Vehicle body state estimation system, vehicle body state estimation method, and program

Abstract

This vehicle body state estimation system (1) for estimating the state of a vehicle (2), which is either a human-powered vehicle or an electric bicycle, comprises: an acquisition unit (11) for acquiring appearance information that is information indicating the appearance of the vehicle (2); an analysis unit (12) for analyzing the appearance information and extracting a region included in the appearance of the vehicle (2) from the appearance information; a component estimation unit (13) for estimating the color of the region extracted by the analysis unit (12); and a state estimation unit (14) for estimating whether the state of the vehicle (2) is an abnormal state or a normal state on the basis of the color of the region estimated by the component estimation unit (13), and outputting the estimation result.

Description

Vehicle body state estimation system, vehicle body state estimation method, and program

[0001] The present disclosure relates to a vehicle body state estimation system, a vehicle body state estimation method, and a program.

[0002] As a conventional technique, Patent Document 1 discloses a detection device that detects worn-out parts of a human-powered vehicle as detectable worn-out parts from a first image that includes at least a portion of the human-powered vehicle, and includes a control unit that outputs wear information related to the degree of wear of the detected worn-out parts.

[0003] Japanese Patent Application Laid-Open No. 2020-203547

[0004] For example, determining the condition of a vehicle requires specialized knowledge, but if a vehicle user does not ask a specialist who can determine the condition of the vehicle, the vehicle user will have to wait until the vehicle actually breaks down before sending it in for repairs, which will require repair costs and time.

[0005] In this regard, Patent Document 1 discloses a detection device that allows a vehicle user to easily obtain information about the degree of wear of wear parts of a human-powered vehicle.

[0006] However, even if the detection device described in Patent Document 1 displays the degree of wear, the timing for replacing vehicle parts is determined by the user, so parts may not be replaced until they fail. Furthermore, simply displaying information about the degree of wear of parts results in only replacing a portion of the many parts that make up the vehicle. This can lead to issues such as an increased frequency of vehicle failures and increased maintenance costs.

[0007] Therefore, the present disclosure aims to provide a vehicle body state estimation system, a vehicle body state estimation method, and a program that can suppress an increase in the frequency of vehicle failures while suppressing an increase in vehicle maintenance costs.

[0008] In order to achieve the above object, a vehicle body state estimation system according to one aspect of the present disclosure is a vehicle body state estimation system that estimates the state of a vehicle that is either a human-powered vehicle or an electric bicycle, and includes an acquisition unit that acquires appearance information that is information indicating the appearance of the vehicle, an analysis unit that analyzes the appearance information and extracts areas included in the vehicle's appearance from the appearance information, a part estimation unit that estimates the color of the area extracted by the analysis unit, and a state estimation unit that estimates whether the vehicle's state is abnormal or normal based on the color of the area estimated by the part estimation unit and outputs the estimated result.

[0009] In addition, in order to achieve the above-mentioned object, a vehicle body state estimation method according to one aspect of the present disclosure is a vehicle body state estimation method for estimating the state of a vehicle that is either a human-powered vehicle or an electric bicycle, and includes: an acquisition unit acquiring appearance information that is information indicating the appearance of the vehicle; an analysis unit analyzing the appearance information and extracting an area included in the appearance of the vehicle from the appearance information; a part estimation unit estimating the color of the area extracted by the analysis unit; and a state estimation unit estimating whether the state of the vehicle is abnormal or normal based on the color of the area estimated by the part estimation unit, and outputting the estimation result.

[0010] In order to achieve the above object, a program according to one aspect of the present disclosure is a program for causing a computer to execute a vehicle body state estimation method.

[0011] According to the vehicle body state estimation system etc. disclosed herein, it is possible to suppress an increase in the frequency of vehicle failures while suppressing an increase in vehicle maintenance costs.

[0012] Fig. 1 is a block diagram showing a vehicle body state estimation system according to an embodiment. Fig. 2A is a diagram showing how a mechanical component of a vehicle is imaged and the imaged appearance information. Fig. 2B is a diagram showing a plurality of mechanical components whose colors have been estimated. Fig. 3 is a flowchart showing an operation example 1 of the vehicle body state estimation system according to an embodiment. Fig. 4 is a flowchart showing an operation example 2 of the vehicle body state estimation system according to an embodiment. Fig. 5 is a flowchart showing an operation example 3 of the vehicle body state estimation system according to an embodiment.

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. Note that each of the embodiments described below represents a specific example of the present disclosure. Therefore, the numerical values, shapes, materials, components, component arrangements and connection forms, steps, step order, etc. shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Therefore, among the components in the following embodiments, components not recited in independent claims will be described as optional components.

[0014] Furthermore, each figure is a schematic diagram and is not necessarily an exact illustration. Therefore, for example, the scales and the like do not necessarily match in each figure. Furthermore, in each figure, substantially the same configurations are assigned the same reference numerals, and duplicate explanations are omitted or simplified.

[0015] A vehicle body state estimation system, a vehicle body state estimation method, and a program according to this embodiment will be described below.

[0016] (Embodiment) <Configuration> First, the configuration of a vehicle body state estimation system 1 will be described with reference to FIGS. 1 and 2A.

[0017] Fig. 1 is a block diagram showing a vehicle body state estimation system 1 according to an embodiment. Fig. 2A is a diagram showing how mechanical components of a vehicle 2 are imaged and the captured appearance information. Fig. 2B is a diagram showing a plurality of mechanical components whose colors have been estimated. In Fig. 2B, the colors of each region are indicated by different hatching.

[0018] 1 , the vehicle body state estimation system 1 is, for example, a portable external device such as a smartphone, a tablet terminal, or a wearable terminal, or a stationary external device such as a surveillance camera or a port-mounted sensor. In this embodiment, a portable external device is illustrated. In this embodiment, the portable external device and the stationary external device may be collectively referred to as a terminal device.

[0019] Such a vehicle body state estimation system 1 can estimate the state of the vehicle 2, which is either a human-powered vehicle or an electric bicycle. The state of the vehicle 2 is the state of the mechanical parts that make up the vehicle 2. In this embodiment, an electric bicycle is used as an example of the vehicle 2.

[0020] Specifically, the vehicle body state estimation system 1 includes an acquisition unit 11 , an analysis unit 12 , a part estimation unit 13 , a state estimation unit 14 , and a notification unit 15 .

[0021] The acquisition unit 11 acquires appearance information, which is information indicating the appearance of the vehicle 2. The appearance information includes mechanical parts that constitute the vehicle 2. The mechanical parts are one or more of a chain, gears, a motor (particularly a motor shaft), a transmission, sprockets, pulleys, pedals, cranks, wheels, rims, hubs, tires, lights, frames, brakes, tire tubes, lights, batteries, bolts, locks, suspensions, and stands.

[0022] The appearance information acquired by the acquisition unit 11 is one or more pieces of image information obtained by non-contact sensing, including RGB (Red, Green, Blue) camera information, monochrome camera information, thermal image information, ultrasonic image information, laser light information, and IR (Infrared Light) image information. This appearance information is primarily still images acquired by various types of sensor cameras, such as RGB cameras, monochrome cameras, thermal image cameras, ultrasonic cameras, laser diodes, and image sensors. For example, as shown in FIG. 2A , the appearance information is acquired by non-contact sensing in which a terminal device captures an image of a mechanical component of the vehicle 2. In other words, the acquisition unit 11 acquires the appearance information from a sensor mounted on the terminal device.

[0023] The acquisition unit 11 outputs the acquired appearance information to the analysis unit 12 .

[0024] The analysis unit 12 analyzes the appearance information and extracts regions included in the appearance of the vehicle 2 from the appearance information. For example, the analysis unit 12 divides the appearance information into regions having similar feature amounts (color, brightness, texture, etc.) and extracts multiple regions. In other words, the analysis unit 12 extracts multiple regions by dividing the appearance information into multiple regions according to the feature amounts indicated in the appearance information. The multiple regions extracted by the analysis unit 12 include mechanical parts that constitute the vehicle 2 because their outer shapes are indicated.

[0025] The analysis unit 12 outputs the extracted regions, that is, the analysis results, to the part estimation unit 13.

[0026] Based on the results of the analysis by the analysis unit 12, the part estimation unit 13 estimates the color of each region extracted by the analysis unit 12, as shown in FIG. 2B . That is, the part estimation unit 13 estimates the color of the mechanical part included in each region extracted by the analysis unit 12. For example, because the regions are composed of equivalent feature amounts, the part estimation unit 13 can estimate the part shape from the outer shell of the region. Because one region is composed of multiple pixels, the part estimation unit 13 can estimate the mechanical part pixel by pixel.

[0027] The part estimation unit 13 estimates the mechanical parts included in each region from the part shapes estimated for each region and the colors estimated for each region.

[0028] Such a part estimation unit 13 may be a machine learning model that has learned to be able to estimate the color of the mechanical part included in each area extracted by the analysis unit 12.

[0029] The part estimation unit 13 outputs the coordinates of each pixel estimated for each estimated mechanical part and the color estimated for each mechanical part (the color of the multiple pixels that make up the mechanical part) to the state estimation unit 14.

[0030] The state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the color of the area estimated by the part estimation unit 13, i.e., the mechanical part estimated by the part estimation unit 13, and outputs the estimation result. For example, since the estimated mechanical part is made up of multiple pixels, the state estimation unit 14 may estimate whether the state of each mechanical part is abnormal or normal for each pixel based on the color estimated by the part estimation unit 13.

[0031] Specifically, the state estimation unit 14 calculates the color difference between the color of each pixel representing a mechanical part estimated by the part estimation unit 13 and the color of a mechanical part in a normal state, and determines that the state of the mechanical part is normal if the calculated value is within a predetermined range.On the other hand, the state estimation unit 14 calculates the color difference between the color of each pixel representing a mechanical part estimated by the part estimation unit 13 and the color of a mechanical part in an abnormal state, and determines that the state of the mechanical part is abnormal if the calculated value is within a predetermined range.

[0032] If it is determined that the states of all of the mechanical components that make up the vehicle 2 are normal, the state estimation unit 14 determines that the state of the vehicle 2 is normal. On the other hand, if it is determined that the states of one or more mechanical components that make up the vehicle 2 are abnormal, the state estimation unit 14 determines that the state of the vehicle 2 is abnormal.

[0033] Such a state estimation unit 14 may be a machine learning model that has learned to be able to estimate whether the state of the vehicle 2 is abnormal or normal based on the color of the area estimated by the part estimation unit 13.

[0034] Furthermore, the state estimation unit 14 may further estimate one or more of the probability that the vehicle 2 is in an abnormal state and the remaining time until the vehicle 2 becomes in an abnormal state, and output the estimates to the notification unit 15. Specifically, when the state estimation unit 14 estimates that the state of the vehicle 2 is in an abnormal state, the state estimation unit 14 may estimate one or more of the probability that each mechanical component is in an abnormal state and the remaining time until each mechanical component becomes in an abnormal state, and output the estimates to the notification unit 15. The state estimation unit 14 may estimate one or more of the probability that the vehicle 2 is in an abnormal state and the remaining time until the vehicle 2 becomes in an abnormal state, based on one or more of the probability that each mechanical component is in an abnormal state and the remaining time until each mechanical component becomes in an abnormal state, and output the estimates to the notification unit 15.

[0035] For example, when multiple mechanical components are in an abnormal state, the probability that the vehicle 2 is in an abnormal state may be estimated based on the mechanical component that is most likely to be in an abnormal state, and output to the notification unit 15. Furthermore, when multiple mechanical components are in an abnormal state, the remaining time until the vehicle 2 becomes abnormal may be estimated based on the mechanical component that has the shortest remaining time until it becomes abnormal, and output to the notification unit 15.

[0036] The state estimation unit 14 outputs the determination result. In this embodiment, the state estimation unit 14 outputs the determination result to the notification unit 15.

[0037] The notification unit 15 notifies the user that the state of the vehicle 2 is an abnormal state or a normal state, which is the result determined by the state estimation unit 14. The notification unit 15 is, for example, a display unit such as a display, an audio unit that outputs sound, a light source unit that turns on or blinks a lamp, etc. This allows the user to recognize the state of the vehicle 2 via the notification unit 15.

[0038] Next, the state of the vehicle 2 may be estimated by taking into account the color of the mechanical part included in the appearance information and the operation of the vehicle 2 included in the appearance information, and the estimated result may be output. Below, the same content as above will be omitted as appropriate. For example, even if the mechanical part is operating, the analysis by the analysis unit 12 and the estimation by the part estimation unit 13 are the same as above, and therefore the description thereof will be omitted.

[0039] Specifically, the appearance information may further include the operation of the vehicle 2. In other words, the appearance information is image information of a moving image.

[0040] In this case, the acquisition unit 11 acquires appearance information, which is information indicating the appearance of the vehicle 2. The acquisition unit 11 outputs the acquired appearance information to the analysis unit 12.

[0041] The analysis unit 12 analyzes the moving image included in the appearance information and extracts from the moving image of the appearance information an area included in the appearance of the vehicle 2. The analysis unit 12 outputs the area extracted for each equivalent color (group), that is, the analysis result, to the part estimation unit 13.

[0042] Furthermore, the analysis unit 12 analyzes the sound emitted by the vehicle 2, which is included in the appearance information, and outputs an analysis result indicating the frequency spectrum of the sound to the part estimation unit 13. For example, the analysis unit 12 generates a frequency spectrum by decomposing the sound emitted by the vehicle 2, which is included in the appearance information, into frequency components using a Fourier transform, and outputs the frequency spectrum to the part estimation unit 13.

[0043] The part estimation unit 13 estimates the color of the area extracted by the analysis unit 12 based on the result of the analysis by the analysis unit 12. In other words, the part estimation unit 13 estimates the color of the mechanical part included in the area extracted by the analysis unit 12.

[0044] Furthermore, the part estimation unit 13 estimates the operation of the mechanical part included in the region extracted by the analysis unit 12. That is, the part estimation unit 13 estimates the operation of the mechanical part based on the frequency spectrum of the sound emitted by the mechanical part. The operation of the mechanical part includes the sound emitted by the mechanical part, vibration of the mechanical part, etc., and environmental sound, vibration of other objects, etc. are removed.

[0045] Note that the part estimation unit 13 may estimate a mechanical part by storing in a storage unit a sample of the frequency spectrum of the sound emitted by the mechanical part for each mechanical part, and comparing the sample of the frequency spectrum of the sound with the frequency spectrum of the sound actually emitted by the vehicle 2. Note that the part estimation unit 13 may estimate a mechanical part based on the mechanical part included in the region and the frequency spectrum of the sound emitted by the vehicle 2.

[0046] Such a part estimation unit 13 may be a machine learning model that learns to be able to estimate the colors of the mechanical parts included in each area extracted by the analysis unit 12, and that learns to be able to estimate the operation of the mechanical parts, including the sounds emitted by the mechanical parts, vibrations of the mechanical parts, etc., from the frequency spectrum analyzed by the analysis unit 12.

[0047] The part estimation unit 13 outputs the coordinates of each pixel estimated for each estimated mechanical part, the color estimated for each mechanical part, and the sound estimated to be emitted by the mechanical part to the state estimation unit 14.

[0048] Furthermore, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal, and outputs the estimation result, based on the color of the area estimated by the part estimation unit 13 and the operation of the mechanical part estimated by the part estimation unit 13. Such a state estimation unit 14 may be a machine learning model that has learned to be able to estimate whether the state of the vehicle 2 is abnormal or normal, based on the color of the area estimated by the part estimation unit 13 and the operation of the mechanical part estimated by the part estimation unit 13.

[0049] Furthermore, the state estimation unit 14 may further estimate one or more of the probability that the vehicle 2 is in an abnormal state and the remaining time until the vehicle 2 enters an abnormal state.

[0050] The state estimation unit 14 outputs the determination result. In this embodiment, the state estimation unit 14 outputs the determination result to the notification unit 15.

[0051] The notification unit 15 notifies the result of the determination by the state estimation unit 14 that the state of the vehicle 2 is an abnormal state or that the state of the vehicle 2 is a normal state.

[0052] Next, the state estimation unit 14 may estimate the state of the vehicle 2 based on the color of the area estimated by the part estimation unit 13, and may also estimate the state of the vehicle 2 based on the operation of the mechanical part estimated by the part estimation unit 13. In the following, the same content as that described above will be omitted as appropriate. For example, even if the mechanical part is operating, the analysis by the analysis unit 12 and the estimation by the part estimation unit 13 are the same as those described above, and therefore the description thereof will be omitted.

[0053] Specifically, when the part estimation unit 13 estimates the color of the mechanical part included in the area extracted by the analysis unit 12, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the color of the mechanical part estimated by the part estimation unit 13.

[0054] Furthermore, when the part estimation unit 13 estimates the operation of the mechanical parts included in the area extracted by the analysis unit 12, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the operation of the mechanical parts estimated by the part estimation unit 13. The operation of the mechanical parts includes sounds related to the mechanical parts, vibrations of the mechanical parts, etc., and environmental sounds, vibrations of other objects, etc. are removed.

[0055] Such a state estimation unit 14 may be a machine learning model that learns to be able to estimate whether the state of the vehicle 2 is abnormal or normal based on the color of the area estimated by the part estimation unit 13, and further learns to be able to estimate whether the state of the vehicle 2 is abnormal or normal based on the operation of the mechanical part estimated by the part estimation unit 13 once the part estimation unit 13 makes an estimation.

[0056] Furthermore, the state estimation unit 14 may further estimate one or more of the probability that the vehicle 2 is in an abnormal state and the remaining time until the vehicle 2 enters an abnormal state.

[0057] The state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the results of estimation based on the colors of the mechanical parts and the results of estimation based on the operations of the mechanical parts, and outputs the estimated results.

[0058] For example, if the result of estimation based on the color of the mechanical component is a normal state and the result of estimation based on the sound of the mechanical component is a normal state, the state estimation unit 14 estimates that the state of the vehicle 2 is a normal state and outputs the estimated result.

[0059] Furthermore, if the result of the estimation based on the color of the mechanical component is a normal state and the result of the estimation based on the sound of the mechanical component is an abnormal state, the state estimation unit 14 estimates that the state of the vehicle 2 is an abnormal state and outputs the estimated result.

[0060] Furthermore, when the result of estimation based on the color of the mechanical component indicates an abnormal state and the result of estimation based on the sound of the mechanical component indicates a normal state, the state estimation unit 14 determines whether or not there is deformation in the part shape of the mechanical component estimated by the part estimation unit 13. When there is deformation in the part shape of the mechanical component, the state estimation unit 14 estimates that the state of the vehicle 2 is an abnormal state and outputs the estimated result. On the other hand, when there is no deformation in the part shape of the mechanical component, the state estimation unit 14 estimates that the state of the vehicle 2 is a normal state and outputs the estimated result.

[0061] Furthermore, if the result of the estimation based on the color of the mechanical component is an abnormal state and the result of the estimation based on the sound of the mechanical component is an abnormal state, the state estimation unit 14 estimates that the state of the vehicle 2 is an abnormal state and outputs the estimation result to the notification unit 15.

[0062] The notification unit 15 notifies the result of the determination by the state estimation unit 14 that the state of the vehicle 2 is an abnormal state or that the state of the vehicle 2 is a normal state.

[0063] <Operation Example 1> Next, with reference to FIG. 3, a description will be given of an operation example 1 of the vehicle body state estimation system 1 that estimates the state of the vehicle 2 based on the color of a mechanical part.

[0064] FIG. 3 is a flowchart showing a first operation example of the vehicle body state estimation system 1 according to the embodiment.

[0065] First, the vehicle body state estimation system 1 captures an image of the vehicle 2, and the acquisition unit 11 acquires appearance information that is information indicating the appearance of the vehicle 2 (S11). The acquisition unit 11 outputs the acquired appearance information to the analysis unit 12.

[0066] Next, the analysis unit 12 analyzes the appearance information and extracts from the appearance information an area included in the appearance of the vehicle 2 (S12). The analysis unit 12 outputs the extracted area to the part estimation unit 13.

[0067] Next, the part estimation unit 13 estimates the colors of the mechanical parts included in the area extracted by the analysis unit 12 based on the results of the analysis by the analysis unit 12 (S13). The part estimation unit 13 outputs the coordinates of each pixel estimated for each estimated mechanical part and the estimated color for each mechanical part to the state estimation unit 14.

[0068] Next, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the colors of the mechanical parts included in the area estimated by the part estimation unit 13, i.e., the mechanical parts estimated by the part estimation unit 13 (S14). The state estimation unit 14 estimates whether the state of each mechanical part is abnormal or normal, pixel by pixel. The state estimation unit 14 outputs the result of estimating the state of the vehicle 2 to the notification unit 15.

[0069] Next, the notification unit 15 notifies the user that the state of the vehicle 2 is an abnormal state or a normal state, which is the result determined by the state estimation unit 14 (S15). This allows the user to recognize the state of the vehicle 2 via the notification unit 15. Then, the operation example 1 of the vehicle body state estimation system 1 in FIG. 3 ends.

[0070] <Operation Example 2> Next, an operation example 2 of the vehicle body state estimation system 1 that estimates the state of the vehicle 2 based on the color and operation of a mechanical part will be described with reference to Fig. 4. Descriptions of the same processes as in Fig. 3 will be omitted where appropriate.

[0071] FIG. 4 is a flowchart showing a second operation example of the vehicle body state estimation system 1 according to the embodiment.

[0072] First, through steps S11 to S13, the part estimation unit 13 estimates the operation of the mechanical part included in the region extracted by the analysis unit 12 (S13a). The operation of the mechanical part includes at least the sound emitted by the mechanical part. The part estimation unit 13 outputs the coordinates of each pixel estimated for each estimated mechanical part, the estimated color for each mechanical part, and the estimated sound emitted by the mechanical part to the state estimation unit 14.

[0073] Next, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the colors of the mechanical parts included in the area estimated by the part estimation unit 13 and the operations of the mechanical parts estimated by the part estimation unit 13 (S14a). The state estimation unit 14 outputs the result of estimating the state of the vehicle 2 to the notification unit 15.

[0074] Next, the notification unit 15 notifies the user that the state of the vehicle 2 is an abnormal state or a normal state, which is the result determined by the state estimation unit 14 (S15). This allows the user to recognize the state of the vehicle 2 via the notification unit 15. Then, the operation example 2 of the vehicle body state estimation system 1 in FIG. 4 ends.

[0075] <Operation Example 3> Next, an operation example 3 of the vehicle body state estimation system 1 that estimates the state of the vehicle 2 based on the color and operation of a mechanical part will be described with reference to Fig. 5. Descriptions of the same processes as in Fig. 4 will be omitted where appropriate.

[0076] FIG. 5 is a flowchart showing a third operation example of the vehicle body state estimation system 1 according to the embodiment.

[0077] First, through steps S11 to S13, the part estimation unit 13 estimates the operation of the mechanical part included in the region extracted by the analysis unit 12 (S13a). The operation of the mechanical part includes at least the sound emitted by the mechanical part. The part estimation unit 13 outputs the coordinates of each pixel estimated for each estimated mechanical part, the estimated color for each mechanical part, and the estimated sound emitted by the mechanical part to the state estimation unit 14.

[0078] Next, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the colors of the mechanical parts included in the area estimated by the part estimation unit 13 (S14).

[0079] Next, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the operation of the mechanical parts estimated by the part estimation unit 13 (S14b).

[0080] Next, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the result of estimation based on the color of the mechanical component and the result of estimation based on the operation of the mechanical component (S14c). The state estimation unit 14 outputs the estimation result to the notification unit 15.

[0081] Next, the notification unit 15 notifies the user that the state of the vehicle 2 is an abnormal state or a normal state, which is the result determined by the state estimation unit 14 (S15). This allows the user to recognize the state of the vehicle 2 via the notification unit 15. Then, the operation example 3 of the vehicle body state estimation system 1 in FIG. 5 ends.

[0082] <Operations and Effects> Next, operations and effects of the vehicle body state estimation system 1 etc. according to this embodiment will be described.

[0083] As described above, the vehicle body state estimation system 1 of technology 1 in this embodiment is a vehicle body state estimation system 1 that estimates the state of a vehicle 2 that is either a human-powered vehicle or an electric bicycle, and includes an acquisition unit 11 that acquires appearance information that is information that indicates the appearance of the vehicle 2, an analysis unit 12 that analyzes the appearance information and extracts areas included in the appearance of the vehicle 2 from the appearance information, a part estimation unit 13 that estimates the color of the area extracted by the analysis unit 12, and a state estimation unit 14 that estimates whether the state of the vehicle 2 is abnormal or normal based on the color of the area estimated by the part estimation unit 13, and outputs the estimated result.

[0084] According to this, the state estimation unit 14 outputs the state of the vehicle 2, allowing the user to understand the state of the vehicle 2, and if the state of the vehicle 2 is abnormal, the user will be conscious of trying to repair the vehicle 2.

[0085] Furthermore, since the user can grasp the condition of the vehicle 2 without having to ask a specialist who can determine the condition of the vehicle 2, if the condition is normal, the user does not need to perform maintenance on the vehicle 2.

[0086] Therefore, according to this embodiment, it is possible to suppress an increase in the frequency of breakdowns in the vehicle 2 while suppressing an increase in maintenance costs for the vehicle 2.

[0087] In addition, in the vehicle body state estimation system 1 of Technique 2 in this embodiment, the state of the vehicle 2 is the state of the mechanical parts that make up the vehicle 2, which is the vehicle body state estimation system 1 described in Technique 1.

[0088] This makes it possible to output an estimation result as to whether the state of each mechanical component that constitutes the vehicle 2 is normal or abnormal, thereby enabling the user to grasp the state of each mechanical component.

[0089] Furthermore, in the vehicle body state estimation system 1 of Technology 3 in this embodiment, the area extracted by the analysis unit 12 includes mechanical parts that make up the vehicle 2, the part estimation unit 13 estimates the colors of the mechanical parts included in the area extracted by the analysis unit 12, and the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the colors of the mechanical parts estimated by the part estimation unit 13, and outputs the estimated result, which is the vehicle body state estimation system 1 described in Technology 2.

[0090] According to this, since it is estimated whether each mechanical part is in an abnormal state or in a normal state based on the color state of each mechanical part, it is possible to estimate the state of each mechanical part with higher accuracy.

[0091] Furthermore, in the vehicle body state estimation system 1 of Technology 4 in this embodiment, the mechanical parts are one or more of a chain, a gear, a motor, a transmission, a sprocket, a pulley, a pedal, a crank, a wheel, a rim, a hub, a tire, a light, a frame, a brake, a tire tube, a light, a battery, a bolt, a lock, a suspension, and a stand, which is the vehicle body state estimation system 1 described in Technology 2 or 3.

[0092] This makes it possible to estimate the state of many of the mechanical parts that make up the vehicle 2.

[0093] Furthermore, in the vehicle body state estimation system 1 of Technology 5 in this embodiment, the appearance information further includes the operation of the vehicle 2, the part estimation unit 13 further estimates the operation of the mechanical parts included in the area extracted by the analysis unit 12, and the state estimation unit 14 further estimates whether the state of the vehicle 2 is in an abnormal state or a normal state based on the operation of the mechanical parts estimated by the part estimation unit 13, and outputs the estimated result, which is the vehicle body state estimation system 1 described in any one of Technologies 2 to 4.

[0094] According to this, it is possible to estimate whether each mechanical part is in an abnormal state or a normal state based on the operation of each mechanical part, and therefore it is possible to estimate the state of each mechanical part with higher accuracy.

[0095] Furthermore, in the vehicle body state estimation system 1 of Technology 6 in this embodiment, the area extracted by the analysis unit 12 includes mechanical parts that make up the vehicle 2, and the appearance information further includes the operation of the vehicle 2, the part estimation unit 13 estimates the color of the mechanical parts included in the area extracted by the analysis unit 12 and further estimates the operation of the mechanical parts included in the area extracted by the analysis unit 12, and the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the color of the mechanical parts estimated by the part estimation unit 13 and the operation of the mechanical parts estimated by the part estimation unit 13, and outputs the estimated result, which is the vehicle body state estimation system 1 described in any one of Technologies 1 to 5.

[0096] This allows estimation of whether each mechanical part is in an abnormal state or a normal state based on the color and operation of each mechanical part, thereby making it possible to estimate the state of each mechanical part with greater accuracy.

[0097] Furthermore, in the vehicle body state estimation system 1 of Technology 7 in this embodiment, the area extracted by the analysis unit 12 includes mechanical parts that constitute the vehicle 2, the appearance information further includes the operation of the vehicle 2, the part estimation unit 13 estimates the colors of the mechanical parts included in the area extracted by the analysis unit 12, the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the colors of the mechanical parts estimated by the part estimation unit 13, the part estimation unit 13 further estimates the operations of the mechanical parts included in the area extracted by the analysis unit 12, the state estimation unit 14 further estimates whether the state of the vehicle 2 is abnormal or normal based on the operations of the mechanical parts estimated by the part estimation unit 13, and the state estimation unit 14 estimates whether the state of the vehicle 2 is abnormal or normal based on the results of estimation based on the colors of the mechanical parts and the results of estimation based on the operations of the mechanical parts, and outputs the estimated results. This is a vehicle body state estimation system 1 described in Technology 6.

[0098] This makes it possible to estimate whether each mechanical part is in an abnormal state or a normal state from the color-based abnormal state or normal state of each mechanical part and the operation-based abnormal state or normal state of each mechanical part, thereby enabling more accurate estimation of the state of each mechanical part.

[0099] Furthermore, in the vehicle body state estimation system 1 of Technology 8 in this embodiment, the operation of the mechanical parts includes the sound and vibration emitted by the mechanical parts, which is the vehicle body state estimation system 1 described in Technology 6.

[0100] This allows the state of each mechanical part to be estimated more accurately, since it is possible to estimate whether the mechanical part is in an abnormal state or a normal state based on the color, sound, and vibration of each mechanical part.

[0101] Furthermore, in the vehicle body state estimation system 1 of Technology 9 in this embodiment, the operation of the mechanical parts includes the sound emitted by the mechanical parts and the vibration of the mechanical parts, which is the vehicle body state estimation system 1 described in Technology 7.

[0102] This allows the state of each mechanical part to be estimated more accurately, since it is possible to estimate whether the mechanical part is in an abnormal state or a normal state based on the color, sound, and vibration of each mechanical part.

[0103] Furthermore, in the vehicle body state estimation system 1 of Technology 10 in this embodiment, the appearance information acquired by the acquisition unit 11 is one or more of RGB (Red, Green, Blue) camera information, monochrome camera information, thermal image information, ultrasonic image information, laser light information, and IR (Infrared Light) image information obtained by non-contact sensing, which is the vehicle body state estimation system 1 described in any one of Technologies 1 to 9.

[0104] This makes it possible to estimate the color of each mechanical part, and based on the color state of each mechanical part, it is possible to estimate and output whether the state of vehicle 2 is abnormal or normal.

[0105] Furthermore, in the vehicle body state estimation system 1 of Technology 11 in this embodiment, the state estimation unit 14 is a vehicle body state estimation system 1 described in any one of Technologies 1 to 10 that further estimates one or more of the probability that the vehicle 2 is in an abnormal state and the remaining time until the vehicle 2 becomes in an abnormal state.

[0106] This makes it possible to output not only the state of the vehicle 2 but also one or more of the probability that the vehicle 2 is in an abnormal state and the remaining time until the vehicle 2 becomes abnormal. This makes it possible for the user to predict the period until the vehicle 2 breaks down and to be conscious of repairs and part replacement before a breakdown occurs. As a result, it is possible to suppress an increase in the frequency of breakdowns in the vehicle 2 and an increase in maintenance costs for the vehicle 2.

[0107] Furthermore, in the vehicle body state estimation system 1 of Technology 12 in this embodiment, the vehicle body state estimation system 1 is described in any one of Technologies 1 to 11 and is equipped with a notification unit 15 that notifies that the state of the vehicle 2, which is the result output by the state estimation unit 14, is an abnormal state or that the state of the vehicle 2 is a normal state.

[0108] This allows the user to recognize the state of the vehicle 2 notified by the notification unit 15.

[0109] Furthermore, in the vehicle body state estimation system 1 of Technology 13 in this embodiment, the vehicle body state estimation system 1 is a vehicle body state estimation system 1 described in any one of Technologies 1 to 12 that is a portable external device or an installed external device.

[0110] This makes it possible to easily obtain external appearance information of the vehicle 2.

[0111] Furthermore, the vehicle body state estimation method of technique 14 in this embodiment is a vehicle body state estimation method for estimating the state of vehicle 2, which is either a human-powered vehicle or an electric bicycle, and includes the steps of: an acquisition unit 11 acquiring appearance information, which is information indicating the appearance of vehicle 2; an analysis unit 12 analyzing the appearance information and extracting an area included in the appearance of vehicle 2 from the appearance information; a part estimation unit 13 estimating the color of the area extracted by analysis unit 12; and, based on the color of the area estimated by part estimation unit 13, estimating whether the state of vehicle 2 is abnormal or normal, and outputting the estimation result by state estimation unit 14.

[0112] This vehicle body state estimating method also provides the same effects as those described above.

[0113] The program of Technique 15 in this embodiment is a program for causing a computer to execute the vehicle body state estimation method described in Technique 14.

[0114] This program also provides the same effects as those described above.

[0115] (Other Modifications) While the vehicle body state estimation system and the like according to the present disclosure have been described above based on the above-described embodiments, the present disclosure is not limited to these embodiments. As long as the modifications do not deviate from the spirit of the present disclosure, various modifications conceivable by a person skilled in the art may also be included within the scope of the present disclosure.

[0116] For example, in a vehicle body state estimation system or the like according to the present disclosure, a program capable of executing the vehicle body state estimation method may be stored on a cloud server. In this case, the terminal device may transmit appearance information acquired by the terminal device to the cloud server, so that the cloud server may estimate whether the vehicle state is abnormal or normal. The cloud server may transmit the result of estimating the vehicle state to the terminal device. The terminal device may notify the user of the result of estimating the vehicle state received from the cloud server. In this case, the vehicle body state estimation system may include a cloud server storing a program capable of executing the vehicle body state estimation method, and a terminal device capable of communicating with the cloud server, acquiring appearance information, and notifying the user of the result of estimating the vehicle state by the cloud server.

[0117] In addition, this disclosure also includes forms obtained by making various modifications to the above-mentioned embodiments that a person skilled in the art would think of, and forms realized by arbitrarily combining the components and functions of each embodiment within the scope of this disclosure.

[0118] REFERENCE SIGNS LIST 1 Vehicle body state estimation system 2 Vehicle 11 Acquisition unit 12 Analysis unit 13 Part estimation unit 14 State estimation unit 15 Notification unit

Claims

1. A vehicle state estimation system that estimates the state of a vehicle that is either a human-powered vehicle or an electric bicycle, An acquisition unit that acquires exterior information, which is information indicating the exterior appearance of the vehicle, An analysis unit analyzes the aforementioned external information and extracts the regions included in the exterior of the vehicle from the aforementioned external information, A component estimation unit estimates the color of the region extracted by the analysis unit, The system includes a state estimation unit that estimates whether the vehicle is in an abnormal state or a normal state based on the color of the region estimated by the part estimation unit, and outputs the estimated result. Vehicle condition estimation system.

2. The state of the vehicle is the state of the mechanical components that make up the vehicle. The vehicle body condition estimation system according to claim 1.

3. The region extracted by the analysis unit includes the mechanical components that make up the vehicle. The component estimation unit estimates the color of the mechanism component included in the region extracted by the analysis unit, The state estimation unit estimates whether the vehicle is in an abnormal state or a normal state based on the color of the mechanical component estimated by the component estimation unit, and outputs the estimated result. The vehicle body state estimation system according to claim 2.

4. The aforementioned mechanical components are one or more of the following: chain, gear, motor, derailleur, sprocket, pulley, pedal, crank, wheel, rim, hub, tire, light, frame, brake, tire tube, battery, bolt, lock, suspension, and stand. The vehicle body state estimation system according to claim 2 or 3.

5. The aforementioned external information further includes the operation of the vehicle, The component estimation unit further estimates the operation of the mechanical component included in the region extracted by the analysis unit, The state estimation unit further estimates whether the vehicle's state is abnormal or normal based on the operation of the mechanical components estimated by the component estimation unit, and outputs the estimated result. The vehicle body state estimation system according to claim 2 or 3.

6. The region extracted by the analysis unit includes the mechanical components that make up the vehicle. The aforementioned external information further includes the operation of the vehicle, The component estimation unit estimates the color of the mechanical component included in the region extracted by the analysis unit, and further estimates the operation of the mechanical component included in the region extracted by the analysis unit. The state estimation unit estimates whether the vehicle is in an abnormal state or a normal state based on the color of the mechanical component estimated by the component estimation unit and the operation of the mechanical component estimated by the component estimation unit, and outputs the estimated result. A vehicle body condition estimation system according to any one of claims 1 to 3.

7. The region extracted by the analysis unit includes the mechanical components that make up the vehicle. The aforementioned external information further includes the operation of the vehicle, The component estimation unit estimates the color of the mechanism component included in the region extracted by the analysis unit, The state estimation unit estimates whether the vehicle is in an abnormal state or a normal state based on the color of the mechanical component estimated by the component estimation unit. The component estimation unit further estimates the operation of the mechanical component included in the region extracted by the analysis unit, The state estimation unit further estimates whether the vehicle's state is abnormal or normal based on the operation of the mechanical components estimated by the component estimation unit. The state estimation unit estimates whether the vehicle is in an abnormal state or a normal state based on the results estimated based on the color of the mechanical parts and the results estimated based on the operation of the mechanical parts, and outputs the estimated result. A vehicle body condition estimation system according to any one of claims 1 to 3.

8. The operation of the aforementioned mechanical component includes the sound emitted by the mechanical component and the vibration of the mechanical component. The vehicle body condition estimation system according to claim 6.

9. The operation of the aforementioned mechanical component includes the sound emitted by the mechanical component and the vibration of the mechanical component. The vehicle body condition estimation system according to claim 7.

10. The appearance information acquired by the acquisition unit is one or more of the following: RGB (Red, Green, Blue) camera information, monochrome camera information, thermal image information, ultrasonic image information, laser light information, and IR (Infrared Light) image information obtained by non-contact sensing. A vehicle body condition estimation system according to any one of claims 1 to 3.

11. The state estimation unit further estimates and outputs one or more of the following: the probability that the vehicle is in an abnormal state, and the remaining time until the vehicle enters an abnormal state. A vehicle body condition estimation system according to any one of claims 1 to 3.

12. The system includes a notification unit that notifies the system that the vehicle's state, as output by the state estimation unit, is abnormal or normal. A vehicle body condition estimation system according to any one of claims 1 to 3.

13. The vehicle body state estimation system is either a portable external device or a stationary external device. A vehicle body condition estimation system according to any one of claims 1 to 3.

14. A method for estimating the state of a vehicle, which is either a human-powered vehicle or an electric bicycle, The unit acquires exterior information, which is information indicating the exterior appearance of the vehicle. The analysis unit analyzes the aforementioned external information and extracts the regions included in the exterior of the vehicle from the aforementioned external information. The component estimation unit estimates the color of the region extracted by the analysis unit, The component estimation unit estimates whether the vehicle's state is abnormal or normal based on the color of the region estimated by the component estimation unit, and the state estimation unit outputs the estimated result. A method for estimating the condition of a vehicle.

15. A computer to perform the vehicle body state estimation method according to claim 14. program.