Processing device, program, recording medium, and processing method

Abstract

To determine weakening of a cognitive function of a driver on the basis of time from appearance of an object to detection of a danger avoidance motion to the object by the driver.SOLUTION: A processing device comprises: an image acquisition unit 10 which acquires a peripheral image of a vehicle; a detection unit 20 which detects appearance of an object from the acquired peripheral image; a detection unit 30 which detects a danger avoidance motion to the object by the driver of the vehicle; a measurement unit 40 which measures time from the appearance of the object detected by the detection unit 20 to detection of the danger avoidance motion to the object performed by the driver detected by the detection unit 30; and a determination unit 50 which determines weakening of a cognitive function of the driver from a measurement result of the measurement unit 40 and a predetermined threshold.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a processing device, a program, a recording medium, and a processing method. [Background technology]

[0002] In recent years, there has been an increase in accidents that are believed to be caused by the decline in cognitive ability of drivers of automobiles and other vehicles, and this has become a social problem. For this reason, driving aptitude tests that use cognitive function as an index are being implemented, particularly for elderly drivers, when they renew their driver's licenses.

[0003] However, in driving aptitude tests that use cognitive function as an index, the test intervals are long and it is not possible to properly grasp the current cognitive function. Therefore, in order to determine whether a driver can drive from the perspective of dementia risk based on daily vehicle driving, a technology has been disclosed that determines the vehicle driving situation based on road information and vehicle driving information, and determines whether the driving situation corresponds to a predetermined traffic violation that is likely to be committed when cognitive function is reduced, and if the driving situation corresponds to a predetermined traffic violation, determines whether the driver is at risk of dementia based on the vehicle driver's information and violation history, and if it is determined that the driver is at risk of dementia, outputs the information (for example, see Patent Document 1).

[0004] In addition, a technology has been disclosed that aims to more appropriately support safe driving by acquiring vehicle information indicating the vehicle's condition, environmental information indicating the vehicle's traffic environment, and biometric information of the driver driving the vehicle, determining whether the vehicle is in a dangerous state using the vehicle information and environmental information, estimating the driver's cognitive state using the vehicle information and biometric information, and controlling one or more devices installed in the vehicle based on the determination result of the dangerous state and the estimation result of the cognitive state to provide the driver with stimuli to support safe driving (see, for example, Patent Document 2). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2019-124975 A [Patent Document 2] JP 2019-200544 A Summary of the Invention [Problem to be solved by the invention]

[0006] The technology described in Patent Document 1 determines whether a driver's driving conditions correspond to specific traffic violations that are likely to be committed when cognitive function is impaired, and if so, determines whether the driver is at risk of dementia based on the vehicle driver's information and violation history. In other words, with the technology described in Patent Document 1, if a driver's driving conditions do not fall under certain traffic violations that are likely to be committed when cognitive function is impaired, the driver's dementia risk is not assessed. However, for example, when a driver's cognitive function has significantly declined, even if the driver's driving behavior does not fall under the specific traffic violations that are likely to be committed when the driver's cognitive function is impaired, there is a very high possibility that the driver will cause an accident, and no measures are taken to address this issue.

[0007] The technology described in Patent Document 2 describes estimating the driver's cognitive state using vehicle information and biometric information, but does not provide a specific method for estimating the driver's cognitive state, and since there is a lot described regarding cognitive recovery, the estimating of the driver's cognitive state in the technology described in Patent Document 2 refers to estimating the cognitive state of a driver who has sufficient cognitive ability under normal circumstances but whose cognitive ability temporarily declines due to drowsiness, fatigue, or decreased attention, and does not grasp the cognitive ability of a driver whose cognitive ability is declining under normal circumstances.

[0008] Therefore, the techniques of Patent Document 1 and Patent Document 2 have a problem in that they are unable to appropriately determine the decline in the driver's cognitive function. The above-mentioned problem is one example of the problem that the present invention is intended to solve.

[0009] The present invention has been made in consideration of the problems cited as examples above, and its main objective is to provide a processing device, program, recording medium, and processing method for determining the decline in a driver's cognitive function based on the time between the appearance of an object and the detection of the driver's danger avoidance action toward the object. [Means for solving the problem]

[0010] The invention described in claim 1 includes an image acquisition unit that acquires an image of the surroundings of a vehicle, and a detection unit that detects the appearance of an object from the acquired surrounding image. No. 1 a detection unit that detects a danger avoidance action of a driver of the vehicle with respect to the object; No. 1 A measurement unit that measures a time from appearance of the object by a detection unit to detection of a danger avoidance action of the driver with respect to the object by the detection unit; A second detection unit that detects the line of sight of the driver, and when it is determined that the line of sight of the driver is capturing the object, The processing device is characterized by comprising a judgment unit that judges the decline in the driver's cognitive function based on the measurement results of the measurement unit and a predetermined threshold value.

[0011] The invention described in claim 9 includes an image acquisition unit, No. 1 A detection unit, a detection unit, and a measurement unit, A second detection unit; a determination unit; and a processing method for a processing device including the image acquisition unit, the image acquisition unit acquiring an image of a surrounding area of ​​a vehicle; No. 1 a second step of detecting an appearance of an object from the acquired peripheral image by a detection unit; and a third step of detecting a danger avoidance action of a driver of the vehicle with respect to the object by the detection unit. A fourth step in which the second detection unit detects the driver's line of sight; The measuring unit No. 1 measuring a time from appearance of the object by a detection unit to detection of a danger avoidance action of the driver with respect to the object by the detection unit; 5 The step of the determination unit When it is determined that the driver's line of sight is capturing the object, A method for determining a decline in the cognitive function of the driver based on a measurement result of the measurement unit and a predetermined threshold value. 6 The present invention is characterized in that it is a program for causing a computer to execute the steps of:

[0012] The invention described in claim 11 includes an image acquisition unit, No. 1 A detection unit, a detection unit, and a measurement unit, A second detection unit; A processing method for a processing device including a determination unit, the processing method comprising: a first step in which the image acquisition unit acquires an image of a surrounding area of ​​a vehicle; No. 1 a second step of detecting an appearance of an object from the acquired peripheral image by a detection unit; and a third step of detecting a danger avoidance action of a driver of the vehicle with respect to the object by the detection unit. A fourth step in which the second detection unit detects the driver's line of sight; The measuring unit No. 1 measuring a time from appearance of the object by a detection unit to detection of a danger avoidance action of the driver with respect to the object by the detection unit; 5 The step of the determination unit When it is determined that the driver's line of sight is capturing the object, A method for determining a decline in the cognitive function of the driver based on a measurement result of the measurement unit and a predetermined threshold value. 6 The present invention is characterized in that the method comprises the steps of: [Brief description of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram illustrating a configuration of a processing device according to a first embodiment of the present invention. [Diagram 2] FIG. 4 is a diagram illustrating a determination threshold value stored in a storage unit of the processing device according to the first embodiment of the present invention. [Diagram 3] 2 is a diagram illustrating an example of a database stored in a storage unit of the processing device according to the first embodiment of the present invention. FIG. [Figure 4] FIG. 2 is a process flow diagram of the processing device according to the first embodiment of the present invention. [Diagram 5] FIG. 11 is a diagram illustrating a configuration of a processing device according to a second embodiment of the present invention. [Figure 6] FIG. 11 is a diagram illustrating a database stored in a storage unit of a processing device according to a second embodiment of the present invention. [Figure 7] FIG. 11 is a process flow diagram of an estimation unit in the processing device according to the second embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] <Embodiment> The processing device according to this embodiment includes an image acquisition unit, a sensing unit, a detection unit, a measurement unit, and a determination unit.

[0015] The image acquisition unit acquires images of the surroundings of the vehicle from an imaging device disposed inside the vehicle, for example. Here, the imaging device may be a video camera that captures images of the surroundings in front of the vehicle (in the driving direction), or may be individual video cameras that capture images of the surroundings in front of the vehicle, behind the vehicle, and to the left and right of the vehicle. Alternatively, the imaging device may be a 360-degree camera disposed in the center of the vehicle.

[0016] The detection unit detects the appearance of an object from the image of the surroundings of the vehicle acquired by the image acquisition unit. Here, the object may be, for example, a dynamic object such as another vehicle, a person, or an animal, or a static object such as an obstacle such as a guardrail, a road sign, or an exterior wall.

[0017] The detection unit detects a danger avoidance action of the driver of the vehicle with respect to an object. Here, examples of the danger avoidance action include sudden braking, sudden steering, etc. The detection unit detects the danger avoidance action of the driver, for example, by a signal from the ECU of the vehicle.

[0018] The measurement unit measures the time from when the object appears to the detection unit to when the detection unit detects the driver's danger avoidance action toward the object. The measurement unit is, for example, configured with a timer, and the measurement result is output to the determination unit described later.

[0019] The determination unit determines the decline of the driver's cognitive function based on the measurement result of the measurement unit and a predetermined threshold. Here, the predetermined threshold can be, for example, a statistical reaction time. The statistical reaction time can be, for example, a reaction time for each cognitive function level obtained by statistically analyzing the time required from the appearance of an object to the driver's danger avoidance action for the object, for a person whose cognitive function level is already known.

[0020] As described above, the detection unit of the processing device according to this embodiment detects the appearance of objects, for example, dynamic objects such as other vehicles, people, and animals, and static objects such as obstacles such as guardrails, road signs, and exterior walls, from the images of the surroundings of the vehicle acquired by the image acquisition unit. Therefore, the measurement unit can measure the time from the appearance of any object that may be expected during normal vehicle driving to the detection of the driver's danger avoidance action against the object.

[0021] In addition, the determination unit of the processing device according to this embodiment determines the decline in the driver's cognitive function from the measurement results of the measurement unit and the reaction time for each cognitive function level obtained by statistically analyzing the time taken by a person with a known cognitive function level from the appearance of an object to the driver's risk avoidance action for the object as a predetermined threshold. Therefore, it is possible to accurately determine the driver's current cognitive function level with respect to the appearance of any object that may be expected during normal driving of the vehicle.

[0022] <Example 1> The first embodiment will be described with reference to FIGS. 1 to 4. FIG.

[0023] <Configuration of Processing Device 1> As shown in FIG. 1, the processing device 1 of this embodiment is configured to include an image acquisition unit 10, a detection unit 20, a detection unit 30, a measurement unit 40, a judgment unit 50, an acquisition unit 60, and a memory unit 70.

[0024] The image acquisition unit 10 is provided, for example, in the vehicle cabin, and acquires images of the surroundings of the vehicle from an imaging device that captures images in directions including the running direction of the vehicle and the left and right directions. Examples of the imaging device include a video camera and a drive recorder, and examples of the imaging device include at least a device that captures images while the vehicle is traveling.

[0025] The detection unit 20 detects the appearance of an object from the image of the surroundings of the vehicle acquired by the image acquisition unit 10. Specifically, for example, the detection unit 20 performs image analysis on the image of the surroundings of the vehicle acquired by the image acquisition unit 10 to detect an object appearing from outside the region of the imaging angle of view. Regardless of the type of object, the detection unit 20 outputs the appearance timing of the object to the measurement unit 40 described later. Here, an object is not limited to dynamic objects such as other vehicles, people, and animals, but also static objects such as obstacles such as guardrails, road signs, and exterior walls, and is an object that may affect vehicle travel.

[0026] The detection unit 30 detects a danger avoidance action of the vehicle driver with respect to an object. The danger avoidance action is a danger avoidance behavior that occurs upon detecting the appearance of an object, and examples of this include sudden braking and sudden steering. The detection unit 30 detects the driver's danger avoidance action, for example, by a signal from the vehicle's ECU. More specifically, for example, the detection unit 30 detects the driver's danger avoidance action against an object when, for example, a sudden acceleration or deceleration is detected in a short time by a signal from the vehicle's ECU that monitors a sensor output signal from an acceleration sensor mounted on the vehicle, or a sudden change in steering angle is detected in a short time by a signal from the vehicle's ECU that monitors a sensor output signal from a steering angle sensor mounted near the steering wheel of the vehicle. The detection signal from the detection unit 30 is output to a measurement unit 40, which will be described later.

[0027] The measurement unit 40 measures the time from when the detection unit 20 detects the appearance of an object to when the detection unit 30 detects the driver's danger avoidance action toward the object. Specifically, the measurement unit 40 is configured with, for example, a timer or the like, and starts the timer upon input of a detection signal from the detection unit 20, and measures the time until the detection signal from the detection unit 30 is input. The measurement result of the measuring unit 40 is output to the determining unit 50, which will be described later.

[0028] The judgment unit 50 judges the deterioration of the driver's cognitive function based on the measurement result of the measurement unit 40 and a predetermined threshold. Here, the predetermined threshold can be, for example, a statistical reaction time. The statistical reaction time can be, for example, a reaction time for each cognitive function level obtained by statistically analyzing the time taken by a person whose cognitive function level is known in advance from the appearance of an object to the driver's danger avoidance action against the object. According to research results, reaction times are roughly divided into startle reaction times for unexpected events and predicted reaction times for events that can be predicted empirically in advance, and the statistical reaction times for these are "startle reaction times" of 1.5 seconds and "predicted reaction times" of 0.75 seconds. Therefore, the judgment unit 50 in this embodiment judges the judgment result in three levels, S level, A level, and B level, based on these indices, as shown in Fig. 2. On the other hand, since reaction time is also affected by risk factors described below, a weight may be set for each risk factor, which may then be quantified using a formula, and the judgment level of the person being judged may be calculated from the reaction times of other drivers under the same conditions. As for the weights, a huge amount of data as shown in FIG. 3 may be collected, the effect of each risk factor on the reaction time may be analyzed, and a weight for each risk factor may be derived. The determination result of the determination unit 50 is stored in the storage unit 70, which will be described later, together with the measurement result of the measurement unit 40.

[0029] The acquisition unit 60 acquires risk factors in vehicle driving obtained from an external device. Here, examples of risk factors during vehicle driving include vehicle body information, the conditions of other vehicles around the vehicle, the weather when the vehicle is driving, the time the vehicle is driving, attribute information, etc.

[0030] The storage unit 70 stores the risk factors detected by the acquisition unit 60 and the judgment result by the judgment unit 50 in association with each other. Specifically, as shown in Fig. 3, for example, the judgment date and time, vehicle width margin information as vehicle body information, vehicle travel volume as the status of other vehicles around the vehicle, weather information when the vehicle is traveling, and traveling time zone information as the vehicle travel time are stored in association with the precedent level. Here, the "vehicle width margin" refers to the margin of vehicle width with respect to the road width, and is a scale indicated by three levels, for example, "wide", "medium", and "narrow". In addition to the above information, driver attribute information such as gender, age, place of residence, etc. may be added.

[0031] <Processing of Processing Device 1> The processing of the processing device 1 according to the present embodiment will be described with reference to FIGS.

[0032] 4, the image acquisition unit 10 acquires an image of the surroundings of the vehicle (step S110). The image of the surroundings of the vehicle acquired by the image acquisition unit 10 is output to the detection unit 20.

[0033] The detection unit 20 detects the appearance of an object from the peripheral image acquired by the image acquisition unit 10. For example, the detection unit 20 detects a pedestrian jumping out from the right front of the vehicle by image analysis (step S120). The detection information of the detection unit 20, specifically, the appearance timing of the pedestrian, is output to the measurement unit 40.

[0034] The detection unit 30 detects a danger avoidance action of the vehicle driver against an object. Specifically, the timing of abrupt steering operation as a danger avoidance action of the driver against a pedestrian jumping out as an object is detected (step S130). The detection information of the detection unit 30, specifically, the timing of the abrupt steering operation, is output to the measurement unit 40.

[0035] The measurement unit 40 measures the time from the appearance of the object by the detection unit 20 to the detection of the driver's risk avoidance operation for the object by the detection unit 30 (step S140). The measurement result of the measurement unit 40 is output to the determination unit 50.

[0036] The determination unit 50 determines the decline of the driver's cognitive function from the measurement result of the measurement unit 40 and a predetermined threshold value (step S150). Specifically, the determination unit 50 applies the measurement result of the measurement unit 40 to, for example, the chart shown in FIG. 2 to determine the cognitive function level. That is, when the measurement result t of the measurement unit 40 is "t ≤ 0.75 seconds", the cognitive function level is determined as "S", and when "0.75 seconds < t ≤ 1.5 seconds", the cognitive function level is determined as "A", and when "t > 1.5 seconds", the cognitive function level is determined as "B", and a series of processes are terminated.

[0037] Note that the determination result of the determination unit 50 is stored in the storage unit 70 in the form of a database as shown in FIG. 3 together with the risk factors at the time of determination acquired by the acquisition unit 60 from an external device.

[0038] <Function and Effect> As described above, in the processing device 1 according to the present embodiment, the detection unit 20 detects the appearance of an object from the surrounding image of the vehicle acquired by the image acquisition unit 10, and the detection unit 30 detects the driver's risk avoidance operation for the object. Then, the measurement unit 40 measures the time from the appearance of the object by the detection unit 20 to the detection of the driver's risk avoidance operation for the object by the detection unit 30, and the determination unit 50 determines the decline of the driver's cognitive function from the measurement result of the measurement unit 40 and a predetermined threshold value. That is, the detection unit 20 detects the appearance of an object, for example, a dynamic object such as another vehicle, a person, or an animal, or a static object such as an obstacle such as a guardrail, a road sign, or an outer wall, from the surrounding image of the vehicle acquired by the image acquisition unit 10. Therefore, the measurement unit 40 can measure the time from the appearance of any object that can be assumed during normal driving of the vehicle to the detection of the driver's risk avoidance operation for the object. In addition, the judgment unit 50 evaluates the measurement results of the measurement unit 40 and the time taken by a person with a known cognitive function level from the appearance of an object to the driver taking a danger avoidance action against the object based on a predetermined threshold, and judges the decline in the driver's cognitive function. Therefore, it is possible to accurately determine the driver's current cognitive function level with respect to the appearance of any object that may be expected during normal vehicle driving.

[0039] In addition, in the processing device 1 according to this embodiment, the judgment unit 50 judges the deterioration of the driver's cognitive function based on the measurement result of the measurement unit 40 and the statistical reaction time. Here, statistical reaction times are reaction times obtained based on academic research. Therefore, the judgment unit 50 judges the decline in the driver's cognitive function based on the reaction time for each cognitive function level obtained through statistical and academic analysis, and can therefore make a qualitative and accurate judgment of the driver's current cognitive function level in response to the appearance of any object that may be expected during normal driving of the vehicle.

[0040] In addition, the processing device 1 of this embodiment further includes an acquisition unit 60 that acquires risk factors in vehicle driving, and a memory unit 70 that links and stores the risk factors detected by the acquisition unit 60 and the judgment result by the judgment unit 50. Specifically, the memory unit 70 stores, for example, the judgment date and time, vehicle width margin information as vehicle body information, vehicle travel distance as the status of other vehicles around the vehicle, weather information when the vehicle is traveling, and traveling time zone information as the time the vehicle is traveling, in association with the precedent level, which is the judgment result of the judgment unit 50. In other words, by analyzing the above database stored in memory unit 70, it is possible to understand what risk factors affect the decline in the driver's cognitive function and to what extent, and by reflecting this information in a predetermined threshold value, it is possible to more accurately determine the degree of decline in the driver's cognitive function.

[0041] In addition, since the data with the determination date and time is stored in the storage unit 70 in a database format, multiple pieces of data relating to the same driver that differ only in the determination date and time are also stored. Therefore, by examining the progress of the judgment results for the same driver under the same conditions, it is possible to accurately grasp the degree of decline in the cognitive function level of that driver, etc.

[0042] <Example 2> The second embodiment will be described with reference to FIGS.

[0043] <Configuration of Processing Device 1A> As shown in FIG. 5, the processing device 1A of this embodiment is configured to include an image acquisition unit 10, a detection unit 20, a detection unit 30, a measurement unit 40, a judgment unit 50, an acquisition unit 60, a memory unit 70, and an estimation unit 80. Note that components having the same reference numerals as those in the first embodiment have similar functions, and therefore detailed descriptions thereof will be omitted.

[0044] When there is a risk factor among the risk factors for which a judgment result has not been obtained by the judgment unit 50, the estimation unit 80 estimates the judgment result by the judgment unit 50 for the risk factor for which a judgment result has not been obtained by the judgment unit 50, based on the judgment result by the judgment unit 50 of another person that has already been judged for this risk factor.

[0045] Specifically, when a database such as that shown in FIG. 6 is stored in the memory unit 70, for the following four items for which the judgment date and time is not indicated for driver D2, the estimation unit 80 estimates the judgment results by the judgment unit 50 for the following four items for driver D2 for which no judgment results have been obtained by the judgment unit 50, based on the judgment results by the judgment unit 50 for driver D1 as another person who has been judged for the following four items:

[0046] <Processing of Processing Device 1A> The processing of the processing device 1A according to this embodiment will be described with reference to FIGS.

[0047] As shown in FIG. 7, the estimation unit 80 searches the data in the database stored in the storage unit 70 for data of other drivers having similar data to the driver whose judgment result is to be estimated (step S210). To explain using Figure 6, if we assume that the driver whose judgment result is to be estimated is "driver D2," the judgment result for "driver D2" is "S" for the conditions of "vehicle width margin; medium," "mileage; normal," "weather; sunny," and "time of day," while the judgment level is "S" for the conditions of "vehicle width margin; medium," "mileage; low," "weather; sunny," and "time of day," the data for "driver D1" is searched for as similar data, as data for a driver with a similar judgment level under the same conditions.

[0048] Next, the estimation unit 80 judges the similarity between the data of "driver D2" and the data of "driver D1" (step S220). Here, it is judged whether the similarity is equal to or greater than a predetermined value. Note that the predetermined value may be arbitrarily determined depending on various conditions such as the accuracy for the judgment level.

[0049] If the estimation unit 80 determines that the similarity is lower than the predetermined value ("NO" in step S220), the process returns to step S220, and the next similar data is searched for.

[0050] On the other hand, if the estimation unit 80 determines that the similarity is equal to or greater than the predetermined value ("YES" in step S220), the searched data is stored in the storage unit 70 as temporary data (step S230), and the process proceeds to step S240.

[0051] The estimation unit 80 determines whether or not the temporary data stored in the storage unit 70 includes data on the determination result by the determination unit 50 (step S240). If the estimation unit 80 determines that the temporary data stored in the memory unit 70 does not include the judgment result data by the judgment unit 50 ("NO" in step S240), the estimation unit 80 returns the process to step S220 and searches for the next similar data.

[0052] On the other hand, if the estimation unit 80 determines that the temporary data stored in the memory unit 70 includes judgment result data by the judgment unit 50 ("YES" in step S240), it complements the judgment result of the driver who estimates the judgment result with the temporary data (step S250) and terminates all processing.

[0053] <Actions and Effects> As described above, in the processing device 1A of this embodiment, when there is a risk factor for which a judgment result has not been obtained by the judgment unit 50, the estimation unit 80 estimates the judgment result by the judgment unit 50 for the risk factor for which a judgment result has not been obtained by the judgment unit 50, based on the judgment result by the judgment unit 50 of another person that has already been judged for this risk factor. Therefore, even when the judgment result in the processing device 1A is used for operation control or the like, the operation control can be made to function effectively. In addition, when a judgment result is obtained by the judgment unit 50 under the same conditions after the data complementation by the estimation unit 80, the complemented data may be replaced with a true value and the difference between the complemented data and the true value may be fed back to improve the estimation accuracy by the estimation unit 80.

[0054] <Variation 1> In the second embodiment, a method has been described in which data having a similarity degree equal to or greater than a predetermined value is searched for among data in a database stored in the storage unit 70, and the determination result by the determination unit 50 is complemented based on the searched data. However, in a method in which the judgment results by the judgment unit 50 are managed as numerical data, if a huge amount of data is accumulated in the database, the judgment results by the judgment unit 50 may be derived by performing machine learning using a neural network. In this case, the accuracy of the judgment result may be further improved by referring to the score derived by the neural network for the extracted numerical data of the judgment result.

[0055] <Variation 2> In the first embodiment, it has been described that the determination unit 50 determines the decline in the cognitive function of the driver based on the measurement result of the measurement unit 40 and the statistical reaction time. However, in cases where the driver misses the target object, the measurement result of the measuring unit 40 will be much longer than the expected range, and the judgment result based on the measurement result will not reflect the actual situation. In such cases, the judgment process by the judgment unit 50 may be stopped, or the transmission of the measurement result from the measuring unit 40 may be restricted. In addition, a functional block may be added for detecting not only the image data acquired by the image acquisition unit 10 but also the movement of the driver's line of sight, and the judgment process by the judgment unit 50 may be executed only when it can be determined that the driver's line of sight is capturing an object based on both sets of image data.

[0056] <Variation 3> In addition, the image data of the vehicle's surroundings during normal driving and the vehicle's speed data may be used to determine whether the vehicle is driving in line with the flow of other vehicles, thereby judging the driver's level of attention while the vehicle is driving, and this judgment factor may be reflected in the judgment process in the judgment unit 50. Generally, when a vehicle is not following the flow of other vehicles and is moving slowly, it is expected that a higher assessment result will be obtained than in reality even if cognitive function is impaired. However, as described above, by also assessing the driver's level of attention while driving the vehicle, a more realistic assessment result can be obtained.

[0057] <Variation 4> Furthermore, for example, if the judgment result of the judgment unit 50 is significantly inferior in dark conditions such as at night or during rainy weather compared to daytime or sunny days, it may be due to a decrease in visibility in the dark rather than simply a decrease in cognitive function. In such a case, the determination unit 50 may make a determination taking into consideration the decrease in visibility in the dark. Also, if a decrease in visibility in the dark is suspected, the driver may be notified of this via another device. Furthermore, regardless of whether the judgment result of the judgment unit 50 is clearly deteriorating or not, a warning may be issued if a deterioration in the judgment result is recognized under certain conditions compared to past judgment results of the same person, even if the judgment result of the judgment unit 50 is not clearly deteriorating.

[0058] The processing devices 1 and 1A of the present invention can be realized by recording the processing of the processing devices 1 and 1A in a recording medium readable by a computer system and having the estimation device read and execute the program recorded in the recording medium. The computer system here includes hardware such as an OS and peripheral devices.

[0059] Furthermore, if a WWW (World Wide Web) system is used, the "computer system" also includes the home page provision environment (or display environment). The above program may be transmitted from a computer system in which the program is stored in a storage device or the like to another computer system via a transmission medium, or by transmission waves in the transmission medium. Here, the "transmission medium" that transmits the program refers to a medium that has the function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.

[0060] The program may be for implementing some of the functions described above, or may be a so-called differential file (differential program) that can implement the functions described above in combination with a program already recorded in the computer system.

[0061] Although the embodiments and examples of the present invention have been described in detail above with reference to the drawings, the specific configurations are not limited to these embodiments or examples, and designs that do not deviate from the gist of the present invention are also included. [Explanation of symbols]

[0062] 1; Processing equipment 10. Image acquisition section 20:Detection unit 30: Detection section 40: Measurement section 50; Judgment section 60;Acquisition Department 70;Memory part

Claims

1. An image acquisition unit that acquires a peripheral image of a vehicle; A first detection unit that detects the appearance of an object from the acquired peripheral image; A detection unit that detects a risk avoidance operation of the driver of the vehicle with respect to the object; A measurement unit that measures the time from the appearance of the object by the first detection unit to the detection of the risk avoidance operation of the driver with respect to the object by the detection unit; A second detection unit that detects the line of sight of the driver; A determination unit that determines the decline of the driver's cognitive function from the measurement result of the measurement unit and a predetermined threshold value when it is determined that the driver's line of sight has captured the object; A processing device characterized by comprising the above.

2. The processing device according to claim 1, wherein the determination unit determines the decline of the driver's cognitive function from the measurement result of the measurement unit and a statistical reaction time.

3. An acquisition unit that acquires risk factors in vehicle driving; A storage unit that associates and stores the risk factors detected by the acquisition unit and the determination result by the determination unit; The processing device according to claim 2, characterized by comprising the above.

4. The processing device according to claim 3, wherein the risk factor is a margin of the vehicle width with respect to the road width.

5. The processing device according to claim 3, wherein the risk factor is the situation of other vehicles around the vehicle.

6. The processing device according to claim 3, wherein the risk factor is the weather during the running of the vehicle.

7. The processing device according to claim 3, wherein the risk factor is the running time of the vehicle.

8. When there is a risk factor for which the determination result has not been obtained among the risk factors, Comprising an estimation unit that estimates the determination result for the risk factor for which the determination result has not been obtained based on the determination results of others that have already been determined for the risk factor, The processing device according to any one of claims 3 to 7, characterized in that until the determination result for the risk factor for which the determination result has not been obtained is obtained from the determination unit, the determination result estimated by the estimation unit is temporarily used as the determination result by the determination unit.

9. A program for causing a computer to execute a processing method in a processing device including an image acquisition unit, a first detection unit, a detection unit, a measurement unit, a second detection unit, and a determination unit, a first step in which the image acquisition unit acquires a peripheral image of the vehicle; a second step in which the first detection unit detects the appearance of an object from the acquired peripheral image; a third step in which the detection unit detects a risk avoidance operation of the driver of the vehicle with respect to the object; a fourth step in which the second detection unit detects the line of sight of the driver; a fifth step in which the measurement unit measures the time from the appearance of the object by the first detection unit to the detection of the risk avoidance operation of the driver of the vehicle with respect to the object by the detection unit; a sixth step in which the determination unit determines the decline of the driver's cognitive function from the measurement result of the measurement unit and a predetermined threshold value when it is determined that the driver's line of sight catches the object; A program for causing a computer to execute the above steps.

10. A recording medium storing the program of Claim 9.

11. A processing method in a processing device including an image acquisition unit, a first detection unit, a detection unit, a measurement unit, a second detection unit, and a determination unit, comprising: a first step in which the image acquisition unit acquires a peripheral image of the vehicle; a second step in which the first detection unit detects the appearance of an object from the acquired peripheral image; a third step in which the detection unit detects a risk avoidance operation of the driver of the vehicle with respect to the object; a fourth step in which the second detection unit detects the line of sight of the driver; a fifth step in which the measurement unit measures the time from the appearance of the object by the first detection unit to the detection of the risk avoidance operation of the driver of the vehicle with respect to the object by the detection unit; a sixth step in which the determination unit determines the decline of the driver's cognitive function from the measurement result of the measurement unit and a predetermined threshold value when it is determined that the driver's line of sight catches the object; A processing method comprising the above steps.

Images