JP6476828B2 - Object detection apparatus and object detection method - Google Patents

Object detection apparatus and object detection method Download PDF

Info

Publication number
JP6476828B2
JP6476828B2 JP2014255922A JP2014255922A JP6476828B2 JP 6476828 B2 JP6476828 B2 JP 6476828B2 JP 2014255922 A JP2014255922 A JP 2014255922A JP 2014255922 A JP2014255922 A JP 2014255922A JP 6476828 B2 JP6476828 B2 JP 6476828B2
Authority
JP
Japan
Prior art keywords
object
target
road
target road
area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
JP2014255922A
Other languages
Japanese (ja)
Other versions
JP2016115311A (en
Inventor
藤田 晋
晋 藤田
騰 孫
騰 孫
Original Assignee
日産自動車株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日産自動車株式会社 filed Critical 日産自動車株式会社
Priority to JP2014255922A priority Critical patent/JP6476828B2/en
Publication of JP2016115311A publication Critical patent/JP2016115311A/en
Application granted granted Critical
Publication of JP6476828B2 publication Critical patent/JP6476828B2/en
Application status is Active legal-status Critical
Anticipated expiration legal-status Critical

Links

Images

Description

  The present invention relates to an object detection device and an object detection method.

  2. Description of the Related Art Conventionally, an object detection device that detects an object such as a vehicle or a pedestrian with a sensor is known. In such an object detection device, a technique is known in which object candidates are virtually arranged in an area where the object cannot be detected by a sensor due to a shield such as a building wall or a fence (for example, Patent Document 1). .

JP 2007-233864 A

  In the prior art, since the candidate objects are arranged at a uniform arrangement interval in a region where the object cannot be detected, the arrangement of the candidate objects may greatly deviate from the actual arrangement of the objects.

  The problem to be solved by the present invention is to provide an object detection device capable of appropriately arranging object candidates.

  The present invention determines the arrangement density of candidate objects in the non-detectable area based on the moving speed of the target object on the target road when there is a non-detectable area where the target object cannot be detected on the target road. Based on the arrangement density of the object candidates, the object problem is solved by arranging the object candidates in the undetectable region.

  According to the present invention, by determining the arrangement density of the candidate objects in the undetectable area based on the moving speed of the object on the target road, the arrangement of the object candidates in the undetectable area It can be adapted by arrangement.

It is a block diagram of the target object detection apparatus which concerns on this embodiment. It is a figure for demonstrating a target road and a target object undetectable area | region. It is the figure which showed the mode of the surroundings of the own vehicle shown in FIG. It is a figure for demonstrating the arrangement | positioning start position of a target object candidate. It is a figure for demonstrating the arrangement space | interval of a target object candidate. It is a flowchart which shows the target object detection process which concerns on 1st Embodiment. It is a figure which shows the example of arrangement | positioning which arrange | positioned several different types of object candidate. It is a flowchart (the 1) which shows the target object detection process which concerns on 2nd Embodiment. It is a flowchart (the 2) which shows the target object detection process which concerns on 2nd Embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description, a configuration in which the object detection device is mounted on an automobile (vehicle) will be described as an example. However, the configuration is not limited to this configuration. For example, the object detection device is a two-wheeled vehicle (motorcycle or bicycle). It is good also as a structure mounted in a smart phone, a tablet, etc. which a pedestrian carries a target object detection apparatus. In the following, a configuration in which the object detection device detects a moving body other than the own vehicle such as another vehicle (including a four-wheeled vehicle and a two-wheeled vehicle) or a pedestrian as an object will be described.

<< First Embodiment >>
FIG. 1 is a diagram illustrating a configuration of an object detection device 100 according to the present embodiment. As shown in FIG. 1, the object detection device 100 according to the present embodiment includes an object detection sensor 110, a vehicle position detection device 120, a map database 130, and a control device 140.

  The object detection sensor 110 can be composed of one or more types of sensors such as a camera, a laser scanner, and a radar. In the present embodiment, the object detection sensor 110 is configured using a plurality of types of sensors such as a camera, a laser scanner, and a radar. As described above, by using a plurality of types of sensors, it is possible to improve the detection accuracy of an object existing around the host vehicle. For example, by combining a camera and a laser scanner, the type of an object can be recognized by the camera, and a more accurate shape of the object can be recognized by the laser scanner. Then, by integrating the results detected by a plurality of types of sensors as described above, it is possible to grasp with high accuracy what kind and shape of an object (target object) exists.

  The own vehicle position detection device 120 is composed of a GPS unit, a gyro sensor, a vehicle speed sensor, and the like, detects radio waves transmitted from a plurality of satellite communications by the GPS unit, and periodically acquires position information of the own vehicle. The current position of the host vehicle is detected based on the acquired position information of the host vehicle, the angle change information acquired from the gyro sensor, and the vehicle speed acquired from the vehicle speed sensor. Furthermore, the host vehicle position detection device 120 detects a lane in which the host vehicle travels based on a captured image acquired from a camera that captures the front in the traveling direction of the host vehicle, and considers information on the lane in which the host vehicle travels. Thus, the current position of the host vehicle can be detected. The position information of the host vehicle detected by the host vehicle position detection device 120 is transmitted to the control device 140.

  The map database 130 stores map information including road information. The road information stored in the map database 130 includes information on the shape and legal speed of each road, statistical values (for example, average values) of travel speed when the host vehicle and other vehicles have traveled on the road in the past, and the like. Can be included. The map information can include area information such as residential areas and school zones.

  The control device 140 includes a ROM (Read Only Memory) that stores a program for detecting an object (a moving body other than the host vehicle), a CPU (Central Processing Unit) that executes the program stored in the ROM, It is composed of a RAM (Random Access Memory) that functions as an accessible storage device. As an operation circuit, instead of or in addition to a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), etc. Can be used.

  The control device 140 executes a program stored in the ROM by the CPU, thereby acquiring an object information acquisition function for acquiring information on an object such as another vehicle or a pedestrian, and vehicle information for acquiring vehicle information of the host vehicle. An acquisition function, a moving range setting function for setting a range in which the host vehicle will move in the near future as a moving range, a target road setting function for setting a predetermined road within the moving range as a target road, and movement of an object on the target road A speed information acquisition function for acquiring speed, an area detection function for detecting an area in which an object cannot be detected as an object non-detectable area, and an object candidate placement function for placing an object candidate in an object non-detectable area Realize. Below, each function with which the control apparatus 140 is provided is demonstrated.

  The object information acquisition function of the control device 140 acquires information on the object detected by the object detection sensor 110 from the object detection sensor 110. Information on the object acquired by the object information acquisition function includes information such as the position, shape, and size of the object. In addition, the object information acquisition function is information on the area where the object detection sensor 110 detects (searches) the object or the area where the object detection sensor 110 cannot detect the object. Can also get.

  The vehicle information acquisition function of the control device 140 acquires information including the current position of the host vehicle and the vehicle speed as vehicle information. For example, the vehicle information acquisition function can acquire the position information of the own vehicle from the own vehicle position detection device 120 and can acquire the vehicle speed information of the own vehicle from the vehicle speed sensor.

  The movement range setting function of the control device 140 sets a range in which the host vehicle may move in the near future as the movement range. Specifically, the moving range setting function first specifies the position of the host vehicle on the map by mapping the position information of the host vehicle to the map information acquired from the map database 130. Then, the movement range setting function sets a range within a predetermined distance from the position of the host vehicle on the map as a movement range in which the host vehicle may move in the near future. Furthermore, the moving range setting function can change the size of the moving range according to the moving speed of the host vehicle. For example, the moving range setting function can set the size of the moving range wider as the moving speed of the host vehicle is faster, and can set the size of the moving range narrower as the moving speed of the host vehicle is lower. The shape of the moving range is not particularly limited, and may be a circular range centered on the host vehicle, an elliptical or rectangular range extending in the traveling direction of the host vehicle, It is good also as a fan-shaped range which spreads in the advancing direction from the position as a vertex.

  The target road setting function of the control device 140 is a road in which the host vehicle may move in the near future among roads existing in the moving range set by the moving range setting function and the host vehicle traveling in the near future. A road that may enter the road to be set is set as a target road. Specifically, the target road setting function sets, as a target road, a road connected to a road on which the host vehicle travels among roads existing in the movement range. The target road setting function also sets a road ahead in the traveling direction of the host vehicle as a target road among roads on which the host vehicle travels.

  Here, FIG. 2 is a diagram for explaining the target road and the target object undetectable region. In the example shown in FIG. 2, roads L1 to L3 exist in the movement range, and the scene in which the host vehicle is traveling on the road L1 is shown. In this case, the target road setting function sets the road L2 connected to the road L1 on which the host vehicle V1 travels as the target road. The target road setting function also sets the road L1 ahead of the traveling direction of the host vehicle V1 as the target road among the roads L1 on which the host vehicle V1 travels. The target road setting function excludes roads facing the road on which the host vehicle is traveling from the target road when the roads are separated by the median strip. For example, in the example shown in FIG. 2, the road L3 is separated from the road L1 on which the host vehicle V1 travels by the central separation band, and therefore the target road setting function excludes the road L3 from the target road. This is because the object existing on the road L3 facing the road L1 on which the host vehicle V1 travels is unlikely to approach the host vehicle V1.

  The speed information acquisition function of the control device 140 acquires the moving speed at which the object moves on the target road for each target road set by the target road setting function. For example, the speed information acquisition function can acquire the legal speed of the target road included in the road information acquired from the map database 130 as the moving speed of the target object on the target road. In addition, it is usually assumed that the object is moving on the target road in compliance with the legal speed, but when the target road is congested, the moving speed of the moving object on the target road is higher than the legal speed. Expected to be slow. Therefore, when the target road is congested, the speed information acquisition function can acquire the statistical value of the moving speed of the target object on the target road as the moving speed of the target object on the target road.

  For example, by storing the average speed when the host vehicle has traveled on the target road in the past as the statistical value of the moving speed of the target object on the target road in the RAM of the control device 140, the speed information acquisition function is The statistical value of the moving speed of the object on the target road can be acquired as the moving speed of the object on the target road. In addition, when the host vehicle and other vehicles travel on the target road, the speed information acquisition function is transmitted from the external server when the host vehicle and other vehicles travel on the target road. The average value of the traveling speed can also be acquired as the moving speed of the object on the target road. Alternatively, the speed information acquisition function can also acquire a statistical value of the moving speed of the object on the target road as a moving speed of the target object on the target road from a VICS (registered trademark) server via a communication device (not shown). . The speed information acquisition function can also acquire the statistical value of the moving speed of the target object when the target road is empty as the moving speed of the target object on the target road when the target road is empty. .

  The region detection function of the control device 140 detects a region where the target object cannot be detected by the target object detection sensor 110 as a target object non-detectable region. For example, in the area detection function, the area information acquired by the object information acquisition function and the object detection sensor 110 can detect the object, or the object detection sensor 110 cannot detect the object. Based on the area information, the area where the object is detected can be detected as the object undetectable area.

  Here, FIG. 3 is a bird's-eye view of the surroundings of the host vehicle V1 shown in FIG. For example, in the example shown in FIG. 3, there are relatively high buildings B2 and B4 in front of the left side of the host vehicle V1, and there are other vehicles V2 and V3 in front of the host vehicle V1. In this case, the object detection sensor 110 cannot detect the object in the region on the back side of the buildings B2 and B4 (the side opposite to the side on which the host vehicle V1 is present), and is more than the buildings B2 and B4. The area on the far side becomes the blind spot of the driver of the host vehicle V1. In particular, in the example shown in FIG. 3, there is a road L2 between the building B2 and the building B4, but most of the road L2 is blocked by the building B2, and the object detection sensor 110 can detect the object. No region O1.

  In the example shown in FIG. 3, the preceding vehicle V2 exists in front of the host vehicle V1, the area ahead (back side) of the preceding vehicle V2 is blocked by the preceding vehicle V2, and the object is detected by the object detection sensor 110. The region O2 cannot be detected. Further, in the example shown in FIG. 3, there is another vehicle V3 in the lane that is in front of the host vehicle V1 and that is adjacent to the lane in which the host vehicle V1 travels. The region on the side opposite to the side where the vehicle V1 exists is blocked by the other vehicle V3, and becomes a region O3 where the object detection sensor 110 cannot detect the object. In this case, the area detection function detects the areas O1, O2, and O3 shown in FIG. 3 as the object detection unusable areas where the object cannot be detected. Note that the area detection function detects an object non-detectable area within the movement range of the target road, and does not detect an object non-detectable area for an area of the target road that exceeds the movement range.

The target object candidate placement function of the control device 140 virtually places the target object candidate in the target object undetectable area when the target object undetectable area exists on the target road. Specifically, the target object candidate placement function first determines the target object placement interval in the target object non-detectable region based on the moving speed of the target object on the target road acquired by the speed information acquisition function. Here, in general, when a driver drives an automobile, the distance between the vehicles tends to increase when moving at high speed, and the distance between the vehicles tends to decrease when moving at low speed. It is also known that there is a correlation between the traveling speed of the host vehicle and the traveling speed of the other vehicle and the relative distance between the host vehicle and the other vehicle. Therefore, as shown in the following formula (1), the target object candidate placement function determines the target object placement interval D based on the target moving speed Vr on the target road.
D = Td × Vr (1)
In the above formula (1), Td is an inter-vehicle time required for the driver to travel without feeling uneasy. Td is a function value established by TTC (Time To Contact) and THW (Time-Headway), and can be calculated based on the following equation (2). In the following formula (2), α and β are predetermined constants.
1 / Td = α / TTC + β / THW (2)

  Next, the object candidate arrangement function determines an arrangement start position of the object candidate in the object detection impossible area. For example, as shown in FIG. 4, when the preceding vehicle V2 exists in front of the target road L1 on which the host vehicle V1 travels, and the target object non-detectable area O2 exists in front of the preceding vehicle V2, the target candidate placement function Determines the position P10 separated from the preceding vehicle V2 by the arrangement interval D as the arrangement start position of the candidate object. FIG. 4 is a diagram for explaining the arrangement start position of the candidate object. As shown in FIG. 4, when the target object undetectable area O1 exists on the target road L2 connected to the road L1 on which the host vehicle V1 travels, the host vehicle V1 is included in the target object undetectable area O1. The position P20 closest to the road L1 on which the vehicle travels is determined as the arrangement start position of the candidate object.

  The target object candidate placement function places one or a plurality of target object candidates in each target object non-detectable region based on the target object placement interval D and the target candidate placement start position. Specifically, as shown in FIG. 4, the target candidate placement function first places the first target candidate at the placement start position of the target candidate. Furthermore, as shown in FIG. 5, the object candidate arrangement function arranges the next object candidate at a position separated from the arrangement start position by the arrangement interval D in the direction along the lane. Similarly, the object candidate placement function is located at a position separated by the placement interval D in the direction along the lane from the position of the nearest candidate object until there is no space to place the candidate object in the target object undetectable area. The next candidate object is repeatedly arranged.

  For example, in the example illustrated in FIG. 5, a position P10 that is separated from the preceding vehicle V2 by the arrangement interval D1 in the target object undetectable region O2 is determined as the target position for starting the target object. Therefore, as shown in FIG. 5, the object candidate placement function first places the object candidate at the placement start position P10, and then positions away from the placement start position P10 by the placement interval D1 in the direction along the lane. A second object candidate is placed in P11. Further, the candidate object placement function repeatedly places the candidate objects in the direction along the lane at every placement interval D1 until there is no space for placing the candidate object in the target object undetectable region O2.

  Further, in the target object undetectable region O1, the position P20 closest to the road L1 on which the host vehicle V1 travels is determined as the target start position of the target object. Therefore, as shown in FIG. 5, the candidate object placement function first places a candidate object at the placement start position P20, and then positions away from the placement start position P20 by the placement interval D2 in the direction along the lane. An object candidate is arranged at P21. Further, the target object candidate placement function places target object candidates at positions P22 and P23 by placing target object candidates at every placement interval D2 until there is no space for placing target object candidates in the target object non-detectable region O2. Deploy.

  In the first embodiment, the object candidate modeled on a four-wheeled vehicle is described as being arranged. However, the present invention is not limited to this configuration. For example, a candidate object or a pedestrian modeled on a two-wheeled vehicle is modeled. It can also be set as the structure which arrange | positions the target object made.

  Next, the object detection process according to the first embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing the object detection process according to the first embodiment. Note that the object detection process described below is executed by the control device 140.

  First, in step S101, information on an object (moving body other than the own vehicle) existing around the own vehicle is obtained by the object information obtaining function. Specifically, the object information acquisition function acquires information such as the type, shape, and position of the object detected by the object detection sensor 110 from the object detection sensor 110. The object information acquisition function also acquires information on an area where the object is detected by the object detection sensor 110 or an area where the object is not detected by the object detection sensor 110.

  In step S102, vehicle information including the current position and the vehicle speed of the host vehicle is acquired by the vehicle information acquisition function. For example, the vehicle information acquisition function can acquire the position information of the own vehicle from the own vehicle position detection device 120 and can acquire the vehicle speed information of the own vehicle from the vehicle speed sensor.

  In step S103, the moving range is set by the moving range setting function. In the present embodiment, the movement range setting function sets a range at a predetermined distance from the current position of the host vehicle as the movement range. The moving range setting function can set the size of the moving range wider as the moving speed of the host vehicle is faster, and can set the size of the moving range narrower as the moving range of the host vehicle is lower.

  In step S104, the target road is set by the target road setting function. In the present embodiment, as shown in FIG. 2, the target road setting function uses, as a target road, a road L2 connected to a road L1 on which the host vehicle V1 travels among roads existing in the movement range set in step S103. Set. The target road setting function also sets a road ahead in the traveling direction of the host vehicle as the target road among the road L1 on which the host vehicle V1 travels.

  In step S105, the movement speed of the object on the target road set in step S104 is acquired by the speed information acquisition function. For example, the speed information acquisition function refers to the map database 130, and calculates the legal speed of the target road included in the road information or the statistical value (for example, average value) of the moving speed of the target object on the target road. It can be acquired as the moving speed of an object.

  In step S106, the region where the object cannot be detected is detected by the region detection function. For example, in the area detection function, information on the area where the object detection sensor 110 can detect (search) the object or the area where the object detection sensor 110 could not detect the object acquired in step S101. Based on the above, an area where the object cannot be detected is detected as an object undetectable area. For example, in the example shown in FIG. 3, the region O1 on the back side of the building B2, the region O2 on the back side of the preceding vehicle V2, and the region O3 on the back side of the other vehicle V3 are detected as the object non-detectable regions. The

  In step S107, the object candidate arrangement function determines the arrangement interval of the object candidates in the object non-detectable area detected in step S106. Specifically, the object candidate arrangement function calculates the object candidate arrangement interval D based on the movement speed Vr of the object on the object road acquired in step S105, as shown in the above equation (1). .

  As shown in the above equation (1), the arrangement interval D is determined according to the moving speed of the object on the target road. For example, in the example shown in FIG. 5, the moving speed of the object on the target road L1 is 60 km / h, and the moving speed of the object on the target road L2 is 30 km / h. In this case, when the object candidate arrangement interval D is calculated based on the above formula (1), the object candidate arrangement interval D1 on the target road L1 is larger than the object candidate arrangement interval D2 on the target road L2. become longer. Thus, in this embodiment, since the arrangement interval of the candidate object is determined according to the moving speed of the target object on the target road, the road in which the inter-vehicle distance tends to be long because the target object moves at high speed. Then, the object candidates are arranged at a wide arrangement interval, and the object candidates are set at a narrow arrangement interval on a road where the distance between the vehicles tends to be short because the object moves at a low speed. Thereby, it becomes possible to adapt the arrangement of the object candidates in the object non-detectable area by the arrangement of the objects on the actual road.

  In step S108, the target object placement start position is determined by the target object candidate placement function. Specifically, as shown in FIG. 5, the object candidate arrangement function is separated from the preceding vehicle V2 by the arrangement interval D when the object detection impossible region O2 exists in front of the road on which the host vehicle is traveling. The determined position P10 is determined as the arrangement start position of the candidate object. Further, as shown in FIG. 5, the object candidate function includes the object detection impossible area O1 when the object detection impossible area O1 exists on the target road L2 connected to the road L1 on which the host vehicle travels. The position P20 closest to the road L1 on which the host vehicle V1 travels is determined as the arrangement start position of the target object.

  In step S109, candidate object placement is performed by the candidate object placement function. Specifically, as shown in FIG. 5, the target object candidate placement function is based on the target candidate placement interval D determined in step S107 and the target candidate placement start position determined in step S108. Thus, the object candidate is arranged at every arrangement interval D in the direction along the lane from the arrangement start position in the object non-detectable region.

  As described above, in the first embodiment, based on the moving speed Vr of the target object on the target road, the target object placement interval D in the target object undetectable area is determined, and the target distance is determined for each determined placement interval D. Place object candidates. Specifically, the higher the moving speed Vr of the target object on the target road, the lower the target object arrangement density in the target object non-detectable area by increasing the target object arrangement interval D. In general, when a driver drives a vehicle, the distance between the vehicles tends to increase when traveling at a high speed, and the distance between the vehicles tends to decrease when traveling at a low speed. Therefore, the higher the moving speed of the target object on the target road, the wider the target object placement interval D on the target road, thereby changing the target candidate placement in the target non-detectable area to the actual target placement. It becomes possible to adapt. As a result, for example, a situation caused by an object existing in the object undetectable area, such as popping out of an object existing in the object undetectable area, can be presented to the driver with high accuracy.

  Further, in the present embodiment, as shown in FIG. 4, when the target road is a road on which the host vehicle V1 travels and is a road L1 ahead of the host vehicle, the inter-vehicle spacing is greater than the preceding vehicle V2. A position P10 separated by D1 is set as an arrangement start position of the candidate object. As shown in FIG. 4, when the target road is a side road L2 connected to the road L1 on which the host vehicle V1 travels, a position P20 closest to the road L1 on which the host vehicle V1 travels is selected as a target candidate. Set as placement start position. As described above, in the present embodiment, based on the attribute of the target road, the position where the target object is likely to actually exist on the target road is determined as the target position of the target object detection. It is possible to match the arrangement of the candidate objects in the impossible area with the actual arrangement of the objects.

  Furthermore, in the present embodiment, the legal candidate speed of the target road is acquired as the moving speed of the target object on the target road, so that the target candidate is appropriately placed at a placement density according to the typical moving speed of the target object. can do. Furthermore, in the present embodiment, when the target road is congested or vacant, a statistical value (for example, an average value) of the moving speed of the target object in each scene is used as the moving speed of the target object on the target road. As a result, it is possible to appropriately arrange object candidates with an arrangement density corresponding to a speed close to the actual moving speed of the object.

<< Second Embodiment >>
Then, the target object detection apparatus which concerns on 2nd Embodiment is demonstrated. The object detection apparatus 100 according to the second embodiment has the same configuration as the object detection apparatus 100 shown in FIG. 1 and operates as described below, except that the object detection apparatus according to the first embodiment is operated. 100.

  In the second embodiment, the target object placement function of the control device 140 places a plurality of different types of target candidates in the target object undetectable area. For example, in the second embodiment, the object candidate placement function includes an object candidate modeled on a four-wheeled vehicle and an object candidate modeled on a two-wheeled vehicle, or an object candidate modeled on a four-wheeled vehicle and a pedestrian. Are combined with candidate objects and the like as models, and placed in the target object undetectable region. In the following description, an object candidate modeled on a four-wheel vehicle will be described as a first object candidate, and an object candidate modeled on a moving body other than a four-wheeled vehicle will be described as a second object candidate.

  Specifically, the object candidate arrangement function firstly, as in the first embodiment, the arrangement start position of the first object candidate modeled on a four-wheeled vehicle based on the moving speed of the object on the object road. And the arrangement | positioning space | interval D is determined, and based on the determined arrangement | positioning start position and arrangement | positioning space | interval D, a 1st target object candidate is arrange | positioned in a target object undetectable area | region.

  In the second embodiment, the object candidate placement function determines whether or not the target road satisfies a predetermined condition. When the target road satisfies the predetermined condition, the target object placement function is in accordance with the condition that the target road satisfies. The second object candidate is determined, and the determined second object candidate is placed in the object detection unusable area.

  For example, when the object candidate placement function satisfies the condition that the target road is a side road L2 that the driver cannot overlook as shown in FIG. 3 as shown in FIG. A second object candidate T3 modeled on a two-wheeled vehicle is arranged on the side (vehicle width direction side) of the first object candidate T1 modeled on a wheeled vehicle. This is because, for example, when the leading vehicle on the side road L2 stops at the side road L2 and enters the road L1 before entering the road L1 on which the host vehicle travels, the motorcycle becomes the leading vehicle. This is because it is assumed that the vehicle passes through the side of the following vehicle and moves to the side of the leading vehicle on the side road L2.

  Further, as shown in FIG. 7, the object candidate placement function satisfies the condition that the target road is a road L1 in front of the host vehicle V1 and the preceding vehicle V2 existing on the target road is a parked vehicle. In this case, a second object candidate T4 modeled on a pedestrian is placed behind the parked vehicle V2 (back side). In addition, the object candidate placement function is stopped when the condition that the target road is a road ahead of the host vehicle V1 and the preceding vehicle V2 existing on the target road is a stopped bus is satisfied. A second object candidate T4 modeled on a pedestrian is arranged behind the bus V2 (back side). In the second embodiment, for example, candidate objects having shapes and sizes that model a four-wheeled vehicle, a two-wheeled vehicle, a pedestrian, and the like are stored in the ROM included in the control device 140. A second object candidate modeled on a four-wheeled vehicle, a two-wheeled vehicle, a pedestrian, or the like can be arranged according to the conditions satisfied by the road.

  Furthermore, the object candidate arrangement function determines an arrangement interval W between the object or the first object candidate and the second object candidate when the second object candidate is arranged. Specifically, as shown in FIG. 7, the object candidate placement function includes a first object candidate T1 modeled on a four-wheeled vehicle and a second object candidate T3 modeled on a two-wheeled vehicle on the target road L2. In the case of arrangement, the arrangement interval W1 between the first object candidate T1 modeled on a four-wheeled vehicle and the second object candidate T3 modeled on a two-wheeled vehicle can be set to 1 m in the vehicle width direction, for example. This is because the actual distance between the two-wheeled vehicle and the four-wheeled vehicle in the vehicle width direction can be assumed to be about 50 cm to 1 m in a scene where the two-wheeled vehicle passes alongside the succeeding vehicle and is lined up next to the leading vehicle. Further, as shown in FIG. 7, the object candidate placement function places a first object candidate T2 modeled on a four-wheeled vehicle and a second object candidate T4 modeled on a pedestrian on the target road L1. In this case, the arrangement interval W2 of the second object candidate T4 can be set to, for example, 1 m from the preceding vehicle V2 to the back side.

  In addition, in the second embodiment, the object candidate placement function can change the size of the first object candidate and the second object candidate depending on the type of the target road. For example, when the target road is a late-night bypass road, the target object candidate placement function can increase the size of the first target object candidate to a size modeled on a truck. This is because large-scale trucks tend to travel frequently on late-night bypass roads. The object candidate placement function can also set the size of the second object candidate to be the size of a large motorcycle larger than, for example, a bicycle or a pedestrian when the target road is an expressway. .

  Subsequently, an object detection process according to the second embodiment will be described with reference to FIGS. 8 and 9. 8 and 9 are flowcharts showing the object detection process according to the second embodiment. The object detection process described below is executed by the control device 140 as in the first embodiment.

  As shown in FIG. 8, in steps S101 to S108, processing similar to that in the first embodiment is performed. That is, information on the object existing around the host vehicle and vehicle information of the host vehicle are acquired (steps S101 and S102). In addition, a movement range in which the host vehicle can move in the near future is set (step S103), and a target road is set from roads existing in the movement range (step S104). Furthermore, the movement speed of the target object on the target road is acquired (step S105), and the target non-detectable area where the target cannot be detected is detected (step S106). Based on the moving speed of the object on the target road, the arrangement interval D of the first object candidates is determined (step S107), and the arrangement start position of the first object candidates is determined (step S108). .

  In subsequent step S201, the target road attribute information is acquired by the target candidate placement function. For example, in the target object placement function, the target road is a side road connected to the road on which the host vehicle travels, or the road on which the host vehicle travels, and the road ahead of the host vehicle in the traveling direction. Get information such as whether or not. In addition, the target candidate placement function, whether the target road is a road on which the host vehicle is traveling and a road ahead of the traveling direction of the host vehicle, whether or not there is a parked vehicle on the target road, Alternatively, information on whether or not there is a stopped bus on the target road is acquired. Furthermore, the object candidate placement function also acquires information such as whether the target road is a late-night bypass road or an expressway.

  In step S202, the object candidate placement function determines whether the target road satisfies a predetermined condition based on the attribute information of the target road acquired in step S201. For example, as shown in FIG. 7, the object candidate placement function determines whether or not a condition that the target road is a side road L2 that cannot be overlooked by a wall or a fence of a building is satisfied. Further, as shown in FIG. 7, the object candidate placement function is such that the target road is a road L1 in front of the host vehicle V1 on which the host vehicle V1 travels, and the preceding vehicle V2 existing on the target road is a parked vehicle. Alternatively, it is determined whether or not the condition that the bus is stopped is satisfied. If the target road satisfies the predetermined condition, the process proceeds to step S203. If the target road does not satisfy the predetermined condition, the process proceeds to step S109.

  In step S203, a second candidate candidate corresponding to a condition satisfied by the target road is determined by the target candidate placement function. For example, when the object candidate placement function satisfies the condition that the target road is a side road L2 that cannot be overlooked by a wall or a fence of a building, as shown in FIG. It is determined that the second object candidate modeled on the two-wheeled vehicle is arranged on the side of the first object candidate modeled on the four-wheeled vehicle. Further, the object candidate placement function is such that the target road is a road L1 in front of the host vehicle V1 on which the host vehicle V1 travels, and the preceding vehicle V2 existing on the target road is a parked vehicle or a stopped bus. When satisfy | filling, it determines that the 2nd target object model which made a pedestrian a model is arrange | positioned behind the parked vehicle V2 or the bus | bath V2 stopped (back side).

  In step S204, the size and shape of the second target object candidate are determined based on the conditions satisfied by the target road by the target object candidate placement function. For example, when the object candidate placement function determines to place a second object candidate modeled on a four-wheeled vehicle, a two-wheeled vehicle, a pedestrian, etc., the size and shape of each second object candidate are set. Determine the size and shape of a model such as a four-wheeled vehicle, two-wheeled vehicle, or pedestrian.

  Further, in step S205, the arrangement interval W of the second object candidates is determined by the object candidate arrangement function based on the conditions satisfied by the object road. For example, as shown in FIG. 7, the object candidate placement function includes a first object candidate T1 modeled on a four-wheeled vehicle and a second object candidate T3 modeled on a two-wheeled vehicle on a target road L2 that is a side road. , The arrangement interval W1 between the first object candidate T1 modeled on a four-wheeled vehicle and the second object candidate T3 modeled on a two-wheeled vehicle can be set to 1 m in the vehicle width direction. .

  In step S206, the first object candidate and the second object candidate are arranged in the object non-detectable area by the object candidate arrangement function. Specifically, the object candidate arrangement function arranges the first object candidates with the arrangement interval D determined in step S107 in the direction along the lane from the arrangement start position determined in step S108. In addition, the object candidate placement function uses the second object candidate determined in step S203 from the position of the object or the first object candidate in the size and shape determined in step S204. The object candidates are arranged apart by an arrangement interval W.

  For example, when the target road is a side road L2 that cannot be overlooked by a building or a fence as shown in FIG. 7, the object candidate placement function is a first object having a shape and size modeled on a four-wheeled vehicle. An object candidate T1 and a second object candidate T3 having a shape and size modeled on a two-wheeled vehicle are arranged with an arrangement interval W1 of 1 m in the vehicle width direction. Further, as shown in FIG. 7, the object candidate placement function is such that the target road is a road ahead of the host vehicle V1 among the roads traveled by the host vehicle V1, and the preceding vehicle V2 existing on the target road is parked. In the case of a vehicle or a stopped bus, the second object candidate T2 having a shape and size modeled on a pedestrian is placed 1 m from the preceding vehicle V2 on the far side (opposite to the host vehicle V1), for example. It arrange | positions at intervals W2.

  Furthermore, in step S207, the size and shape of the first object candidate and the second object candidate are changed based on the type of the target road by the object candidate placement function. For example, when the target road is a late-night bypass road, the target object candidate placement function can increase the size of the first target object candidate to a size modeled on a truck. Further, the object candidate placement function can make the size of the second object candidate larger than the size of a bicycle or a pedestrian when the target road is an expressway.

  When it is determined in step S202 that the target road does not satisfy the predetermined condition, the process proceeds to step S109, and only the first target candidate is included in the target object non-detectable area, as in the first embodiment. Will be placed. Also in this case, in the subsequent step S207, the size and shape of the first object candidate are changed according to the type of the target road.

  As described above, in the second embodiment, when the target road satisfies a predetermined condition, a second target candidate of a type different from the first target candidate is determined according to the condition satisfied by the target road. The second target object candidate is arranged in the target object undetectable area together with the first target object candidate. That is, when the target road satisfies a predetermined condition, a plurality of different types of target candidates are arranged in the target object non-detectable area. Thereby, in 2nd Embodiment, in addition to the effect of 1st Embodiment, it becomes possible to adapt the arrangement | positioning of the object candidate in a target object undetectable area | region by the arrangement | positioning of the target object in an actual road. As a result, drivers can more accurately detect situations caused by multiple different objects, such as a two-wheeled vehicle jumping out from behind a four-wheeled vehicle and a pedestrian jumping out from behind a parked vehicle or parked bus. It can be presented.

  In the second embodiment, when the target road is a late-night bypass or an expressway, the size of the target in the target non-detectable area is increased. In this way, by changing the size of the candidate object in the undetectable area of the target road based on the type of the target road, the size of the target candidate on the target road is changed to the size of the target object actually traveling on the target road. It can be adapted according to the size.

  The embodiment described above is described for facilitating understanding of the present invention, and is not described for limiting the present invention. Therefore, each element disclosed in the above embodiment is intended to include all design changes and equivalents belonging to the technical scope of the present invention.

  For example, in the above-described embodiment, as the moving speed of the target object on the target road is faster, the arrangement density of the target object candidates is reduced by increasing the arrangement interval of the target object candidates. For example, the arrangement density of the object candidates may be increased by increasing the size of the object candidates as the moving speed of the object on the object road increases. Moreover, it is good also as a structure which estimates the moving speed of the target object in a target road based on the classification of a target road. For example, when the target road is a narrow street, the speed that is slower than when the target road is a general road is acquired as the moving speed of the target object on the target road, and when the target road is a highway, the target road It can be set as the structure which acquires a speed faster than the case where a road is a general road as a moving speed of the target object in a target road.

  Further, in the above-described embodiment, among the roads existing in the movement range, all the roads where the own vehicle may move in the near future, and other vehicles can enter the road where the own vehicle travels in the near future. Although the configuration in which all the roads having characteristics are set as target roads is illustrated, the present invention is not limited to this configuration, and only the roads that are likely to approach the host vehicle and the target object are set as target roads. be able to. For example, a side road with relatively good visibility from the position of the host vehicle may be excluded from the target road, and a road that can overlook the host vehicle from other vehicles existing on the side road can also be excluded from the target road.

  Further, in the above-described embodiment, the configuration in which the road L1 in front of the host vehicle and the road L2 connected to the road on which the host vehicle is traveling is set as the target road among the roads on which the host vehicle travels. For example, the road behind the host vehicle among the roads on which the host vehicle travels may be set as the target road. In this case, a four-wheeled vehicle, a two-wheeled vehicle, or the like hidden behind a subsequent vehicle traveling immediately after the host vehicle can be arranged as a candidate object. Alternatively, only the road L2 connected to the road on which the host vehicle travels may be set as the target road, or all roads included in the movement range may be set as the target road.

  In addition, in the second embodiment described above, object candidates modeled on a four-wheeled vehicle are exemplified as the first object candidates, and object candidates modeled on a two-wheeled vehicle or a pedestrian are exemplified as the second object candidates. However, the present invention is not limited to this configuration. For example, the first object candidate may be an object candidate modeled on a two-wheeled vehicle or a pedestrian, and the second object candidate may be a four-wheeled vehicle as a model. It may be a candidate object.

  The object detection sensor 110 of the above-described embodiment is the object detection means of the present invention, the area detection function of the control device 140 is the area detection means of the present invention, and the object road setting function of the control apparatus 140 is the object of the present invention. In the setting means, the speed information acquisition function of the control device 140 corresponds to the acquisition means of the present invention, and the object candidate placement function of the control device 140 corresponds to the placement means of the present invention.

DESCRIPTION OF SYMBOLS 100 ... Object detection apparatus 110 ... Object detection sensor 120 ... Own vehicle position detection apparatus 130 ... Map database 140 ... Control apparatus

Claims (9)

  1. Object detection means for detecting an object present around the moving body;
    An area detection unit that detects, as an undetectable area, an area in which the object detection unit cannot detect the object among the areas around the moving body;
    Setting means for setting a road existing around the moving body as a target road;
    Obtaining means for obtaining information on the moving speed of the object on the target road;
    When the non-detectable area exists on the target road, the arrangement density of the candidate objects in the non-detectable area is determined based on the moving speed of the target object on the target road, and the arrangement density of the target candidates based on, and a placement means for placing the object candidate to the undetectable region,
    The setting means sets at least one of a road on which the moving body moves and a road connected to the road as the target road .
  2. Object detection means for detecting an object present around the moving body;
    An area detection unit that detects, as an undetectable area, an area in which the object detection unit cannot detect the object among the areas around the moving body;
    Setting means for setting a road existing around the moving body as a target road;
    Obtaining means for obtaining information on the moving speed of the object on the target road;
    When the non-detectable area exists on the target road, the arrangement density of the candidate objects in the non-detectable area is determined based on the moving speed of the target object on the target road, and the arrangement density of the target candidates An arrangement means for arranging the candidate object in the non-detectable region based on
    The object detection apparatus according to claim 1, wherein the placement unit lowers the placement density of the object candidates in the non-detectable region of the target road as the moving speed of the object on the target road increases.
  3. The object detection device according to claim 2,
    The arrangement means decreases the arrangement density of the object candidates by increasing the arrangement interval of the object candidates in the non-detectable area of the object road as the moving speed of the object on the object road increases. An object detection apparatus characterized by:
  4. The object detection device according to claim 3,
    When the non-detectable area exists on the target road, the placement unit determines a placement start position of the target object candidate in the non-detectable area based on the attribute information of the target road, and An object detection apparatus that arranges the object candidates at an arrangement interval of the object candidates from an arrangement start position.
  5. Object detection means for detecting an object present around the moving body;
    An area detection unit that detects, as an undetectable area, an area in which the object detection unit cannot detect the object among the areas around the moving body;
    Setting means for setting a road existing around the moving body as a target road;
    Obtaining means for obtaining information on the moving speed of the object on the target road;
    When the non-detectable area exists on the target road, the arrangement density of the candidate objects in the non-detectable area is determined based on the moving speed of the target object on the target road, and the arrangement density of the target candidates An arrangement means for arranging the candidate object in the non-detectable region based on
    The acquisition unit acquires the legal speed of the target road as a moving speed of the target on the target road.
  6. Object detection means for detecting an object present around the moving body;
    An area detection unit that detects, as an undetectable area, an area in which the object detection unit cannot detect the object among the areas around the moving body;
    Setting means for setting a road existing around the moving body as a target road;
    Obtaining means for obtaining information on the moving speed of the object on the target road;
    When the non-detectable area exists on the target road, the arrangement density of the candidate objects in the non-detectable area is determined based on the moving speed of the target object on the target road, and the arrangement density of the target candidates An arrangement means for arranging the candidate object in the non-detectable region based on
    The acquisition means acquires the statistical value of the moving speed of the object on the target road as the moving speed of the object on the target road.
  7. Object detection means for detecting an object present around the moving body;
    An area detection unit that detects, as an undetectable area, an area in which the object detection unit cannot detect the object among the areas around the moving body;
    Setting means for setting a road existing around the moving body as a target road;
    Obtaining means for obtaining information on the moving speed of the object on the target road;
    When the non-detectable area exists on the target road, the arrangement density of the candidate objects in the non-detectable area is determined based on the moving speed of the target object on the target road, and the arrangement density of the target candidates An arrangement means for arranging the candidate object in the non-detectable region based on
    The object detection device according to claim 1, wherein the placement unit changes a size of the object candidate in a non-detectable region of the target road based on a type of the target road.
  8. Object detection means for detecting an object present around the moving body;
    An area detection unit that detects, as an undetectable area, an area in which the object detection unit cannot detect the object among the areas around the moving body;
    Setting means for setting a road existing around the moving body as a target road;
    Obtaining means for obtaining information on the moving speed of the object on the target road;
    When the non-detectable area exists on the target road, the arrangement density of the candidate objects in the non-detectable area is determined based on the moving speed of the target object on the target road, and the arrangement density of the target candidates An arrangement means for arranging the candidate object in the non-detectable region based on
    When the target road satisfies a predetermined condition, the placement means places a plurality of different types of target candidates according to the condition in a non-detectable region of the target road ,
    The predetermined condition is a road that is connected to a road on which the moving body moves and cannot be overlooked by an occupant of the moving body, or a road on which the moving body moves and is parked in front of the moving body. An object detection apparatus characterized by being a road on which a vehicle or a stopped bus exists .
  9. A region in which the object cannot be detected by a sensor that detects an object existing around the moving body is detected as a non-detectable area, and the road on which the moving body moves, If the set as a target road at least one of the roads that connect to the road, to acquire information of the moving speed of the object in the target road, the undetectable region in the target road is present, the target road Based on the moving speed of the target object in, determine the density of target object placement in the non-detectable region, and place the target candidate in the non-detectable region based on the determined target candidate placement density An object detection method characterized by:
JP2014255922A 2014-12-18 2014-12-18 Object detection apparatus and object detection method Active JP6476828B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2014255922A JP6476828B2 (en) 2014-12-18 2014-12-18 Object detection apparatus and object detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2014255922A JP6476828B2 (en) 2014-12-18 2014-12-18 Object detection apparatus and object detection method

Publications (2)

Publication Number Publication Date
JP2016115311A JP2016115311A (en) 2016-06-23
JP6476828B2 true JP6476828B2 (en) 2019-03-06

Family

ID=56141863

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2014255922A Active JP6476828B2 (en) 2014-12-18 2014-12-18 Object detection apparatus and object detection method

Country Status (1)

Country Link
JP (1) JP6476828B2 (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003154873A (en) * 2001-11-20 2003-05-27 Nissan Motor Co Ltd Travel control device for vehicle
JP4400584B2 (en) * 2006-03-01 2010-01-20 トヨタ自動車株式会社 Obstacle detection method and obstacle detection device
JP5440149B2 (en) * 2009-12-18 2014-03-12 凸版印刷株式会社 Image display body, blank medium and personal authentication medium
JP5625603B2 (en) * 2010-08-09 2014-11-19 トヨタ自動車株式会社 Vehicle control device, vehicle control system, and control device

Also Published As

Publication number Publication date
JP2016115311A (en) 2016-06-23

Similar Documents

Publication Publication Date Title
US10162355B2 (en) Road model management based on selective feedback
US20100030474A1 (en) Driving support apparatus for vehicle
DE102009012917B4 (en) Obstacle detection device for vehicles
DE102015202367A1 (en) Autonomic control in a sealed vehicle environment
JP2006085285A (en) Dangerous vehicle prediction device
JP5505427B2 (en) Collision position prediction device
US9140792B2 (en) System and method for sensor based environmental model construction
US7840331B2 (en) Travel support system and travel support method
EP2002210B1 (en) A driving aid system for creating a model of surroundings of a vehicle
JP6325670B2 (en) Lane selection device, vehicle control system, and lane selection method
JP5939357B2 (en) Moving track prediction apparatus and moving track prediction method
KR20090125795A (en) Safe driving assisting device
US9864918B2 (en) Predicting vehicle movements based on driver body language
JP2011013039A (en) Lane determination device and navigation system
US10507807B2 (en) Systems and methods for causing a vehicle response based on traffic light detection
US9983591B2 (en) Autonomous driving at intersections based on perception data
DE102008007481A1 (en) A collision avoidance system and method for detecting transfer locations using a data merge
JP5429380B2 (en) Driving assistance device
EP2884476A1 (en) Object detection apparatus and driving assistance apparatus
EP3021305B1 (en) Alerting apparatus
EP2492888A2 (en) Lane departure warning apparatus and system
EP2549457B1 (en) Vehicle-mounting vehicle-surroundings recognition apparatus and vehicle-mounting vehicle-surroundings recognition system
CN104691447B (en) System and method for dynamically focusing on vehicle sensors
EP3048022B1 (en) Collision avoidance control system and control method
DE102017100199A1 (en) Pedestrian recognition with ticket cards

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20171030

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20180731

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20180725

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20180928

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20190108

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20190121

R151 Written notification of patent or utility model registration

Ref document number: 6476828

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R151