Electronic equipment and systems

Abstract

The present invention provides an electronic device and system for estimating the position of a moving object based on captured images. [Solution] The electronic device includes a recognition unit that recognizes at least one of at least one first object whose position is known and at least one second object whose position is unknown in an image captured from a moving object, and an estimation unit that, once the first and second objects are recognized in the image, estimates the position of the second object based on the position of the first object. The estimation unit estimates the position of the moving object based on the position of the first object or the position of the second object.

Description

Technical Field

[0001] The present disclosure relates to electronic devices and systems. More specifically, the present disclosure relates to electronic devices and systems for estimating the position of a host vehicle or the like.

Background Art

[0002] Conventionally, various techniques for measuring or estimating the position of a moving body such as a vehicle have been proposed. For example, Patent Document 1 discloses a positioning device that detects a marker included in an image captured by a photographing device such as a camera and estimates the position of a moving body such as a vehicle based on the position of the marker or the like. As described above, the technique of estimating the position of a moving body or the like from an image is expected to become increasingly important in the future with the development of technologies for assisting the driving of a driver and / or technologies related to autonomous driving that automate part or all of the driving.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need for a technique for accurately estimating the position of a moving body based on an image captured from the moving body.

[0005] An object of the present disclosure is to provide an electronic device and a system for estimating the position of a moving body based on a captured image.

Means for Solving the Problems

[0006] An electronic device according to one embodiment includes: a recognition unit that recognizes at least one of at least one first object whose position is known and at least one second object whose position is unknown in an image captured from a moving body; When the first object and the second object are recognized in the aforementioned image, an estimation unit estimates the position of the second object based on the position of the first object, It is equipped with. The estimation unit estimates the position of the moving body based on the position of the first object or the position of the second object.

[0007] The system according to one embodiment is An imaging unit that captures images from a moving object, A recognition unit recognizes at least one of at least one first object whose position is known and at least one second object whose position is unknown in the image captured by the imaging unit, When the first object and the second object are recognized in the aforementioned image, an estimation unit estimates the position of the second object based on the position of the first object, It is equipped with. The estimation unit estimates the position of the moving body based on the position of the first object or the position of the second object. [Effects of the Invention]

[0008] According to one embodiment, an electronic device and system can be provided that estimates the position of a moving object based on an image that is captured. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of the system configuration according to one embodiment. [Figure 2] This figure shows another example configuration of the system according to one embodiment. [Figure 3] This figure shows another example configuration of the system according to one embodiment. [Figure 4] This is a diagram illustrating the operational concept of an electronic device according to one embodiment. [Figure 5] This is a diagram illustrating the operational concept of an electronic device according to one embodiment. [Figure 6] This is a diagram illustrating the operational concept of an electronic device according to one embodiment. [Figure 7] This flowchart shows an example of operation by an electronic device according to one embodiment. [Figure 8] This flowchart shows an example of operation by an electronic device according to one embodiment. [Figure 9] This flowchart shows an example of operation by an electronic device according to one embodiment. [Figure 10] This flowchart shows an example of operation by an electronic device according to one embodiment. [Modes for carrying out the invention]

[0010] In this disclosure, “electronic device” may mean an electric-powered device (or apparatus, etc.). “System” may mean a device or set of devices including an electric-powered device (i.e., an electronic device). “User” may mean a person (typically a human) using the system and / or electronic device according to one embodiment. By using the system and / or electronic device according to one embodiment, the position of a moving object can be estimated based on images captured from the moving object.

[0011] First, let's describe the system configuration of one embodiment.

[0012] Figure 1 is a schematic diagram showing an example of a system including electronic equipment according to one embodiment. Figure 1 is a diagram showing an example of the configuration of a system including electronic equipment according to one embodiment, mainly from a functional standpoint.

[0013] As shown in FIG. 1, a system 1 according to an embodiment may be configured to include an electronic device 10 and an imaging unit 20. The electronic device 10 and the imaging unit 20 do not necessarily need to be separated as distinct entities, and may be integrally configured such that one includes the other. As shown in FIG. 1, the electronic device 10 may include a recognition unit 12, an estimation unit 14, a control unit 16, and a storage unit 18. The system 1 according to an embodiment may not include some of the functional units shown in FIG. 1, or may include functional units other than those shown in FIG. 1. Also, the electronic device 10 according to an embodiment may not include some of the functional units shown in FIG. 1, or may include functional units other than those shown in FIG. 1.

[0014] The system 1 according to an embodiment may be installed in a moving body such as, for example, an automobile. The moving body in which the system 1 according to an embodiment is installed is not limited to an automobile, and may be, for example, an agricultural machine such as a tractor, a bicycle, a motorcycle, a drone, or a ship. Also, the moving body in which the system 1 according to an embodiment is installed may be, for example, a human or an animal carrying the system 1. The system 1 according to an embodiment can estimate the position of the moving body based on an image captured from the moving body. The system 1 according to an embodiment may be installed in any moving body for which the position is to be estimated.

[0015] The electronic device 10 shown in FIG. 1 may be a terminal or a device that is specially designed and manufactured, or may be a general-purpose terminal or device. For example, the electronic device 10 according to an embodiment may be, for example, a smartphone or a tablet terminal. Also, the system 1 according to an embodiment may be, for example, a smartphone or a tablet terminal including an imaging unit 20 such as a digital camera.

[0016] The imaging unit 20 may include an image sensor that electronically captures images, such as a digital camera. The imaging unit 20 may include an image sensor that performs photoelectric conversion, such as a CCD (Charge Coupled Device Image Sensor) or a CMOS (Complementary Metal Oxide Semiconductor) sensor. The imaging unit 20 may convert the captured image into a signal and transmit it to, for example, the recognition unit 12 of the electronic device 10. The imaging unit 20 may transmit the signal based on the captured image to, for example, the estimation unit 14, control unit 16, and / or storage unit 18 of the electronic device 10. The imaging unit 20 may be connected to, for example, the recognition unit 12 of the electronic device 10 by at least one of wired and wireless connections.

[0017] In one embodiment, the imaging unit 20 may capture images of the monitored object T as still images at predetermined time intervals (e.g., every 0.1 seconds). In another embodiment, the imaging unit 20 may capture images as a series of still images or as a video. The imaging unit 20 is not limited to imaging devices such as digital cameras, but may be any device that captures images from a moving object.

[0018] In one embodiment, the imaging unit 20 may capture an image from a specific moving object. For this purpose, the imaging unit 20 may be installed at a predetermined location on the moving object so as to capture an image of, for example, the front of the moving object. Alternatively, the imaging unit 20 may be installed at a predetermined location on the moving object so as to capture an image of, for example, the side (lateral direction) or rear of the moving object. In one embodiment, the electronic device 10 can estimate the position of the moving object based on the image captured by the imaging unit 20 installed on the moving object, i.e., the image captured from the moving object.

[0019] In one embodiment, the imaging unit 20 may include a camera that can record information in the depth direction of an object by simultaneously photographing the object from multiple different directions, such as a stereo camera. For example, the imaging unit 20 may enable three-dimensional spatial perception by reproducing the parallax of multiple eyes, such as binoculars. In one embodiment, when the imaging unit 20 captures an image including a predetermined object photographed from a moving object, it may also acquire information indicating the distance from the imaging unit 20 to the object.

[0020] In one embodiment, the imaging unit 20 may also include, for example, a LiDAR (Light Detection And Ranging) sensor along with the digital camera. In this case as well, the imaging unit 20 can capture an image and acquire information indicating the distance to an object captured in the image. That is, in this case as well, when the imaging unit 20 captures an image including a predetermined object captured from a moving object, it can also acquire information indicating the distance from the imaging unit 20 to the object.

[0021] The recognition unit 12 of the electronic device 10 may have the function of recognizing a predetermined object from an image captured by the imaging unit 20. For example, the recognition unit 12 may recognize a predetermined stationary object from an image captured by the imaging unit 20. For example, the recognition unit 12 may determine whether or not a predetermined object exists that is stationary relative to the surrounding environment of a moving object, based on a plurality of images captured over time from a moving object. For example, the recognition unit 12 may determine whether or not an object is stationary relative to the surrounding environment of a moving object, taking into account the movement of the moving object, based on the degree of movement (transition) of the pixels in which the predetermined object is captured in a plurality of images captured over time from the moving object. Furthermore, the recognition unit 12 may recognize at least one of a first object and a second object from among the stationary objects included in the image. The first object and the second object will be described further later. Information based on the recognition result by the recognition unit 12 may be supplied to an estimation unit 14 or the like.

[0022] The recognition unit 12 may employ various known image recognition techniques (such as pattern recognition) when recognizing predetermined objects such as stationary objects, a first object, and / or a second object from images captured by the imaging unit 20. The recognition unit 12 may employ various known techniques when performing image recognition. For example, the recognition unit 12 may perform image recognition by employing various methods such as various machine learning or deep learning techniques utilizing AI (Artificial Intelligence).

[0023] The estimation unit 14 may have the function of estimating various positional information, such as the position of a moving object, based on the recognition results of the recognition unit 12. For example, the estimation unit 14 may estimate the position of a moving object based on the position of a first object recognized by the recognition unit 12. The estimation of positions by the estimation unit 14 as described above will be described further later. The information based on the estimation results by the estimation unit 14 may be supplied to the control unit 16 or the like.

[0024] The control unit 16 has the function of performing various controls based on the position information estimated by the estimation unit 14. The control unit 16 may include at least one processor, such as a CPU (Central Processing Unit) or a DSP (Digital Signal Processor), in order to provide control and processing capabilities for performing various functions. The control unit 16 may be implemented as a single processor, as several processors, or as separate processors. The processor may be implemented as a single integrated circuit. An integrated circuit is also called an IC (Integrated Circuit). The processor may be implemented as a plurality of communicably connected integrated circuits and discrete circuits. The processor may be implemented based on various other known technologies. In one embodiment, the control unit 16 may be configured as, for example, a CPU (hardware) and a program (software) executed by the CPU. At least a part of each functional unit constituting the electronic device 10 according to one embodiment may be configured by specific means in which software and hardware resources cooperate. The control unit 16 may appropriately include any storage unit (memory) for storing programs and / or data necessary for the operation of the control unit 16.

[0025] For example, the control unit 16 may be responsible for at least part of the control of the movement of the moving object based on the current position of the moving object estimated by the estimation unit 14. For example, the control unit 16 may control the system to issue a predetermined alarm to the operator of the moving object if the current position of the moving object deviates from a desired position. Alternatively, for example, the control unit 16 may perform at least part of the automatic driving of the moving object (e.g., driving assistance) if the current position of the moving object deviates from a desired position. Alternatively, for example, the control unit 16 may perform automatic driving of the moving object by constantly or at predetermined time intervals, so as not to deviate from a desired path by more than a predetermined range.

[0026] In one embodiment, the control unit 16 may have the function of controlling at least a portion of each functional unit constituting the electronic device 10. The control unit 16 may also have the function of controlling at least a portion of the imaging unit 20 that supplies images to the electronic device 10. Information based on the control results of the control unit 16 may be supplied to, for example, a storage unit 18. Furthermore, information based on the control results of the control unit 16 may be supplied to external equipment of the electronic device 10, for example, via an arbitrary communication unit.

[0027] The storage unit 18 may be any storage medium (memory), such as RAM, ROM, HDD, or SSD. The storage unit 18 may be capable of storing various programs and / or data, such as an OS (Operating System) and / or application software used in the electronic device 10.

[0028] The memory unit 18 may store, for example, at least a portion of the information based on the control results of the control unit 16. The memory unit 18 may also store various types of information necessary for the operation of the control unit 16. For example, the memory unit 18 may store various types of information such as map information necessary for the automatic driving of the mobile body, control information for the mobile body, and / or the path taken by the mobile body.

[0029] At least one of the functional components shown in Figure 1 may be configured to include, for example, at least one of software and hardware resources. In one embodiment, at least one of the aforementioned functional components may be configured by specific means in which software and hardware resources cooperate.

[0030] Figure 2 shows another example of a system including electronic equipment according to one embodiment. Similar to Figure 1, Figure 2 shows another configuration example of a system including electronic equipment according to one embodiment, primarily from a functional standpoint. Hereafter, explanations of content similar to or identical to that in Figure 1 will be simplified or omitted as appropriate.

[0031] As shown in Figure 2, System 2 is similar to System 1 described in Figure 1 in that it includes the electronic device 10 and the imaging unit 20. System 1 described in Figure 1 is assumed to be installed on a predetermined mobile body or the like. On the other hand, System 2 described in Figure 2 is assumed to be installed on the mobile body VC only with respect to the functional parts related to the imaging unit 20, and the parts related to the electronic device 10 are installed outside the mobile body VC. System 2 may be configured to include a transmitting unit 32 and a receiving unit 34 in order to transmit the image information captured by the imaging unit 20 to the electronic device 10.

[0032] As shown in Figure 2, in system 2, the imaging unit 20 and the transmitting unit 32 may be installed on the mobile body VC. That is, the mobile body VC shown in Figure 2 may include the imaging unit 20 and the transmitting unit 32. The imaging unit 20 may be based on the same concept as the one described in Figure 1.

[0033] In system 2, the imaging unit 20 may capture images from the moving object VC. For this reason, the imaging unit 20 may be installed at a predetermined location on the moving object VC so as to be able to capture images of the moving object VC, for example, in front of it. Alternatively, the imaging unit 20 may be installed at a predetermined location on the moving object VC so as to be able to capture images of the moving object VC, for example, to the side (lateral direction) or behind it. In system 2, the electronic device 10 can estimate the position of the moving object VC based on the images captured by the imaging unit 20 installed on the moving object VC, i.e., the images captured from the moving object VC. Here, the "position" of the moving object VC may be, for example, the absolute position of the moving object VC in its surrounding environment (for example, the two-dimensional coordinates of the moving object VC relative to the surrounding environment). Hereinafter, the moving object VC will be described as being able to move with the direction of the arrow FW shown in Figure 2 as the forward direction.

[0034] The imaging unit 20 may convert the captured image into a signal and supply it to the transmitting unit 32. The transmitting unit 32 may have the function of transmitting information based on the image captured by the imaging unit 20 to the receiving unit 34, for example, by wireless communication. The transmitting unit 32 may be any functional unit capable of transmitting image-based information to another location, such as the receiving unit 34, by wireless communication.

[0035] The receiving unit 34 may be located outside the mobile body VC, for example. The receiving unit 34 may also be included in the electronic device 10. The receiving unit 34 receives information based on the image captured by the imaging unit 20 from the transmitting unit 32. The image information received by the receiving unit 34 may be supplied to the recognition unit 12. The receiving unit 34 may also transmit signals based on the captured image to, for example, the estimation unit 14, control unit 16, and / or storage unit 18 of the electronic device 10. The receiving unit 34 may be connected to, for example, the recognition unit 12 of the electronic device 10 by at least one of wired and wireless connections.

[0036] Figure 3 is a diagram showing another example of a system including electronic equipment according to one embodiment. Similar to Figure 1 or 2, Figure 3 shows another configuration example of a system including electronic equipment according to one embodiment, primarily from a functional standpoint. Hereafter, explanations of content similar to or identical to that in Figure 1 or 2 will be simplified or omitted as appropriate.

[0037] As shown in Figure 3, system 3 according to one embodiment may include a communication unit 36 ​​and a communication unit 38. In addition, in system 3 according to one embodiment, the mobile body VC may include a mobile body control unit 40.

[0038] The communication unit 38 may have the function of realizing bidirectional communication between the electronic device 10 and the mobile device VC, instead of the receiving unit 34 shown in Figure 2. For example, the communication unit 38 may receive information based on images captured by the imaging unit 20 from the communication unit 36 ​​of the mobile device VC, similar to the receiving unit 34 shown in Figure 2. The communication unit 38 may also transmit predetermined information to the communication unit 36 ​​of the mobile device VC. The predetermined information transmitted from the communication unit 38 may be supplied, for example, from the control unit 16 of the electronic device 10.

[0039] The communication unit 36 ​​may have a function to enable bidirectional communication between the electronic device 10 and the mobile device VC, instead of the transmission unit 32 shown in Figure 2. For example, the communication unit 36 ​​may have a function to transmit information based on images captured by the imaging unit 20 to the communication unit 38, for example, by wireless communication, similar to the transmission unit 32 shown in Figure 2. The communication unit 36 ​​may also receive predetermined information from the communication unit 38 on the electronic device 10 side. The communication unit 36 ​​may supply the predetermined information received from the communication unit 38 on the electronic device 10 side to the mobile device control unit 40, for example.

[0040] The mobile unit control unit 40 may have functions to control the entire mobile unit VC, including each functional part of the mobile unit VC. For example, the mobile unit control unit 40 may have a function to present predetermined information to the driver of the mobile unit VC. Also, for example, the mobile unit control unit 40 may have functions to assist the driver of the mobile unit VC in driving, and / or functions related to automated driving that automates part or all of the driving of the mobile unit VC.

[0041] In one embodiment of system 3, the electronic device 10 may transmit information related to the control of part or all of the operation of the mobile body VC to the communication unit 36 ​​of the mobile body VC. Then, in one embodiment of system 3, the mobile body control unit 40 may control part or all of the operation of the mobile body VC based on the information related to the control of part or all of the operation of the mobile body VC received from the electronic device 10. In this way, in one embodiment of system 3, the electronic device 10 estimates the position of the mobile body VC, and based on the estimation result, the mobile body control unit 40 may control part or all of the operation of the mobile body VC.

[0042] Next, the operation of the electronic device 10 according to one embodiment will be described. Hereinafter, the description will assume that the imaging unit 20 is mounted on the mobile body VC, as shown in System 2 or System 3 in Figure 2 or 3, as an example of how the electronic device 10 according to one embodiment is used.

[0043] First, the surrounding environment in which the electronic device 10 according to one embodiment operates will be described. At the time the electronic device 10 according to one embodiment starts operating, at least one first object α and at least one second object β are present around the mobile body VC.

[0044] Here, the first object α is defined as a stationary object whose position (e.g., coordinates) is known in advance and is positioned around the moving object VC. The first object α may be placed around the moving object VC, for example, and then its position (e.g., coordinates) may be measured by actual measurement or other means. Alternatively, the first object α may be placed at a fixed point whose position (e.g., coordinates) has been measured in advance around the moving object VC.

[0045] The first object α may be any marker, such as a pole or pylon (traffic cone) or color cone (registered trademark) placed around the moving object VC. Alternatively, the first object α may be a buoy or buoy present around the moving object VC. The first object α may be an object that is clearly imaged to some extent by the imaging unit 20. Furthermore, the first object α does not necessarily have to be an object with a three-dimensional shape. The first object α may be a predetermined marker painted on a road or the ground, for example.

[0046] The second object β may be, for example, a stone, pebble, or rock present around the moving object VC. Alternatively, the second object β may be, for example, plants such as grass or flowers present around the moving object VC. The second object β may also be, for example, trash present around the moving object VC. The second object β may also be an object that is clearly imaged to some extent by the imaging unit 20. Furthermore, the second object β does not necessarily have to be an object with a three-dimensional shape. The second object β may be, for example, any mark painted on a road or the ground, or a depression or some kind of mark present on a road or the ground. In addition, the second object β may be, for example, the boundary between soil and concrete, or the boundary between different types of concrete.

[0047] When the electronic device 10 according to one embodiment starts operating, the imaging unit 20 installed on the mobile body VC captures an image at a predetermined timing that includes at least one of at least one first object α and at least one second object β present around the mobile body VC.

[0048] Figures 4 to 6 show examples of images captured over time by the imaging unit 20 while the moving object VC is in motion. Figures 4, 5, and 6 may sequentially show images captured by the imaging unit 20 over time. For example, image IM(t0) shown in Figure 4 may be an example of an image captured by the imaging unit 20 at time t0. Image IM(t1) shown in Figure 5 may be an example of an image captured by the imaging unit 20 at time t1. Image IM(t2) shown in Figure 6 may be an example of an image captured by the imaging unit 20 at time t2. Times t0, t1, and t2 may each be arbitrary timings in order. For example, images IM(t0), IM(t1), and IM(t2) may each sequentially show images captured by the imaging unit 20 at time intervals of 1 second.

[0049] As shown in Figure 4, image IM(t0) contains the first object α1, the first object α2, the first object α3, and the first object α4. Hereafter, when multiple first objects such as the first object α1, the first object α2, the first object α3, and the first object α4 are not specifically distinguished in notation, they will be collectively referred to as "first object α".

[0050] As described above, the positions (e.g., coordinates) of the multiple first objects α shown in Figure 4 are assumed to be known. That is, the positions Pα1 of the first object α1, Pα2 of the first object α2, Pα3 of the first object α3, and Pα4 of the first object α4 are assumed to be known. Hereafter, when the positions of multiple first objects α such as Pα1 of the first object α1, Pα2 of the first object α2, Pα3 of the first object α3, and Pα4 of the first object α4 are not specifically distinguished in notation, they will be collectively referred to as "position Pα of the first object α".

[0051] In Figure 4, four first objects α are arranged to surround a rectangular plot of land. However, any number of first objects α can be placed at any location, as long as their positions are known.

[0052] The recognition unit 12 of the electronic device 10 can determine the position Pα of at least one of the four first objects α in the image IM(t0) captured by the imaging unit 20. Furthermore, as described above, the imaging unit 20 acquires information indicating the distance to the first object α along with the image in which the first object α is captured. Therefore, in this case, the estimation unit 14 can estimate the position PV of the imaging unit 20 (moving body VC) based on the position Pα (known) of the first object α and the distance to the first object α.

[0053] In one embodiment, the estimation unit 14 may estimate the position PV of the imaging unit 20 (mobile body VC) based on the position of at least one of the four first objects α. Alternatively, if multiple first objects α are recognized by the recognition unit 12, the estimation unit 14 may estimate the position PV of the imaging unit 20 (mobile body VC) based on the position of the first object α closest to the imaging unit 20 (mobile body VC). Furthermore, if multiple first objects α are recognized by the recognition unit 12, the estimation unit 14 may estimate the position PV of the imaging unit 20 (mobile body VC) based on the position of the first object α recognized by the imaging unit 20 (mobile body VC) with the highest contrast ratio. Finally, if multiple first objects α are recognized by the recognition unit 12, the estimation unit 14 may estimate the position PV of the imaging unit 20 (mobile body VC) based on the positions of the multiple first objects α (for example, by averaging the estimated positions for each). Hereinafter, "position PV of imaging unit 20 (mobile body VC)" will also be referred to as "position PV of mobile body VC" as appropriate.

[0054] In one embodiment, in order for the recognition unit 12 to identify a plurality of first objects α, each of the plurality of first objects α may be given different characteristics (such as color and / or shape). In this case, the electronic device 10 may acquire different characteristics for each of the plurality of first objects α and store them, for example, in a storage unit 18. Alternatively, the recognition unit 12 may identify the plurality of first objects α based, for example, the number of pixels each of the plurality of first objects α occupies in an image captured by the imaging unit 20 (for example, their size in the height direction). In this case as well, the electronic device 10 may acquire characteristics for the plurality of first objects α and store them, for example, in a storage unit 18.

[0055] Furthermore, as shown in Figure 4, image IM(t0) contains second object β1, second object β2, second object β3, and second object β4. Hereafter, when multiple second objects such as second object β1, second object β2, second object β3, and second object β4 are not specifically distinguished in notation, they will simply be referred to as "second object β".

[0056] As described above, the positions (e.g., coordinates) of each of the multiple second objects β shown in Figure 4 may be unknown. That is, the positions Pβ1 of second object β1, Pβ2 of second object β2, Pβ3 of second object β3, and Pβ4 of second object β4 may each be unknown. Hereafter, when the positions of multiple second objects β, such as Pβ1 of second object β1, Pβ2 of second object β2, Pβ3 of second object β3, and Pβ4 of second object β4 are not specifically distinguished in notation, they will be collectively referred to as "position Pβ of second object β".

[0057] Furthermore, the recognition unit 12 can estimate the position Pβ of the second object β by recognizing at least one of the four first objects α and at least one second object β in the image IM(t0) captured by the imaging unit 20. As described above, the imaging unit 20 acquires information indicating the distance to the first object α along with the image in which the first object α is captured. The imaging unit 20 also acquires information indicating the distance to the second object β along with the image in which the second object β is captured. Therefore, in this case, the estimation unit 14 can estimate the position Pβ of the second object β based on the position Pα (known) of the first object α, the distance to the first object α, and the distance to the second object β.

[0058] In one embodiment, the estimation unit 14 may estimate the position Pβ of the second object β based on the position of at least one of the four first objects α. Alternatively, if multiple first objects α are recognized by the recognition unit 12, the estimation unit 14 may estimate the position Pβ of the second object β based on the position of the first object α closest to the imaging unit 20 (moving object VC). Alternatively, if multiple first objects α are recognized by the recognition unit 12, the estimation unit 14 may estimate the position Pβ of the second object β based on the position of the first object α recognized by the imaging unit 20 (moving object VC) with the highest contrast ratio. Alternatively, if multiple first objects α are recognized by the recognition unit 12, the estimation unit 14 may estimate the position Pβ of the second object β based on the positions of the multiple first objects α (for example, by averaging the estimated positions for each).

[0059] The image IM(t1) shown in Figure 5 may be an image captured by the imaging unit 20 after a predetermined time, such as 1 second, has elapsed since the image IM(t0) shown in Figure 4. From time t0 to time t1, the moving object VC is assumed to have moved in the direction of the arrow FW shown in Figure 2 or Figure 3, i.e., forward. Therefore, the image IM(t1) shown in Figure 5 is an image taken slightly further forward than the image IM(t0) shown in Figure 4.

[0060] The image IM(t0) shown in Figure 4 included (was captured) the first object α1 and the first object α2. On the other hand, the image IM(t1) shown in Figure 5 includes the first object α3 and the first object α4, but does not include (was not captured) the first object α1 and the first object α2. Therefore, in the image IM(t1) shown in Figure 5, it is not possible to estimate the position PV of the moving object VC based on, for example, the position Pα1 of the first object α1 or the position Pα2 of the first object α2. However, suppose the estimation unit 14 estimated the position Pβ1 of the second object β1 based on, for example, the position Pα1 of the first object α in the image IM(t0) shown in Figure 4. In this case, the estimation unit 14 can estimate the position PV of the moving object VC based on the estimated position Pβ1 of the second object β1 in the image IM(t1) shown in Figure 5.

[0061] In this case, even if, for example, the first object α3 and / or the first object α4 are not included (not visible) in the image IM(t1) shown in Figure 5, the estimation unit 14 can estimate the position PV of the moving object VC based on the estimated position Pβ1 of the second object β1. Therefore, the estimation unit 14 may estimate the position PV of the moving object VC based on the estimated position Pβ1 of the second object β1 even if, for example, the first object α3 and / or the first object α4 are not included (not visible) in the image IM(t1).

[0062] Furthermore, the image IM(t1) shown in Figure 5 includes the first object α3 and the first object α4. Therefore, in the image IM(t1) shown in Figure 5, the recognition unit 12 can determine the position Pα3 of the first object α3 or the position Pα4 of the first object α4. Accordingly, in the image IM(t1) shown in Figure 5, the estimation unit 14 may estimate the position PV of the moving object VC based on the position Pα3 of the first object α3 and the distance to the first object α3. Alternatively, in the image IM(t1) shown in Figure 5, the estimation unit 14 may estimate the position PV of the moving object VC based on the position Pα4 of the first object α4 and the distance to the first object α4. For example, if the image IM(t1) shown in Figure 5 includes a first object α3 and / or a first object α4, the estimation unit 14 may preferentially estimate the position PV of the moving body VC based on the position Pα3 of the first object α3 and / or the position Pα4 of the first object α4. In other words, in this case, even if the position Pβ1 of the second object β1, etc., has been estimated, the estimation unit 14 may estimate the position PV of the moving body VC based on the position Pα3 of the first object α3 and / or the position Pα4 of the first object α4.

[0063] The image IM(t2) shown in Figure 6 may be an image captured by the imaging unit 20 after a predetermined time, such as 1 second, has elapsed since the image IM(t1) shown in Figure 5. From time t1 to time t2, the moving object VC is assumed to have moved further in the direction of the arrow FW shown in Figure 2 or Figure 3, i.e., forward of the moving object VC. Therefore, the image IM(t2) shown in Figure 6 is an image taken slightly further forward than the image IM(t1) shown in Figure 5.

[0064] The image IM(t1) shown in Figure 5 included (was captured) the second object β1. On the other hand, the image IM(t2) shown in Figure 6 does not include (was not captured) the second object β1. Therefore, in the image IM(t2) shown in Figure 6, it is not possible to estimate the position PV of the moving object VC based on the position Pβ1 of the second object β1. However, suppose the estimation unit 14 had already estimated the position Pβ2 of the third object β2 in the image IM(t1) shown in Figure 5, for example, based on the already estimated position Pβ1 of the second object β1. In this case, the estimation unit 14 can estimate the position PV of the moving object VC in the image IM(t2) shown in Figure 6, based on the estimated position Pβ2 of the third object β2.

[0065] In one embodiment, if there are multiple third objects β whose positions are estimated, the estimation unit 14 may estimate the position PV of the moving body VC based on the position of at least one of the third objects β. Alternatively, if multiple third objects β whose positions are estimated are recognized, the estimation unit 14 may estimate the position PV of the moving body VC based on the position of the third object β closest to the imaging unit 20 (moving body VC). Alternatively, if multiple third objects β whose positions are estimated are recognized, the estimation unit 14 may estimate the position PV of the moving body VC based on the position of the third object β recognized by the imaging unit 20 (moving body VC) with the highest contrast ratio. Alternatively, if multiple third objects β whose positions are estimated are recognized, the estimation unit 14 may estimate the position PV of the moving body VC based on the positions of the multiple third objects β (for example, by averaging the positions estimated for each).

[0066] Thus, the recognition unit 12 may further recognize a third object β whose position is unknown. In this case, if the first object α is not recognized in the image captured by the imaging unit 20, and the second object β whose position has been estimated and the third object are recognized, the estimation unit 14 may estimate the position of the third object based on the second object β whose position has been estimated. Alternatively, in this case, if the first object α and the second object β whose position has been estimated are not recognized, but the third object is recognized, the estimation unit 14 may estimate the position PV of the moving object VC based on the position of the third object.

[0067] Furthermore, the image IM(t2) shown in Figure 6 also includes the first object α3 and the first object α4. Therefore, in the image IM(t2) shown in Figure 6, the estimation unit 14 may estimate the position PV of the moving body VC based on the position Pα3 of the first object α3 and the distance to the first object α3. Alternatively, in the image IM(t2) shown in Figure 6, the estimation unit 14 may estimate the position PV of the moving body VC based on the position Pα4 of the first object α4 and the distance to the first object α4.

[0068] As described above, in one embodiment of the electronic device 10, the recognition unit 12 may recognize at least one of at least one first object α and at least one second object β in the image IM captured from the moving object VC (by the imaging unit 20). Here, the first object α may be an object whose position is known. On the other hand, the second object β may be an object whose position is unknown. Furthermore, the recognition unit 12 may recognize the first object α and the second object β from among objects that are determined to be stationary relative to the surrounding environment of the moving object VC, based on a plurality of image IMs captured over time from the moving object VC (by the imaging unit 20).

[0069] Furthermore, in one embodiment, in the electronic device 10, when a first object α is recognized in the image IM captured from the moving object VC (by the imaging unit 20), the estimation unit 14 may estimate the position PV of the moving object VC based on the position Pα of the first object α. Also, when a first object α and a second object β are recognized in the image IM captured from the moving object VC (by the imaging unit 20), the estimation unit 14 may estimate the position Pβ of the second object β based on the position Pα of the first object α. In this case, the estimation unit 14 may estimate the position PV of the moving object VC based on the estimated position Pβ of the second object β. Thus, the estimation unit 14 may estimate the position PV of the moving object VC based on the position Pα of the first object α or the position Pβ of the second object β.

[0070] In one embodiment, if the first object α is not recognized in the image IM captured from the moving object VC (by the imaging unit 20) but the second object β is recognized, the estimation unit 14 may estimate the position PV of the moving object VC based on the position Pβ of the second object β. Alternatively, if multiple second objects β are recognized in the image IM captured from the moving object VC (by the imaging unit 20), the estimation unit 14 may estimate the position PV of the moving object VC based on the position Pβ of the second object β that is closest to the moving object VC among the recognized multiple second objects β. Furthermore, if multiple second objects β are recognized in the image IM captured from the moving object VC, the estimation unit 14 may estimate the position PV of the moving object VC based on the position of the second object β that is recognized with the highest contrast ratio among the recognized multiple second objects β.

[0071] In one embodiment, the estimation unit 14 may estimate the position of at least one of the second object β and the mobile body VC (Pβ and / or PV) based on information acquired from the mobile body VC by a stereo camera. Alternatively, the estimation unit 14 may estimate the position of at least one of the second object β and the mobile body VC (Pβ and / or PV) based on image information acquired from the mobile body VC along with distance information.

[0072] A system 1 or system 2 according to one embodiment may include, for example, an imaging unit 20, a recognition unit 12, and an estimation unit 14. The imaging unit 20 captures an image from a moving object VC. The recognition unit 12 recognizes at least one of at least one first object α whose position is known and at least one second object whose position is unknown in the image captured by the imaging unit 20. When the first object α and the second object β are recognized in the image captured by the imaging unit 20, the estimation unit 14 estimates the position Pβ of the second object β based on the position Pα of the first object α. The estimation unit 14 estimates the position PV of the moving object VC based on the position Pα of the first object α or the position Pβ of the second object β.

[0073] Next, the operation of the electronic device 10 according to one embodiment will be described in more detail.

[0074] Figure 7 is a flowchart illustrating the operation of the electronic device 10 according to one embodiment. The operation of the electronic device 10 according to one embodiment in recognizing a first object or a second object will be described below with reference to Figure 7.

[0075] When the operation shown in Figure 7 begins, the recognition unit 12 of the electronic device 10 acquires the image captured by the imaging unit 20 (image IM captured from the moving object VC) (step S11).

[0076] When the imaging unit 20 acquires an image, the recognition unit 12 determines whether or not it has detected a stationary object (a still object) among the objects included in the image (step S12). In step S12, the recognition unit 12 may, for example, determine whether or not a stationary object has been detected in the image by taking into account the movement of the moving object VC, based on a series of still images taken in succession over time. If no stationary object is detected in step S12, the recognition unit 12 returns to step S11 to acquire the image.

[0077] On the other hand, if a stationary object is detected in step S12, the recognition unit 12 determines whether the position of the stationary object is known or not (step S13). In step S13, the recognition unit 12 may, for example, determine whether the position of the image-recognized stationary object has been registered in advance. In this case, if the position of the image-recognized stationary object has been registered in advance, the recognition unit 12 may determine that the position of the stationary object is known. On the other hand, if the position of the image-recognized stationary object has not been registered in advance, the recognition unit 12 may determine that the position of the stationary object is not known, i.e., unknown. Furthermore, even if the position of the image-recognized stationary object has not been registered, if the position of the stationary object can be obtained by making an inquiry or the like at that time, the recognition unit 12 may determine that the position of the stationary object is known.

[0078] If it is determined in step S13 that the position of a stationary object is known, the recognition unit 12 may determine that the stationary object is the first object α (step S14). On the other hand, if it is determined in step S13 that the position of a stationary object is not known, the recognition unit 12 may determine that the stationary object is the second object β (step S15). After step S14 or step S15, the recognition unit 12 may return to step S11 to acquire an image.

[0079] Figure 8 is a flowchart illustrating the operation of the electronic device 10 according to one embodiment. The operation of the electronic device 10 in estimating the position PV of the moving object VC will be described below with reference to Figure 8. The operation shown in Figure 8 may be performed immediately following the operation shown in Figure 7, or it may be performed in parallel with the operation shown in Figure 7.

[0080] When the operation shown in Figure 8 begins, the recognition unit 12 determines whether or not it recognizes the first object α and the second object β in the image IM (step S21). In step S21, the recognition unit 12 may determine whether or not both the first object α and the second object β are recognized in the image IM at a certain point in time, that is, whether or not both the first object α and the second object β are included (captured) in the image IM at a certain point in time.

[0081] If both the first object α and the second object β are recognized in step S21, the estimation unit 14 estimates the position Pβ (unknown) of the second object β based on the position Pα (known) of the first object α (step S22). After step S22, the estimation unit 14 estimates the position PV of the moving body VC based on the position Pα (known) of the first object α (step S23), and may terminate the operation shown in Figure 8.

[0082] If neither the first object α nor the second object β is recognized in step S21, the recognition unit 12 determines whether or not the first object α is recognized in the image IM (step S24). If the process proceeds to Yes in step S24, the recognition unit 12 determines that, in the image IM at a certain point in time, neither the first object α nor the second object β is recognized, but only the first object α is recognized; that is, only the first object α is recognized in that image IM. In this case, the image IM at a certain point in time includes (is captured) the first object α, but does not include (is not captured) the second object β. Therefore, in this case, the estimation unit 14 may estimate the position PV of the moving object VC based on the position Pα (known) of the first object α (step S23), and terminate the operation shown in Figure 8.

[0083] On the other hand, if the system proceeds to No in step S24, the recognition unit 12 proceeds to step S25. In step S25, the recognition unit 12 determines whether or not it recognizes the second object β in the image IM. If the system proceeds to Yes in step S25, the recognition unit 12 determines that, in the image IM at a certain point in time, it does not recognize the first object α, but it does recognize the second object β, that is, it recognizes only the second object β in that image IM.

[0084] If the second object β is recognized in step S25, the estimation unit 14 determines whether the position Pβ of the second object has already been estimated (step S26). If the position Pβ of the second object has already been estimated in step S26, for example, the position Pβ of the second object β may have been estimated in a previous cycle of the operation shown in Figure 8 by the execution of the process in step S22. If the position Pβ of the second object has already been estimated in step S26, the estimation unit 14 may estimate the position PV of the moving body VC based on the position Pβ of the second object β (step S27) and terminate the operation shown in Figure 8.

[0085] Furthermore, if the process proceeds to No in step S25, the recognition unit 12 has not recognized either the first object α or the second object β in the image IM at a certain point in time; that is, it has not recognized either the first object α or only the second object β in that image IM. In this case, the estimation unit 14 may either terminate the operation shown in Figure 8 without estimating the position PV of the moving object VC, or it may restart the operation shown in Figure 8.

[0086] Furthermore, if the process proceeds to No in step S26, the position Pβ of the second object β, which was determined to have been recognized in step S25, has not been estimated. In this case as well, the estimation unit 14 may either terminate the operation shown in Figure 8 without estimating the position PV of the moving body VC, or it may restart the operation shown in Figure 8.

[0087] Figure 9 is a flowchart illustrating the operation of the electronic device 10 according to one embodiment. The operation by which the electronic device 10 estimates the position PV of the moving object VC according to one embodiment will be described below with reference to Figure 9. The operation shown in Figure 9 may be performed immediately following the operation shown in Figure 7, or it may be performed in parallel with the operation shown in Figure 7 or Figure 8.

[0088] For example, while estimating the position PV of a moving object VC based on the estimated position Pβ of a certain second object β, it is conceivable that the moving object VC may move, causing the second object β to no longer be included in the image captured by the imaging unit 20. In such a case, the electronic device 10 according to one embodiment may perform the operation shown in Figure 9.

[0089] When the operation shown in Figure 9 begins, the recognition unit 12 determines whether the second object β (hereinafter also referred to as the "reference second object β"), which has been used as a reference for estimating the position PV of the moving object VC, is still recognized (step S31). If the reference second object β is still recognized in step S31, the estimation unit 14 estimates the position PV of the moving object VC based on the position Pβ of the reference second object β (step S32), and may terminate the operation shown in Figure 9.

[0090] Thus, in one embodiment, when the estimation unit 14 is no longer recognized in the image IM captured from the moving body VC (by the imaging unit 20) by the second object β that was used to estimate the position PV of the moving body VC, the estimation unit 14 may operate as follows. That is, in this case, the estimation unit 14 may estimate the position PV of the moving body VC based on the position Pβ of the second object β whose position Pβ has been estimated among the second object β recognized in the image IM.

[0091] Figure 10 is a flowchart illustrating the operation of an electronic device 10 according to one embodiment. Hereinafter, with reference to Figure 10, the operation of the electronic device 10 according to one embodiment in correcting the already estimated position Pβ of the second object β will be described. The operation shown in Figure 10 may be performed immediately following the operation shown in Figure 7, or it may be performed in parallel with the operations shown in Figures 7 to 9.

[0092] For example, while the electronic device 10 is operating, the moving object VC moves, causing the previously recognized first object α to no longer be recognized. However, the recognition unit 12 may then recognize the previously recognized first object α again. Alternatively, while the electronic device 10 is operating, the moving object VC moves, causing the recognition unit 12 to newly recognize a first object α that it had not previously recognized. In such cases, the electronic device 10 according to one embodiment may perform the operation shown in Figure 10.

[0093] When the operation shown in Figure 10 begins, the recognition unit 12 determines whether or not it has recognized the first object α (again or anew) (step S41). In step S41, the recognition unit 12 may determine whether or not it has recognized the first object α that it had previously recognized. Alternatively, in step S41, the recognition unit 12 may determine whether or not it has recognized the first object α that it had not previously recognized. If the first object α is recognized again or anew in step S41, the estimation unit 14 may correct the position Pβ of the second object β that has already been estimated based on the position Pα of the first object α that has been recognized again or anew (step S42). If the first object α is not recognized again or anew in step S41, the estimation unit 14 does not need to perform the operation in step S42.

[0094] Thus, in one embodiment, when the first object α is recognized again in the image IM captured from the moving body VC (by the imaging unit 20), the estimation unit 14 may correct the already estimated position Pβ of the second object β based on the position Pα of the newly recognized first object α. Alternatively, when the first object α is newly recognized in the image IM captured from the moving body VC (by the imaging unit 20), the estimation unit 14 may correct the already estimated position Pβ of the second object β based on the position Pα of the newly recognized first object α.

[0095] If the moving object VC is moving, the estimated position Pβ of the second object β may change due to the influence of the movement of the moving object VC. Therefore, for example, the receiving unit 34 shown in Figure 2 may acquire the movement path of the moving object VC. Alternatively, for example, the communication unit 38 shown in Figure 3 may acquire the movement path of the moving object VC. Furthermore, if the second object β is recognized again after the moving object VC has passed over the second object β whose position has been estimated based on the first object α, the estimation unit 14 may re-estimate the position Pβ of the second object β.

[0096] Thus, the electronic device 10 according to one embodiment may include a receiving unit 34 that acquires the movement path of a moving object VC. In this case, if the estimation unit 14 recognizes the second object β again after the moving object VC has passed over the second object β whose position has been estimated based on the first object α, it may re-estimate the position Pβ of the second object β. In this way, even when the moving object VC is moving, it is expected that the influence of the estimated position Pβ of the second object β changing due to the movement of the moving object VC will be reduced.

[0097] As described above, according to the electronic device 10 or system 1 or system 2 of one embodiment, the position of a moving object can be accurately estimated based on the captured image.

[0098] While embodiments relating to this disclosure have been described based on the drawings and examples, it should be noted that those skilled in the art will find it easy to make various modifications or alterations based on this disclosure. Therefore, it should be noted that these modifications or alterations are included within the scope of this disclosure. For example, the functions included in each component or step can be rearranged in a logically consistent manner, and multiple components or steps can be combined into one or divided. While embodiments relating to this disclosure have been described primarily in terms of apparatus, embodiments relating to this disclosure can also be realized as methods including steps performed by each component of the apparatus. Embodiments relating to this disclosure can also be realized as methods, programs, or storage media or recording media on which programs are recorded, executed by a processor in an electronic device. These should also be understood to be included within the scope of this disclosure. Furthermore, the embodiments described above may be implemented, for example, as programs executed by an electronic device 10 or a system 1 or system 2 including the electronic device 10, or by an information processing device (e.g., a computer).

[0099] Although an electronic device and system according to one embodiment have been described above, the electronic device and system according to one embodiment may be implemented, for example, as follows, as long as it is not logically contradictory. [Note 1] A recognition unit that recognizes at least one of at least one first object whose position is known and at least one second object whose position is unknown in an image captured from a moving object, When the first object and the second object are recognized in the aforementioned image, an estimation unit estimates the position of the second object based on the position of the first object, Equipped with, The estimation unit is an electronic device that estimates the position of the moving body based on the position of the first object or the position of the second object. [Note 2] The recognition unit is an electronic device as described in Appendix 1, which recognizes the first object and the second object from among objects that are determined to be stationary relative to the surrounding environment of the moving object, based on a plurality of images captured over time from the moving object. [Note 3] The electronic device according to Appendix 1 or 2, wherein the estimation unit estimates the position of the moving body based on the position of the first object when the first object is recognized in the image. [Note 4] The electronic device according to Appendix 1, wherein the estimation unit estimates the position of the moving body based on the position of the second object when the first object is not recognized in the image but the second object is recognized. [Note 5] The electronic device according to Appendix 1 to 4, wherein, when multiple second objects are recognized in the image, the estimation unit estimates the position of the moving body based on the position of the second object that is closest to the moving body among the second objects. [Note 6] The electronic device according to Appendix 1 to 4, wherein, when multiple second objects are recognized in the image, the estimation unit estimates the position of the moving body based on the position of the second object recognized with the highest contrast ratio among the second objects. [Note 7] The electronic device according to Appendix 1 to 6, wherein the estimation unit estimates the position of the moving body based on the position of the second object whose position has been estimated among the second objects recognized in the image when the second object used to estimate the position of the moving body among the second objects is no longer recognized in the image. [Note 8] The recognition unit further recognizes a third object whose position is unknown, The estimation unit, in the image, if the first object is not recognized and the second object whose position has been estimated and the third object are recognized, estimates the position of the third object based on the second object whose position has been estimated, as described in Appendix 1 or Appendix 4 to 7 of the electronic device. [Note 9] The electronic device according to Appendix 8, wherein the estimation unit estimates the position of the moving body based on the position of the third object when the first object and the second object whose position has been estimated are not recognized and the third object is recognized. [Note 10] The system further includes a receiving unit that acquires the movement path of the aforementioned moving object, If the estimation unit recognizes the second object again after the moving body has passed over the second object whose position has been estimated based on the first object, it will perform the estimation of the position of the second object again. Electronic devices as described in Appendix 1 to 9. [Note 11] The electronic device according to Appendix 1 to 10, wherein the estimation unit corrects the already estimated position of the second object based on the position of the first object that has been recognized again in the image. [Note 12] The electronic device according to Appendix 1 to 11, wherein the estimation unit corrects the already estimated position of the second object based on the position of the newly recognized first object when the first object is newly recognized in the image. [Note 13] The electronic device according to Appendix 1 to 12, wherein the estimation unit estimates the position of at least one of the second object and the moving body based on information acquired from the moving body by a stereo camera. [Note 14] The electronic device according to Appendix 1 to 13, wherein the estimation unit estimates the position of at least one of the second object and the moving body based on image information acquired from the moving body along with distance information. [Note 15] An imaging unit that captures images from a moving object, A recognition unit recognizes at least one of at least one first object whose position is known and at least one second object whose position is unknown in the image captured by the imaging unit, When the first object and the second object are recognized in the aforementioned image, an estimation unit estimates the position of the second object based on the position of the first object, Equipped with, The estimation unit is a system that estimates the position of the moving body based on the position of the first object or the position of the second object. [Explanation of Symbols]

[0100] 1,2 System 10 Electronic equipment 12 Recognition part 14 Estimation part 16 Control Unit 18 Memory section 20 Imaging Department 32 Transmitter 34 Receiving Unit 36,38 Transmitter / Receiver Section 40 Mobile Unit Control

Claims

1. A recognition unit that recognizes at least one of at least one first object whose position is known and at least one second object whose position is unknown in an image captured from a moving object, When the first object and the second object are recognized in the aforementioned image, an estimation unit estimates the position of the second object based on the position of the first object, Equipped with, The estimation unit is an electronic device that estimates the position of the moving body based on the position of the first object or the position of the second object.

2. The electronic device according to claim 1, wherein the recognition unit recognizes the first object and the second object from among objects that are determined to be stationary relative to the surrounding environment of the moving object, based on a plurality of images captured over time from the moving object.

3. The electronic device according to claim 1, wherein the estimation unit estimates the position of the moving body based on the position of the first object when the first object is recognized in the image.

4. The electronic device according to claim 1, wherein the estimation unit estimates the position of the moving body based on the position of the second object when the first object is not recognized in the image but the second object is recognized.

5. The electronic device according to claim 4, wherein, when multiple second objects are recognized in the image, the estimation unit estimates the position of the moving body based on the position of the second object that is closest to the moving body among the second objects.

6. The electronic device according to claim 4, wherein, when multiple second objects are recognized in the image, the estimation unit estimates the position of the moving body based on the position of the second object recognized with the highest contrast ratio among the second objects.

7. The electronic device according to claim 1, wherein when the estimation unit is no longer recognized in the image as a second object that was used to estimate the position of the moving body, it estimates the position of the moving body based on the position of the second object whose position has been estimated among the second objects that are recognized in the image.

8. The recognition unit further recognizes a third object whose position is unknown, The electronic device according to claim 1, wherein, in the image, the estimation unit estimates the position of the third object based on the second object whose position has been estimated, when the first object is not recognized and the second object whose position has been estimated and the third object are recognized.

9. The electronic device according to claim 8, wherein the estimation unit estimates the position of the moving body based on the position of the third object when the first object and the second object whose position has been estimated are not recognized and the third object is recognized.

10. The system further includes a receiving unit that acquires the movement path of the aforementioned moving object, If the estimation unit recognizes the second object again after the moving body has passed over the second object whose position has been estimated based on the first object, it will perform the estimation of the position of the second object again. The electronic device according to claim 1.

11. The electronic device according to claim 1, wherein the estimation unit corrects the already estimated position of the second object based on the position of the first object that has been recognized again in the image.

12. The electronic device according to claim 1, wherein when the estimation unit newly recognizes the first object in the image, it corrects the already estimated position of the second object based on the position of the newly recognized first object.

13. The electronic device according to claim 1, wherein the estimation unit estimates the position of at least one of the second object and the moving body based on information acquired from the moving body by a stereo camera.

14. The electronic device according to claim 1, wherein the estimation unit estimates the position of at least one of the second object and the moving body based on image information acquired from the moving body along with distance information.

15. An imaging unit that captures images from a moving object, A recognition unit recognizes at least one of at least one first object whose position is known and at least one second object whose position is unknown in the image captured by the imaging unit, When the first object and the second object are recognized in the aforementioned image, an estimation unit estimates the position of the second object based on the position of the first object, Equipped with, The estimation unit is a system that estimates the position of the moving body based on the position of the first object or the position of the second object.

Images