Evaluation device and evaluation program

Abstract

To appropriately evaluate driving of a driver.SOLUTION: An evaluation device comprises a control unit and evaluates driving of a driver of a vehicle. The evaluation device acquires vehicle information related to a traveling state of the vehicle, detects a scene of kindness performed by the driver on the basis of the acquired vehicle information, and makes an evaluation advantageous for the driver on driving evaluation of the driver if a scene of kindness is detected.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to an evaluation device Place and an evaluation Program method.

Background Art

[0002] Conventionally, there has been an evaluation system for evaluating a driver's driving. For example, in the evaluation system, a technique has been proposed for recognizing a sign or a stop line from an image of a camera that captures the front of a vehicle and determining whether or not the driver has appropriately made a stop (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional technology only determines whether or not the Road Traffic Law has been appropriately complied with, and there is room for improvement in appropriately evaluating the driver's driving.

[0005] The present invention has been made in view of the above, and an object thereof is to provide an evaluation device, an evaluation system, and an evaluation method capable of appropriately evaluating a driver's driving.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, an evaluation apparatus according to the present invention includes a control unit and is an evaluation apparatus for evaluating the driving of a driver of a vehicle. The control unit acquires vehicle information regarding the driving state of the vehicle, detects a considerate scene performed by the driver based on the acquired vehicle information, and when the considerate scene is detected, performs an evaluation that is advantageous to the driver with respect to the driving evaluation of the driver.

Effect of the Invention

[0007] According to the present invention, the driving of the driver can be appropriately evaluated.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Best Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments for implementing the evaluation apparatus, evaluation system, and evaluation method according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the evaluation apparatus, evaluation system, and evaluation method according to the present application are not limited by this embodiment.

[0010] First, the outline of the evaluation apparatus, evaluation system, and evaluation method according to the embodiment will be described with reference to FIGS. 1 to 3. FIG. 1 is a diagram showing the outline of the evaluation system. FIGS. 2 and 3 are diagrams showing the outline of the evaluation method. Hereinafter, the case where the evaluation apparatus is the evaluation server 10 shown in FIG. 1 will be described, but the evaluation apparatus may be an in-vehicle device 50. Further, hereinafter, the case where the evaluation system 1 is introduced into a company will be described. That is, the case where each vehicle 100 is a commercial vehicle and the evaluation results of the drivers of each vehicle 100 are provided to the company and the drivers will be described.

[0011] The evaluation system 1 according to the embodiment includes an evaluation server 10 and an in-vehicle device 50. For example, the evaluation server 10 and the in-vehicle device 50 perform communication connection via a network such as various wireless communication networks such as 4G (Generation), 5G, LTE (Long Term Evolution), Wifi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0012] The evaluation server 10 is a server device that evaluates the driving of the driver of each vehicle 100 based on the vehicle information collected from each in-vehicle device 50. The in-vehicle device 50 is a drive recorder mounted on each vehicle 100 and having a communication function with the evaluation server 10.

[0013] For example, the in-vehicle device 50 has a camera 61 (see FIG. 4) that captures the front of the vehicle 100, and further collects driving data related to the driving state of the vehicle 100 and transmits it to the evaluation server 10 at a predetermined cycle. Also, as will be described later, the in-vehicle device 50 has a function of uploading the requested data to the evaluation server 10 in response to a request from the evaluation server 10.

[0014] By the way, as a method for evaluating a driver's driving, a point deduction method is generally adopted. Therefore, once a driver is deducted points, it is impossible to raise the evaluation thereafter, so there is a risk that the motivation for driving evaluation will decrease.

[0015] In contrast, in the evaluation system 1 according to the embodiment, in order to improve the motivation of the driver for driving evaluation, an evaluation system that is advantageous to the driver is introduced. Specifically, in the evaluation system 1 according to the embodiment, a driving evaluation that is advantageous to the driver who performs considerate driving is performed.

[0016] For example, in the present embodiment, the evaluation server 10 detects a considerate scene based on vehicle information, and when a considerate scene is detected, gives a point addition evaluation to the driver.

[0017] Here, the considerate scene is a scene in which the driver shows consideration for others such as pedestrians and other vehicles. For example, it includes scenes such as securing a passage for pedestrians and other vehicles, and giving way to pedestrians and other vehicles.

[0018] For example, when the driver performs considerate driving, the vehicle 100 may show irregular behavior, and the evaluation server 10 detects a considerate scene using such behavior as a trigger.

[0019] Specifically, as shown in FIG. 2, when the vehicle 100 stops in front of a crosswalk without a traffic signal (step S1), taking this stop as a trigger, image analysis is performed on the image captured in front of the vehicle 100 during the period when the vehicle 100 stops (step S2). Thereby, for example, the cause of the vehicle 100 stopping can be identified. That is, by using image analysis in combination, cause identification can be performed with high precision, and it becomes possible to appropriately detect a considerate scene.

[0020] For example, as shown in FIG. 3, when it is detected as a result of image analysis that the pedestrian P1 is crossing the crosswalk, the scene where the vehicle 100 stops is detected as a considerate scene (step S3). That is, when it is determined that the cause of the vehicle 100 stopping is the result of consideration for the pedestrian P1, it is detected as a considerate scene. On the other hand, for example, when the pedestrian P1 cannot be detected as a result of image analysis, it is not detected as a considerate scene. That is, by analyzing the image at the time of stopping, when another person who is the target of consideration is detected, it is detected as a considerate scene.

[0021] In the example of FIG. 3, the pedestrian P1 is riding a bicycle and shows a scene of crossing the crosswalk from the right side to the left side. In this case, in the evaluation method according to the embodiment, in image analysis, by detecting that the pedestrian P1 has moved along the arrow shown in the figure, it is detected that the vehicle 100 has yielded the road to the pedestrian P1.

[0022] And in the evaluation method according to the embodiment, when a considerate scene is detected, points are added to the driver of the vehicle 100 (step S4). Thus, in the evaluation method according to the embodiment, considerate driving by the driver is detected and points are added to the driver.

[0023] Therefore, according to the evaluation method according to the embodiment, the driving of the driver can be appropriately evaluated, and by adding points, it is possible to contribute to improving the driver's motivation.

[0024] Next, with reference to FIG. 4, a configuration example of the in-vehicle device 50 will be described. FIG. 4 is a block diagram of the in-vehicle device 50. As shown in FIG. 4, the in-vehicle device 50 includes a communication unit 60, a camera 61, a storage unit 70, and a control unit 80.

[0025] The communication unit 60 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 60 transmits and receives information to and from the evaluation server 10 via various wireless communication networks such as 4G (Generation), 5G, LTE (Long Term Evolution), Wifi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0026] The camera 61 is an imaging device including an imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). For example, the camera 61 captures an image of the front of the vehicle 100. Note that the camera 61 may be a camera that captures an image of the surroundings of the vehicle 100, such as the rear or side of the vehicle 100.

[0027] The storage unit 70 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. In the example of FIG. 4, the storage unit 70 includes a vehicle information storage unit 71.

[0028] The vehicle information storage unit 71 stores vehicle information. Here, the vehicle information includes vehicle speed information regarding the vehicle speed of the vehicle 100, position information indicating the current location of the vehicle 100, brake information regarding the brake, and steering angle information regarding the steering angle.

[0029] Also, as described later, the vehicle information may include information regarding the analysis result of the image captured by the camera 61. For example, the vehicle information includes the inter-vehicle distance from the vehicle ahead, the lighting mode of the traffic signal located ahead, and information regarding the lane in which the vehicle is traveling. Regarding the inter-vehicle distance, for example, the value of a distance measuring sensor such as Lidar may be used.

[0030] The control unit 80 is a controller, which is realized, for example, by various programs (not shown) stored in the storage unit 70 being executed with the RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Further, the control unit 80 can be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0031] As shown in FIG. 4, the control unit 80 includes an acquisition unit 81, a processing unit 82, an extraction unit 83, and a transmission unit 84. The acquisition unit 81 acquires various vehicle information and stores it in the vehicle information storage unit 71.

[0032] For example, the acquisition unit 81 acquires speed information, steering angle information, and brake information from the speed sensor, steering angle sensor, and brake sensor (all not shown) of the vehicle 100. The acquisition unit 81 also acquires an image from the camera 61.

[0033] The processing unit 82 performs various processes on the image captured by the camera 61. For example, the processing unit 82 detects the white line (travel lane) reflected in the image, identifies the lighting state of the traffic signal reflected in the image, calculates the distance (inter-vehicle distance) to the vehicle ahead reflected in the image, and stores these processing results in the vehicle information storage unit 71.

[0034] The extraction unit 83 extracts the images in the time period requested by the evaluation server 10 from the vehicle information storage unit 71. More specifically, from the perspective of communication load, the in-vehicle device 50 transmits vehicle information other than images with a large data volume to the evaluation server 10 at a predetermined cycle, and when requested by the evaluation server 10, transmits the images to the evaluation server 10.

[0035] At this time, the extraction unit 83 is responsible for the function of extracting the transmission images for transmission to the evaluation server 10. Thereby, compared with the case of transmitting all the images captured by the camera 61 to the evaluation server 10, the communication load can be reduced.

[0036] The transmission unit 84 transmits vehicle information to the evaluation server 10. For example, the transmission unit 84 transmits vehicle speed information, brake information, steering angle information, position information, inter-vehicle distance information, information on the lighting state of signals, and information on the relative distance between the vehicle 100 and the lane to the evaluation server 10 at a predetermined cycle.

[0037] Also, the transmission unit 84 transmits the images extracted by the extraction unit 83 to the evaluation server 10 based on the request of the evaluation server 10.

[0038] Next, with reference to FIG. 5, a configuration example of the evaluation server 10 according to the embodiment will be described. FIG. 5 is a block diagram of the evaluation server 10. As shown in FIG. 5, the evaluation server 10 includes a communication unit 20, a storage unit 30, and a control unit 40.

[0039] The communication unit 20 is realized by, for example, a NIC (Network Interface Card) or the like. And the communication unit 60 performs information transmission and reception with the in-vehicle device 50 via various wireless communication networks such as 4G (Generation), 5G, LTE (Long Term Evolution), Wifi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0040] The storage unit 30 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0041] As shown in FIG. 5, the storage unit 30 includes a detection condition database 31, a vehicle information database 32, and an evaluation result database 33. The detection condition database 31 is a database that stores detection conditions for detecting a considerate scene.

[0042] Here, an example of the detection conditions will be described with reference to FIGS. 6 to 11. FIG. 6 is a diagram showing an example of the detection condition database 31. FIGS. 7 to 11 are diagrams showing an example of a considerate scene. Note that the detection conditions shown below are merely examples, and the situations and numerical values can be arbitrarily changed.

[0043] As shown in FIG. 6, the detection condition database 31 stores a detection condition table that defines the detection conditions. As shown in FIG. 6, the detection condition table stores information on items such as "scene ID", "first condition", and "second condition" in association with each other.

[0044] The "scene ID" is identification information for identifying each considerate scene. The "first condition" and the "second condition" respectively indicate conditions for detecting a considerate scene. For example, in the evaluation system 1 according to the embodiment, based on the vehicle information transmitted from the in-vehicle device 50 at a predetermined cycle, it is determined whether the first condition is satisfied. When it is determined that the first condition is satisfied, processing related to the second condition is performed.

[0045] As shown in FIG. 6, for example, the "first condition" defines "position" and "detection condition", and the "second condition" defines "target data" and "detection condition". That is, for each considerate scene, different detection conditions are defined by the "first condition" and the "second condition" according to the position of the vehicle 100.

[0046] The scene of kindness identified by the scene ID "♯1" is a scene of yielding to a pedestrian crossing a crosswalk, as described in FIGS. 2 and 3. When it is detected that the traveling speed of 0 km / h has continued for 10 seconds or more in front of a crosswalk without a traffic signal, it is determined that the first condition is satisfied. Here, the 10 seconds corresponds to an example of the threshold time.

[0047] In this case, when pedestrian is detected using the video data of ±5 seconds as the target data, it is determined that the second condition is satisfied. Also, the scene of kindness identified by the scene ID "♯2" is, for example, a scene where when vehicle 100 cannot reach a sufficient speed on a slope or the like, vehicle 100 stops or decelerates while leaning to the left, and the driver intentionally allows a following vehicle to overtake.

[0048] For example, in this case, on a one-lane road on one side, when it has continued for 10 seconds or more with a crossing of the left lane to the left lane of 5 cm and a traveling speed of 0 km / h or 20 km / h or less, it is determined that the first condition is satisfied.

[0049] Here, the left lane means the left lane based on the front of vehicle 100, and crossing the left lane means the state where vehicle 100 has crossed the left lane. Also, 5 cm to the left lane means that the distance between the right end of vehicle 100 and the left lane is 5 cm.

[0050] And in this case, when overtaking by a following vehicle is detected using the video data of ±5 seconds as the target data, it is determined that the second condition is satisfied. More specifically, as shown in FIG. 7, when the video data is analyzed and it is detected that the following vehicle C1 has moved from the lower right of the frame to the center of the frame over time, and it is detected that the distance between the following vehicle C1 reflected in front of vehicle 100 and vehicle 100 is gradually increasing, it is determined that the second condition is satisfied.

[0051] Also, at this time, a logic may be incorporated to determine that the second condition is satisfied when the following vehicle C1 does not protrude into the passing lane or when the following vehicle C1 is not an emergency vehicle (police car, ambulance, fire truck, etc.). Note that whether the vehicle protrudes into the passing lane or whether it is an emergency vehicle can be determined by image analysis.

[0052] Returning to the description of FIG. 6, the considerate scene identified by the scene ID “#3” is a scene where a pedestrian (including a bicycle) exists on the right side of the vehicle 100, and the passage of the pedestrian is secured, that is, the distance from the pedestrian is secured.

[0053] For example, in this case, for all roads, when the vehicle 100 is in a state of straddling the right lane to 5 cm in the right lane and the traveling speed is 20 km / h or less for 10 seconds or more, it is determined that the first condition is satisfied.

[0054] And in this case, when lateral pedestrians existing on the side of the road are detected for the video data of ±5 seconds, it is determined that the second condition is satisfied. More specifically, as shown in FIG. 8, for example, it is assumed that when the vehicle 100 is traveling on a road without a sidewalk, a lateral pedestrian P2 riding a bicycle exists on the side of the road.

[0055] In this case, the video data is analyzed, and when the lateral pedestrian P2 transitions from the center of the frame to the lower left of the frame and exits the frame, it is determined that the second condition is satisfied. That is, in this case, when the vehicle 100 takes a driving trajectory that bulges to the right, that is, when it meanders to the right side of the traveling direction, it is detected by image analysis that the cause of the traveling is the lateral pedestrian P2. Note that the lateral pedestrian P2 is not limited to a bicycle, and may be a pedestrian or a moped, etc.

[0056] Returning to the description of FIG. 6, the considerate scene identified by the scene ID “#4” is a scene where, when the driver of the preceding vehicle is a beginner or an elderly person, a sufficient inter-vehicle distance is secured in consideration of the beginner or the elderly person.

[0057] For example, in this case, when the inter-vehicle distance between the vehicle 100 and the preceding vehicle is equal to or greater than the inter-vehicle distance threshold value, it is determined that the first condition is satisfied. Here, the inter-vehicle distance threshold value is a distance that is wider than the generally recommended recommended inter-vehicle distance from the vehicle ahead, and is a distance that shows consideration by the driver for the driver of the vehicle ahead.

[0058] In this case, when a sign (mark) attached to the vehicle ahead is detected for the video data of the current period, it is determined that the second condition is satisfied. More specifically, as shown in FIG. 9, when analyzing the video data and detecting the novice mark M attached to the vehicle ahead, it is determined that the second condition is satisfied. Note that the sign is not limited to the novice mark M, and may be a senior mark, a hearing-impaired mark, a physically disabled mark, or a provisional license practice plate.

[0059] Returning to the description of FIG. 6, the considerate scene identified by the scene ID “♯5” is a scene where the vehicle yields the road to an oncoming vehicle on a narrow road. For example, in this case, the width of the parking position of the vehicle 100 > A, and the width after the vehicle 100 starts moving < B. Here, for example, the width of the parking position is a value that allows the oncoming vehicle to pass by the side of the vehicle 100, and the width after the vehicle 100 starts moving is a value that does not allow the oncoming vehicle to pass by the side of the vehicle 100.

[0060] In this case, when the traveling speed of 0 km / h continues for 10 seconds or more, it is determined that the first condition is satisfied. That is, the first condition in this case indicates that the vehicle 100 is stopped at a position where the vehicle 100 and the oncoming vehicle can pass by each other.

[0061] And in this case, when the passing of the oncoming vehicle is detected for the video data of ±5 seconds, it is determined that the second condition is satisfied. Specifically, as shown in FIG. 10, when analyzing the video data and determining that the oncoming vehicle C3 transitions from the center of the frame to the lower right and exits the frame, it is determined that the second condition is satisfied.

[0062] Returning to the description of FIG. 6, the scene of consideration identified by the scene ID “#6” is, for example, a scene in which when another vehicle exits from a vehicle entrance located in front of the vehicle 100, the vehicle 100 yields the way to the other vehicle. That is, it is a scene in which when another vehicle exiting from the vehicle entrance crosses in front of the vehicle 100, or when another vehicle merges in front of the vehicle 100, the vehicle 100 yields the way to the other vehicle. Note that the vehicle entrance is, for example, a parking lot of a facility or the like, but may be, for example, an intersection where no traffic signal is installed.

[0063] For example, in this case, when there is no intersection within 30 m in front of the vehicle 100 and the traveling speed of 0 km / h continues for 10 seconds or more, it is determined that the first condition is satisfied. Also, in this case, when other vehicles entering the vehicle entrance and other vehicles exiting the vehicle entrance are detected for the video data of ±5 seconds, it is determined that the second condition is satisfied.

[0064] More specifically, as shown in FIG. 11, for example, when analyzing the image data and detecting another vehicle C4 that transitions from the left side to the center of the frame, it is determined that the second condition is satisfied. Also, at this time, when detecting another vehicle that transitions from the center to the left of the frame, another vehicle entering the vehicle entrance from the oncoming lane may be detected and it may be determined that the second condition is satisfied.

[0065] Returning to the description of FIG. 6, the scene of consideration identified by the scene ID “#7” is a scene in which the vehicle 100 is traveling on a local road at a traveling speed of 20 km / h or less, that is, a scene in which the vehicle is traveling slowly on the local road. Here, a case where the local road is defined as having a width of 3 m or more and 5.5 m or less is shown.

[0066] The scene of consideration identified by the scene ID “#8” is a scene in which when traveling in front of a traffic signal, the stop start time is a yellow signal. That is, in this case, it is a scene in which the driver predicts that the lighting state of the traffic signal changes from blue to red, and when the traffic signal turns yellow, immediately applies the brakes.

[0067] For example, in the considerate scenes with scene IDs "♯7" and "♯8", it can be detected based on the vehicle information transmitted from the in-vehicle device 50, and the processing related to the second condition can be omitted. That is, in the considerate scenes with scene IDs "♯7" and "♯8", it is a process where confirmation of others is not required by image analysis. In this case, for example, regardless of the presence of others, it is detected as a considerate scene.

[0068] Returning to the description of FIG. 5, the vehicle information database 32 will be described. The vehicle information database 32 is a database that stores the vehicle information transmitted from each in-vehicle device 50. The evaluation result database 33 is a database that stores the evaluation results of each driver.

[0069] The control unit 40 is a controller, which is realized, for example, by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc., when various programs (not shown) stored in the storage unit 30 are executed with the RAM as the working area. Also, the control unit 40 can be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0070] As shown in FIG. 5, the control unit 40 includes an acquisition unit 41, a first detection unit 42, a second detection unit 43, and an evaluation unit 44. The acquisition unit 41 acquires driving information regarding the driving state of each vehicle 100 from each in-vehicle device 50 and stores it in the vehicle information database 32.

[0071] The acquisition unit 41 acquires vehicle speed information, brake information, steering angle information, position information, inter-vehicle distance information, information regarding the lighting state of traffic lights, and information regarding the relative distance between the vehicle 100 and the lane as driving information from each in-vehicle device 50 at a predetermined cycle.

[0072] The first detection unit 42 detects vehicle information that satisfies a first condition preset for each consideration scene among the vehicle information acquired from each in-vehicle device 50. For example, first, the first detection unit 42 collates the position set for each consideration scene (see FIG. 6) with the position information of the vehicle 100, and detects vehicle information that satisfies the detection condition corresponding to the position.

[0073] For example, in the scene identified by ♯1 shown in FIG. 6, vehicle information that satisfies the first condition is detected for vehicle information in which the vehicle 100 stops in front of a crosswalk without a traffic signal for 10 seconds or more.

[0074] For example, when the first detection unit 42 detects vehicle information that satisfies the first condition, it requests the in-vehicle device 50, which is the transmission source of the vehicle information, to transmit target data. As a result, video data for detecting the second condition is transmitted from the in-vehicle device 50 to the evaluation server 10.

[0075] Here, for example, when the first detection unit 42 detects a sudden deceleration of the vehicle 100 based on the vehicle information, the vehicle information for a predetermined period from the sudden deceleration is excluded from the detection target of the first condition. That is, for example, when the vehicle 100 stops in front of a crosswalk due to sudden braking, stops or travels slowly to give way to other vehicles, or stops due to sudden braking, it is excluded from the detection target of the consideration scene.

[0076] This is because when the driver performs sudden braking, it is assumed that the action is taken to avoid a collision with others, and it is assumed that the intention is different from considerate driving. That is, by excluding the vehicle information after sudden deceleration from the detection target of the consideration scene, the detection accuracy of the consideration scene can be improved.

[0077] Note that, for example, the function of the first detection unit 42 may be provided in the in-vehicle device 50. That is, the processing related to the first condition may be executed on the in-vehicle device 50 side, and only the processing related to the second condition may be executed on the evaluation server 10 side.

[0078] When the vehicle information satisfying the first condition is detected by the first detection unit 42, the second detection unit 43 analyzes an image obtained by photographing the front of the vehicle 100 that is the transmission source of the vehicle information, and detects a considerate scene.

[0079] Specifically, based on the detection result of the first condition, the second detection unit 43 acquires the video data transmitted from the in-vehicle device 50 and analyzes the video data. For example, when the second detection unit 43 detects a considerate scene, it passes the detection result to the evaluation unit 44. Note that various methods such as deep learning can be used for the analysis of video data.

[0080] When the behavior of others matches the second condition as a result of analyzing the video data, the second detection unit 43 detects it as a considerate scene. As an example, in the scene identified by ♯1 shown in FIG. 6, when it is found that the reason the vehicle 100 stopped in front of the crosswalk is to wait for a pedestrian to cross as a result of analyzing the video data, it is detected as a considerate scene.

[0081] That is, the first detection unit 42 determines whether the vehicle information transmitted from each in-vehicle device 50 satisfies the first condition set for each considerate scene, and the second detection unit 43 further analyzes the image for the vehicle information determined to satisfy the first condition to determine whether it satisfies the second condition.

[0082] Then, both the first detection unit 42 and the second detection unit 43 detect an event determined to satisfy the first condition and the second condition as a considerate scene. Note that, for example, for an event that satisfies the first condition, such as the scene IDs “♯7” and “♯8” shown in FIG. 6, it may be detected as a considerate scene without going through the process related to the second condition.

[0083] The evaluation unit 44 evaluates the driving of each driver based on the vehicle information transmitted from each in-vehicle device 50. At this time, for a driver in whom a considerate scene is detected, the evaluation unit 44 performs an evaluation (for example, gives points) so that the evaluation result becomes advantageous.

[0084] Examples of items evaluated by the evaluation unit 44 include speeding, non-stop for a moment, parking violation, signal violation, eco-driving, sudden acceleration, sudden deceleration, and dangerous inter-vehicle distance. In addition, the evaluation unit 44 stores the evaluation result in the evaluation result database 33.

[0085] In addition, the evaluation unit 44 notifies the driver of the evaluation result. FIG. 12 is a diagram showing an example of the evaluation result. In the example shown in FIG. 12, the case where the evaluation result is displayed as a radar chart is shown. For example, in the radar chart, the evaluation results of each evaluation item are displayed as scores.

[0086] In the example shown in the figure, the evaluation items are "compliance with laws and regulations", "sudden acceleration", "eco-driving", "inter-vehicle distance", and "consideration". For example, each time a considerate scene is detected, points are added to the evaluation item of "consideration". Note that points may be added to other evaluation items each time a considerate scene is detected.

[0087] Also, as shown in the figure, the comprehensive evaluation, the department average, and the company-wide average are displayed together. Note that the department average is the average of the comprehensive evaluations in the department to which the driver belongs, and the company-wide average is the average of the comprehensive evaluations in the entire company to which the driver belongs.

[0088] Next, with reference to FIG. 13, the processing procedure executed by the evaluation server 10 according to the embodiment will be described. FIG. 13 is a flowchart showing the processing procedure executed by the evaluation server 10. Note that the following processing procedure is repeatedly executed by the control unit 40 of the evaluation server 10 every time vehicle information is acquired.

[0089] As shown in FIG. 13, when the evaluation server 10 acquires vehicle information from the in-vehicle device 50 (step S101), it determines whether or not the first condition is satisfied based on the vehicle information (step S102).

[0090] When the evaluation server 10 determines that the first condition is satisfied (step S102; Yes), it proceeds to the process of step S103. When it determines that the first condition is not satisfied (step S102; No), the process ends.

[0091] Subsequently, the evaluation server 10 determines whether or not image analysis is necessary for determining the second condition corresponding to the first condition (step S103). When the evaluation server 10 determines that image analysis is necessary for determining the second condition (step S103; Yes), it proceeds to the process of step S104. When it determines that image analysis is not necessary for determining the second condition (step S103; No), it proceeds to the process of step S107.

[0092] Subsequently, the evaluation server 10 acquires an image (video data) from the in-vehicle device 50 (step S104) and analyzes the acquired image (step S105). Subsequently, the evaluation server 10 determines whether or not the second condition is satisfied based on the result of the image analysis (step S106).

[0093] That is, in step S106, the evaluation server 10 determines whether or not the detection condition of the considerate scene is satisfied. When the evaluation server 10 determines that the second condition is satisfied (step S106; Yes), it gives a point evaluation to the driver (step S107) and ends the process. Also, when the evaluation server 10 determines that the second condition is not satisfied (step S106; No), it omits the process of step S107 and ends the process.

[0094] As described above, the evaluation server 10 (an example of an evaluation device) according to the embodiment includes a control unit 40 and is an evaluation device that evaluates the driving of a driver of a vehicle. The control unit 40 acquires vehicle information regarding the driving state of the vehicle 100, detects a considerate scene performed by the driver based on the acquired vehicle information, and when a considerate scene is detected, performs an evaluation that is advantageous to the driver with respect to the driving evaluation of the driver. Therefore, according to the evaluation device according to the embodiment, the driving of the driver can be appropriately evaluated.

[0095] Incidentally, in the above-described embodiment, the case where image analysis is used in combination to detect a considerate scene has been described, but the present invention is not limited to this. For example, based on the vehicle information of other vehicles considered by the vehicle 100, after specifying the behavior of other vehicles, a considerate scene may be detected.

[0096] Further, in the above-described embodiment, the case where the evaluation device is the evaluation server 10 has been described, but the present invention is not limited to this. The evaluation device may be an in-vehicle device 50.

[0097] Further, in the above-described embodiment, the case where points are added as an evaluation that is advantageous to the driver has been described, but the present invention is not limited to this as long as the evaluation contributes to improving the driver's motivation.

[0098] Further effects and modifications can be easily derived by those skilled in the art. Therefore, a broader aspect of the present invention is not limited to the specific details and representative embodiments described and represented as above. Accordingly, various changes can be made without departing from the spirit or scope of the general inventive concept defined by the appended claims and their equivalents.

Explanation of Reference Numerals

[0099] 1 Evaluation system 10 Evaluation server 20 Communication unit 30 Storage unit 31 Detection condition database 32 Vehicle information database 33 Evaluation result database 40 Control unit 41 Acquisition unit 42 First detection unit 43 Second detection unit 44 Evaluation unit 50 In-vehicle device 60 Communication unit 61 Camera 70 Memory unit 71 Vehicle information memory unit 80 Control unit 81 Acquisition unit 82 Processing unit 83 Extraction unit 84 Transmission unit 100 Vehicle

Claims

1. An evaluation device having a control unit for performing a driving evaluation of a driver, wherein the control unit, acquires vehicle information regarding a driving state of a vehicle, and when it is determined from the acquired vehicle information that a period during which the vehicle has stopped in front of a crosswalk is equal to or longer than a preset threshold value, and a pedestrian crossing the crosswalk is detected from an image taken of the front of the vehicle, performs a point-adding evaluation on the driver. Evaluation device.

2. An evaluation program for performing a driving evaluation of a driver, which acquires vehicle information regarding a driving state of a vehicle, and when it is determined from the acquired vehicle information that a period during which the vehicle has stopped in front of a crosswalk is equal to or longer than a preset threshold value, and a pedestrian crossing the crosswalk is detected from an image taken of the front of the vehicle, performs a point-adding evaluation on the driver. An evaluation program for causing a computer to execute the process.

Images