JP2017068688A - Inter-vehicle distance detection device, inter-vehicle distance detection method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an inter-vehicle distance detection device, inter-vehicle distance detection method, and program capable of estimating a traffic situation and supporting driving with high reliability in consideration of an empty state of a road.SOLUTION: An inter-vehicle distance detection device includes a reception section, a detection section, and a control section. The reception section receives image data obtained by imaging a forward side of a first vehicle by an imaging part. The detection section performs first processing to detect a second vehicle traveling on the forward side of the first vehicle and also to detect an inter-vehicle distance between the first vehicle and the second vehicle on the basis of the image data. The control section identifies a factor not to detect the second vehicle when the second vehicle is not detected in the first processing, and invalidates a second detection result of an inter-vehicle distance when reliability of a first detection result which indicates that the second vehicle is not detected and corresponds to the identified factor is equal to or less than a predetermined threshold.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to an inter-vehicle distance detection device, an inter-vehicle distance detection method, and a program.

  The inter-vehicle distance that detects the inter-vehicle distance by performing image processing on an image such as a moving image obtained by imaging the front of the vehicle with a camera, and estimates the traffic situation and supports driving based on the inter-vehicle distance. There is detection technology. The inter-vehicle distance detection technology cannot detect the inter-vehicle distance when the vehicle ahead is out of the angle of view of the camera at a sharp curve, or when the image quality of the moving image is affected by the direction of sunlight, etc. It is determined that there is no vehicle ahead.

JP 2014-130439 A

  However, in the above-mentioned inter-vehicle distance detection technology, since there is no vehicle in front, the case in which the inter-vehicle distance cannot be detected and in the case in which the vehicle actually exists in front, the inter-vehicle distance is detected. Since the case where the vehicle cannot be processed is processed in the same way, the generation of road traffic information and the driving support based on the detection result of the inter-vehicle distance may not function correctly.

  The inter-vehicle distance detection device according to the embodiment includes a reception unit, a detection unit, and a control unit. The receiving unit receives image data obtained by imaging the front of the first vehicle by the imaging unit. The detection unit performs a first process of detecting a second vehicle traveling in front of the first vehicle and detecting an inter-vehicle distance between the first vehicle and the second vehicle based on the image data. When the second vehicle is not detected by the first process, the control unit specifies a factor that the second vehicle is not detected, and indicates that the second vehicle is not detected according to the specified factor. When the reliability of one detection result is equal to or less than a predetermined threshold, the second detection result of the inter-vehicle distance is invalidated.

FIG. 1 is a diagram illustrating an example of the configuration of the inter-vehicle distance detection system according to the first embodiment. FIG. 2 is a diagram illustrating an example of a configuration around the cockpit in the vehicle of the probe car according to the first embodiment. FIG. 3 is a block diagram illustrating an example of a functional configuration of the probe car control device and the server according to the first embodiment. FIG. 4 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the probe car control device according to the first embodiment. FIG. 5 is a diagram illustrating an example of a bit string of a factor code used in the inter-vehicle distance detection system according to the first embodiment. FIG. 6 is a table showing an example of a factor code used in the inter-vehicle distance detection system according to the first embodiment. FIG. 7 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the server according to the first embodiment. FIG. 8 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the probe car control device according to the seventh embodiment. FIG. 9 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the server according to the seventh embodiment.

  Hereinafter, an inter-vehicle distance detection device, an inter-vehicle distance detection method, and an inter-vehicle distance detection system to which a program is applied will be described with reference to the accompanying drawings.

(First embodiment)
FIG. 1 is a diagram illustrating an example of the configuration of the inter-vehicle distance detection system according to the first embodiment. As shown in FIG. 1, the inter-vehicle distance detection system according to the present embodiment includes a probe car 1, a front vehicle 2, a GPS satellite 3, a base station 4, and a server 5. The probe car 1 captures a moving image by imaging the front of the probe car 1 at a predetermined measurement cycle (for example, several seconds). The probe car 1 (an example of the first vehicle) detects a front vehicle 2 (an example of the second vehicle) that is a vehicle traveling in front of the probe car 1 based on the acquired moving image, and the probe car. An inter-vehicle distance L that is a distance between 1 and the preceding vehicle 2 is detected. Further, the probe car 1 performs driving support based on the detection result of the inter-vehicle distance L.

  A GPS (Global Positioning System) satellite 3 transmits a GPS signal to the probe car 1. The base station 4 receives the detection result of the inter-vehicle distance L from the probe car 1 by wireless communication. Then, the base station 4 transmits the detection result of the inter-vehicle distance L received from the probe car 1 to the server 5. The server 5 receives the detection result of the inter-vehicle distance L from the base station 4 and estimates road traffic information based on the received detection result of the inter-vehicle distance L. Then, the server 5 distributes the estimated road traffic information and the like to the probe car 1 via the base station 4.

  FIG. 2 is a diagram illustrating an example of a configuration around the cockpit in the vehicle of the probe car according to the first embodiment. As shown in FIG. 2, in the present embodiment, the probe car 1 includes a control device 10, a first camera 11, a second camera 12, a mobile terminal 13, and a GPS antenna 14. The control device 10 controls the entire probe car 1.

  The first camera 11 (an example of an imaging unit) is provided on the left side when viewed from the driver's seat with respect to the rearview mirror BM of the probe car 1 and images the front of the probe car 1. The second camera 12 (an example of an imaging unit) is provided on the right side when viewed from the driver's seat with respect to the rearview mirror BM of the probe car 1 and images the front of the probe car 1. The portable terminal 13 is a smartphone or the like, and is a display unit that displays various information such as road traffic information distributed from the server 5. The GPS antenna 14 receives a GPS signal transmitted from the GPS satellite 3.

  FIG. 3 is a block diagram illustrating an example of a functional configuration of the probe car control device and the server according to the first embodiment. First, the functional configuration of the control device 10 will be described with reference to FIG. As shown in FIG. 3, in the present embodiment, the control device 10 includes an image receiving unit 101, an image processing unit 102, an inter-vehicle distance analyzing unit 103, a GPS module 104, a GPS communication unit 105, a reject determining unit 106, an external input / output. Unit 107 and HTTP communication unit 108.

  The image receiving unit 101 (an example of a receiving unit) receives a moving image obtained by imaging each camera from the first camera 11 and the second camera 12 (an example of an external device). The image processing unit 102 performs image processing on a camera image (an example of image data) that is a frame constituting the received moving image, and detects an object included in the camera image. Then, the inter-vehicle distance analysis unit 103 performs pattern recognition on the object detected by the image processing unit 102 to detect the front vehicle 2, and the inter-vehicle distance between the probe car 1 and the detected front vehicle 2. A detection process (an example of a first process) for detecting L is executed. In the present embodiment, the image processing unit 102 and the inter-vehicle distance analysis unit 103 execute a detection process of detecting the front vehicle 2 and detecting the inter-vehicle distance L between the probe car 1 and the front vehicle 2 based on the camera image. It functions as an example of a detection unit that performs.

  Specifically, the inter-vehicle distance analysis unit 103 performs pattern recognition on the object detected by the image processing unit 102 to detect a vehicle. The inter-vehicle distance analysis unit 103 performs pattern recognition on the object and detects a lane in which the probe car 1 (own vehicle) travels. Then, the inter-vehicle distance analyzing unit 103 detects a vehicle in the detected lane among the detected vehicles as the front vehicle 2.

  Next, the inter-vehicle distance analysis unit 103 detects the inter-vehicle distance L between the probe car 1 and the front vehicle 2 based on the angle of view of the first camera 11 and the second camera 12 and the size of the vehicle in the lane. . Alternatively, when the first camera 11 and the second camera 12 constitute a stereo camera, the inter-vehicle distance analysis unit 103 is obtained by the camera image obtained by the imaging of the first camera 11 and the imaging of the second camera 12. It is also possible to detect the inter-vehicle distance L between the probe car 1 and the front vehicle 2 based on the parallax of the camera image.

  In pattern recognition for detecting a vehicle, the imaging conditions of the first camera 11 and the second camera 12 may be a factor that prevents the preceding vehicle 2 from being detected based on the camera image (hereinafter referred to as a non-detectable factor). Imaging conditions that are undetectable factors include backlighting due to the influence of sunlight, backlighting due to the influence of headlights of oncoming vehicles, changes in the amount of light at the entrance and exit of the tunnel, steep curves, steep slopes, etc. For example, the front vehicle 2 protrudes from the angle of view of the second camera 12.

  Therefore, when the front vehicle 2 cannot be detected, the inter-vehicle distance analysis unit 103 indicates that the brightness of the entire camera image is equal to or higher than the predetermined brightness, and that the light source having the predetermined brightness or higher is included in the camera image. The fact that an image of a part of the shape of the vehicle exists at the end of the camera image is specified as a non-detectable factor based on the imaging conditions. Then, the inter-vehicle distance analyzing unit 103 sets a factor code indicating the specified undetectable factor.

  In the pattern recognition for detecting the lane, the lane change of the front vehicle 2, the lane change of the probe car 1, the temporary disappearance of the lane itself, etc. cannot be detected from the camera image and become a non-detectable factor. There is. Therefore, the inter-vehicle distance analysis unit 103 identifies that the lane cannot be detected as a non-detectable factor based on the imaging condition, and sets a factor code indicating the non-detectable factor.

  The GPS module 104 receives a GPS signal transmitted from the GPS satellite 3. The GPS communication unit 105 acquires GPS data based on GPS signals received from the plurality of GPS satellites 3 by the GPS module 104. Here, the GPS data is position information (for example, latitude, longitude, altitude) indicating the position where the probe car 1 is traveling, the current time, and the number of captured satellites that is the number of GPS satellites 3 that captured the GPS signal. including.

  The external input / output unit 107 acquires operation information indicating an operation state of the probe car 1 such as a traveling speed of the probe car 1 and an operation of a wiper included in the probe car 1. In the present embodiment, the external input / output unit 107 acquires the speed of the probe car 1 as operation information from the traveling system of the probe car 1. The external input / output unit 107 can also acquire the traveling speed of the probe car 1 using the position information of the probe car 1 acquired based on the GPS signal and the current time.

  When the preceding vehicle 2 cannot be detected, the reject determination unit 106 acquires operation information from the external input / output unit 107. Then, when it is determined that the operation state of the probe car 1 indicated by the acquired operation information matches the predetermined operation state, the reject determination unit 106 specifies the operation state indicated by the operation information as a non-detectable factor. Here, the predetermined operation state is an operation state of the probe car 1 that becomes a non-detectable factor. For example, if the reject determination unit 106 determines that the wiper operation indicated by the acquired operation information matches the high-speed operation of the wiper, which is an example of a predetermined operation state, the wiper operates at a high speed due to heavy rain or the like. Considering that the vehicle 2 cannot be detected, the operation of the wiper is specified as a non-detectable factor. Thereafter, the reject determination unit 106 sets a factor code indicating the identified undetectable factor.

  In addition, when the preceding vehicle 2 cannot be detected, the reject determining unit 106 performs a continuity determining process for determining whether or not the preceding vehicle 2 cannot be detected continuously for a predetermined number of frames. If the rejection determination unit 106 determines that the preceding vehicle 2 cannot be detected continuously for a predetermined number of frames, the rejection determination unit 106 specifies that the preceding vehicle 2 cannot be detected continuously as an undetectable factor. Then, the reject determination unit 106 sets a factor code indicating the specified undetectable factor.

  Next, when the preceding vehicle 2 cannot be detected by the inter-vehicle distance analyzing unit 103, the rejection determination unit 106 detects a result of detection indicating that the preceding vehicle 2 could not be detected in accordance with the set non-detectable factor (hereinafter referred to as a detection result). This is referred to as a detection result of the front vehicle 2. An example of the first detection result) is given a determination point that represents the reliability of the detection result. In the present embodiment, the reject determination unit 106 gives a determination point to the detection result of the preceding vehicle 2 according to the set factor code. Specifically, the rejection determination unit 106 gives the total of determination points corresponding to the set factor codes to the detection result of the preceding vehicle 2.

  Next, when the determination point given to the detection result of the preceding vehicle 2 is lower than a predetermined threshold, the rejection determination unit 106 determines that the detection result of the preceding vehicle 2 is noise, and the detection result of the inter-vehicle distance L (second) Invalidate (example of detection result). As a result, when the preceding vehicle 2 cannot be detected, traffic state estimation and driving assistance (for example, a probe car) using the detection result of the inter-vehicle distance L in a case where there is a high possibility that the preceding vehicle 2 does not actually exist. 1 can be adjusted and automatic switching to a high beam can be performed, so that it is possible to estimate traffic conditions and drive support with higher reliability in consideration of road availability.

  Here, the predetermined threshold is a lower limit value of the reliability that determines that the detection result of the inter-vehicle distance L is reliable. In the present embodiment, the rejection determination unit 106 invalidates the detection result of the inter-vehicle distance L when the determination point given to the detection result of the preceding vehicle 2 is equal to or less than a predetermined threshold, and based on the detection result of the inter-vehicle distance L. Prohibit road traffic information estimation and driving support. On the other hand, when the determination point given to the detection result of the preceding vehicle 2 is equal to or greater than a predetermined threshold, the rejection determination unit 106 transmits the detection result of the inter-vehicle distance L to the server 5 via the HTTP communication unit 108 described later. To do.

  An HTTP (Hypertext Transfer Protocol) communication unit 108 transmits a detection processing result (hereinafter referred to as a processing result) by the inter-vehicle distance analysis unit 103 to the server 5. In the present embodiment, the HTTP communication unit 108 sends the detection result of the preceding vehicle 2, the detection result of the inter-vehicle distance L, the determination point given to the detection result of the inter-vehicle distance L, and the processing result including the GPS data to the server 5. Send.

  Next, the functional configuration of the server 5 will be described with reference to FIG. As shown in FIG. 3, in this embodiment, the server 5 includes an HTTP communication unit 501, a server-side rejection determination unit 502, a position conversion unit 503, a map information storage unit 504, a learning data control unit 505, and a learning data storage unit 506. And an environmental information acquisition unit 507. The HTTP communication unit 501 receives a processing result from the probe car control device 10.

  The map information storage unit 504 stores map information indicating a map of a road on which the probe car 1 can travel. The position conversion unit 503 acquires GPS data included in the processing result from the HTTP communication unit 501 via the server-side reject determination unit 502. Then, the position conversion unit 503 specifies the road on which the probe car 1 travels based on the acquired GPS data and the map information stored in the map information storage unit 504. Then, the position conversion unit 503 notifies the server-side reject determination unit 502 of the identified road.

  The learning data storage unit 506 stores road conditions that are conditions for roads in which the preceding vehicle 2 cannot be detected (for example, the preceding vehicle 2 that is more than a predetermined distance away from the probe car 1 due to a sharp curve or a steep slope cannot be detected). To do. The learning data control unit 505 determines whether or not the road identified by the position conversion unit 503 matches the road condition stored in the learning data storage unit 506. When the learning data control unit 505 determines that the road specified by the position conversion unit 503 matches the road condition, the learning data control unit 505 specifies the specified road as a non-detectable factor, and a factor code indicating the non-detectable factor Set.

  The environment information acquisition unit 507 acquires GPS data included in the processing result from the HTTP communication unit 501 via the server-side reject determination unit 502. In addition, the environment information acquisition unit 507 receives the environment information on the road where the probe car 1 can travel from the terminal T of the environment information provider, such as weather information such as rain, snow and fog, PM2.5, photochemical smog warning, yellow sand, etc. Get environmental information about. Then, the environmental information acquisition unit 507 determines whether or not the environmental information of the position indicated by the position information included in the GPS data (that is, the position of the probe car 1) among the acquired environmental information matches the predetermined environmental information. judge. Here, the predetermined environment information is information indicating an environmental condition in which the front vehicle 2 cannot be detected. The environmental information acquisition unit 507 identifies the environmental information of the position of the probe car 1 as a non-detectable factor when the environmental information of the position of the probe car 1 matches the predetermined environmental information, and a factor indicating the non-detectable factor Set the code.

  When the detection result of the preceding vehicle 2 included in the processing result received by the HTTP communication unit 501 indicates that the preceding vehicle 2 cannot be detected, the server-side rejection determination unit 502 uses the learning data control unit 505 and the environment information acquisition unit 507. A determination point is given to the detection result of the inter-vehicle distance L according to the non-detectable factor indicated by each set factor code. And the server side rejection determination part 502 determines whether the sum total of the determination point provided to the detection result of the inter-vehicle distance L is more than a predetermined threshold value.

  Next, when the sum of the determination points is lower than a predetermined threshold, the server-side reject determination unit 502 determines that the detection result of the preceding vehicle 2 is noise and invalidates the detection result of the inter-vehicle distance L. On the other hand, the server-side reject determination unit 502 determines that the detection result of the preceding vehicle 2 is valid and determines that there is no preceding vehicle 2 when the total of the determination points is equal to or greater than a predetermined threshold.

  In the present embodiment, the inter-vehicle distance analysis unit 103, the rejection determination unit 106, the server-side rejection determination unit 502, the learning data control unit 505, and the environment information acquisition unit 507 are not detected when the preceding vehicle 2 is not detected. When the reliability of the detection result of the preceding vehicle 2 corresponding to the undetectable factor is equal to or less than a predetermined threshold value, it functions as a control unit that invalidates the detection result of the inter-vehicle distance L. Moreover, in this embodiment, although an example of the inter-vehicle distance detection device is realized in the control device 10 and the server 5, an example of the inter-vehicle distance detection device may be realized in either the control device 10 or the server 5. good.

  Next, an example of a flow of detection processing of the inter-vehicle distance by the control device 10 of the probe car 1 according to the present embodiment will be described with reference to FIG. FIG. 4 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the probe car control device according to the first embodiment.

  The image processing unit 102 performs image processing on the camera images constituting the moving image received by the image receiving unit 101, and detects an object included in the camera image (step S401). Next, the inter-vehicle distance analysis unit 103 performs pattern recognition on the detected object, detects the front vehicle 2, and detects the inter-vehicle distance L between the probe car 1 and the detected front vehicle 2 (step) S401). Further, when the preceding vehicle 2 cannot be detected, the inter-vehicle distance analysis unit 103 identifies a non-detectable factor based on the imaging condition, and outputs a factor code indicating the non-detectable factor to the reject determining unit 106 (step S401). .

  Here, the factor codes used in the inter-vehicle distance detection system according to the present embodiment will be described with reference to FIG. FIG. 5 is a diagram illustrating an example of a bit string of a factor code used in the inter-vehicle distance detection system according to the first embodiment.

  As shown in FIG. 5, the factor code is represented by a 64-bit bit string, and a plurality of undetectable factors can be represented by a value assigned to each bit of the bit string. When the factor code is “0”, the factor code indicates that no undetectable factor has been identified. As shown in FIG. 5, the factor code is the lower 32 bits out of 64 bits and represents a non-detectable factor based on the imaging condition of the camera image. Further, the factor code is the middle 16 bits out of 64 bits and represents a non-detectable factor based on the continuity determination process or the operation state. Further, the factor code is the upper 16 bits of the 64 bits and represents a non-detectable factor based on road conditions or environmental conditions.

  Returning to FIG. 4, the rejection determination unit 106 determines whether or not the preceding vehicle 2 could not be detected by the inter-vehicle distance analysis unit 103 (step S402). When the front vehicle 2 can be detected (step S402: No), the rejection determination unit 106 transmits the processing result to the server 5 via the HTTP communication unit 108 (step S408). On the other hand, when the front vehicle 2 cannot be detected (step S402: Yes), the rejection determination unit 106 acquires operation information from the external input / output unit 107 (step S403). Then, when the operation state of the probe car 1 indicated by the acquired operation information matches the predetermined operation state, the reject determination unit 106 specifies the operation state of the probe car 1 indicated by the operation information as a non-detectable factor, A factor code corresponding to the undetectable factor is set (step S403).

  In addition, the rejection determination unit 106 performs a continuity determination process for determining whether or not the preceding vehicle 2 cannot be detected continuously for a predetermined number of frames (step S404). When it is determined that the preceding vehicle 2 cannot be detected continuously for a predetermined number of frames, the rejection determination unit 106 specifies that the preceding vehicle 2 cannot be detected continuously as a non-detectable factor, and handles the non-detectable factor. The cause code to be set is set (step S404).

  Next, the rejection determination unit 106 converts each of the factor code output from the inter-vehicle distance analysis unit 103 and the factor code set by the rejection determination unit 106 into a determination point (step S405). In the present embodiment, the rejection determination unit 106 associates a factor code, a non-detectable factor indicated by the factor code, and a determination point to which a detection result of the preceding vehicle 2 is assigned when the non-detectable factor is specified. The attached table T1 is stored. Then, the rejection determination unit 106 gives the determination point stored in association with the set factor code to the detection result of the preceding vehicle 2 in the table T1.

FIG. 6 is a table showing an example of a factor code used in the inter-vehicle distance detection system according to the first embodiment. For example, as illustrated in FIG. 6, the rejection determination unit 106 stores a table T1 in which a factor code, a determination point, and a non-detectable factor are associated with each other. The reject judgment unit 106, undetectable factor, can not be detected as the vehicle, if it has been detected only a part of the lower side of the vehicle, cause code: 2 ⁰ association with the stored decision point : -50 is added to the detection result of the front vehicle 2.

Furthermore, the reject judgment unit 106, undetectable factor, can not be detected as the vehicle, if it has been detected only a part of the right side of the vehicle, cause code: 2 ¹ association with the stored decision point: -50 is added to the detection result of the front vehicle 2. Furthermore, the reject judgment unit 106, undetectable factors have been able to detect the vehicle, before the vehicle type of the vehicle 2 (e.g., ordinary car or large vehicles) When is it can not be detected, cause code: association with 2 ⁴ The determined determination point: −40 is added to the detection result of the preceding vehicle 2.

Furthermore, the reject judgment unit 106, when undetectable factor is that the wiper heavy rain or snow is operated at a high speed, cause code: 2 ¹⁶ association with the stored decision point: -30 previous vehicle 2 Is added to the detection result. Furthermore, the reject judgment unit 106, undetectable factors, when a high beam of continuous lighting, cause code: 2 ¹⁷ with association with the stored decision point: imparting to the detection result before the vehicle 2 +10.

Furthermore, the reject judgment unit 106, undetectable factor, a predetermined number of frames (e.g., 10 frames) when the vehicle 2 before continuously is the inability to detect, cause code: determination 2 ²⁴ and associated with stored Point: +10 is added to the detection result of the preceding vehicle 2. Furthermore, the reject judgment unit 106, undetectable factor, when the inter-vehicle distance L detected last time is a predetermined distance (e.g., 80 m) or more, cause code: 2 ²⁵ with association with the stored decision point: +10 ago This is given to the detection result of the vehicle 2. Furthermore, the reject judgment unit 106, undetectable factor, a predetermined number of frames (e.g., five frames) when the vehicle 2 before continuously is the inability to detect, cause code: determination 2 ²⁶ and associated with stored Point: -10 is assigned to the detection result of the front vehicle 2.

Furthermore, the reject judgment unit 106, when undetectable factor is that running a sharp curve region, cause code: 2 ⁴⁸ and correlated with the stored decision point: -30 detection result before the vehicle 2 To grant. Furthermore, the reject judgment unit 106, when undetectable factor is that running a steep region, cause code: 2 ⁴⁹ with association with the stored decision point: -30 detection result before the vehicle 2 To grant. Furthermore, the reject judgment unit 106, undetectable factor, if that is traveling the area dense fog or snow and heavy rain alarm or the like is issued, cause code: 2 ⁵⁰ and decision point stored in association : -20 is added to the detection result of the front vehicle 2.

  Returning to FIG. 4, the rejection determination unit 106 determines whether or not the total of the determination points given to the detection result of the preceding vehicle 2 is greater than or equal to a predetermined threshold (for example, +10) (step S406). And when the sum total of the determination point given to the detection result of the front vehicle 2 is more than a predetermined threshold value (step S406: Yes), the rejection determination part 106 sends a process result to the server 5 via the HTTP communication part 108. (Step S408). When the sum of the determination points given to the detection result of the preceding vehicle 2 is lower than the predetermined threshold (step S406: No), the rejection determination unit 106 invalidates the detection result of the inter-vehicle distance L, and detects the inter-vehicle distance L. Is finished (step S407).

  Next, an example of a flow of detection processing of the inter-vehicle distance L by the server 10 according to the present embodiment will be described with reference to FIG. FIG. 7 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the server according to the first embodiment.

  When the position conversion unit 503 receives the processing result by the HTTP communication unit 501, the position conversion unit 503 acquires GPS data included in the processing result. Next, the position conversion unit 503 specifies the position of the road on which the probe car 1 travels based on the acquired GPS data and the map information stored in the map information storage unit 504 (step S701).

  The server-side reject determination unit 502 determines whether or not the detection result of the preceding vehicle 2 included in the processing result received by the HTTP communication unit 501 indicates that the preceding vehicle 2 could not be detected (step S702). When the detection result of the preceding vehicle 2 indicates that the preceding vehicle 2 could not be detected (step S702: Yes), the learning data control unit 505 indicates that the road identified by the position conversion unit 503 is stored as learning data. It is determined whether or not the road conditions stored in the unit 506 match. When the learning data control unit 505 determines that the road identified by the position conversion unit 503 matches the road condition, the learning data control unit 505 identifies the identified road as a non-detectable factor, and generates a factor code indicating the non-detectable factor. Setting is performed (step S703).

  Furthermore, the environment information acquisition unit 507 determines whether or not the environment information on the position of the probe car 1 matches the predetermined environment information (step S704). When the environment information acquisition unit 507 determines that the environment information of the position of the probe car 1 matches the predetermined environment information, the environment information acquisition unit 507 identifies the environment information of the position of the probe car 1 as a non-detectable factor, and performs the detection. A factor code indicating an unusable factor is set (step S704).

  The server-side reject determination unit 502 converts each factor code set by the learning data control unit 505 and the environment information acquisition unit 507 into a determination point (step S705). Then, the server-side reject determination unit 502 determines whether or not the total of the determination points is equal to or greater than a predetermined threshold (Step S706). Here, the total of the determination points is the total of the determination points included in the processing result received from the probe car 1 and the determination points including the factor codes set by the learning data control unit 505 and the environment information acquisition unit 507. When the sum of the determination points is equal to or greater than a predetermined threshold (step S706: Yes), the server-side reject determination unit 502 determines that the detection result of the preceding vehicle 2 is correct and determines that the preceding vehicle 2 has not been detected. (Step S707). On the other hand, when the total of the determination points is smaller than the predetermined threshold (step S706: No), the server-side reject determination unit 502 determines that the detection result of the preceding vehicle 2 is incorrect, and determines the detection result of the inter-vehicle distance L. It is invalidated (step S708).

  If it is determined in step S702 that the preceding vehicle 2 has been detected (step S702: No), the server-side reject determination unit 502 determines that the distance between the vehicles based on the traveling speed of the probe car 1 and the detected inter-vehicle distance L. It is determined whether or not the distance L is within a predetermined effective detection range (step S709). Here, the predetermined effective detection range is a distance range in which the inter-vehicle distance L can be detected based on the camera image. When it is determined that the inter-vehicle distance L is not within the predetermined effective detection range (step S709: No), the server-side reject determination unit 502 invalidates the detection result of the inter-vehicle distance L (step S708). On the other hand, when it is determined that the inter-vehicle distance L is within the predetermined effective detection range (step S709: Yes), the server-side reject determination unit 502 permits estimation of road traffic information and the like based on the detection result of the inter-vehicle distance L. Then, the detection process of the inter-vehicle distance L is terminated.

  Thus, according to the inter-vehicle distance detection system according to the first embodiment, when the front vehicle 2 cannot be detected, the detection of the inter-vehicle distance L in a case where there is a high possibility that the front vehicle 2 does not actually exist. Since the traffic situation can be estimated and the driving assistance can be performed using the result, the traffic situation can be estimated and the driving assistance can be performed with higher reliability in consideration of the empty state of the road.

(Second Embodiment)
The present embodiment is an example in which the determination point given to the detection result of the preceding vehicle is raised when the preceding vehicle is not detected and the probe car is stopped. In the following description, description of the same parts as those in the first embodiment is omitted.

  In the present embodiment, the rejection determination unit 106 is set when the preceding vehicle 2 cannot be detected and the operation information acquired by the external input / output unit 107 indicates that the probe car 1 is stopped. The determination point corresponding to each factor code is increased by a predetermined value (for example, +5). That is, when the detection of the preceding vehicle 2 fails and the probe car 1 is stopped, the reject determination unit 106 detects that the probe car 1 is at the head of the train line at a signal, level crossing, toll booth, road construction, accident, etc. Considering that there is a high possibility that the vehicle will stop and there is no front vehicle 2, the determination point corresponding to each set factor code is raised.

  As described above, according to the inter-vehicle distance detection system according to the second embodiment, when the preceding vehicle 2 is not detected and the probe car 1 is stopped at the head of the vehicle train, it corresponds to each set factor code. Therefore, the reliability of the detection result of the inter-vehicle distance L when the preceding vehicle 2 is not detected and the probe car 1 is stopped at the head of the vehicle train can be easily exceeded. Can be improved.

(Third embodiment)
This embodiment determines that the preceding vehicle is not detected continuously for a predetermined number of frames by the continuity determination process, and the last detected vehicle distance is longer than the upper limit of the predetermined effective detection range. It is an example which raises the judgment point given to the result. In the following description, description of the same parts as those in the first embodiment is omitted.

  In this embodiment, the rejection determination unit 106 determines that the preceding vehicle 2 is not detected continuously for a predetermined number of frames by the continuity determination process, and the inter-vehicle distance detected last is greater than the upper limit of the predetermined effective detection range. If it is long, the determination point given to the detection result of the front vehicle 2 is increased by a predetermined value (for example, +5). That is, the rejection determination unit 106 is given to the detection result of the preceding vehicle 2 in consideration of the high possibility that the preceding vehicle 2 is not present when the preceding vehicle 2 is gradually away from the probe car 1. Raise the judgment point.

  As described above, according to the inter-vehicle distance detection system according to the third embodiment, when the front vehicle 2 gradually moves away from the probe car 1 and deviates from the predetermined effective detection range, the detection result of the front vehicle 2 is detected. Since the sum of the determination points given to the vehicle can easily exceed a predetermined threshold, when the preceding vehicle 2 gradually moves away from the probe car 1, the reliability of the detection result of the inter-vehicle distance L is improved. Can do.

(Fourth embodiment)
This embodiment is an example in which the detection result of the inter-vehicle distance is invalidated when front vehicle information indicating that there is a front vehicle is input from an external device. In the following description, description of the same parts as those in the first embodiment is omitted.

  In the present embodiment, the rejection determination unit 106 acquires a detection result indicating whether or not the preceding vehicle 2 has been detected from the server 5 via the HTTP communication unit 108. Then, when it is determined that the preceding vehicle 2 is not detected, the reject determining unit 106 provides a message indicating that the preceding vehicle 2 has not been detected via the external input / output unit 107. Display on the system display. Thereby, the rejection determination unit 106 notifies the passenger of the probe car 1 of the detection result of the front vehicle 2.

  Thereafter, when it is determined that the preceding vehicle 2 is not detected, the rejection determination unit 106 has the preceding vehicle 2 via the external input / output unit 107 using an operation unit or a microphone included in the car navigation system. Is input, the detection result of the inter-vehicle distance L is invalidated.

  As described above, according to the inter-vehicle distance detection system according to the fourth embodiment, the preceding vehicle 2 could not be detected. However, when the preceding vehicle 2 actually exists, it is input by the passenger of the probe car 1. Since the detection result of the inter-vehicle distance L can be invalidated based on the previous vehicle information, it is possible to prevent road traffic information estimation and driving assistance from being performed based on the erroneous detection result of the inter-vehicle distance L.

(Fifth embodiment)
The present embodiment is an example in which the detection result of the inter-vehicle distance is invalidated when the preceding vehicle information indicating that the preceding vehicle cannot be detected is input from an external device without detecting the preceding vehicle. In the following description, description of the same parts as those in the first embodiment is omitted.

  In the present embodiment, the rejection determination unit 106 detects the preceding vehicle 2 and from the operation unit or microphone (an example of an external device) of the car navigation system included in the probe car 1 via the external input / output unit 107. When the preceding vehicle information indicating that the preceding vehicle 2 cannot be detected is input, the detection result of the inter-vehicle distance L is invalidated.

  As described above, according to the inter-vehicle distance detection system according to the fifth embodiment, when it is difficult to specify whether or not the preceding vehicle 2 exists due to the influence of rain, snow, fog, or the like, the inter-vehicle distance Since the detection result of L can be invalidated, it is possible to prevent road traffic information estimation and driving assistance from being performed based on the erroneous detection result of the inter-vehicle distance L.

(Sixth embodiment)
The present embodiment is an example in which the camera image used for the detection process is stored in the learning data storage unit when the preceding vehicle is not detected. In the following description, description of the same parts as those in the first embodiment is omitted.

  In the present embodiment, the rejection determination unit 106 acquires a determination result as to whether or not the preceding vehicle 2 has been detected by the server-side rejection determination unit 502 from the server 5 via the HTTP communication unit 108. When the server-side reject determination unit 502 determines that the preceding vehicle 2 is not detected, the reject determination unit 106 acquires a camera image used for the detection process, and transmits the acquired camera image to the HTTP communication unit 108. To the server 5.

  When the server-side reject determination unit 502 receives a camera image from the control device 10 via the HTTP communication unit 501, the server-side reject determination unit 502 stores the received camera image in the learning data storage unit 506 (an example of a storage unit).

  Thus, according to the inter-vehicle distance detection system according to the sixth embodiment, when analyzing the detection result of the inter-vehicle distance L, the inter-vehicle distance is used using the camera image stored in the learning data storage unit 506. The detection result of L can be analyzed. In addition, the camera image stored in the learning data storage unit 506 can be used for maintenance of the inter-vehicle distance detection system, and can be used to add a non-detectable factor, change a predetermined threshold value, or the like, thereby detecting the front vehicle 2. Accuracy can be improved.

(Seventh embodiment)
The present embodiment is an example in which the position information of the road is stored in the storage unit when the road on which the probe car travels is specified as a non-detectable factor. In the following description, description of the same parts as those in the first embodiment is omitted.

  In the present embodiment, when the learning data control unit 505 determines that the road identified by the position conversion unit 503 matches the road condition, the learning data storage unit 506 (storage unit) stores the position information of the identified road. Save to example). Then, when the road identified by the position conversion unit 503 matches the road indicated by the position information stored in the learning data storage unit 506, the learning data control unit 505 sets the identified road as an undetectable factor. Identify.

  FIG. 8 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the probe car control device according to the seventh embodiment. In the following description, description of the same parts as those in the flowchart of FIG. 4 described in the first embodiment will be omitted. In the present embodiment, when the detection result of the inter-vehicle distance L is invalidated (step S409), the rejection determination unit 106 includes a factor code of a non-detectable factor learned in the server 5 in the set factor code. Whether or not (step S801). Here, the undetectable factor learned in the server 5 is a non-detectable factor based on the imaging condition, and a road specified as a non-detectable factor by the learning data control unit 505.

  If the set reason code includes the cause code of the undetectable cause to be learned (step S801: Yes), the rejection determination unit 106 transmits the processing result to the server 5 via the HTTP communication unit 108. (Step S408). In addition, when the cause code of the undetectable factor to be learned is not included in the set cause code (step S801: No), the reject determination unit 408 does not transmit the processing result to the server 5, The detection process of the inter-vehicle distance L is terminated.

  FIG. 9 is a flowchart illustrating an example of a flow of detection processing of the inter-vehicle distance by the server according to the seventh embodiment. In the following description, description of the same parts as those in the flowchart of FIG. 7 described in the first embodiment will be omitted. In the present embodiment, after it is determined that the front vehicle 2 has not been detected (step S707), the detection result of the inter-vehicle distance L is invalidated (step S708), or the inter-vehicle distance L is within the effective detection range. Is determined (step S709: Yes), the server-side reject determination unit 502 learns a non-detectable factor (road identified as a non-detectable factor by the learning data control unit 505) in the set factor code. It is determined whether or not the cause code is included (step S901). When it is determined that the factor code of the undetectable factor to be learned is not included (step S901: No), the server-side reject determination unit 502 ends the detection process of the inter-vehicle distance L. On the other hand, when it is determined that the factor code of the undetectable factor to be learned is included (step S901: Yes), the learning data control unit 505 learns the positional information of the road specified as the undetectable factor by the learning data control unit 505. A learning process stored in the data storage unit 506 is executed (step S902). When the factor code of the undetectable factor to be learned is not included (step S901: No), the server-side reject determination unit 502 ends the inter-vehicle distance L detection process.

  As described above, according to the inter-vehicle distance detection system according to the seventh embodiment, roads that cannot be specified only by road conditions stored in the learning data storage unit 506 can be specified as undetectable factors. The accuracy can be further improved.

  As described above, according to the first to seventh embodiments, it is possible to perform more reliable estimation of traffic conditions and driving support in consideration of the free state of the road.

  The program executed by the control device 10 and the server 5 of the present embodiment is provided by being incorporated in advance in a ROM (Read Only Memory) or the like. The program executed by the control device 10 and the server 5 of the present embodiment is a file in an installable or executable format, and is a CD-ROM, flexible disk (FD), CD-R, DVD (Digital Versatile Disk). ) Or the like may be recorded and provided on a computer-readable recording medium.

  Further, the program executed by the control device 10 and the server 5 of the present embodiment may be provided by being stored on a computer connected to a network such as the Internet and downloaded via the network. Moreover, you may comprise so that the program run with the control apparatus 10 and the server 5 of this embodiment may be provided or distributed via networks, such as the internet.

  The program executed by the control device 10 of the present embodiment includes the above-described units (the image reception unit 101, the image processing unit 102, the inter-vehicle distance analysis unit 103, the GPS communication unit 105, the rejection determination unit 106, the external input / output unit 107, The module configuration includes an HTTP communication unit 108). As actual hardware, a CPU (Central Processing Unit) reads a program from the ROM and executes the program to load each unit on the main storage device. A receiving unit 101, an image processing unit 102, an inter-vehicle distance analysis unit 103, a GPS communication unit 105, a rejection determination unit 106, an external input / output unit 107, and an HTTP communication unit 108 are generated on the main storage device.

  The program executed by the server 5 according to the present embodiment includes a module configuration including the above-described units (HTTP communication unit 501, server-side rejection determination unit 502, position conversion unit 503, learning data control unit 505, and environment information acquisition unit 507). As the actual hardware, the CPU reads the program from the ROM and executes it, so that the respective units are loaded on the main storage device, and the HTTP communication unit 501, the server-side reject determination unit 502, the position conversion unit A learning data control unit 505 and an environment information acquisition unit 507 are generated on the main storage device.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

DESCRIPTION OF SYMBOLS 1 Probe car 2 Front vehicle 3 GPS satellite 4 Base station 5 Server 10 Control apparatus 11 1st camera 12 2nd camera 13 Portable terminal 14 GPS antenna 101 Image receiving part 102 Image processing part 103 Inter-vehicle distance analysis part 104 GPS module 105 GPS communication Unit 106 rejection determination unit 107 external input / output unit 108,501 HTTP communication unit 502 server-side rejection determination unit 503 position conversion unit 504 map information storage unit 505 learning data control unit 506 learning data storage unit 507 environment information acquisition unit

Claims (13)

A receiving unit for receiving image data obtained by imaging the front of the first vehicle by the imaging unit;
A detection unit that executes a first process of detecting a second vehicle traveling in front of the first vehicle and detecting an inter-vehicle distance between the first vehicle and the second vehicle based on the image data;
When the second vehicle is not detected by the first process, a factor that the second vehicle is not detected is specified, and the second vehicle corresponding to the specified factor is not detected. A control unit that invalidates the second detection result of the inter-vehicle distance when the reliability of the one detection result is equal to or less than a predetermined threshold;
A vehicle-to-vehicle distance detection device.   2. The inter-vehicle distance detection device according to claim 1, wherein when the second vehicle is not detected and the first vehicle is stopped, the control unit increases the reliability by a predetermined value. The image data is a frame of a moving image obtained by imaging of the imaging unit,
The control unit increases the reliability when the second vehicle is not detected continuously for a predetermined number of frames and the last detected inter-vehicle distance is longer than an upper limit of a predetermined effective detection range. The inter-vehicle distance detection device described in 1. A display unit for displaying the first detection result;
The inter-vehicle distance detection device according to claim 1, wherein the control unit invalidates the second detection result when information indicating that the second vehicle is present is input from an external device.   2. The control unit according to claim 1, wherein the control unit invalidates the second detection result when the second vehicle is not detected and information indicating that the second vehicle cannot be detected is input from an external device. Inter-vehicle distance detection device.   The inter-vehicle distance detection device according to claim 1, wherein the control unit includes a storage unit that stores position information of the road when the factor is specified based on a road condition of a road on which the first vehicle travels. . Receiving image data obtained by imaging the front of the first vehicle by the imaging unit;
Performing a first process of detecting a second vehicle traveling in front of the first vehicle and detecting an inter-vehicle distance between the first vehicle and the second vehicle based on the image data;
When the second vehicle is not detected by the first process, a factor that the second vehicle is not detected is specified, and the second vehicle corresponding to the specified factor is not detected. If the reliability of one detection result is equal to or less than a predetermined threshold, the second detection result of the inter-vehicle distance is invalidated;
The inter-vehicle distance detection method including the above.   The inter-vehicle distance detection method according to claim 7, wherein when the second vehicle is not detected and the first vehicle is stopped, the reliability is increased by a predetermined value. The image data is a frame of a moving image obtained by imaging of the imaging unit,
8. The reliability is increased when the second vehicle is not detected by the first process continuously for a predetermined number of frames and the last detected inter-vehicle distance is longer than the upper limit of a predetermined inter-vehicle distance detection effective range. The inter-vehicle distance detection method described in 1. Displaying the first detection result on a display unit;
The inter-vehicle distance detection method according to claim 7, wherein, when information indicating that the second vehicle cannot be detected is input from an external device, the second detection result is invalidated.   The inter-vehicle distance detection method according to claim 7, wherein when the second vehicle is not detected and information indicating that the second vehicle cannot be detected is input from an external device, the second detection result is invalidated.   The inter-vehicle distance detection method according to claim 7, wherein when the factor is specified based on a road condition of a road on which the first vehicle travels, the position information of the road is stored in a storage unit. Computer
A receiving unit for receiving image data obtained by imaging the front of the first vehicle by the imaging unit;
A detection unit that executes a first process of detecting a second vehicle traveling in front of the first vehicle and detecting an inter-vehicle distance between the first vehicle and the second vehicle based on the image data;
When the second vehicle is not detected by the first process, a factor that the second vehicle is not detected is specified, and the second vehicle corresponding to the specified factor is not detected. A control unit that invalidates the second detection result of the inter-vehicle distance when the reliability of the one detection result is equal to or less than a predetermined threshold;
Program to function as.

Images