Detection device and detection program

Abstract

To prevent accidents from happening. [Solution] The detection device according to the embodiment has a controller that performs processing for driving assistance. The controller calculates the amount of increase over time in the area occupied by an object in an image captured by a camera mounted on the vehicle. Based on the amount of increase, the controller determines the visibility of the surroundings from the vehicle.

Description

Technical Field

[0007]

[0001] The present invention relates to a detection device and a detection program.

Background Art

[0002] Conventionally, a technology for assisting driving by detecting risks related to a vehicle is known. For example, a communication-type drive recorder having a safe driving support function for detecting dangerous driving behaviors and evaluating warnings and driving diagnoses based on the detection results is known. Dangerous driving behaviors include ignoring traffic lights, exceeding the speed limit, etc. In addition, the evaluation of the driving diagnosis is performed by driving diagnosis, scoring, improvement comments, etc. on the behavior of the G-sensor by accelerator, brake, and steering wheel operations.

[0003] Also, an ADAS (Advanced Driver-Assistance Systems) that detects pedestrians, vehicles, bicycles, etc. approaching from the left and right at intersections and performs warnings and brake control is known.

[0004] Furthermore, a technology for diagnosing whether correct driving actions are performed according to the visibility from a vehicle and determining the presence or absence of an obstacle based on the ratio of the total of the visual field angles occupied by the obstacle is known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, with the conventional technology, it may be difficult to prevent accidents in advance.

[0007] For example, when a vehicle enters a road from off-road, the movement of other vehicles and pedestrians can narrow the vehicle's field of vision, allowing it to perceive what is in front of and to the sides of the road. This reduces the accuracy of ADAS (Advanced Driver-Assistance Systems) in detecting pedestrians, vehicles, and bicycles approaching from the sides, increasing the risk of collisions and accidents.

[0008] Furthermore, the technology described in Patent Document 1 detects the presence or absence of an obstruction and does not take into account changes in the field of view due to the movement of an object that could act as an obstruction.

[0009] This invention has been made in view of the above, and aims to prevent accidents. [Means for solving the problem]

[0010] The detection device of the present invention has a controller that performs processing for driving assistance. The controller calculates the amount of increase over time in the area occupied by objects in an image captured by a camera mounted on the vehicle. Based on the amount of increase, the controller determines the visibility of the surroundings from the vehicle. [Effects of the Invention]

[0011] In this invention, the visibility of the surroundings from the vehicle is determined by considering cases where objects captured in images taken by the vehicle's camera move, thereby worsening the vehicle's visibility. This allows for a more accurate driving evaluation compared to when objects are considered stationary. As a result, according to this invention, accident prevention can be achieved through accurate driving evaluation. [Brief explanation of the drawing]

[0012] [Figure 1] Figure 1 shows an example of the configuration of a driving evaluation system. [Figure 2] Figure 2 shows an example of an ECU configuration. [Figure 3] Figure 3 is a diagram illustrating the overview of the controller processing according to Example 1. [Figure 4]FIG. 4 is a diagram for explaining a method of calculating an area ratio. [Figure 5] FIG. 5 is a diagram for explaining a change in the area ratio. [Figure 6] FIG. 6 is a flowchart showing the flow of processing of the controller. [Figure 7] FIG. 7 is a flowchart showing the flow of processing for calculating the area ratio according to Example 1. [Figure 8] FIG. 8 is a flowchart showing the flow of driving diagnosis processing. [Figure 9] FIG. 9 is a diagram showing an example of a screen displayed on the terminal. [Figure 10] FIG. 10 is a diagram for explaining an outline of processing of the controller according to Example 2. [Figure 11] FIG. 11 is a flowchart showing the flow of processing for calculating the area ratio according to Example 2. [Figure 12] FIG. 12 is a diagram for explaining an outline of processing of the controller according to Example 3. [Figure 13] FIG. 13 is a flowchart showing the flow of processing for calculating the area ratio according to Example 3.

Mode for Carrying Out the Invention

[0013] Hereinafter, embodiments of the detection device and detection program disclosed in the present application will be described in detail with reference to the accompanying drawings. Note that the present invention is not limited by the embodiments shown below.

[0014] First, the configuration of the driving evaluation system will be described using FIG. 1. FIG. 1 is a diagram showing a configuration example of the driving evaluation system.

[0015] The driving evaluation system 1 performs a driving evaluation based on information acquired from the vehicle 10 or the like. For example, the driving evaluation system 1 performs a driving evaluation by calculating a score indicating the safety of the driver's driving.

[0016] As shown in FIG. 1, the driving evaluation system 1 includes a vehicle 10, a server 20, a terminal 30, and a terminal 40.

[0017] The vehicle 10 transmits sensor data of sensors mounted on the vehicle 10 and the results of processing performed based on the sensor data and the like to the server 20. The server 20 performs a driving evaluation based on the collected information. The server 20 transmits the results of the driving evaluation to the terminal 30 and the terminal 40.

[0018] The terminal 30 includes an application for administrators used by administrators. The terminal 30 stores and manages the evaluation results of a plurality of drivers.

[0019] The terminal 40 includes an application for drivers used by drivers. The driver checks the results of his / her own driving evaluation transmitted to the terminal 40. For example, the results of the driving evaluation may be a score indicating safety, an image of a scene diagnosed as dangerous driving, an image of a scene diagnosed as excellent driving, and the like. Note that the images include still images and moving images (videos).

[0020] Here, the configuration of the vehicle 10 will be described in detail. The vehicle 10 includes an ECU (Electronic Control Unit) 11, a camera 12, a camera 13, a microphone 14, a communication unit 15, an output device 16, and a receiver 17.

[0021] The ECU 11 performs information processing related to the vehicle 10. In particular, the ECU 11 determines the visibility around the vehicle 10 based on the image captured by the camera 12. The details of the process for determining the visibility will be described later. The visibility may be described as the width of the cognitive visual angle. A deterioration in visibility is synonymous with a decrease in the cognitive visual angle.

[0022] The camera 12 is provided at a position where it can image the front of the vehicle 10 (the traveling direction when moving forward). The camera 13 is provided at a position where it can image the rear of the vehicle 10 (the traveling direction when moving backward). Note that the camera 12 and the camera 13 may be provided in a drive recorder.

[0023] Microphone 14 collects sound from around or inside the vehicle 10. Communication unit 15 communicates data between the vehicle 10 and an external device (e.g., server 20). Output device 16 is a device that outputs information. Output device 16 is, for example, a speaker and a display. Receiver 17 receives signals to determine the position of the vehicle 10. Receiver 17 receives, for example, GNSS (Global Navigation Satellite System) signals.

[0024] Figure 2 shows an example of the configuration of an ECU. As shown in Figure 2, the ECU 11 has an interface 111, a controller 112, and a memory 113.

[0025] Interface 111 performs data input and output between the controller 112 and other devices. These other devices include both internal devices of the ECU 11 (e.g., memory 113) and external devices of the ECU 11.

[0026] The controller 112 reads and executes the program stored in memory 113. The controller 112 can be a CPU (Central Processing Unit), DSP (Digital Signal Processor), FPGA (Field Programmable Gate Array), GPU (Graphics Processing Unit), SoC (System on a Chip), etc.

[0027] The controller 112 may be a single processor. The controller 112 may be a multi-processor configuration. Alternatively, the controller 112 may be a multi-core configuration having multiple cores within a single chip connected by a single socket.

[0028] The controller 112 calculates the amount of increase over time in the area occupied by objects in the image captured by the camera 12 mounted on the vehicle 10. The controller 112 also determines the visibility of the surroundings from the vehicle 10 based on this increase.

[0029] The results of the determination by the controller 112 are used for driving diagnostics in the server 20. As a result, the ECU 11 enables driving assistance that takes into account changes in visibility due to the movement of objects around the vehicle. The processing by the controller 112 will be described in detail below for each of the embodiments.

[0030] [Example 1] Figure 3 is a diagram illustrating the overview of the controller processing according to Example 1. Figure 3 is a view of the vehicle 10 from above (viewed vertically downwards). The front, back, left, and right directions in the following explanation are as shown in Figure 3.

[0031] In Figure 3, vehicle 10 is moving forward from the parking lot and attempting to merge onto the road. At this time, an object (for example, another vehicle or a pedestrian) located in front of vehicle 10 (for example, reference numeral 511) may obstruct vehicle 10's view.

[0032] At that time, the image of the front of the vehicle 10 captured by the camera 12 will show an object that acts as an obstruction. The controller 112 calculates the area ratio based on the image showing such an object. The controller 112 uses the calculated area ratio to determine the visibility of the surroundings from the vehicle 10.

[0033] Figure 4 is a diagram illustrating the method for calculating the area ratio. As shown in Figure 4, vehicles 81, pedestrians 82, and vehicles 83 are recognized from the image 70 captured by camera 12. The controller 112 can recognize objects captured by camera 12 using existing AI (Artificial Intelligence) or other methods.

[0034] Furthermore, the rectangular area 71 is pre-set as the area where visibility may be impaired if an object is present. Vehicle 81, pedestrian 82, and vehicle 83 are all located within the rectangular area 71.

[0035] The controller 112 obtains the lateral (left-right) length of the objects within the rectangular area 71. Let X be the total lateral (left-right) length of image 70. Although Figure 4 shows the entire vehicle 81, in reality, image 70 only shows the front portion of the vehicle 81, which has a length W1. Also, the lateral length of the pedestrian 82 in image 70 is W2. Also, the lateral length of the vehicle 83 in image 70 is W3.

[0036] The controller 112 calculates the area ratio as the ratio of the sum of the horizontal lengths of the objects in the image 70 to the total horizontal length. For example, in the example in Figure 4, the controller 112 calculates the area ratio as shown in equation (1).

[0037] Area ratio = (W1 + W2 + W3) ÷ X × 100 (1)

[0038] Figure 5 will be used to explain the change in area proportion. Figure 5 is a diagram illustrating the change in area proportion. Images 70a, 70b, and 70c shown in Figure 5 are frames of a video captured by camera 12. Image 70b is captured after image 70a, and then image 70c is captured after that. In other words, images 70a, 70b, and 70c in Figure 5 are arranged in chronological order.

[0039] Pedestrian 84, vehicle 85, and vehicle 86 are moving in front of vehicle 10, crossing from left to right. At this time, as time progresses, the area ratio may increase, and visibility from vehicle 10 may worsen. Controller 112 calculates the area ratio taking this increase into account.

[0040] The processing flow of controller 112, including the calculation of area percentages, will be explained using the flowchart in Figure 6. Figure 6 is a flowchart of the controller's processing flow.

[0041] As shown in Figure 6, the controller 112 waits until it detects a scene in which a vehicle is about to merge onto the roadway from a parking lot or the like (Step S11; No). If the controller 112 detects a scene in which a vehicle is about to merge onto the roadway from a parking lot or the like (Step S11; Yes), it proceeds to Step S12.

[0042] The controller 112 may detect scenes based on images, or it may detect scenes based on the position information of the vehicle 10.

[0043] The controller 112 calculates the area ratio Y1 (step S12). The area ratio Y1 is the area ratio considering the increase.

[0044] The controller 112 determines whether the area ratio Y1 is less than or equal to the threshold TH1 (step S13). If the area ratio Y1 is less than or equal to the threshold TH1 (step S13; Yes), the controller 112 determines that the visibility is good and assigns 1 to THRU (step S14). If the area ratio Y1 is not less than or equal to the threshold TH1 (step S13; No), the controller 112 determines that the visibility is poor and assigns 0 to THRU (step S15). THRU=1 means that the visibility is good. THRU=0 means that the visibility is poor.

[0045] Next, the controller 112 detects driving behavior (step S16). Then, the controller 112 transmits video data, safe driving behavior, and dangerous driving behavior to the center, i.e., the server 20 (step S17). Safe driving behavior and dangerous driving behavior are the results of the driving behavior detection. If dangerous driving behavior is detected, the controller 112 may issue a warning via an alarm through the output device 16.

[0046] The controller 112 detects driving behavior based on sensor data and images. For example, the controller 112 detects driving behavior based on vehicle speed, slow-moving detection (determined from position information, vehicle speed sensor, and G sensor), stop line detection (using image recognition), whether the driver has checked left and right (determined from face direction and gaze detection), presence of surrounding vehicles, pedestrians, bicycles, etc., and lane detection.

[0047] For example, when making a right turn, the controller 112 counts the number of detected driving behaviors as safe driving behaviors and the number of undetected driving behaviors as dangerous driving behaviors. (1-1) Slow down (1-2) Check left and right sides of the sidewalk and roadway. (1-3) Stop briefly before the sidewalk. (1-4) Check left and right sides of the sidewalk and roadway. Sidewalk: Check for pedestrians and cyclists. Roadway: Check for vehicles traveling in the left and right-facing lanes, and vehicles entering the parking lot from the right-facing lane. (1-5) Stop briefly before reaching the roadway. (1-6) Check left and right on the roadway Roadway: Check for vehicles traveling in the left and right-facing lanes, and vehicles entering the parking lot from the right-facing lane. (1-7) Turn right slowly

[0048] For example, when making a left turn, the controller 112 counts the number of detected driving behaviors as safe driving behaviors and the number of undetected driving behaviors as dangerous driving behaviors. (2-1) Slow down (2-2) Check left and right sides of the sidewalk and roadway. (2-3) Stop briefly before the sidewalk. (2-4) Check left and right sides of the sidewalk and roadway. Sidewalk: Check for pedestrians and cyclists. Roadway: Check for vehicles traveling in the left-bound lane and vehicles entering the parking lot from the right-bound lane. (2-5) Stop briefly before reaching the roadway. (2-6) Check left and right on the roadway Roadway: Check for vehicles traveling in the left-hand lane. (2-7) Turn left slowly

[0049] The controller 112 sends the number of safe driving actions (points), DRVOK, and the number of dangerous driving actions (points), DRVNG, to the server 20 along with THRU.

[0050] Figure 7 is a flowchart showing the process for calculating the area ratio in Example 1. Figure 7 provides a detailed explanation of S12 in Figure 6 in Example 1.

[0051] As shown in Figure 7, the controller 112 calculates the increase in area percentage Y within a certain period of time (step S1211). In the example in Figure 5, the controller 112 can calculate the increase in area percentage Y as shown in equation (2). However, the controller 112 calculates the area percentage of image 70a as X1. The controller 112 also calculates the area percentage of image 70b as X2. The controller 112 also calculates the area percentage of image 70c as X3.

[0052] Y = ((X2 - X1) + (X3 - X2)) / 2 (2)

[0053] Y can be defined as the average increase in area percentage between frames. The controller 112 obtains Y1 by adding the area percentage increase Y to the area percentage X1 (step S1212).

[0054] In this way, the controller 112 calculates the amount of increase over time in the area occupied by objects in the image captured by the camera 12 mounted on the vehicle 10. Then, the controller 112 determines the visibility based on this increase. By considering the increase in area percentage, the driving evaluation described later becomes more accurate. As a result, accurate driving evaluation makes it possible to prevent accidents.

[0055] Figure 8 illustrates the flow of the operational diagnostic process performed by the server 20. Figure 8 is a flowchart showing the flow of the operational diagnostic process. The main component of the process in Figure 8 is assumed to be the controller installed in the server 20.

[0056] The controller 21 determines whether THRU is 0 or not (step S21). If THRU is 0 (step S21; Yes), i.e., visibility is poor, the controller 21 proceeds to step S22. If THRU is not 0 (step S21; No), i.e., visibility is good, the controller 21 proceeds to step S24.

[0057] Furthermore, if the controller 112 determines that visibility is poor, it may notify the driver of the vehicle 10 of an alert via the output device 16 by voice or screen display. This allows the ECU 11 to promptly notify the driver of poor visibility and prevent accidents.

[0058] The controller 21 determines whether DRVNG is greater than or equal to THRNG (step S22). THRNG is a threshold used to determine whether a driver has truly engaged in dangerous driving behavior, based on the number of dangerous driving behaviors.

[0059] If DRVNG is THRNG or higher (Step S22; Yes), that is, if there was truly dangerous driving behavior, the controller 21 proceeds to Step S23. If DRVNG is not THRNG or higher (Step S22; No), that is, if there was not truly dangerous driving behavior, the controller 21 proceeds to Step S24.

[0060] The controller 21 notifies the results of the driving diagnosis regarding dangerous driving behavior (step S23). For example, the controller 21 transmits the driving diagnosis results to terminals 30 and 40.

[0061] The controller 21 determines whether DRVOK is greater than or equal to THROK (step S24). THROK is a threshold used to determine whether the driver truly performed safe driving actions based on the number of safe driving actions. If DRVOK is greater than or equal to THROK (step S24; Yes), the controller 21 proceeds to step 25. If DRVOK is not greater than or equal to THROK (step S24; No), the controller 21 terminates the process.

[0062] The controller 21 notifies the driver of the driving diagnostic results regarding safe driving behavior (step S25). For example, the controller 21 transmits the driving diagnostic results to terminals 30 and 40.

[0063] The screen of terminal 40 displays the driving diagnostic results. Figure 9 shows an example of the screen displayed on the terminal. As shown in Figure 9, the screen showing the driving diagnostic results displays the assessment result for visibility, safe driving behavior points, and dangerous driving behavior points.

[0064] The processing performed by server 20 described here is just one example. The processing that server 20 performs using the information transmitted from ECU 11 is not limited to what is described here. Furthermore, the processing described as being performed by server 20 may also be performed by ECU 11.

[0065] The controller 21 (or controller 112) evaluates the driving of the vehicle 10 driver based on the result of the visibility assessment. The controller 21 (or controller 112) also notifies the driver's terminal 40 of the results of the evaluation of the vehicle 10 driver's driving.

[0066] This allows drivers to review their driving performance evaluations and become more mindful of avoiding dangerous driving, thus preventing accidents.

[0067] [Example 2] In Example 1, the area ratio Y1 calculated by the controller 112 can be said to be a value that reflects the probability that visibility will be worsened by moving objects. Factors that worsen visibility are not limited to moving objects.

[0068] In Example 2, the controller 112 reflects in the area percentage the probability that visibility will be impaired due to the structure of the area where the vehicle 10 is traveling. In other words, the controller 112 further increases the amount of increase depending on the structure of the area around the vehicle 10. This enables a more accurate driving evaluation that takes into account the structure of the area around the vehicle 10.

[0069] Figure 10 is a diagram illustrating the overview of the controller processing according to Example 2. As shown in Figure 10, the structure near the exit of a parking lot may impair visibility.

[0070] For example, stop lines near the exit of a parking lot (symbol 521), steps between the parking lot and the sidewalk (symbol 522), and low shoulder blocks between the sidewalk and the roadway (symbol 523) can attract the driver's attention and worsen visibility. In addition, traffic lights or intersections (symbol 524) located close to the exit of a parking lot can worsen visibility.

[0071] Therefore, the controller 112 adds the probability that visibility will be impaired due to the structure of the location to the area ratio Y1. Figure 11 is a flowchart showing the process flow for calculating the area ratio according to Example 2. In Example 2, the process S12 in Figure 6 is replaced by the process shown in Figure 11.

[0072] As shown in Figure 11, the controller 112 determines whether or not there is a step between the parking lot and the roadway (step S1221). If there is a step (step S1221; Yes), the controller 112 increases the area ratio (step S1222). For example, the controller 112 adds D1 to the area ratio Y1. D1 is a value predetermined to be added when there is a step. If there is no step (step S1221; No), the controller 112 proceeds to the next process without increasing the area ratio.

[0073] The controller 112 determines whether or not there is a block between the parking lot and the roadway (step S1223). If there is a block (step S1223; Yes), the controller 112 increases the area ratio (step S1224). For example, the controller 112 adds D2 to the area ratio Y1. D2 is a predetermined value to be added when there is a block. If there is no block (step S1223; No), the controller 112 proceeds to the next process without increasing the area ratio.

[0074] The controller 112 determines whether there is a traffic light within a certain distance after exiting the parking lot onto the roadway and turning left (step S1225). If there is a traffic light (step S1225; Yes), the controller 112 increases the area ratio (step S1226). For example, the controller 112 adds D3 to the area ratio Y1. D3 is a value predetermined to be added when there is a traffic light. If there is no traffic light (step S1225; No), the controller 112 proceeds to the next process without increasing the area ratio.

[0075] The presence or absence of steps, blocks, signals, etc., may be detected by the AI, or they may be provided in advance as part of the map data. Furthermore, the controller 112 may change the value to be added according to the size and range of steps and blocks, the distance to signals, etc.

[0076] [Example 3] Visibility may be impaired due to the movement of other vehicles near the parking lot exit. Near the parking lot exit, drivers of vehicles traveling on the roadway may stop or slow down their vehicles to give way to vehicles trying to exit the parking lot, in other words, they may yield the right of way.

[0077] The controller 112 further increases the boost amount if the vehicle in front of the vehicle is stopped or moving slowly. This allows for a more accurate driving assessment, taking into account the influence of vehicles that are yielding the right of way.

[0078] Figure 12 shows a scene where another vehicle is about to yield the right of way. Figure 12 is a diagram illustrating the overview of the controller processing according to Embodiment 3.

[0079] In Figure 12, assume that vehicle 10 is turning left out of a parking lot while vehicle 531 is stopped or moving slowly. At this time, the driver of vehicle 10 needs to keep a close eye on vehicle 531. This is because accidents can occur due to mistaking vehicle 531 for vehicle 10 yielding the right of way, or due to other vehicles or pedestrians appearing from the blind spot of the vehicle that was yielding. As a result, visibility from vehicle 10 will be reduced.

[0080] Furthermore, vehicle 532 may have been stopped or moving slowly as vehicle 10 was turning right out of the parking lot, and may have been trying to yield the right of way to vehicle 10.

[0081] Therefore, in Example 3, the controller 112 adds the probability of worsening visibility to the area ratio Y1, depending on the presence of a vehicle that may be yielding the right of way. Figure 13 is a flowchart showing the process flow for calculating the area ratio in Example 3. In Example 3, the process S12 in Figure 6 is replaced by the process shown in Figure 13.

[0082] The controller 112 increases the area ratio (step S1232) if its own vehicle (vehicle 10) is about to turn right or left and a vehicle traveling on the roadway to the left (for example, vehicle 532) is stopped or moving slowly (step S1231; Yes). This is a case where a vehicle coming from the right may be about to yield the right of way.

[0083] In cases where a vehicle approaching from the right may be yielding the right of way, the controller 112 adds C1 to the area ratio Y1. C1 is a predetermined value to be added in cases where a vehicle approaching from the right may be yielding the right of way. If the case does not fall under the category of a vehicle approaching from the right potentially yielding the right of way (step S1231; No), the controller 112 proceeds to the next process without increasing the area ratio.

[0084] The controller 112 increases the area ratio (step S1234) if its own vehicle (vehicle 10) is about to turn right and a vehicle traveling to the right on the roadway (for example, vehicle 531) is stopped or moving slowly (step S1233; Yes). This is a case where a vehicle coming from the left may be about to yield the right of way.

[0085] In cases where a vehicle approaching from the left may be yielding the right of way, the controller 112 adds C2 to the area ratio Y1. C2 is a predetermined value to be added in cases where a vehicle approaching from the left may be yielding the right of way. If the case does not fall under the category of a vehicle approaching from the left potentially yielding the right of way (step S1233; No), the controller 112 proceeds to the next process without increasing the area ratio.

[0086] In addition to the processing in Example 1, the controller 112 may also perform the processing in Examples 2 and 3. For example, after calculating Y1 by the processing in Figure 7, the controller 112 may determine whether or not to add D1, D2, D3, C1, and C2, and perform the addition according to the result of the determination, by the processing in Figures 11 and 13.

[0087] Up to this point, it has been explained that the controller 112 calculates the area ratio based on the lateral length of moving objects. However, stationary objects (walls, fences, bridge piers, signs, etc.) are also included in the area ratio calculation. However, stationary objects do not affect the increase in the area over time if the vehicle 10 is not moving.

[0088] The ECU11, or both the ECU11 and the server 20, constitute the detection device. The detection device performs processes for calculating the area ratio, determining the visibility, and performing operational diagnostic processes. The process for calculating the area ratio may be performed by the server 20. The operational diagnostic process may be performed by the ECU11.

[0089] Further effects and modifications can be readily derived by those skilled in the art. Therefore, broader aspects of the present invention are not limited to the specific details and representative embodiments expressed and described above. Accordingly, various modifications are possible without departing from the spirit or scope of the overall concept of the invention as defined by the appended claims and equivalents. [Explanation of Symbols]

[0090] 1. Operation Evaluation System 10 vehicles 11 ECU 12, 13 Cameras 14 Mike 15 Communication Unit 16 Output device 17 Receiver 20 servers 30, 40 devices 111 Interface 112 Controllers 113 memory

Claims

1. It has a controller that performs processing for driver assistance, The aforementioned controller, The amount of increase over time in the area occupied by an object in an image captured by a camera mounted on the vehicle is calculated. Based on the aforementioned increase, the degree of visibility of the surroundings from the vehicle is determined. Detection device.

2. The aforementioned controller, Depending on the structure of the area surrounding the vehicle, the amount of increase may be further increased. The detection device according to claim 1.

3. The aforementioned controller, If the vehicle in front of the aforementioned vehicle is stopped or moving slowly, the aforementioned increase amount shall be further increased. The detection device according to claim 1.

4. The aforementioned controller, Based on the results of the assessment of visibility, the driving of the vehicle's driver is evaluated. The detection device according to claim 1.

5. The aforementioned controller, The results of the evaluation of the vehicle driver's driving are notified to the driver's terminal. The detection device according to claim 4.

6. The aforementioned controller, If it is determined that visibility is poor, an alert will be sent to the driver of the vehicle. The detection device according to claim 1.

7. The controller that performs processing for driver assistance, The amount of increase over time in the area occupied by an object in an image captured by a camera mounted on the vehicle is calculated. Based on the aforementioned increase, the degree of visibility of the surroundings from the vehicle is determined. A detection program that initiates processing.

Images