WO2021094800A1 - 信号機認識方法及び信号機認識装置 - Google Patents
信号機認識方法及び信号機認識装置 Download PDFInfo
- Publication number
- WO2021094800A1 WO2021094800A1 PCT/IB2019/001270 IB2019001270W WO2021094800A1 WO 2021094800 A1 WO2021094800 A1 WO 2021094800A1 IB 2019001270 W IB2019001270 W IB 2019001270W WO 2021094800 A1 WO2021094800 A1 WO 2021094800A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- threshold value
- traffic light
- result
- determination result
- display
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/09623—Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096855—Systems involving transmission of navigation instructions to the vehicle where the output is provided in a suitable form to the driver
Definitions
- the present invention relates to a traffic light recognition method and a traffic light recognition device.
- Patent Document 1 in order to avoid a situation in which a traffic light controlled to be lit is erroneously determined to be controlled to be turned off or blinking, the traffic light is turned off in a predetermined number of consecutive captured images.
- a technique has been proposed in which it is determined that the traffic light is off or blinking based on whether or not the number of captured images determined to be off exceeds the threshold value.
- the present invention has been made in view of the above problems, and an object of the present invention is from the actual transition of the display state of a traffic signal to the start of the process corresponding to the display state after the transition. It is an object of the present invention to provide a traffic light recognition method and a traffic light recognition device capable of determining a display state of a traffic light by referring to a plurality of images arranged in a time series while suppressing a delay time and recognizing the traffic light.
- the traffic light recognition method and the traffic light recognition device are obtained by determining the display state of the traffic light based on a plurality of images of the traveling direction of the vehicle.
- a result string consisting of multiple judgment results in chronological order is acquired, and the latest specific judgment result among the judgment results constituting the result row is a permission display that allows the passage of the stop line corresponding to the traffic light.
- the determination result is that the first threshold value is set to the number threshold value, and the specific determination result is other than the determination result that the display state is the permission display, it is smaller than the first threshold value.
- the second threshold value is set to the number threshold value, and when the number of determination results having the same as the specific determination result is larger than the number threshold value, the specific determination result is output.
- a plurality of images arranged in chronological order can be displayed while suppressing the delay time from the actual transition of the display state of the traffic light to the start of the process corresponding to the display state after the transition. It is possible to determine the display state of the traffic light by referring to it and recognize the traffic light.
- FIG. 1 is a block diagram showing a configuration of a traffic light recognition device according to an embodiment of the present invention.
- FIG. 2 is a flowchart showing a processing procedure of the traffic light recognition device according to the embodiment of the present invention.
- FIG. 3 is a flowchart showing a modified example of the processing procedure of the traffic signal recognition device according to the embodiment of the present invention.
- FIG. 4 is a diagram showing an example of a result sequence composed of a plurality of determination results in chronological order.
- FIG. 5A is a diagram showing a first example of a change in the output value corresponding to the result sequence.
- FIG. 5B is a diagram showing a second example of the change in the output value corresponding to the result sequence.
- FIG. 1 is a block diagram showing a configuration of a traffic light recognition device according to the present embodiment.
- the traffic light recognition device according to the present embodiment includes an imaging unit 71 and a controller 100, and the controller 100 includes an imaging unit 71, an in-vehicle sensor 73, and map information by a wired or wireless communication path. It is connected to the acquisition unit 75 and the vehicle control device 400.
- the image pickup unit 71, the vehicle-mounted sensor 73, and the vehicle control device 400 are mounted on a vehicle (not shown), but the map information acquisition unit 75 and the controller 100 may be mounted on the vehicle or the vehicle. It may be installed outside the.
- the imaging unit 71 captures an image of the vehicle in the traveling direction.
- the image pickup unit 71 is a digital camera provided with a solid-state image sensor such as a CCD or CMOS, and images the surroundings of the vehicle to acquire a digital image of the peripheral region.
- the imaging unit 71 images a predetermined range around the vehicle by setting the focal length, the angle of view of the lens, the vertical and horizontal angles of the camera, and the like.
- the captured image captured by the imaging unit 71 is output to the controller 100 and stored in a storage unit (not shown) for a predetermined period of time.
- the imaging unit 71 acquires captured images at predetermined time intervals, and the captured images acquired at predetermined time intervals are stored in the storage unit as past images.
- the past image may be deleted after a predetermined period has elapsed from the time when the past image was captured.
- the in-vehicle sensor 73 includes an object detection sensor mounted on the vehicle, such as a laser radar, a millimeter wave radar, and a camera, which detects an object existing around the vehicle.
- the in-vehicle sensor 73 may include a plurality of different types of object detection sensors.
- the in-vehicle sensor 73 detects the environment around the vehicle. For example, the in-vehicle sensor 73 detects a moving object including another vehicle, a motorcycle, a bicycle, a pedestrian, and a stationary object including a stopped vehicle, and the position, posture, size, speed, and acceleration of the moving object and the stationary object with respect to the vehicle. , Deceleration, yaw rate, etc. may be detected.
- the in-vehicle sensor 73 may output, for example, the behavior of a two-dimensional object in a zenith view (also referred to as a plan view) viewed from the air above the vehicle as a detection result.
- the in-vehicle sensor 73 may detect a sign (a road sign or a sign displayed on the road surface), a guide rail, or the like existing around the vehicle.
- the vehicle-mounted sensor 73 may detect the slipperiness of the road surface in the lane in which the vehicle is traveling by detecting the rotation speed and the difference in rotation speed of the wheels provided in the vehicle.
- the in-vehicle sensor 73 detects the state of the vehicle in addition to the environment around the vehicle.
- the in-vehicle sensor 73 may detect the moving speed of the vehicle (moving speed in the front-rear direction, left-right direction, turning speed), the steering angle of the wheels provided in the vehicle, and the changing speed of the steering angle. ..
- the in-vehicle sensor 73 uses a position detection sensor that measures the absolute position of the vehicle, such as a position detection sensor that measures the absolute position of the vehicle such as GPS (Global Positioning System) and odometry, and uses an absolute position of the vehicle, that is, , May include sensors that measure the position, attitude and speed of the vehicle relative to a given reference point.
- a position detection sensor that measures the absolute position of the vehicle
- GPS Global Positioning System
- odometry uses an absolute position of the vehicle, that is, May include sensors that measure the position, attitude and speed of the vehicle relative to a given reference point.
- the map information acquisition unit 75 acquires map information indicating the structure of the road on which the vehicle travels.
- the map information acquired by the map information acquisition unit 75 includes road structure information such as absolute lane positions, lane connection relationships, and relative positional relationships. Further, the map information acquired by the map information acquisition unit 75 may include facility information such as a parking lot and a gas station. In addition, the map information may include the position information of the traffic light, the type of the traffic light, the position of the stop line corresponding to the traffic light, and the like.
- the map information acquisition unit 75 may own a map database that stores the map information, or may acquire the map information from an external map data server by cloud computing. Further, the map information acquisition unit 75 may acquire map information by using vehicle-to-vehicle communication and road-to-vehicle communication.
- the vehicle control device 400 controls a vehicle (not shown) based on the recognition result of the traffic light obtained by the controller 100.
- the vehicle control device 400 may drive the vehicle by automatic driving according to a predetermined traveling route, or may support the driving operation of the occupants of the vehicle.
- the vehicle control device 400 may be a notification device that notifies the occupants of the vehicle of the recognition result of the traffic light.
- the controller 100 (an example of a control unit or a processing unit) is a general-purpose microcomputer including a CPU (central processing unit), a memory, and an input / output unit.
- a computer program (traffic light recognition program) for functioning as a part of the traffic light recognition device is installed in the controller 100. By executing the computer program, the controller 100 functions as a plurality of information processing circuits (150, 155, 160, 180, 190) included in the traffic signal recognition device.
- a plurality of information processing circuits (150, 155, 160, 180, 190) included in the traffic signal recognition device are realized by software.
- information processing circuits (150, 155, 160, 180, 190) may be configured by individual hardware.
- the information processing circuit (150, 155, 160, 180, 190) may also be used as an electronic control unit (ECU) used for other control related to the vehicle.
- ECU electronice control unit
- the controller 100 includes a determination unit 150, a determination result storage unit 155, a threshold value setting unit 180, an output determination unit 190, and an output unit 160 as a plurality of information processing circuits (150, 155, 160, 180, 190).
- the determination unit 150 sets the detection area corresponding to the traffic light on the image captured by the image pickup unit 71.
- the "detection area” means an area in the image where a traffic light is presumed to be present.
- the position of the traffic light reflected in the imaging range in the image can be estimated based on the imaging direction of the imaging unit 71, the position and orientation of the vehicle at the time of imaging, and the position of the traffic light.
- the determination unit 150 sets, for example, a partial region of the captured image, which includes the estimated position of the traffic light in the image, as the detection region.
- the determination unit 150 executes image processing on the detection area, detects the traffic light in the detection area, and determines the display state of the traffic light.
- the determination unit 150 detects a traffic light by, for example, template matching.
- template matching a standard traffic light image is used as a template, and the detection area is scanned while shifting the image by one pixel, for example, the correlation of the brightness distribution is calculated. Then, when the correlation becomes the highest value, it is detected that the traffic light is at the position on the image where the template is located.
- the "color signal” indicated by the traffic light includes “green light”, “yellow light”, and “red light”.
- the meaning of "color signal” is determined by the traffic regulations that the vehicle should follow. For example, “green light” means “may proceed” and “red light” means “stop at the stop position”.
- the “yellow traffic light” represents the meaning of “stop at the stop position unless it is not possible to stop safely because it is close to the stop position”.
- the traffic light may indicate not only a “color signal” but also an “arrow signal” indicating the direction permitted to the vehicle at the intersection where the traffic light is installed. Examples include a “right turn signal”, a “straight ahead signal”, and a “left turn signal”.
- the “arrow signal” is not limited to the “right turn signal”, “straight ahead signal”, and “left turn signal”, and various variations can be considered depending on the structure of the intersection where the traffic light is installed.
- the meaning of the "arrow signal” is determined by the traffic regulations that the vehicle should obey.
- the determination unit 150 executes image processing on the detection area and determines the lighting state of the "color signal” and the "arrow signal” of the traffic light as the display state of the traffic light.
- the image processing of the traffic light detection by the determination unit 150 may use machine learning such as a support vector machine or a neural network.
- the recognition rate can be improved by preparing a learning database in which templates of traffic lights of different sizes are stored in advance and using a learning database to be referred to according to the distance to the traffic light.
- the determination result storage unit 155 stores the display state of the traffic light determined by the determination unit 150. Specifically, the determination unit 150 sequentially determines the plurality of images acquired by the imaging unit 71 in chronological order, and the obtained determination results are sequentially determined by the determination result storage unit 155 from the determination unit 150. get. Then, the determination result storage unit 155 stores a plurality of determination results in chronological order as a result sequence.
- FIG. 4 is a diagram showing an example of a result sequence composed of a plurality of determination results in chronological order.
- the judgment results obtained by the judgment unit 150 are "green light”, “yellow light”, “red light”, and “unknown” (judgment result that the displayed state is unknown). It is assumed that there are four types.
- the determination results “green light”, “yellow light”, “red light”, and “unknown” are indicated by symbols “G”, “Y”, “R”, and “ ⁇ ”, respectively.
- the reason why the determination result by the determination unit 150 is "unknown” is, for example, the flicker phenomenon (when the traffic light lamp is a lamp that blinks periodically like an LED lamp, the imaging timing by the imaging unit 71).
- the number N of judgment results stored by the judgment result storage unit 155 is preset. That is, the number N of the determination results constituting the result sequence is preset as a predetermined number larger than the number threshold NC.
- Subscripts from 0 to N-1 are added to each of the N determination results stored by the determination result storage unit 155.
- the determination result of the subscript 0 is the latest determination result obtained by the determination unit 150, and means that as the number of subscripts assigned to the determination result increases, the determination result becomes older in order.
- the judgment result storage unit 155 increases the subscript given to the judgment result by 1, and the new judgment result input to the judgment result storage unit 155 is used. Add subscript 0. The determination result in which the subscript is N is deleted.
- the determination result storage unit 155 stores the determination results with subscripts from 0 to N-1 as a result sequence.
- the determination result storage unit 155 may have a determination result complementing function. Specifically, when "unknown” is included in the determination results constituting the result sequence stored in the determination result storage unit 155, the determination result immediately before the “unknown” and the “unknown” are included. Based on the determination result immediately after, the "unknown" determination result may be replaced.
- the determination result of the subscript 2 is "unknown".
- the determination result storage unit 155 refers to the determination result of the subscript 3 immediately before the determination result of the subscript 2 and the determination result of the subscript 1 immediately after the determination result of the subscript 2.
- the determination result of the subscript 1 and the determination result of the subscript 3 are both "yellow traffic lights”. Therefore, the determination result of the subscript 2 may not be “unknown” but may be a "yellow signal" which is the determination result of the subscript 3 immediately before the determination result of the subscript 2.
- the determination result storage unit 155 extracts the determination result that the display state is unknown from the determination results constituting the result sequence as the first determination result, and among the determination results constituting the result sequence.
- the judgment result immediately before the first judgment result and the judgment result immediately after the first judgment result from the judgment results excluding the judgment result that the displayed state is unknown are the second judgment results, respectively.
- the first determination result in the result column may be replaced with the second determination result.
- the above-mentioned determination result complementing function by the determination result storage unit 155 is effective for improving the recognition accuracy of the traffic light. ..
- the number of determination results stored in the determination result storage unit 155 is N, but the present invention is not limited to this.
- the determination result storage unit 155 may determine whether or not to store the determination result based on the imaging time of the image that is the source of the determination result, instead of the number of determination results. More specifically, the determination result storage unit 155 erases the determination result corresponding to the captured image in which a predetermined time or more has passed since the image was taken, and the determination result stored in the determination result storage unit 155 is currently. It may be only those corresponding to the images captured up to a predetermined time in the past.
- the number of determination results stored in the determination result storage unit 155 may be limited based on the number N or the predetermined time. The result is the same.
- the result may change depending on whether the image is limited based on the number N or the predetermined time.
- the number of determination results to be stored is limited based on the number N or a predetermined time, it can be adopted as the configuration of the determination result storage unit 155.
- the threshold value setting unit 180 sets the number threshold value NC, which is a value used in the output determination unit 190 described later, based on the display state of the traffic light (threshold value setting process).
- the number threshold NC is set to a predetermined initial value when the controller 100 is started for the first time, and is subsequently updated by the threshold setting unit 180.
- the threshold value setting unit 180 refers to the latest determination result among the determination results constituting the result sequence stored in the determination result storage unit 155, and the latest determination result is the stop line corresponding to the traffic light.
- the permission display (“green light”) that permits the passage of the first threshold value
- the number threshold value NC is set.
- a second threshold value smaller than the first threshold value is set as the number threshold value NC.
- the threshold setting unit 180 displays the latest determination result as a prohibition display (“red light”) prohibiting the passage of the stop line, or after the permission display and before the prohibition display.
- the value of the number threshold NC may be set based on whether the display is an intermediate display (“yellow signal”).
- the threshold value setting unit 180 may set a third threshold value smaller than the first threshold value to the number threshold value NC when the latest determination result is a prohibited display. Further, the threshold value setting unit 180 sets the number threshold value NC to a second threshold value smaller than the third threshold value set in the case of the prohibited display when the latest determination result is the intermediate display. Good.
- the first threshold value, the second threshold value, and the third threshold value are determined based on the performance of the imaging unit 71, the length of the result sequence held by the determination result storage unit 155, the imaging cycle of the imaging unit 71, and the like. It may be one.
- the threshold value setting unit 180 determines that the traffic light is not lit by the determination unit 150 (when the latest determination result by the determination unit 150 is a determination result that the displayed state is unknown). May maintain the value of the number threshold NC that has already been set without setting the number threshold NC.
- the threshold value setting unit 180 resets the number threshold value NC to the initial value after the vehicle passes the stop line corresponding to the target traffic light.
- the output determination unit 190 determines the output value based on the number threshold value NC set by the threshold value setting unit 180 and the result sequence stored in the determination result storage unit 155. Specifically, the output determination unit 190 subscripts when the number of determination results that are the same as the latest determination result (determination result of subscript 0) among the determination results constituting the result sequence is larger than the number threshold NC. The determination result of 0 is used as the output value.
- the output determination unit 190 sets the previous output value when the number of determination results that are the same as the latest determination result (determination result of subscript 0) among the determination results constituting the result sequence is equal to or less than the number threshold value NC.
- the output value may be maintained as it is.
- FIG. 5A is a diagram showing a first example of a change in the output value corresponding to the result sequence.
- the number N of the determination results constituting the result sequence is 8 and the number threshold NC is 4. Further, it is assumed that the images acquired by the imaging unit 71 are from frame F001 to frame F010 in chronological order, and the determination result by the determination unit 150 is obtained for each frame. Further, in the example shown in FIG. 5A, it is assumed that the determination result complement function by the determination result storage unit 155 is disabled.
- the display of "G" on the left side of the result column means that the determination result of the determination unit 150 for frame F001 is "green light”. Further, the display of "G” on the right side of the result column means that the output value determined by the output determination unit 190 is "green light” when the determination result of the frame F001 is input to the result column. ..
- the other frames F002 to F010 are also displayed in the same manner.
- the output determination unit 190 maintains the output value as the "green light" which is the immediately preceding output value.
- the output value determined by the output determination unit 190 changes from "green signal” to "yellow signal” at the time of frame F010.
- the number of determination results that are the same as the determination result “Y” in the result column is 5, which is larger than the number threshold value NC. Therefore, the output determination unit 190 sets the output value as the “yellow signal” at the time of frame F010.
- FIG. 5B is a diagram showing a second example of the change in the output value corresponding to the result sequence.
- the number threshold value NC is 2.
- the output value determined by the output determination unit 190 changes from the “green signal” to the “yellow signal” at the time of frame F008.
- the time delay from the actual change of the display state of the traffic light to the change of the output value is 3 frames.
- the determination result complement function by the determination result storage unit 155 is enabled, when the determination result for the frame F007 is stored in the determination result storage unit 155, the determination result of the subscript 1 is displayed. Complementation is performed, and the determination result of the subscript 1 changes from "unknown" to "yellow light". As a result, the output value determined by the output determination unit 190 changes from the "green signal" to the "yellow signal" at the time of frame F007. In this case, the time delay from the actual change of the display state of the traffic light to the change of the output value is two frames.
- the threshold setting unit 180 sets the number threshold NC smaller in order to shorten the free running distance when the vehicle is closer to the stop line than when the vehicle is far from the stop line. Further, when the display state of the traffic light is a yellow signal or a red signal as compared with the case where the display state of the traffic light is a green signal, the threshold setting unit 180 is set to the number threshold NC in order to shorten the free running distance. It is desirable to set small.
- the output unit 160 outputs the output value determined by the output determination unit 190 as the display state of the traffic light.
- the display state of the traffic light is output from the output unit 160 to the vehicle control device 400 and used for controlling the vehicle.
- the display state of the traffic light may be output from the output unit 160 to a notification device (not shown) and notified to the occupant via the notification device.
- FIG. 2 is a flowchart showing a processing procedure of the traffic light recognition device according to the present embodiment.
- FIG. 3 is a flowchart showing a modified example of the processing procedure of the traffic signal recognition device according to the present embodiment.
- the traffic light recognition process shown in FIGS. 2 and 3 may be executed every time the image pickup unit 71 acquires an image, or after the image pickup unit 71 acquires the image, the image is transferred to the detection region. It may be executed every cycle in which the process is executed.
- step S107 the determination unit 150 determines the display state of the traffic light based on the image captured by the image pickup unit 71.
- step S109 the determination result storage unit 155 stores the display state of the traffic light determined by the determination unit 150.
- step S141 the threshold setting unit 180 determines whether or not the traffic light is lit. Specifically, it is determined whether or not the traffic light is lit by referring to the latest determination result in the result sequence stored in the determination result storage unit 155.
- step S141 When the traffic light is not lit (NO in step S141), the threshold setting unit 180 maintains the number threshold NC in step S145. If the traffic light is lit (YES in step S141), the process proceeds to step S142.
- step S142 the threshold value setting unit 180 determines whether or not the green light is lit. Specifically, it is determined whether or not the latest determination result is a permission display (“green light”) that permits the passage of the stop line corresponding to the traffic light.
- step S146 the threshold value setting unit 180 sets the first threshold value to the number threshold value NC.
- step S147 the threshold value setting unit 180 sets a second threshold value smaller than the first threshold value to the number threshold value NC.
- step S142 If the green light is not lit (NO in step S142), as shown in the flowchart of FIG. 3, the process proceeds to step S143 to determine whether or not the yellow light is lit. Good.
- the threshold value setting unit 180 sets the second threshold value to the number threshold value NC.
- the threshold value setting unit 180 may set a third threshold value smaller than the first threshold value to the number threshold NC.
- the third threshold may be smaller than the first threshold and larger than the second threshold.
- step S171 After the setting of the number threshold value NC is completed in step S145, step S146, step S147, and step S148, in step S171, the output determination unit 190 sets the output value based on the result sequence stored in the determination result storage unit 155. To determine.
- step S173 the output unit 160 outputs the display state of the traffic light determined by the output determination unit 190.
- the output state of the traffic light is used, for example, in the vehicle control device 400.
- the number threshold NC is sequentially updated by repeatedly executing the processes shown by the flowcharts of FIGS. 2 and 3.
- the traffic light recognition method and the traffic light recognition device are time series obtained by determining the display state of the traffic light based on a plurality of images of the traveling direction of the vehicle. It is said that the latest specific judgment result among the judgment results constituting the result row is the permission display that allows the passage of the stop line corresponding to the traffic light.
- a second threshold value smaller than the first threshold value is set when the first threshold value is set to the number threshold value and the specific judgment result is other than the judgment result that the display state is the permission display. Is set to the number threshold value, and when the number of judgment results that are the same as the specific judgment result is larger than the number threshold value, the specific judgment result is output.
- the plurality of images arranged in chronological order can be referred to. It is possible to determine the display state of the traffic light and recognize the traffic light. In particular, it is possible to suppress the delay time of recognition of the traffic light when the traffic light is in the display state other than the permission display as compared with the case where the traffic light is the permission display. As a result, it is possible to accelerate the start of processing corresponding to the display state other than the permission display (for example, processing for warning the occupant, processing for braking the vehicle, etc.).
- the traffic light recognition method and the traffic light recognition device are at least one of a permission display, a prohibition display prohibiting the passage of the stop line, and an intermediate display displayed after the permission display and before the prohibition display.
- the second threshold value may be set to the number threshold value when the specific determination result is the prohibition display or the intermediate display with respect to the traffic light that displays.
- the traffic light recognition method and the traffic light recognition device may set a third threshold value smaller than the first threshold value as the number threshold value when the specific determination result is a prohibited display. As a result, it is possible to suppress the delay time of the recognition of the traffic light when the traffic light is the prohibition display as compared with the case where the traffic light is the permission display.
- the second threshold value set may be smaller than the third threshold value.
- the result sequence may be composed of a predetermined number of determination results larger than the number threshold value.
- the traffic light recognition method and the traffic light recognition device extract the judgment result that the present state is unknown from the judgment results constituting the result row as the first judgment result, and form the result row.
- the judgment result immediately before the first judgment result and the judgment result immediately after the first judgment result are selected from the judgment results excluding the judgment result that the displayed state is unknown.
- the second judgment result and the third judgment result are extracted, and when the second judgment result and the third judgment result are the same, the first judgment result in the result column is replaced with the second judgment result. You may.
- Processing circuits include programmed processors, electrical circuits, etc., as well as devices such as application specific integrated circuits (ASICs) and circuit components arranged to perform the described functions. Etc. are also included.
- ASICs application specific integrated circuits
- Imaging unit 73 Imaging unit 73
- In-vehicle sensor 75 Map information acquisition unit 100
- Controller 150 Judgment unit 155
- Output unit 180 Threshold setting unit 190
- Output determination unit 400 Vehicle control device
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
図1は、本実施形態に係る信号機認識装置の構成を示すブロック図である。図1に示すように、本実施形態に係る信号機認識装置は、撮像部71と、コントローラ100とを備え、コントローラ100は、有線あるいは無線の通信路によって、撮像部71、車載センサ73、地図情報取得部75、車両制御装置400と接続されている。
次に、本実施形態に係る信号機認識装置による信号機認識の処理手順を、図2及び図3のフローチャートを参照して説明する。図2は、本実施形態に係る信号機認識装置の処理手順を示すフローチャートである。図3は、本実施形態に係る信号機認識装置の処理手順の変形例を示すフローチャートである。
以上詳細に説明したように、本実施形態に係る信号機認識方法及び信号機認識装置は、車両の進行方向を撮像した複数枚の画像に基づいて信号機の現示状態を判定して得られた時系列順の複数の判定結果からなる結果列を取得し、結果列を構成する判定結果のうち最新の特定判定結果が、現示状態は信号機に対応する停止線の通過を許可する許可表示であるとする判定結果である場合に、第1閾値を個数閾値に設定し、特定判定結果が、現示状態は許可表示であるとする判定結果以外である場合に、第1閾値よりも小さい第2閾値を個数閾値に設定し、特定判定結果と同一の判定結果の個数が個数閾値よりも多い場合に、特定判定結果を出力する。
73 車載センサ
75 地図情報取得部
100 コントローラ
150 判定部
155 判定結果記憶部
160 出力部
180 閾値設定部
190 出力決定部
400 車両制御装置
Claims (7)
- 車両に搭載された撮像部を用いて前記車両の進行方向にある信号機を複数回撮像して、複数の画像を取得し、
前記画像ごとに前記信号機の現示状態を判定して得られた時系列順の複数の判定結果からなる結果列を取得し、
前記結果列を構成する判定結果のうち最新の判定結果である特定判定結果に基づいて個数閾値を設定する際、
前記特定判定結果が、前記現示状態は前記信号機に対応する停止線の通過を許可する許可表示であるとする判定結果である場合に、第1閾値を前記個数閾値に設定し、
前記特定判定結果が、前記現示状態は前記許可表示であるとする判定結果以外である場合に、前記第1閾値よりも小さい第2閾値を前記個数閾値に設定し、
前記特定判定結果と同一の判定結果の個数が、前記個数閾値よりも多い場合に、前記特定判定結果を出力すること
を特徴とする信号機認識方法。 - 請求項1に記載の信号機認識方法であって、
前記許可表示、前記停止線の通過を禁止する禁止表示、前記許可表示の後であって前記禁止表示の前に表示される中間表示、の少なくともいずれかを表示する前記信号機に対して、
前記特定判定結果が、前記禁止表示または前記中間表示である場合に、前記第2閾値を前記個数閾値に設定すること
を特徴とする信号機認識方法。 - 請求項2に記載の信号機認識方法であって、
前記特定判定結果が前記禁止表示である場合に、前記第1閾値よりも小さい第3閾値を前記個数閾値に設定すること
を特徴とする信号機認識方法。 - 請求項3に記載の信号機認識方法であって、
前記第2閾値は前記第3閾値よりも小さいこと
を特徴とする信号機認識方法。 - 請求項1~4のいずれか一項に記載の信号機認識方法であって、
前記結果列は、前記個数閾値よりも多い所定個数の判定結果から構成されること
を特徴とする信号機認識方法。 - 請求項1~5のいずれか一項に記載の信号機認識方法であって、
前記結果列を構成する判定結果のうち、前記現示状態が不明であるとする判定結果を第1判定結果として抽出し、
前記結果列を構成する判定結果のうち、前記現示状態が不明であるとする判定結果を除いた判定結果の中から、前記第1判定結果の直前の判定結果、及び、前記第1判定結果の直後の判定結果を、それぞれ、第2判定結果、及び、第3判定結果として抽出し、
前記第2判定結果と前記第3判定結果が同一である場合に、前記結果列内の前記第1判定結果を前記第2判定結果で置き換えること
を特徴とする信号機認識方法。 - 車両に搭載された撮像部と、コントローラとを備える信号機認識装置であって、
前記コントローラは、
前記撮像部を用いて前記車両の進行方向にある信号機を複数回撮像して、複数の画像を取得し、
前記画像ごとに前記信号機の現示状態を判定して得られた時系列順の複数の判定結果からなる結果列を取得し、
前記結果列を構成する判定結果のうち最新の判定結果である特定判定結果に基づいて個数閾値を設定する際、
前記特定判定結果が、前記現示状態は前記信号機に対応する停止線の通過を許可する許可表示であるとする判定結果である場合に、第1閾値を前記個数閾値に設定し、
前記特定判定結果が、前記現示状態は前記許可表示であるとする判定結果以外である場合に、前記第1閾値よりも小さい第2閾値を前記個数閾値に設定し、
前記特定判定結果と同一の判定結果の個数が、前記個数閾値よりも多い場合に、前記特定判定結果を出力すること
を特徴とする信号機認識装置。
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP19952385.3A EP4060639B1 (en) | 2019-11-12 | 2019-11-12 | Traffic signal recognition method and traffic signal recognition device |
US17/775,528 US11663834B2 (en) | 2019-11-12 | 2019-11-12 | Traffic signal recognition method and traffic signal recognition device |
BR112022008079A BR112022008079A2 (pt) | 2019-11-12 | 2019-11-12 | Método de reconhecimento de sinal de tráfego e dispositivo de reconhecimento de sinal de tráfego |
JP2021555893A JP7255706B2 (ja) | 2019-11-12 | 2019-11-12 | 信号機認識方法及び信号機認識装置 |
CN201980102181.XA CN114746915B (zh) | 2019-11-12 | 2019-11-12 | 信号机识别方法及信号机识别装置 |
PCT/IB2019/001270 WO2021094800A1 (ja) | 2019-11-12 | 2019-11-12 | 信号機認識方法及び信号機認識装置 |
MX2022005516A MX2022005516A (es) | 2019-11-12 | 2019-11-12 | Metodo de reconocimiento de semaforo y dispositivo de reconocimiento de semaforo. |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/IB2019/001270 WO2021094800A1 (ja) | 2019-11-12 | 2019-11-12 | 信号機認識方法及び信号機認識装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021094800A1 true WO2021094800A1 (ja) | 2021-05-20 |
Family
ID=75911355
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IB2019/001270 WO2021094800A1 (ja) | 2019-11-12 | 2019-11-12 | 信号機認識方法及び信号機認識装置 |
Country Status (7)
Country | Link |
---|---|
US (1) | US11663834B2 (ja) |
EP (1) | EP4060639B1 (ja) |
JP (1) | JP7255706B2 (ja) |
CN (1) | CN114746915B (ja) |
BR (1) | BR112022008079A2 (ja) |
MX (1) | MX2022005516A (ja) |
WO (1) | WO2021094800A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024161521A1 (ja) * | 2023-01-31 | 2024-08-08 | 日産自動車株式会社 | 信号機認識方法及び信号機認識装置 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7384131B2 (ja) * | 2020-08-31 | 2023-11-21 | トヨタ自動車株式会社 | 車両の運転支援装置、車両の運転支援方法、およびプログラム |
JP2022126350A (ja) * | 2021-02-18 | 2022-08-30 | 本田技研工業株式会社 | 認識装置、移動体、認識方法、およびプログラム |
WO2024161469A1 (ja) * | 2023-01-30 | 2024-08-08 | 日産自動車株式会社 | 信号機認識方法及び信号機認識装置 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6228492B1 (en) | 1997-09-23 | 2001-05-08 | Zipperling Kessler & Co. (Gmbh & Co.) | Preparation of fibers containing intrinsically conductive polymers |
JP2015170240A (ja) * | 2014-03-10 | 2015-09-28 | 富士重工業株式会社 | 車外環境認識装置 |
US20170024622A1 (en) * | 2015-07-24 | 2017-01-26 | Honda Motor Co., Ltd. | Surrounding environment recognition device |
JP2019109602A (ja) * | 2017-12-15 | 2019-07-04 | クラリオン株式会社 | 信号機認識装置 |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6547292B2 (ja) * | 2014-02-05 | 2019-07-24 | 株式会社リコー | 画像処理装置、機器制御システム、および画像処理プログラム |
US9747508B2 (en) * | 2015-07-24 | 2017-08-29 | Honda Motor Co., Ltd. | Surrounding environment recognition device |
US10275669B2 (en) * | 2015-09-09 | 2019-04-30 | Lightmetrics Technologies Pvt. Ltd. | System and method for detecting objects in an automotive environment |
WO2017171659A1 (en) * | 2016-03-31 | 2017-10-05 | Agency For Science, Technology And Research | Signal light detection |
KR20190078664A (ko) * | 2017-12-11 | 2019-07-05 | 삼성전자주식회사 | 컨텐츠를 표시하기 위한 장치 및 방법 |
JP7151633B2 (ja) * | 2019-06-12 | 2022-10-12 | トヨタ自動車株式会社 | 情報表示装置 |
JP7088135B2 (ja) * | 2019-07-23 | 2022-06-21 | トヨタ自動車株式会社 | 信号表示推定システム |
JP7167880B2 (ja) * | 2019-08-27 | 2022-11-09 | トヨタ自動車株式会社 | 停止線位置推定装置及び車両制御システム |
JP7156252B2 (ja) * | 2019-11-13 | 2022-10-19 | トヨタ自動車株式会社 | 運転支援装置 |
JP7243600B2 (ja) * | 2019-11-29 | 2023-03-22 | トヨタ自動車株式会社 | 車両用運転支援装置 |
-
2019
- 2019-11-12 WO PCT/IB2019/001270 patent/WO2021094800A1/ja unknown
- 2019-11-12 JP JP2021555893A patent/JP7255706B2/ja active Active
- 2019-11-12 CN CN201980102181.XA patent/CN114746915B/zh active Active
- 2019-11-12 EP EP19952385.3A patent/EP4060639B1/en active Active
- 2019-11-12 MX MX2022005516A patent/MX2022005516A/es unknown
- 2019-11-12 BR BR112022008079A patent/BR112022008079A2/pt unknown
- 2019-11-12 US US17/775,528 patent/US11663834B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6228492B1 (en) | 1997-09-23 | 2001-05-08 | Zipperling Kessler & Co. (Gmbh & Co.) | Preparation of fibers containing intrinsically conductive polymers |
JP2015170240A (ja) * | 2014-03-10 | 2015-09-28 | 富士重工業株式会社 | 車外環境認識装置 |
US20170024622A1 (en) * | 2015-07-24 | 2017-01-26 | Honda Motor Co., Ltd. | Surrounding environment recognition device |
JP2019109602A (ja) * | 2017-12-15 | 2019-07-04 | クラリオン株式会社 | 信号機認識装置 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024161521A1 (ja) * | 2023-01-31 | 2024-08-08 | 日産自動車株式会社 | 信号機認識方法及び信号機認識装置 |
Also Published As
Publication number | Publication date |
---|---|
EP4060639B1 (en) | 2024-01-03 |
JP7255706B2 (ja) | 2023-04-11 |
CN114746915B (zh) | 2023-03-28 |
EP4060639A1 (en) | 2022-09-21 |
BR112022008079A2 (pt) | 2022-07-12 |
CN114746915A (zh) | 2022-07-12 |
JPWO2021094800A1 (ja) | 2021-05-20 |
US11663834B2 (en) | 2023-05-30 |
US20220398853A1 (en) | 2022-12-15 |
MX2022005516A (es) | 2022-11-17 |
EP4060639A4 (en) | 2022-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021094800A1 (ja) | 信号機認識方法及び信号機認識装置 | |
US10339805B2 (en) | Traffic light recognition device and traffic light recognition method | |
US20170253177A1 (en) | Vehicle lighting system | |
JP5883833B2 (ja) | 車外環境認識装置 | |
JP7251582B2 (ja) | 表示制御装置および表示制御プログラム | |
JP7472832B2 (ja) | 車両制御装置、車両制御方法及び車両制御用コンピュータプログラム | |
JP2017054343A (ja) | 挙動検出装置 | |
US11679769B2 (en) | Traffic signal recognition method and traffic signal recognition device | |
US11208036B2 (en) | Automated driving enabled vehicle | |
US11769337B2 (en) | Traffic signal recognition method and traffic signal recognition device | |
RU2779798C1 (ru) | Способ распознавания светофора и устройство распознавания светофора | |
JP2022060118A (ja) | 区画線認識装置 | |
WO2024161521A1 (ja) | 信号機認識方法及び信号機認識装置 | |
JP7035339B2 (ja) | ブレーキ判定方法及びブレーキ判定装置 | |
WO2024161469A1 (ja) | 信号機認識方法及び信号機認識装置 | |
RU2779921C1 (ru) | Способ распознавания светофора и устройство распознавания светофора | |
RU2779773C1 (ru) | Способ распознавания светофора и устройство распознавания светофора | |
US20210094585A1 (en) | Automated driving enabled vehicle | |
US11338828B2 (en) | Automated driving enabled vehicle | |
WO2023286806A1 (ja) | 静止物情報取得装置、プログラム、及び静止物情報取得方法 | |
JP2023094930A (ja) | 挙動予測方法及び挙動予測装置 | |
JP2022138524A (ja) | 走行支援方法及び走行支援装置 | |
JP2022138525A (ja) | 走行支援方法及び走行支援装置 | |
JP2024047487A (ja) | 車載装置、車載装置の動作方法、およびプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19952385 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2021555893 Country of ref document: JP Kind code of ref document: A |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112022008079 Country of ref document: BR |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2019952385 Country of ref document: EP Effective date: 20220613 |
|
ENP | Entry into the national phase |
Ref document number: 112022008079 Country of ref document: BR Kind code of ref document: A2 Effective date: 20220427 |