular screen (for example, a screen having an aspect ratio of 4: 3) in the display device 50, as described above, the excavator image CG and the peripheral image arranged around the excavator image CG are provided. A monitoring image including the EP is displayed. Accordingly, the operator can appropriately grasp the positional relationship between the object including the person shown in the peripheral image EP and the excavator.

  The peripheral image EP in this example is a viewpoint conversion image that is a combination of a road surface image of the excavator periphery viewed from directly above and a horizontal image that is disposed around the road surface image and viewed in the horizontal direction of the excavator periphery. Peripheral images (viewpoint conversion images) are obtained by projecting captured images of the rear camera 40B, the left camera 40L, and the right camera 40R onto a spatial model, and then projecting the projection image projected onto the spatial model into another two images. It is obtained by reprojecting on a dimensional plane. The space model is a projection target of the captured image in the virtual space, and is configured by one or a plurality of planes or curved surfaces including a plane or curved surface other than the plane on which the captured image is located. Hereinafter, the description will be continued on the assumption that the peripheral image in the present embodiment is a viewpoint conversion image obtained by combining the road surface image and the horizontal image.

  Further, the guideline LN1 is superimposed and displayed on the monitoring image. The guideline LN1 represents a position where the distance from the shovel is a predetermined distance D2 (<D1). Thereby, when the object containing a person is reflected in the surrounding image, the operator can grasp how far the excavator is located.

  Returning to FIG. 2, the display control unit 302 detects the detection target (person) in the through image or the peripheral image displayed on the display device 50 when the human detection unit 301 detects the detection target person. The region (detection target region) including is emphasized. Hereinafter, with reference to FIG. 4, a display mode in which the detection target region in the through image and the peripheral image is emphasized will be described.

  Note that the above-described functions of the display control unit 302 may be built in the display device 50. In this case, information such as a captured image of the imaging device 40 (rear camera 40B, left side camera 40L, right side camera 40R) and a detection result of the human detection unit 301 is displayed from the imaging device 40 and the controller 30 to the display device 50, respectively. Is input.

  FIG. 4 is a diagram illustrating an example of a display mode in which a detection target region in the through image and the peripheral image displayed on the display device 50 is emphasized. Specifically, FIG. 4A is an example of a display mode in which a detection target region in the through image is emphasized, and FIG. 4B is a detection in a peripheral image included in the monitoring image. It is an example of the display mode in which the target region is emphasized. In this example, as shown in FIGS. 4A and 4B, the detection target region including the detection target (person) in the through image TP and the peripheral image EP is surrounded by a thick frame FR. It is emphasized. Thereby, the operator or the like can easily grasp where the person detected by the person detection unit 301 exists around the excavator.

  The display control unit 302 may use any method other than surrounding the detection target region with a thick line frame as a display mode for emphasizing the detection target region in the through image and the peripheral image. The luminance may be made higher than that in other areas, or the color of the detection target area may be different from that in other areas.

  Returning to FIG. 2, when the person detection unit 301 detects a person within a predetermined distance D <b> 1 from the shovel, the alarm output unit 303 issues an alarm to an operator or the like. For example, the alarm output unit 303 outputs an alarm by sound. Specifically, the warning output unit 303 outputs a warning sound through the voice output device 52. Further, for example, the alarm output unit 303 may perform an alarm with a higher alarm level indicating a danger level as the distance is shorter within a predetermined range around the excavator (within a predetermined distance D1 from the excavator). Specifically, the alarm output unit 303 determines whether or not the distance D from the person's excavator detected by the human detection unit 301 is equal to or smaller than a predetermined distance D2 (for example, 2.5 meters) smaller than the predetermined distance D1. May change the alarm level (alarm specifications). More specifically, the alarm output unit 303 is in a caution state (alarm level 1) with a relatively low risk level when the detected distance D from the excavator of the person is less than the predetermined distance D1 and greater than the predetermined distance D2. A preliminary alarm (for example, a warning sound with a relatively low volume is output to the speaker) is output. In addition, when the detected distance from the excavator of the person is equal to or less than the predetermined distance D2, the alarm output unit 303 determines that the alarm state (alarm level 2) is a relatively high risk level, for example, a formal alarm (for example, comparison) Output a loud warning sound to a speaker or the like.

  The alarm output unit 303 may display an alarm indicating that there is a person around the shovel on the display device 50 by sending a display request to the display control unit 302.

  Next, characteristic processing by the periphery monitoring system 100 (human detection unit 301) according to the present embodiment will be described with reference to FIGS.

  First, FIG. 5 is a flowchart schematically showing a first example of processing by the periphery monitoring system 100 (human detection unit 301). The processing according to this flowchart may be repeatedly executed in a state where a through image or a monitoring image is displayed on the display device 50 during operation of the excavator, for example.

  In addition, the person detection part 301 is set so that the person who is a detection target may be detected by any one of the sensitivity-specific person detection parts 3011 to 3013 as an initial state. Hereinafter, the human detection unit 301 will be described on the premise that the person is detected by the sensitivity-specific human detection unit 3012 as an initial state. The same applies to FIGS. 8 and 9 described later.

  In step S102, the human detection unit 301 determines whether or not an operation (sensitivity change operation) for changing (that is, increasing or decreasing) the sensitivity for detecting the detection target has been performed on the screen operation unit 44. . In the case of this embodiment, the sensitivity change operation is an operation of changing the sensitivity-specific person detection unit used for human detection by the human detection unit 301 in the sensitivity-specific person detection units 3011 to 3013. The operation may be realized by touching on the touch panel an icon corresponding to each of the sensitivity-specific person detection units 3011 to 3013 displayed superimposed on the through image or the monitoring image. When the sensitivity change operation is performed on the screen operation unit 44, the human detection unit 301 proceeds to step S104, and when the sensitivity change operation is not performed, the human detection unit 301 proceeds to step S110.

  In step S104, the human detection unit 301 selects an area for changing the sensitivity for detecting the detection target in the through image or the entire peripheral image with respect to the screen operation unit 44 before the sensitivity change operation. It is determined whether (area selection operation) is performed. For example, the region selection operation is performed by touching a desired position on the touch panel on the premise that the through image and the entire peripheral image are previously divided into a plurality of small regions. A mode in which a small region including the position is selected may be selected, or a mode in which an arbitrary region is selected by performing an operation of tracing a desired region on the touch panel may be performed. . When the region selection operation is not performed on the screen operation unit 44, the human detection unit 301 proceeds to step S106. When the region selection operation is performed, the human detection unit 301 proceeds to step S108.

  In step S106, the human detection unit 301 changes the sensitivity for detecting the detection target in the peripheral region of the shovel corresponding to the through image or the entire peripheral image in accordance with the content of the sensitivity change operation, and ends the current process. To do. That is, the human detection unit 301 changes the sensitivity-specific human detection unit used for detection of the detection target in the peripheral region of the shovel corresponding to the entire through image or the peripheral image, and ends the current process.

  On the other hand, in step S108, the human detection unit 301 detects in the peripheral region of the shovel corresponding to the partial region of the through image or the peripheral image (region selected by the region selection operation) according to the content of the sensitivity change operation. The sensitivity for detecting the target is changed, and the current process ends. That is, the human detection unit 301 changes the sensitivity-specific human detection unit used for detection of the detection target in the peripheral region of the shovel corresponding to the through image or a partial region of the peripheral image, and ends the current process.

  In addition, since the range imaged by the imaging device 40 changes according to the movement of the excavator due to traveling by the lower traveling body 1 or the turning of the upper revolving body 3, for example, the human detection unit 301 may By calculating the movement amount and the turning amount and buffering, it is possible to determine the absolute position of the through image or the entire peripheral image or the partial region selected by the region selection operation.

  On the other hand, in step S110, the human detection unit 301 determines whether or not an operation (reset operation) for returning the sensitivity for detecting the detection target to the initial state has been performed. The reset operation may be, for example, an operation of touching a predetermined icon displayed superimposed on the through image or the monitoring image, or a predetermined operation on the screen operation unit 44 (for example, an operation of double-tapping the touch panel) The operation that is uniquely realized by () may be used. When the reset operation is performed on the screen operation unit 44, the human detection unit 301 proceeds to step S112. When the reset operation is not performed, the human detection unit 301 ends the current process.

  In step S112, the human detection unit 301 returns the sensitivity for detecting the detection target to the initial state, that is, the detection target (person) using the sensitivity-specific human detection unit 3012 among the sensitivity-specific human detection units 3011 to 3013. Is returned to the state of detecting, and the current process is terminated.

  As described above, in this embodiment, the sensitivity for detecting the detection target by the human detection unit 301 is changed according to a predetermined area around the excavator (in accordance with the sensitivity change operation for the screen operation unit 44. As a result, the operator or the like If necessary, the detection performance of the human detection unit 301 can be adjusted. As a result, the false alarm of the alarm output unit 303 due to the false detection of the detection target (person) by the human detection unit 301 or the detection omission is detected. Output and alarm leakage can be suppressed.

  For example, FIG. 6 is a diagram illustrating an example of the through image TP displayed on the display device 50 when the detection target of the detection target is missed (FIG. 6A) and erroneous detection (FIG. 6B). FIG. 7 is a diagram illustrating an example of a monitoring image displayed on the display device 50 when a detection target is missed or erroneously detected. In this example, icons BT1 to BT3 for selecting each of the sensitivity detection person detection units 3011 to 3013 are provided at the lower ends of the through image TP and the monitoring image, and are currently used by the person detection unit 301. The sensitivity-specific person detection unit 3012 is highlighted with a thick frame.

  In the example shown in FIG. 6A, the person detection unit 301 is not emphasized because the area AR1 including the person in the through image is not surrounded by a thick line frame FR even though a person is shown in the through image. Shows that the person is not detected. On the other hand, the operator or the like performs a sensitivity changing operation on the touch panel by touching the BT1 corresponding to the sensitivity-specific person detection unit 3011 having a higher sensitivity for detecting the detection target than the currently set sensitivity-specific person detection unit 3012. Good. At this time, the operator or the like may select the area AR1 as an area for changing the sensitivity for detecting the detection target by an area selection operation. Thereby, since the sensitivity which detects the detection target of the person detection part 301 in the peripheral area | region of the shovel corresponding to the area | region AR1 in which the whole through-image or a person exists exists, a detection omission can be suppressed.

  In the example shown in FIG. 6B, the object (the bush plant) other than the detection target included in the through image is surrounded by the thick frame FR although the detection target (person) is not shown in the through image. Therefore, it can be seen that the human detection unit 301 erroneously detects an object other than the detection target. On the other hand, an operator or the like performs a sensitivity change operation on the touch panel by touching the BT 3 corresponding to the sensitivity-specific person detection unit 3013 having a lower sensitivity than the currently set sensitivity-specific person detection unit 3012. Good. At this time, the operator or the like may select the area AR2 surrounded by the thick frame FR as the area for changing the sensitivity for detecting the detection target by the area selection operation. Thereby, since the sensitivity which detects the detection target of the human detection part 301 in the peripheral area | region of the shovel corresponding to the area | region AR2 in which the whole through-image or the misdetected object exists exists, a false detection can be suppressed.

  Further, in the example shown in FIG. 7, the area AR3 including the person shown in the peripheral image EP is not emphasized by being surrounded by the thick line frame FR, and therefore the person detection unit 301 cannot detect the person. I understand. In addition, since an object (bush plant) other than the detection target shown in the peripheral image EP is surrounded by a thick line frame FR, it can be seen that the human detection unit 301 erroneously detects an object other than the detection target. . On the other hand, the operator or the like selects the area AR3 including the person in the peripheral image EP by the area selection operation, and detects the detection target on the touch panel from the currently set sensitivity detection unit 3012. It is preferable to perform a sensitivity changing operation of touching BT1 corresponding to the sensitivity-specific person detection unit 3011 having high sensitivity. Thereby, since the sensitivity which detects the detection target of the person detection part 301 in the peripheral area | region of the shovel corresponding to area | region AR3 in which the person of a peripheral image exists exists, a detection omission can be suppressed. At the same time, the operator or the like selects the area AR4 (area surrounded by the thick frame FR) including the object other than the detection target of the peripheral image EP by the area selection operation, and is currently set on the touch panel. A sensitivity change operation may be performed by touching the BT 3 corresponding to the sensitivity-specific person detection unit 3013 having a lower sensitivity for detecting the detection target than the sensitivity-specific person detection unit 3012. Thereby, since the sensitivity which detects the detection target of the human detection part 301 in the peripheral area | region of the shovel corresponding to the area | region AR2 in which the whole through-image or the misdetected object exists exists, a false detection can be suppressed.

  In this embodiment (FIG. 5), instead of the display device 50 capable of notifying an operator or the like that a person has been detected by the person detection unit 301, other notification means (for example, an indicator lamp or a person is detected). A voice output device 52) that outputs a voice to notify the user may be provided. In this case, instead of the screen operation unit 44, another operation unit (for example, a push button switch or the like) is provided, and the human detection unit 301 performs an operation content for the other operation unit (operation to increase or decrease sensitivity). Accordingly, the sensitivity for detecting the person who is the detection target is changed. Thus, for example, when a person has entered the peripheral area of the excavator and no notification is made by another notification means, the operator or the like operates the other operation unit, and the person by the human detection unit 301 By increasing the sensitivity for detecting the detection error, it is possible to suppress the detection omission of people around the excavator. In addition, for example, an operator or the like operates the other operation unit when a notification that a person has been detected by another notification means has been made even though no person has entered the vicinity of the excavator. In addition, by reducing the sensitivity for detecting a person, it is possible to suppress false detection of a person around the excavator.

  Next, FIG. 8 is a flowchart schematically showing a second example of processing by the periphery monitoring system 100 (human detection unit 301). As in the case of FIG. 5, for example, during the operation of the excavator, the processing according to this flowchart may be repeatedly performed in a state where a through image or a monitoring image is displayed on the display device 50.

  In step S202, the human detection unit 301 determines whether or not a detection target (person) is detected, that is, a region (emphasized region) emphasized by a thick line frame or the like on the through image or the peripheral image of the display device 50. ) Is determined. The human detection unit 301 proceeds to step S204 if the detection target (person) is being detected, and proceeds to step S208 otherwise.

  In step S <b> 204, the human detection unit 301 determines whether or not an operation (enhancement region selection operation) for selecting an enhancement region of a through image or a peripheral image has been performed on the screen operation unit 44. The highlight region selection operation may be, for example, an operation in which the highlight region is touched on the touch panel, or an operation realized by performing an operation of enclosing the highlight region on the touch panel. Good. The human detection unit 301 proceeds to step S206 when the highlight region selection operation is performed on the screen operation unit 44, and proceeds to step S208 when the highlight region selection operation is not performed.

  In step S206, the human detection unit 301 lowers the sensitivity of detecting the detection target in the peripheral region of the shovel corresponding to the through region or the enhancement region of the peripheral image selected by the enhancement region selection operation, and performs this processing. finish. That is, the human detection unit 301 uses a sensitivity-specific human detection unit used for detection of a detection target in the peripheral region of the excavator corresponding to the through image or the enhancement region of the peripheral image, and has a lower sensitivity than that currently set. Change this and end the current process.

  In this step, the human detection unit 301 may reduce the sensitivity for detecting the detection target in the peripheral region of the shovel corresponding to the through image or the entire peripheral image.

  On the other hand, in step S208, the human detection unit 301 determines whether or not an operation (reset operation) for returning the sensitivity for detecting the detection target to the initial state has been performed. When the reset operation is performed on the screen operation unit 44, the human detection unit 301 proceeds to step S210. When the reset operation is not performed, the human detection unit 301 ends the current process.

  In step S210, the human detection unit 301 returns the sensitivity for detecting the detection target to the initial state, that is, the detection target (person) using the sensitivity-specific human detection unit 3012 among the sensitivity-specific human detection units 3011 to 3013. Is returned to the state of detecting, and the current process is terminated.

  As described above, in this embodiment, when a through region or an emphasis region of a peripheral image is selected by an emphasis region selection operation on the screen operation unit 44, the sensitivity of automatically detecting a detection target by the human detection unit 301 is increased. Go down. For example, in the example shown in FIG. 6B and FIG. 7 described above, the operator or the like selects the areas AR2 and AR4 including the object (the bush plant) that is the object of false detection included in the through image and the surrounding image. The sensitivity for detecting the detection target by the human detection unit 301 is automatically reduced by performing the highlight region selection operation to be performed (specifically, the sensitivity-specific human detection unit used by the human detection unit 301 detects the sensitivity-specific human detection). The unit 3012 is changed to a sensitivity-specific person detection unit 3013). Thereby, when an erroneous detection in which an object other than the detection target is detected has occurred, the operator or the like simply selects a through image or a surrounding image enhancement region that includes the object that is the target of the erroneous detection, Sensitivity for detecting the detection target by the human detection unit 301 in the enhancement region can be lowered. Therefore, the output of the false alarm of the warning output part 303 by the false detection of the detection target (person) by the human detection part 301 can be suppressed by simpler operation.

  The process according to the present embodiment (FIG. 8) may be executed in combination with the process of the embodiment shown in FIG. In this embodiment (FIG. 8), instead of the display device 50 capable of notifying an operator or the like that a person has been detected by the person detection unit 301, other notification means (for example, an indicator lamp or a person is detected). A voice output device 52) that outputs a voice to notify the user may be provided. In this case, instead of the screen operation unit 44, another operation unit (for example, a push button switch) is provided, and the person detection unit 301 is notified that the person has been detected by the other notification means. In this case, when an operation is performed on the other operation unit, the sensitivity for automatically detecting a person who is a detection target is lowered. Thereby, for example, when a notification that a person has been detected by another notification means has been made even though no person has entered the vicinity of the excavator, the operator or the like Since the sensitivity for detecting a person can be lowered only by operating, it is possible to suppress erroneous detection of a person around the excavator with a simpler operation.

  Next, FIG. 9 is a flowchart schematically showing a third example of processing by the periphery monitoring system 100 (person detection unit 301). Similar to the case of FIGS. 5 and 8, for example, the processing according to the flowchart may be repeatedly executed while the through image or the monitoring image is displayed on the display device 50 during the operation of the shovel.

  In step S302, the human detection unit 301 determines whether or not an operation (selection operation outside the enhancement region) for selecting a region other than the enhancement region of the through image or the peripheral image is performed on the screen operation unit 44. judge. Regardless of whether or not the detection target (person) is detected by the human detection unit 301 in “an area other than the enhancement area”, that is, whether or not there is an enhancement area on the through image or the peripheral image, The entire region that is not the enhancement region in the through image or the peripheral image is included. For example, the selection operation outside the enhancement region is performed on the premise that the whole of the through image and the peripheral image are divided into a plurality of small regions in advance, and a position other than the enhancement region is touched on the touch panel. A mode in which a small area including the touched position may be selected, or an arbitrary area is selected by performing an operation of tracing a desired area other than the emphasized area on the touch panel. It may be an embodiment. The human detection unit 301 proceeds to step S304 when the highlight region selection operation is performed on the screen operation unit 44, and proceeds to step S306 when the highlight region selection operation is not performed.

  In step S304, the human detection unit 301 detects the detection target in the peripheral region of the shovel corresponding to the through image or a partial region of the peripheral image, which is selected by the selection operation outside the enhancement region. To end the current process. That is, the human detection unit 301 uses a sensitivity-specific human detection unit used for detection of a detection target in the peripheral region of the excavator corresponding to the through image or the enhancement region of the peripheral image, and has a lower sensitivity than that currently set. Change this and end the current process.

  In this step, the human detection unit 301 may increase the sensitivity of detecting the detection target in the peripheral region of the shovel corresponding to the through image or the entire peripheral image.

  On the other hand, in step S306, the human detection unit 301 determines whether or not an operation (reset operation) for returning the sensitivity for detecting the detection target to the initial state has been performed. When the reset operation is performed on the screen operation unit 44, the human detection unit 301 proceeds to step S308. When the reset operation is not performed, the human detection unit 301 ends the current process.

  In step S308, the human detection unit 301 returns the sensitivity for detecting the detection target to the initial state, that is, the detection target (person) using the sensitivity-specific human detection unit 3012 among the sensitivity-specific human detection units 3011 to 3013. Is returned to the state of detecting, and the current process is terminated.

  As described above, in this embodiment, when a region other than the enhancement region of the through image or the peripheral image is selected by the selection operation outside the enhancement region on the screen operation unit 44, the detection by the human detection unit 301 is automatically performed. Increases sensitivity to detect objects. For example, in the example shown in FIG. 6A and FIG. 7 described above, the operator or the like includes an area in which a person that is a detection target but is not detected by the human detection unit 301 is included in the through image and the peripheral image. By performing an out-of-emphasis region selection operation for selecting AR1 and AR3, the sensitivity for detecting the detection target by the human detection unit 301 automatically increases (specifically, the human detection by sensitivity used by the human detection unit 301). Is changed from the person-by-sensitivity detection unit 3012 to the person-by-sensitivity detection unit 3011). As a result, the operator or the like, when a detection omission in which the detection target is not detected has occurred, other than the through image including the object that is the detection target that has not been detected by the human detection unit 301 or the enhancement region of the peripheral image The sensitivity of detecting the detection target by the human detection unit 301 in the other region can be lowered simply by selecting another region. Therefore, the alarm leakage of the alarm output unit 303 due to the detection failure of the detection target (person) by the human detection unit 301 can be suppressed by a simpler operation.

  The process according to the present embodiment (FIG. 9) may be executed in combination with at least one of the processes according to the embodiment shown in FIGS. Further, in this embodiment (FIG. 9), instead of the display device 50 capable of notifying an operator or the like that a person has been detected by the person detection unit 301, other notification means (for example, an indicator lamp or a person is detected). A voice output device 52) that outputs a voice to notify the user may be provided. In this case, instead of the screen operation unit 44, another operation unit (for example, a push button switch) is provided, and the human detection unit 301 is not notified that the person has been detected by the other notification unit. In this case, when the other operation unit is operated, the sensitivity of detecting a person who is a detection target is increased. Thereby, for example, when the operator or the like does not receive a notification by other notification means even though a person has entered the peripheral area of the excavator, the operator or the like operates the other operation unit to thereby detect the person detection unit 301. Since the sensitivity for detecting a person can be increased, it is possible to suppress detection omission of a person around the excavator with a simpler operation.

  Further, in the above-described embodiments shown in FIGS. 5, 8, and 9, the human detection unit 301 replaces or in addition to the captured image of the imaging device 40 with other sensors such as a millimeter wave radar and a LIDAR. (LIght Detection And Ranging), a predetermined object to be detected around the excavator may be detected based on a detection result (distance image or the like) of a stereo camera or the like.

  Next, FIG. 10 is a flowchart schematically showing a fourth example of processing by the periphery monitoring system 100 (human detection unit 301). FIG. 11 is a diagram illustrating another example of the configuration of the periphery monitoring system 100, and illustrates a configuration that is a premise of the processing in FIG. The processing according to this flowchart may be repeatedly executed in a state where a through image or a monitoring image is displayed on the display device 50 during the operation of the excavator, for example, as in the case of FIGS.

  Note that the human detection unit 301 is in a state where one of the background-specific person detection units 301A to 301C is selected as an initial state, and any one of the selected background-specific person detection units 301A to 301C. It is set to detect a person who is a detection target by any one of the sensitivity-specific person detection units 3011 to 3013 included in one. Hereinafter, the human detection unit 301 is assumed to be in a state where the background-specific human detection unit 301A is selected as an initial state, and the sensitivity-specific human detection units 3011A to 3013A detect persons by sensitivity. I do.

  Here, as shown in FIG. 11, in the present example, the human detection unit 301 includes a plurality (three in the present embodiment) of background-specific person detection units 301 </ b> A to 301 </ b> C (an example of a background-specific object detection unit). Each of the background-specific person detection units 301A to 301C includes one unique background among a plurality of types of backgrounds (for example, a soil background, a concrete background, a forest background, and a city background) that are defined in advance. It is set so that the ability to detect the detection target from the captured image of the imaging device 40 is the highest. That is, when detecting the detection target from the captured image of the image capturing apparatus 40, the human detection unit 301 responds from a plurality of types of backgrounds (that is, a plurality of types of backgrounds that can be supported) that can be included in the captured image. The background (corresponding background) to be set can be set. Hereinafter, among the person-by-background detection units 301A to 301C, the person-by-background detection unit 301A is set to have the highest ability to detect a detection target from captured images including a soil background, and the person-by-background detection unit 301B is made of concrete. The ability to detect the detection target from the captured image including the background is set to be the highest, and the background-specific person detection unit 301C is set to have the highest ability to detect the detection target from the captured image including the background of the forest. The explanation is based on the premise. The background-specific person detection units 301A to 301C include the above-described sensitivity-specific person detection units 3011 to 3013 (sensitivity-specific person detection units 3011A to 3013A, 3011B to 3013B, and 3011C to 3013C), respectively. The human detection unit 301 is set as a detection target by any one of a plurality of sensitivity-specific human detection units 3011A to 3013A, 3011B to 3013B, and 3011C to 3013C, which are different in sensitivity for detecting the corresponding background and the detection target. Detect people.

  The difference between the corresponding backgrounds of the background-specific person detection units 301A to 301C can be realized, for example, by generating a discriminator used in the above-described discrimination function by machine learning using different teacher images. Specifically, the discriminator used in the background-specific person detection unit 301A (sensitivity-specific person detection units 3011A to 3013A) performs machine learning using a data set in which most of the teacher images including the soil background indicate. May be generated. Further, the classifier used in the background-specific person detection unit 301B (sensitivity-specific person detection units 3011B to 3013B) is generated by performing machine learning using a data set in which a teacher image including a concrete background occupies most. May be. The background-specific person detection unit 301C (sensitivity-specific person detection units 3011C to 3013C) may be generated by performing machine learning using a data set in which a teacher image including a forest background is mostly occupied. As a result, background-specific person detection units 301 </ b> A to 301 </ b> C that have different backgrounds when detecting a detection target (person) from the captured image of the imaging device 40 are generated.

  Returning to FIG. 10, in step S <b> 402, the human detection unit 301 determines whether an operation for changing the corresponding background (corresponding background changing operation) has been performed on the screen operation unit 44. For example, as described later, the corresponding background change operation may be an operation realized by touching a predetermined icon displayed superimposed on the through image or the monitoring image on the touch panel. In step S402, the human detection unit 301 proceeds to step S404 when the corresponding background change operation is performed on the screen operation unit 44, and proceeds to step S408 when the corresponding background change operation is not performed.

  In step S <b> 404, the human detection unit 301 selects an area for changing the corresponding background in the through image or the entire peripheral image with respect to the screen operation unit 44 before the corresponding background change operation. It is determined whether or not a selection operation has been performed. When the region selection operation is not performed on the screen operation unit 44, the human detection unit 301 proceeds to step S406, and when the region selection operation is performed, the human detection unit 301 proceeds to step S408.

  In step S406, the human detection unit 301 changes the corresponding background in the peripheral area of the shovel corresponding to the through image or the entire peripheral image according to the content of the corresponding background change operation, and the process proceeds to step S410. That is, the human detection unit 301 changes the background-specific human detection unit (any of 301A to 301C) used for detection of the detection target in the peripheral region of the excavator corresponding to the through image or the entire peripheral image, and proceeds to step S410. move on.

  On the other hand, in step S <b> 408, the human detection unit 301 determines whether or not in the peripheral region of the excavator corresponding to a partial region of the through image or the peripheral image (region selected by the region selection operation) according to the content of the corresponding background change operation. The corresponding background is changed, and the process proceeds to step S410. That is, the human detection unit 301 changes the background-specific human detection unit (any of 301A to 301C) used for detection of the detection target in the peripheral region of the shovel corresponding to the through image or a partial region of the peripheral image, and step The process proceeds to S410.

  In step S410, as in step S102 of FIG. 5, the human detection unit 301 performs an operation (sensitivity change operation) to change (that is, increase or decrease) the sensitivity for detecting the detection target with respect to the screen operation unit 44. Determine whether it was done. When the sensitivity change operation is performed on the screen operation unit 44, the human detection unit 301 proceeds to step S412. When the sensitivity change operation is not performed, the human detection unit 301 proceeds to step S418.

  In step S412, the human detection unit 301 detects the detection target in the through image or the entire surrounding image with respect to the screen operation unit 44 before the sensitivity change operation, similarly to step S104 in FIG. It is determined whether or not an operation for selecting a region to be changed (region selection operation) is performed. When the region selection operation is not performed on the screen operation unit 44, the human detection unit 301 proceeds to step S414. When the region selection operation is performed, the human detection unit 301 proceeds to step S416.

  In step S414, the human detection unit 301 changes the sensitivity for detecting the detection target in the peripheral region of the excavator corresponding to the through image or the entire peripheral image according to the content of the sensitivity change operation, and ends the current process. To do. That is, the human detection unit 301 changes the sensitivity-specific human detection unit used for detection of the detection target in the peripheral region of the shovel corresponding to the entire through image or the peripheral image, and ends the current process. At this time, the human detection unit 301 sets the sensitivity for detecting the detection target in any of the currently set corresponding backgrounds, that is, the background-specific human detection units 301A to 301C currently used for detection of the detection target. change. For example, if the human detection unit 301 uses the background-specific human detection unit 301A for detection of a detection target in the peripheral region of the shovel corresponding to the entire through image or the peripheral image, the human detection unit 3011A to 3013A has a sensitivity. Make your changes. Further, the human detection unit 301 has different corresponding backgrounds that are set for each partial region of the through image or the peripheral image, that is, the background-specific human detection units (301A to 301C) that are actually used for detection of the detection target. In this case, in accordance with the corresponding scene for each partial area, the sensitivity for detecting the detection target is changed in a different manner for each partial area. The same applies to step S416, which will be described later.

  On the other hand, in step S416, the human detection unit 301 detects in the peripheral region of the shovel corresponding to a partial region of the through image or the peripheral image (region selected by the region selection operation) according to the content of the sensitivity change operation. The sensitivity for detecting the target is changed, and the current process ends. That is, the human detection unit 301 changes the sensitivity-specific human detection unit used for detection of the detection target in the peripheral region of the shovel corresponding to the through image or a partial region of the peripheral image, and ends the current process.

  On the other hand, in step S418, the human detection unit 301 determines whether or not an operation (reset operation) for returning the sensitivity for detecting the corresponding background and the detection target to the initial state has been performed. When the reset operation is performed on the screen operation unit 44, the human detection unit 301 proceeds to step S420, and when the reset operation is not performed, the human detection unit 301 ends the current process.

  In step S420, the human detection unit 301 returns the sensitivity for detecting the detection target to the initial state, that is, the background-specific human detection unit 301A is selected, and among the sensitivity-specific human detection units 3011A to 3013A. Using the sensitivity-specific person detection unit 3012A, the process returns to the state in which the detection target (person) is detected, and the current process ends.

  As described above, in this embodiment, the corresponding background of the human detection unit 301 is changed in accordance with the corresponding background change operation for the screen operation unit 44. Thereby, the operator or the like can change the corresponding background of the human detection unit 301 according to the type of background included in the through image or the peripheral image in addition to the sensitivity for detecting the detection target. The degree of freedom in adjusting the detection performance 301 is further improved. Therefore, as a result, it is possible to further suppress the output of the false alarm of the alarm output unit 303 and the occurrence of the alarm leak due to the false detection or detection omission of the detection target (person) by the human detection unit 301.

  For example, FIG. 12 is a diagram illustrating an example of the through image TP displayed on the display device 50 in accordance with the processing of the present embodiment (FIG. 10). Specifically, FIG. 12A is an example of the through image TP displayed on the display device 50 when the detection target is missed, and FIG. 12B is the detection shown in FIG. It is the through image TP displayed on the display device 50 in accordance with the process of the present embodiment that is executed when the target detection is missed. FIG. 13 is a diagram illustrating another example of the through image TP displayed on the display device 50 in accordance with the processing of the present embodiment. Specifically, FIG. 13A is an example of a through image TP displayed on the display device 50 when an object other than the detection target is erroneously detected. FIG. 13B is an example of FIG. The through image TP displayed on the display device 50 according to the processing of the present embodiment that is executed when an object other than the detection target shown in FIG. In this example, as in the case of FIG. 6, icons BT <b> 1 to BT <b> 3 for selecting each of the sensitivity-specific person detection units 3011 to 3013 are displayed at the lower end portion of the through image TP so as to be superimposed on the through image. The human detection unit 3012 classified by sensitivity currently used by the human detection unit 301 is highlighted with a thick frame. Further, “A1” to “A3” written on the icons BT1 to BT3 correspond to the background-specific person detection units 301A (sensitivity-specific person detection units 3011A to 3013A), respectively, and “B1” to “B3” “C1” to “C3” correspond to the background-specific person detection unit 301C (sensitivity-specific person detection units 3011C to 3013C), corresponding to the background-specific person detection unit 301B (sensitivity-specific person detection units 3011B to 3013B). In addition, an icon BT0 for changing the corresponding background is displayed on the upper left corner of the through image TP in a manner superimposed on the through image.

  In the example shown in FIG. 12, as shown in FIG. 12A, although a person is shown in the through image TP, it is emphasized by being surrounded by a region AR <b> 1 thick line frame FR including the person in the through image TP. Therefore, it can be seen that the person detection unit 301 cannot detect the person. On the other hand, the operator or the like performs a corresponding background change operation by touching the icon BT0 on the touch panel, and displays the background of the soil corresponding to the background-specific person detection unit 301A, which is the currently set corresponding background, as a through image TP. According to the actual background, it is preferable to change to a concrete background corresponding to the background-specific person detection unit 301B. As a result, as shown in FIG. 12B, the human detection unit 301 can detect a person appearing in the through image TP including the concrete background, and thus the area AR1 including the person of the through image TP. Is highlighted by being surrounded by a thick line frame FR, and the detection omission of the detection target can be suppressed.

  In the example shown in FIG. 13, as shown in FIG. 13A, an object other than the detection target (the bush plant) included in the through image, even though the detection target (person) is not shown in the through image. ) Is surrounded by a thick line frame FR, it can be seen that the human detection unit 301 erroneously detects an object other than the detection target. On the other hand, the operator or the like performs a corresponding background change operation by touching the icon BT0 on the touch panel, and displays the background of the soil corresponding to the background-specific person detection unit 301A, which is the currently set corresponding background, as a through image TP. In accordance with the actual background, it may be changed to a forest background corresponding to the background-specific person detection unit 301C. Accordingly, as illustrated in FIG. 13B, the human detection unit 301 can determine that a bush plant reflected in a through image TP including a background similar to a forest is not a detection target. The thick line frame FR surrounding the area AR2 including the plant of TP is not displayed, and detection errors of the detection target can be suppressed.

  The process according to the present embodiment (FIG. 10) may be executed in combination with at least one of the processes according to the embodiments shown in FIGS.

  Further, in this embodiment, on the premise that the sensitivity for detecting the detection target is changed, the corresponding background can be changed. However, the detection function of the human detection unit 301 is adjusted by changing only the corresponding background. An aspect may be sufficient. That is, in the process of the human detection unit 301 in FIG. 10, steps S410 to S416 are omitted, and in the case of No in step S402, a configuration in which the process proceeds to step S418 is adopted. A configuration in which the sensitivity-specific person detection units 3011A to 3013A, 3011B to 3013B, and 3011C to 3013C included in each of the different person detection units 301A to 301C may be employed. Also in this case, the operator or the like can change the corresponding background and adjust the detection performance of the human detection unit 301 as necessary. As a result, an error in the detection target (person) by the human detection unit 301 results. The output of a false alarm of the alarm output unit 303 due to detection or detection omission or the occurrence of alarm omission can be suppressed.

  As mentioned above, although the form for implementing this invention was explained in full detail, this invention is not limited to this specific embodiment, In the range of the summary of this invention described in the claim, various Can be modified or changed.

30 controller 40 imaging device 44 screen operation unit (first operation unit, second operation unit)
40B Rear camera 40L Left side camera 40R Right side camera 50 Display device (notification unit)
100 Perimeter monitoring system (work machine peripheral monitoring system)
301 Human detection unit (object detection unit)
301A to 301C Background-specific person detection unit (background-specific object detection unit)
3011-3013 Sensitivity-specific human detection unit (sensitivity-specific object detection unit)
302 Display control unit 303 Alarm output unit

Claims (10)

An object detection unit for detecting a predetermined object around the work machine;
A notification unit for notifying that the object has been detected when the object is detected by the object detection unit;
A first operating portion provided around a cockpit of the work machine,
The object detection unit changes sensitivity of detecting the object in accordance with a predetermined operation on the first operation unit.
Perimeter monitoring system for work machines. The object detection unit changes the sensitivity of detecting the object in response to an operation to increase and decrease the sensitivity to the first operation unit.
The work machine periphery monitoring system according to claim 1. The object detection unit reduces the sensitivity of detecting the object when the first operation unit is operated when the notification unit notifies that the object has been detected;
The work machine periphery monitoring system according to claim 1 or 2. The object detection unit increases the sensitivity of detecting the object when the first operation unit is operated when the notification unit has not been notified that the object has been detected.
The work machine periphery monitoring system according to any one of claims 1 to 3. Further comprising an imaging device for imaging the periphery of the work machine;
The notification unit includes a display device that is provided around a cockpit of the work machine and displays a captured image of the imaging device or a peripheral image generated based on the captured image,
The object detection unit changes the sensitivity in a peripheral region of the work machine corresponding to a partial region or an entire region of the captured image or the peripheral image in response to a predetermined operation on the first operation unit.
The work machine periphery monitoring system according to any one of claims 1 to 4. The first operation unit is configured to be able to perform an operation of selecting a part of the captured image or the peripheral image displayed on the display device,
The object detection unit changes the sensitivity in a peripheral region of the work machine corresponding to a partial region of the captured image or the peripheral image selected by the first operation unit;
The work machine periphery monitoring system according to claim 5. Further comprising an imaging device for imaging the periphery of the work machine;
The notification unit includes a display device that is provided around a cockpit of the work machine and displays a captured image of the imaging device or a peripheral image generated based on the captured image,
When the object is detected by the object detection unit, the display device highlights and displays a region including the object in the captured image or the peripheral image,
The first operation unit is configured to be able to perform an operation of selecting a part of the captured image or the peripheral image displayed on the display device,
The object detection unit is configured to select the highlighted region to be displayed in an emphasized manner in the captured image or the peripheral image of the display device by the first operation unit. Or lower the sensitivity of detecting the object in the peripheral area of the work machine corresponding to the emphasized area,
The work machine periphery monitoring system according to claim 3. Further comprising an imaging device for imaging the periphery of the work machine;
The notification unit includes a display device that is provided around a cockpit of the work machine and displays a captured image of the imaging device or a peripheral image generated based on the captured image,
When the object is detected by the object detection unit, the display device highlights and displays a region where the object exists in the captured image or the peripheral image,
The first operation unit is configured to be able to select a part of the imaging device or the peripheral image displayed on the display device,
The object detection unit, when a region other than the highlighted region displayed in an emphasized manner in the captured image or the peripheral image of the display device is selected by the first operation unit, the captured image or the Increase the sensitivity of detecting the object in the entire area of the peripheral image or the peripheral area of the work machine corresponding to the other area,
The work machine periphery monitoring system according to claim 4. The object detection unit includes a plurality of sensitivity-specific object detection units having different sensitivity to detect the object, detects the object by any one of the plurality of sensitivity-specific object detection units, and By changing the sensitivity-specific object detection unit used for detection of the object from among the sensitivity-specific object detection units, the sensitivity for detecting the object is changed,
The work machine periphery monitoring system according to any one of claims 1 to 8. The object detection unit detects the object based on the captured image, and detects the object from the captured image, each of which includes one specific background among a plurality of types of backgrounds defined in advance. Including a plurality of background-specific object detection units set to have the highest detection capability,
A second operation unit that performs an operation of selecting any one of the plurality of background-specific object detection units;
The object detection unit detects the object around the work machine by the background object detection unit selected by the second operation unit among the plurality of background object detection units.
The work machine periphery monitoring system according to any one of claims 5 to 8.