Information processing apparatus, control program for information processing apparatus

Abstract

To improve detection accuracy of object detection.SOLUTION: A shovel 100 comprises a distance sensor 41 for measuring a distance to a measurement object D, and a controller 30. The controller 30 acquires the dimension of the measurement object D, sets a desired dimension of a detection object on the basis of the distance to the measurement object D, and determines whether the measurement object D is a detection object or not, on the basis of the acquired dimension of the measurement object D and the set dimension of the detection object.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and a control program therefor.

Background Art

[0002] Conventionally, a technique for detecting a desired detection target using a distance sensor that measures distance has been known. For example, in the technique described in Patent Document 1, map information such as a map (occupancy grid map (OGM)) representing the probability of the presence of an object around a target (vehicle) is created based on distance information from a distance sensor, and the movement control of the target is performed using this map. This OGM is partitioned by grids, and the surrounding situation is judged by indicating the probability of the presence of an object in each grid.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, sufficient detection accuracy may not be obtained simply by using distance information. For example, in the method disclosed in Patent Document 1 above, obstacles around the vehicle body are detected, but the type of the detected object is unknown. Also, simply using a lidar alone makes it difficult to accurately determine the size. In particular, in a place where various types and sizes of objects are mixed, such as a construction site, there has been a problem that detection based only on distance information does not function sufficiently for detecting obstacles.

[0005] The present invention has been made in view of the above circumstances, and an object thereof is to improve the detection accuracy of object detection.

Means for Solving the Problem

[0006] The present invention is an information processing apparatus, distance measuring means for measuring the distance to a measurement target, size acquisition means for acquiring the size of the measurement target, size setting means for setting the size of a desired detection target based on the distance to the measurement target, determination means for determining whether the measurement target is the detection target based on the size of the measurement target acquired by the size acquisition means and the size of the detection target set by the size setting means, Imaging means for acquiring an image of the measurement target, Second determination means for determining whether or not the measurement target is the detection target based on the image, Third determination means for further determining whether or not the measurement target is the detection target based on the determination result of the determination means and the determination result of the second determination means, and is configured to include the above.

[0007] Further, the present invention is a control program for an information processing apparatus including distance measuring means for measuring the distance to a measurement target, causing a computer to function as size acquisition means for acquiring the size of the measurement target, size setting means for setting the size of a desired detection target based on the distance to the measurement target, determination means for determining whether the measurement target is the detection target based on the size of the measurement target acquired by the size acquisition means and the size of the detection target set by the size setting means.

Advantages of the Invention

[0008] According to the present invention, the detection accuracy of object detection can be improved.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0011] [Configuration of Excavator] First, the configuration of the excavator 100 according to the present embodiment will be described. The excavator 100 is configured to be able to suitably improve the detection accuracy of object detection by including the information processing apparatus according to the present invention.

[0012] FIG. 1 is a side view of the excavator 100 according to the present embodiment. As shown in this figure, the excavator 100 includes a lower traveling body 1, an upper revolving body 3 mounted on the lower traveling body 1 so as to be rotatable via a slewing mechanism 2, a boom 4, an arm 5, and a bucket 6 as attachments, and a cabin 10 on which an operator rides. The attachment is not limited to this as long as a working element (for example, a bucket, a crusher, a crane device, etc.) is provided.

[0013] The lower traveling body 1 includes, for example, a pair of left and right crawlers, and each crawler is hydraulically driven by a traveling hydraulic motor (not shown) to move the excavator 100. The upper slewing body 3 is driven by a slewing hydraulic motor or an electric motor (both not shown) etc., and slews with respect to the lower traveling body 1.

[0014] The boom 4 is pivotally attached to the center of the front part of the upper slewing body 3 so as to be able to pitch. At the tip of the boom 4, an arm 5 is pivotally attached so as to be able to rotate up and down. At the tip of the arm 5, a bucket 6 is pivotally attached so as to be able to rotate up and down. The boom 4, the arm 5, and the bucket 6 are each hydraulically driven by a boom cylinder 7, an arm cylinder 8, and a bucket cylinder 9. The cabin 10 is an operator's cab where the operator rides, and is mounted, for example, on the left side of the front part of the upper slewing body 3. The excavator 100 operates the actuator according to the operation of the operator riding in the cabin 10, and drives driven elements such as the lower traveling body 1, the upper slewing body 3, the boom 4, the arm 5, and the bucket 6.

[0015] FIG. 2 is a block diagram showing the system configuration of the excavator 100. As shown in this figure, in addition to the above configuration, the excavator 100 includes a controller 30, an imaging device 40, a distance sensor 41, an operation / posture state sensor 42, a position sensor 43, an operation device 45, a display device 50, an audio output device 60, and a communication device 80. The information processing device according to the present invention includes at least the controller 30.

[0016] The imaging device 40 photographs the periphery of the excavator 100 and outputs the image to the controller 30. The imaging device 40 includes a rear camera 40B, a left camera 40L, and a right camera 40R. The "periphery" of the excavator 100 only needs to include at least a predetermined range within a predetermined distance from the excavator 100. The rear camera 40B is attached to the rear part of the upper slewing body 3 and images the rear of the upper slewing body 3. The left camera 40L is attached to the left side part of the upper slewing body 3 and images the left side of the upper slewing body 3. The right camera 40R is attached to the right side part of the upper slewing body 3 and images the right side of the upper slewing body 3. Each of these rear camera 40B, left camera 40L, and right camera 40R is attached to the upper swing body 3 such that the optical axis is directed obliquely downward, and has an imaging range (angle of view) in the vertical direction including from the ground near the excavator 100 to the far side of the excavator 100. Further, the horizontal imaging ranges (angles of view) of the rear camera 40B, left camera 40L, and right camera 40R are, for example, ranges that together include substantially the entire area around the excavator 100.

[0017] The distance sensor 41 is a distance measuring means for measuring the distance to an object around the excavator 100 and acquiring the information (two-dimensional or three-dimensional distance information), and outputs the acquired information to the controller 30. The distance sensor 41 includes a rear distance sensor 41B, a left distance sensor 41L, and a right distance sensor 41R. The rear distance sensor 41B is attached to the rear part of the upper swing body 3 and measures the area behind the upper swing body 3. The measurement range of the rear distance sensor 41B corresponds to the imaging range of the rear camera 40B. The left distance sensor 41L is attached to the left side part of the upper swing body 3 and measures the left side area of the upper swing body 3. The measurement range of the left distance sensor 41L corresponds to the imaging range of the left camera 40L. The right distance sensor 41R is attached to the right side part of the upper swing body 3 and measures the right side area of the upper swing body 3. The measurement range of the right distance sensor 41R corresponds to the imaging range of the right camera 40R. In this embodiment, as each distance sensor 41, LIDAR (Light Detection and Ranging) using light is used. However, the type of the distance sensor 41 is not particularly limited, and for example, a millimeter wave radar or a distance measuring device using a stereo camera may be used.

[0018] Further, the imaging device 40 and the distance sensor 41 are paired such that those measuring and photographing in the same direction correspond to each other. Specifically, the rear camera 40B and the rear distance sensor 41B constitute a rear sensor unit 46B, the left camera 40L and the left distance sensor 41L constitute a left sensor unit 46L, and the right camera 40R and the right distance sensor 41R constitute a right sensor unit 46R.

[0019] The operation and posture state sensor 42 is a sensor that detects the operation state and posture state of the excavator 100, and outputs the detection result to the controller 30. The operation and posture state sensor 42 includes a boom angle sensor, an arm angle sensor, a bucket angle sensor, a three-axis inertial sensor (IMU: Inertial Measurement Unit), a slewing angle sensor, and an acceleration sensor. These sensors may be composed of sensors that acquire stroke information of cylinders such as the boom, sensors that acquire rotation information such as rotary encoders, or may be replaced by the acceleration (which may also include velocity and position) acquired by the IMU. The arm angle sensor detects the rotation angle of the arm 5 with respect to the boom 4 (hereinafter referred to as the "arm angle"). The bucket angle sensor detects the rotation angle of the bucket 6 with respect to the arm 5 (hereinafter referred to as the "bucket angle"). The IMU is attached to each of the boom 4 and the arm 5, and detects the acceleration of the boom 4 and the arm 5 along a predetermined three axes, and the angular acceleration of the boom 4 and the arm 5 around the predetermined three axes. The slewing angle sensor detects the slewing angle with respect to a predetermined angular direction of the upper slewing structure 3. However, it is not limited to this, and the slewing angle may be detected based on a GPS or IMU sensor provided on the upper slewing structure 3. The acceleration sensor is attached to a position away from the slewing axis of the upper slewing structure 3, and detects the acceleration at that position of the upper slewing structure 3. Thereby, based on the detection result of the acceleration sensor, it can be determined whether the upper slewing structure 3 is slewing, or whether the lower traveling body 1 is traveling, etc.

[0020] The position sensor 43 is a sensor that acquires information on the position (current position) of the excavator 100, and in this embodiment, it is a GPS (Global Positioning System) receiver. The position sensor 43 receives a GPS signal containing information on the position of the excavator 100 from a GPS satellite, and outputs the acquired position information of the excavator 100 to the controller 30. Note that the position sensor 43 does not have to be a GPS receiver as long as it can acquire information on the position of the excavator 100. For example, it may utilize a satellite positioning system other than GPS. The position sensor 43 may be provided on the lower traveling body 1 or may be provided on the upper slewing body 3.

[0021] The operation device 45 is provided near the driver's seat in the cabin 10 and is an operation means for the operator to operate each operating element (the lower traveling body 1, the upper slewing body 3, the boom 4, the arm 5, the bucket 6, etc.). In other words, the operation device 45 is an operation means for operating each hydraulic actuator that drives each operating element. The operation device 45 includes, for example, levers, pedals, various buttons, etc., and outputs an operation signal corresponding to these operation contents to the controller 30. Further, the operation device 45 is also an operation means for operating the imaging device 40, the distance sensor 41, the motion / posture state sensor 42, the position sensor 43, the display device 50, the voice output device 60, the communication device 80, etc., and outputs an operation command for each of these units to the controller 30.

[0022] The display device 50 is provided around the driver's seat in the cabin 10 and displays various image information to be notified to the operator under the control of the controller 30. The display device 50 is, for example, a liquid crystal display or an organic EL (Electroluminescence) display, and may be a touch panel type that also serves as at least a part of the operation device 45.

[0023] The voice output device 60 is provided around the driver's seat in the cabin 10 and outputs various voice information to be notified to the operator under the control of the controller 30. The voice output device 60 is, for example, a speaker or a buzzer.

[0024] The communication device 80 is a communication device that transmits and receives various information to and from remote external devices, other excavators 100, etc. through a predetermined communication network NW (for example, a mobile phone network or the Internet with a base station at the end) based on a predetermined wireless communication standard.

[0025] The controller 30 is a control device that controls the operations of each part of the excavator 100 to perform drive control of the excavator 100. The controller 30 is mounted in the cab 10. The function of the controller 30 may be realized by arbitrary hardware, software, or a combination thereof. For example, it is mainly composed of a microcomputer including a CPU, RAM, ROM, I / O, etc. In addition to these, the controller 30 may also be configured to include, for example, an FPGA or an ASIC.

[0026] Further, the controller 30 includes an OGM calculation unit 31 and an object detection determination unit 32 as functional units that execute various functions. Furthermore, the controller 30 includes a storage unit 35 as a storage area defined in an internal memory such as an EEPROM (Electrically Erasable Programmable Read-Only Memory).

[0027] Based on the outputs from the imaging device 40 and the distance sensor 41, the OGM calculation unit 31 creates a two-dimensional occupancy grid map (OGM: Occupancy Grid Maps) that quantifies and represents distance information. The OGM is a map that shows the probability of the existence of a detected specific object (detection target), such as its position and speed. More specifically, it is a map in which probability information regarding the probability of the existence of the detection target is placed in the corresponding cell on the grid based on the distance information of the detection target (see Figure 4). The details of creating the OGM by the OGM calculation unit 31 will be described later. In this embodiment, a two-dimensional OGM is used, but a three-dimensional OGM with height information added may also be used.

[0028] The object detection determination unit 32 performs detection determination of specific objects (detection targets) around the excavator 100 based on the OGM (the third OGM 73 described later) created by the OGM calculation unit 31. Then, the object detection determination unit 32 causes the display device 50 to output the detection result (determination result).

[0029] The storage unit 35 stores various programs and various data for operating each part of the excavator 100, and also functions as a work area of the controller 30. The storage unit 35 of the present embodiment stores various data, calculation results, etc. acquired by the imaging device 40, the distance sensor 41, etc., in addition to various programs. Further, the storage unit 35 stores in advance feature amounts (image feature amounts) of detection targets in the object detection process described later. In the storage unit 35, at least one feature amount is associated with each of various types of objects and people that can be selected as detection targets by the operator. Furthermore, the storage unit 35 stores in advance detection size data 351 (see FIG. 6) that associates the distance of the detection target with the detection size in the object detection process described later. In the present embodiment, a plurality of detection size data 351 corresponding to a plurality of types of detection targets are stored in advance. Details of the detection size data 351 will be described later.

[0030] Also, the excavator 100 can communicate with the management device 200 through a predetermined communication network NW. The communication network NW may include, for example, a mobile communication network having a base station at its terminal. The communication network NW may also include a satellite communication network using communication satellites in the sky. The communication network NW may also include the Internet network or the like. The communication network NW may also include a short-range communication network compliant with protocols such as WiFi and Bluetooth (registered trademark). Thereby, the excavator 100 can transmit (upload) various information to the management device 200. Also, the excavator 100 may be configured to be able to communicate with the support device 300 through the communication network NW.

[0031] The management device 200 (an example of an external device and an information processing device) is arranged at a position geographically separated from a user who owns the excavator 100 and the support device 300. The management device 200 is, for example, installed in a management center or the like provided outside the work site where the excavator 100 works, and is a server device configured around one or more server computers or the like. In this case, the server device may be a self-owned server operated by an operator who operates the system or an affiliated operator related to the operator, or may be a rental server. Further, this server device may be a so-called cloud server. Further, the management device 200 may be a server device (so-called edge server) arranged in a management office or the like within the work site of the excavator 100, or may be a general-purpose computer terminal of a stationary type or a portable type. As described above, the management device 200 can communicate with each of the excavator 100 and the support device 300 through the communication network NW. Thereby, the management device 200 can receive and store (accumulate) various information uploaded from the excavator 100. Further, the management device 200 can transmit various information to the support device 300 in response to a request from the support device 300.

[0032] The support device 300 (an example of a user terminal and a terminal device) is a user terminal used by a user. The user may include, for example, a supervisor, a manager, an operator of the excavator 100, a manager of the excavator 100, a serviceman of the excavator 100, a developer of the excavator 100, and the like. The support device 300 is, for example, a general-purpose portable terminal such as a laptop computer terminal, a tablet terminal, or a smartphone owned by the user. Further, the support device 300 may be a general-purpose stationary terminal such as a desktop computer. Further, the support device 300 may be a dedicated terminal (portable terminal or stationary terminal) for receiving information. The support device 300 can communicate with the management device 200 through the communication network NW. As a result, the support device 300 can receive the information transmitted from the management device 200 and provide the information to the user through the display device mounted on itself. Further, the support device 300 may be configured to be able to communicate with the excavator 100 through the communication network NW.

[0033] [Operation of Excavator] Subsequently, the operation of the excavator 100 when executing the object detection process for detecting a specific object in the vicinity will be described. FIG. 3 is a data flow diagram showing the data flow in this object detection process, and FIGS. 4(a) to (c) are diagrams showing an example of the first OGM 71, the second OGM 72, and the third OGM 73 described later. FIG. 5 is a diagram showing the measurement target D and its size in the object detection process, and FIG. 6 is a diagram showing an example of the detection size data 351. FIG. 6 is a diagram for explaining the setting conditions of the detection size data 351.

[0034] The object detection process is executed by the controller 30 executing a predetermined program stored in the internal storage device on the CPU. This process may be executed and terminated based on the operation of the operator, or may be continuously executed during the operation of the excavator 100. In this embodiment, it is assumed that a human body (person) is detected as the detection target. Therefore, at the time of executing the process, for example, a human body is selected as the detection target by the operation of the operator, and a feature amount corresponding to this detection target (for example, that of a person's face) is read from the storage unit 35 and set.

[0035] When the object detection process is executed, as shown in FIG. 3, first, the controller 30 acquires image information around the excavator 100 by the imaging device 40, and also acquires distance information to an object around the excavator 100 by the distance sensor 41. The controller 30 causes the acquired image information and distance information to be recorded in the storage unit 35. Here, the imaging device 40 and the distance sensor 41 here correspond to each other as the rear sensor unit 46B, the left sensor unit 46L, or the right sensor unit 46R. Further, the controller 30 may perform shooting and measurement of the entire periphery while turning the upper swing body 3.

[0036] Next, the controller 30 creates an OGM representing the presence of a person (human body) around the excavator 100 by the OGM calculation unit 31. Here, the OGM calculation unit 31 individually creates a first OGM 71 based on the image acquired by the imaging device 40 and a second OGM 72 based on the distance information acquired by the distance sensor 41, and synthesizes these to create a third OGM 73.

[0037] Specifically, in creating the first OGM 71, first, the camera object detection unit 311 detects a human body as a part having a predetermined feature amount from the image acquired by the imaging device 40. That is, here, based on the image acquired by the imaging device 40, it is determined whether the measurement target is the desired detection target (human body). Then, the camera OGM creation unit 312 analyzes the position of the detected human body and displays it on a map, thereby creating the first OGM 71. Here, for example, a first OGM 71 as shown in FIG. 4(a) is created. In the first OGM 71, the position of the object region R1 detected as a human body (and an object presumed to be a human body) from the captured image by the imaging device 40 is displayed in a plane on a two-dimensional map divided into, for example, a grid pattern.

[0038] On the other hand, in the creation of the second OGM72, as shown in FIG. 3, first, the object detection unit 313 for the distance sensor detects an object (hereinafter referred to as "measurement target") D having, for example, height information based on the distance information acquired by the distance sensor 41. Next, the object size calculation unit 314 acquires the size of the measurement target D. In the present embodiment, the width dx, depth dy, and height dz of the measurement target D, which is a human body, are calculated from the point cloud data acquired by the distance sensor 41, which is a LIDAR (see FIG. 5). Note that the size of the measurement target D acquired here may be any parameter corresponding to that used in the later-described determination by the object candidate extraction unit 315.

[0039] Next, the object candidate extraction unit 315 extracts a highly probable human body from the measurement targets D. Here, the object candidate extraction unit 315 sets the range of the detection size of the detection target based on the distance from the excavator 100 (distance sensor 41) to the measurement target D, and determines the measurement target D corresponding to the range as the detection target. Specifically, first, the object candidate extraction unit 315 reads and sets the detection size data 351 corresponding to the type of the detection target from the storage unit 35. As shown in FIG. 6, the detection size data 351 associates the distance from the excavator 100 (distance sensor 41) to the measurement target D with the range of the detection size (detection height in the example of FIG. 6) (the dotted range in FIG. 6). The detection size data 351 in FIG. 6 shows an example in which the detection size changes according to the distance due to the measurement range (viewing angle and orientation) of the distance sensor 41. Specifically, as shown in FIG. 7, when the height of the distance sensor 41 is 2.5 [m], the downward viewing angle of the distance sensor 41 is 40°, and the vertical viewing angle is 20°, the maximum height detectable at the position of the distance a is (2.5√3 - a) / 2 [m]. Therefore, when this value is smaller than approximately the height of a human body, 1.7 [m], the height of the human body is assumed to be (2.5√3 - a) / 2. Also, the minimum height of the human body is set to 0.6 [m].

[0040] Note that the "detection size" may be any one of the parameters (e.g., width, depth, height, etc.) representing the size of the detection target (measurement target D), or a combination thereof including at least two of these. For example, as the detection size, the geometric mean (root mean square) including two or more of the width dx, depth dy, and height dz may be used. Further, when using a plurality of parameters, the plurality of determinations may be made by using the plurality of parameters individually multiple times. By using a plurality of parameters in this way, the detection accuracy of the detection target can be improved. Also, the parameters included in the detection size may be those obtained by machine learning (including distance learning).

[0041] Then, based on the calculated size of the measurement target D and the set detection size, the object candidate extraction unit 315 determines whether the measurement target D is a desired detection target. Specifically, when the calculated size of the measurement target D is within the range of the detection size, it is determined that the measurement target D is a desired detection target. The above process is performed for all detected measurement targets D. Thereby, the likelihood that the measurement target D is a desired detection target can be improved.

[0042] Next, as shown in FIG. 3, the distance sensor OGM creation unit 316 analyzes the position of the measurement target D determined by the object candidate extraction unit 315 to be a detection target and displays it on a map, thereby creating the second OGM 72. Here, for example, the second OGM 72 as shown in FIG. 4(b) is created. In this second OGM 72, the measurement target D determined to be a detection target is displayed as an object region R2 on a two-dimensional map partitioned in a grid pattern, similar to the first OGM 71, for example.

[0043] Next, as shown in FIG. 3, the OGM calculation unit 31 creates the third OGM 73 by synthesizing the first OGM 71 and the second OGM 72 by the OGM synthesis unit 317. In the third OGM 73 of the present embodiment, as shown in FIG. 4(c) for example, a grid in which object regions R1 and R2 exist in both the first OGM 71 shown in FIG. 4(a) and the second OGM 72 shown in FIG. 4(b) has become the object region R3 where a human body is detected. That is, in each of the first OGM 71 and the second OGM 72, "1" is assigned to the grid with an object region, and "0" is assigned to the grid without an object region. When synthesizing, if the sum of corresponding grids is "1", the grid is set as the object region R3. However, this synthesis method is not limited to that of the present embodiment. For example, when creating each of the first OGM 71 and the second OGM 72, not only "0" and "1", but also numerical values weighted according to the probability of the existence of each object region may be assigned to the grids of the object regions. Then, when synthesizing these, if the sum (or product) of the object regions of the corresponding grids is equal to or greater than a predetermined threshold value, the grid may be set as the object region R3.

[0044] Next, as shown in FIG. 3, the controller 30 determines whether a person (human body) around the excavator 100 is detected based on the third OGM 73 created by the OGM calculation unit 31 by the object detection determination unit 32. In the present embodiment, it is determined that a person exists in the grid set as the object region R3 in the third OGM 73. Alternatively, it may be determined that a person exists only in the grid (object region R3) whose assigned numerical value is equal to or greater than a predetermined value. Then, the object detection determination unit 32 outputs the detection result (determination result) to the display device 50. This display mode is not particularly limited as long as the position and the like of the detection target can be identified.

[0045] [Technical Effects of the Present Embodiment] As described above, according to the present embodiment, a desired size of the detection target is set based on the distance to the measurement target D, and based on the size of the measurement target D and the set size of the detection target, it is determined whether the measurement target D is the detection target. Thereby, the detection accuracy of object detection can be improved as compared with the case where distance information is simply used. That is, in object detection using only imaging means such as a camera, false detection was likely to occur due to, for example, the pattern of the ground. On the other hand, in sensor fusion using a distance sensor in combination, although the detection accuracy is improved, there is a risk of false detection, for example, when the detection target is located on a step. In this regard, according to the present embodiment, even in such a case, the detection accuracy of object detection can be improved and the risk of false detection can be reduced. Therefore, it can be particularly preferably applied to a case where the surrounding environment is not flat and is complex (such as unevenness of the ground and miscellaneous object arrangements), such as a construction site.

[0046] Further, according to the present embodiment, detection size data 351 associating the distance to the measurement target D with the range of the size of the detection target is stored in advance, and the range of the size of the detection target is set based on this detection size data 351. Thereby, the range of the size of the detection target can be set simply. Further, according to the present embodiment, a plurality of detection size data 351 corresponding to a plurality of types of detection targets are stored in advance, and the detection size data 351 corresponding to the type of the desired detection target is read out and used. Thereby, the range of the size of the desired detection target can be preferably set, and as a result, various detection targets can be detected with high accuracy.

[0047] Further, according to the present embodiment, it is separately determined whether the measurement target D is a detection target based on the image acquired by the imaging device 40, and based on this determination result and the determination result based on the distance to the measurement target D, it is further determined whether the measurement target D is a detection target. That is, after improving the detection accuracy of object detection based on the distance to the measurement target D, this is combined with the object detection result based on the image information to further perform object detection. Thereby, object detection with even higher detection accuracy can be performed.

[0048] [Others] As described above, the embodiments of the present invention have been described, but the present invention is not limited to the above embodiments and their modifications. For example, in the above-described embodiment, the size of the detection target is set based on the detection size data 351 that associates the distance to the measurement target D with the range of the size of the detection target. However, if the size of the detection target is set based on the distance to the measurement target D, the setting method is not limited to this, and for example, an operator may perform manual setting or the like. Further, the detection size data 351 may have a determination threshold value even if it is not set by the function illustrated in FIG. 6.

[0049] Also, in the above-described embodiment, the imaging device 40 and the distance sensor 41 are mounted on the excavator 100. However, the imaging device 40 and the distance sensor 41 do not necessarily have to be mounted on the excavator 100, and for example, they may be installed at a high place or mounted on an unmanned aircraft such as a drone. Then, the acquired data may be transmitted to the excavator 100, or alternatively, the data may be transmitted to the management device 200 or the support device 300 to execute the detection process, and the result may be transmitted to the excavator 100. That is, the information processing device according to the present invention does not necessarily have to be mounted on a vehicle such as an excavator.

[0050] Also, in the above-described embodiment, the case where the detection target of the object detection process is a human body has been described as an example. However, the detection target is not limited to a human body and includes various living organisms and objects. In addition, the details shown in the embodiments can be appropriately changed without departing from the gist of the invention.

Description of Reference Numerals

[0051] 100 Excavator 30 Controller 35 Storage Unit 40 Imaging Device (Imaging Means) 41 Distance Sensor (Distance Measuring Means) 71 First OGM 72 Second OGM 73 Third OGM 200 Management Device 300 Support Device 351 Detection Size Data (Detection Size Information) D Measurement Target

Claims

1. Distance measuring means for measuring the distance to the object to be measured, Size acquisition means for acquiring the size of the object to be measured, Size setting means for setting the size of a desired detection object based on the distance to the object to be measured, Determination means for determining whether the object to be measured is the detection object based on the size of the object to be measured acquired by the size acquisition means and the size of the detection object set by the size setting means, Imaging means for acquiring an image of the object to be measured, Second determination means for determining whether the object to be measured is the detection object based on the image, Third determination means for further determining whether the object to be measured is the detection object based on the determination result of the determination means and the determination result of the second determination means, An information processing apparatus comprising: An information processing apparatus.

2. Storage means for storing in advance detection size information associating the distance to the object to be measured with the range of the size of the detection object, The size setting means sets the range of the size of the detection object based on the detection size information. The information processing apparatus according to claim 1.

3. The storage means stores in advance a plurality of pieces of the detection size information corresponding to a plurality of types of the detection objects, The size setting means reads out and uses the detection size information corresponding to the type of the detection object from the storage means. The information processing apparatus according to claim 2.

4. The distance measuring means can acquire three-dimensional distance information, The size acquisition means acquires the size of the object to be measured based on the measurement result of the distance measuring means. The information processing apparatus according to any one of claims 1 to 3.

5. The size acquisition means acquires the size of the object to be measured based only on the measurement result of the distance measuring means, The size of the detection object includes the height of the detection object. The information processing apparatus according to claim 4.

6. The detection object is a human body. The information processing apparatus according to any one of claims 1 to 5.

7. A control program for an information processing apparatus including distance measuring means for measuring the distance to an object to be measured and imaging means for acquiring an image of the object to be measured, A computer, Size acquisition means for acquiring the size of the object to be measured, Size setting means for setting the size of a desired detection object based on the distance to the object to be measured, Determination means for determining whether the measurement target is the detection target based on the size of the measurement target acquired by the size acquisition means and the size of the detection target set by the size setting means; Second determination means for determining whether the measurement target is the detection target based on an image of the measurement target; Third determination means for further determining whether the measurement target is the detection target based on the determination result of the determination means and the determination result of the second determination means; Functioning as; A control program for an information processing apparatus.

Images