WO2012172629A1 - 歩行者動作予測装置 - Google Patents
歩行者動作予測装置 Download PDFInfo
- Publication number
- WO2012172629A1 WO2012172629A1 PCT/JP2011/063515 JP2011063515W WO2012172629A1 WO 2012172629 A1 WO2012172629 A1 WO 2012172629A1 JP 2011063515 W JP2011063515 W JP 2011063515W WO 2012172629 A1 WO2012172629 A1 WO 2012172629A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- pedestrian
- shape
- prediction device
- motion prediction
- detected
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
Definitions
- the present invention relates to a pedestrian motion prediction device.
- an edge image is generated from image data input from an external sensor, the opening W of the left and right legs of the pedestrian candidate is detected, and the head of the pedestrian candidate is estimated, and this head
- the height H of the pedestrian candidate is estimated according to the position of the part, and the ratio (W / H) of the leg W to the height H is greater than or equal to a predetermined value ⁇ based on the height H of the pedestrian candidate and the opening W of the leg.
- a pedestrian recognition device is disclosed that determines whether or not there is a possibility that a pedestrian candidate crosses the course of the host vehicle.
- Patent Documents 2 to 4 can be cited as other prior art documents.
- Patent Document 2 the time series change of the position and moving speed of the pedestrian existing in front of the own vehicle and the peripheral information are acquired, and the time series change of the acquired position and moving speed and the pedestrian jumps out on the roadway.
- Patent Document 3 includes a database for storing two-dimensional shape data for detecting a pedestrian, estimates a first three-dimensional model based on the detected pedestrian imaging data, and based on the first three-dimensional model.
- a vehicle pedestrian detection device for estimating the future motion of a pedestrian is disclosed.
- a representative point of a pedestrian (head, neck, hip joint, knee joint, ankle joint, etc.) is identified from image data, and a straight line connecting the identified representative points is parallel to the ground surface.
- a pedestrian recognition support device that calculates angle information of each part of a pedestrian based on a straight line or the like and determines a movement state of the pedestrian based on the calculated angle information.
- This invention is made in view of said situation, Comprising: Before a pedestrian actually starts jumping out, providing the pedestrian movement prediction apparatus which can predict the possibility of jumping out accurately. With the goal.
- the present invention is characterized by predicting pedestrian jumping based on a result of collating the detected pedestrian shape with a pedestrian shape prepared in advance having a possibility of jumping out.
- it is good also as a structure which estimates popping-out of a pedestrian based on the combination of the said pedestrian shape detected at a certain time and the said pedestrian shape detected after the said certain time.
- the detected pedestrian shape is recorded in time series, the periodicity of the recorded time series of the pedestrian shape is analyzed, and pedestrian jumping is predicted based on the analyzed change in periodicity. It is good also as a structure.
- the detected pedestrian shape is recorded in time series, and it is determined whether or not the speed of the pedestrian is continuous based on the recorded time series of the pedestrian shape, and based on the result of the determination.
- the present invention predicts the pedestrian's popping out based on the result of collating the detected pedestrian shape with a pedestrian shape prepared in advance with the possibility of popping out, the pedestrian actually starts popping out Before, there is an effect that the possibility of popping out can be accurately predicted.
- FIG. 1 is a block diagram illustrating an example of a configuration of a pedestrian motion prediction apparatus according to the first embodiment.
- FIG. 2 is a flowchart illustrating an example of an operation executed by the pedestrian motion prediction device according to the first embodiment.
- FIG. 3 is a diagram illustrating an example of a pedestrian jumping posture that is likely to occur.
- FIG. 4 is a diagram illustrating an example of a pedestrian jumping posture that is likely to occur.
- FIG. 5 is a diagram illustrating an example of a pedestrian jumping posture that is likely to occur.
- FIG. 6 is a diagram illustrating an example of a pedestrian jumping posture that is likely to occur.
- FIG. 7 is a block diagram illustrating an example of the configuration of the pedestrian motion prediction apparatus according to the second embodiment.
- FIG. 1 is a block diagram illustrating an example of a configuration of a pedestrian motion prediction apparatus according to the first embodiment.
- FIG. 2 is a flowchart illustrating an example of an operation executed by the pedestrian motion prediction device according to the first embodiment.
- FIG. 8 is a flowchart illustrating an example of an operation executed by the pedestrian motion prediction device according to the second embodiment.
- FIG. 9 is a block diagram illustrating an example of the configuration of the pedestrian motion prediction apparatus according to the third embodiment.
- FIG. 10 is a flowchart illustrating an example of an operation executed by the pedestrian motion prediction device according to the third embodiment.
- FIG. 11 is a diagram illustrating an example of a periodic change in pedestrian shape.
- FIG. 1 is a block diagram showing an example of the configuration of the pedestrian motion prediction apparatus according to the first embodiment.
- the pedestrian motion prediction device 1 is configured using, for example, a general-purpose personal computer, and is connected to a camera 2 mounted on a vehicle so as to be communicable.
- the camera 2 is a device that captures the periphery of the host vehicle and generates image data in which the periphery of the host vehicle is projected.
- the pedestrian motion prediction device 1 includes a control unit 12 and a storage unit 14.
- the control unit 12 is for comprehensively controlling the pedestrian motion prediction device 1 and is, for example, a CPU (Central Processing Unit).
- the storage unit 14 is for storing data, and is, for example, a RAM (Random Access Memory), a ROM (Read Only Memory), or a hard disk.
- the storage unit 14 includes a collation data storage unit 14a.
- the collation data storage unit 14a stores the shape of a pedestrian that is likely to occur in various changing traffic environments (for example, forward tilt, body orientation, leg opening in the front-rear direction, or leg opening in the left-right direction). ) Is stored, or a learned classifier group or a pedestrian recognition template (image) group is stored.
- the control unit 12 includes a detection unit 12a, an acquisition unit 12b, and a prediction unit 12c.
- the detection unit 12 a detects a pedestrian from the image data input from the camera 2.
- the acquisition unit 12b acquires the shape of the pedestrian detected by the detection unit 12a.
- the prediction unit 12c predicts a pedestrian's action (for example, a pedestrian's jump-out) based on the shape of the pedestrian acquired by the acquisition unit 12b.
- FIG. 2 is a flowchart showing an example of an operation executed by the pedestrian motion prediction device 1.
- the detection part 12a detects a pedestrian from the image data input from the camera 2, and cuts out the part where the detected pedestrian is projected from the image data (step SA1).
- the acquisition unit 12b uses the learned classifier group or the pedestrian recognition template stored in the collation data storage unit 14a as the shape of the pedestrian copied in the partial image data cut out in step SA1.
- the shape is classified (step SA2).
- the acquisition unit 12b extracts a feature vector (feature amount) from the partial image data, identifies the extracted feature vector on the identification plane formed by the learned classifier, and is copied to the partial image data.
- Class of pedestrian shape for example, forward tilt posture class as shown in FIG. 3, upper body orientation class as shown in FIG. 4, leg forward and backward opening class as shown in FIG. 5 , And the like, the class of opening of the leg in the left-right direction as shown in FIG. 6 is determined.
- the acquisition unit 12b collates the shape of the pedestrian projected in the partial image data with the shape of the pedestrian in the template for pedestrian recognition, so that the pedestrian projected in the partial image data Determine the shape class.
- the classes of pedestrian shapes can also be divided into classes such as “normal walking motion” and “other than that”.
- the prediction unit 12c predicts a pedestrian's movement (for example, the direction in which the pedestrian jumps out) based on the classification result obtained in step SA2 (step SA3). For example, the predicting unit 12c predicts that the pedestrian jumps in the forward tilt direction (the arrow direction in FIG. 3) when the classification result relates to the class of the forward tilt posture. Further, for example, when the result of classification is related to the class of the upper body direction, the prediction unit 12c jumps in the direction in which the upper body is facing (the arrow direction in FIG. 4). Predict. For example, the prediction unit 12c predicts that the pedestrian jumps forward (in the direction of the arrow in FIG.
- the prediction unit 12c predicts that the pedestrian jumps out in the left direction (the arrow direction in FIG. 6) when the result of the classification is related to the opening class of the leg in the left-right direction. To do.
- the class of the pedestrian shape is divided into the “normal walking motion” class and the “other than that” class, only the presence or absence of the jump is predicted.
- FIG. 7 is a block diagram showing an example of the configuration of the pedestrian motion prediction apparatus according to the second embodiment.
- the control unit 12 further includes an accumulation unit 12d in addition to the detection unit 12a, the acquisition unit 12b, and the prediction unit 12c described in the first embodiment.
- the storage unit 14 further includes a shape data storage unit 14b in addition to the collation data storage unit 14a described in the first embodiment.
- the accumulation unit 12d accumulates the shape of the pedestrian acquired by the acquisition unit 12b in the shape data storage unit 14b.
- the prediction unit 12c predicts a pedestrian's action (for example, a pedestrian's pop-out) based on a combination of pedestrian shapes accumulated in the shape data storage unit 14b.
- the shape data storage unit 14b is for storing data relating to the shape of the pedestrian.
- FIG. 8 is a flowchart showing an example of an operation executed by the pedestrian motion prediction device according to the second embodiment.
- the detection unit 12a detects a pedestrian from the image data input from the camera 2, and cuts out a portion where the detected pedestrian is projected from the image data (step SB1).
- the acquisition unit 12b uses the learned classifier group or pedestrian recognition template stored in the collation data storage unit 14a as the shape of the pedestrian copied in the partial image data cut out in step SB1. By matching with the group, the shape is classified (step SB2).
- the accumulating unit 12d accumulates the classification result obtained in Step SB2 in the shape data storage unit 14b (Step SB3).
- the prediction unit 12c predicts a pedestrian's action (for example, a pedestrian's jumping direction or a pedestrian's jumping speed) based on a combination of classification results accumulated in the shape data storage unit 14b.
- a pedestrian's action for example, a pedestrian's jumping direction or a pedestrian's jumping speed
- the classification result regarding the shape of the pedestrian projected in the partial image data at a certain time point relates to the class of the body orientation, and the time point after the certain time point
- the classification result for the shape of the pedestrian projected in the partial image data is related to the forward leaning posture class, the pedestrian's posture starts to move from the state where it is about to move. Assuming that it has changed, it is predicted that the pedestrian will jump forward.
- FIG. 9 is a block diagram showing an example of the configuration of the pedestrian motion prediction apparatus according to the third embodiment.
- the control unit 12 includes a recording unit 12e and an analysis unit 12f in addition to the detection unit 12a, the acquisition unit 12b, and the prediction unit 12c described in the first embodiment.
- the storage unit 14 further includes a shape data storage unit 14b in addition to the collation data storage unit 14a described in the first embodiment.
- the recording unit 12e records the pedestrian shape acquired by the acquisition unit 12b in the shape data storage unit 14b in time series. Based on the time-series pedestrian shape recorded in the shape data storage unit 14b, the analysis unit 12f analyzes the periodicity of the shape (for example, a periodic change in the shape of the pedestrian). The prediction unit 12c predicts a pedestrian's action (for example, a pedestrian's jump-out) based on the analysis result of the analysis unit 12f.
- the shape data storage unit 14b is for storing data relating to the shape of the pedestrian in time series.
- FIG. 10 is a flowchart illustrating an example of an operation executed by the pedestrian motion prediction device according to the third embodiment.
- the detection part 12a detects a pedestrian from the image data input from the camera 2, and cuts out the part where the detected pedestrian is projected from the image data (step SC1).
- the acquisition unit 12b uses the learned classifier group or pedestrian recognition template stored in the collation data storage unit 14a as the shape of the pedestrian copied in the partial image data cut out in step SC1.
- the shape is classified by collating with the group (step SC2).
- the feature amount itself is held as the shape of the pedestrian.
- the recording unit 12e records the classification result obtained in step SC2 or the feature quantity itself in the shape data storage unit 14b in time series (step SC3).
- the analysis unit 12f analyzes the periodicity of the shape of the pedestrian based on the time-series classification result recorded in the shape data storage unit 14b or the feature amount itself (step SC4). For example, the analysis unit 12f detects periodic breakage from the periodic change shown in FIG. 11 regarding the leg width of the pedestrian obtained from the result of the time-series classification. Alternatively, a certain distance or something equivalent to it, for example, the amount of Kullback-Leibler information, is calculated in the feature amount space, the similarity with n frames before is calculated, and the periodicity breakage is detected.
- the prediction unit 12 c determines the pedestrian movement (for example, the direction in which the pedestrian jumps out or the speed at which the pedestrian jumps out). Prediction is made (step SC5). For example, when the periodicity break is detected in step SC4, the prediction unit 12c predicts that the pedestrian jumps out at the time of the break (see FIG. 11). Further, for example, as shown in FIG. 11, the prediction unit 12 c is based on the change amount of the leg width of the pedestrian before and after the time when the periodicity is broken, and at a speed corresponding to the change amount. Predict that will jump out.
- the prediction unit 12c determines the speed of pedestrian movement (the direction and speed of movement) based on the time-series pedestrian shape (result of time-series classification) recorded in the shape data storage unit 14b. ) Is continuous, and the pedestrian jumping direction and the jumping speed may be predicted based on the determination result.
- the pedestrian jumps out of the road by predicting the posture or motion change that is a precursor to jumping out on the road.
- the pedestrian shape detected by the sensor is collated with pedestrian shape information related to the precursor behavior of the pedestrian who has a possibility of jumping out, and the jump of the pedestrian is predicted based on the collation result. Thereby, before the pedestrian actually starts to jump out, the possibility of jumping out can be accurately predicted.
- the pedestrian's pop-up is predicted by a combination of the pedestrian shape detected at a certain moment and the pedestrian shape detected after that, the prediction of the possibility of pop-out is performed. Accuracy can be improved.
- the time series information of the detected pedestrian shape is recorded, the periodicity of the pedestrian shape is analyzed based on the time series information, and the pedestrian shape obtained by the analysis Since the pedestrian's popping out is predicted based on the change in the periodicity, the prediction accuracy of the popping out possibility can be improved.
- the time series information of the detected pedestrian shape is recorded, the continuity of the pedestrian speed is analyzed based on the time series information, and the pedestrian speed obtained by the analysis is recorded.
- the prediction accuracy of the possibility of pop-out can be improved. Further, according to the above-described embodiment, as the pedestrian shape, at least one of a pedestrian's forward tilt posture, an upper body orientation, a leg opening in the front-rear direction, and a leg opening in the left-right direction is acquired. Therefore, the prediction accuracy of the possibility of popping out can be improved.
- the pedestrian motion prediction apparatus is useful in the automobile manufacturing industry, and is particularly suitable for predicting pop-up of pedestrians around a vehicle.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
第1実施形態にかかる歩行者動作予測装置の構成および当該歩行者動作予測装置で実行される動作について、図1から図6を参照して詳細に説明する。
第2実施形態にかかる歩行者動作予測装置の構成および当該歩行者動作予測装置で実行される動作について、図7および図8を参照して詳細に説明する。なお、第1実施形態で説明した内容と重複するものについては省略する場合がある。
第3実施形態にかかる歩行者動作予測装置の構成および当該歩行者動作予測装置で実行される動作について、図9から図11を参照して詳細に説明する。なお、第1実施形態または第2実施形態で説明した内容と重複するものについては省略する場合がある。
以上、上述した実施形態によれば、歩行者が道路に飛び出す前兆となる姿勢または動作変化を捉え、歩行者の飛び出しを予測する。具体的には、センサにより検出した歩行者形状を、飛び出す可能性を持つ歩行者の前兆行動に関する歩行者形状情報と照合し、照合した結果に基づいて歩行者の飛び出しを予測する。これにより、実際に歩行者が飛び出しを開始する前に、飛び出しの可能性を精度良く予測することができる。
12 制御部
12a 検出部
12b 取得部
12c 予測部
12d 蓄積部
12e 記録部
12f 解析部
14 記憶部
14a 照合用データ記憶部
14b 形状データ記憶部
2 カメラ
Claims (5)
- 検出された歩行者形状を、飛び出す可能性を持つ予め用意された歩行者形状と照合した結果に基づいて、歩行者の飛び出しを予測すること、
を特徴とする歩行者動作予測装置。 - 請求項1に記載の歩行者動作予測装置において、
ある時点に検出された前記歩行者形状と当該ある時点後に検出された前記歩行者形状との組み合わせに基づいて、歩行者の飛び出しを予測すること、
を特徴とする歩行者動作予測装置。 - 請求項1に記載の歩行者動作予測装置において、
検出された前記歩行者形状を時系列で記録し、記録した時系列の前記歩行者形状の周期性を解析し、解析した当該周期性の変化に基づいて歩行者の飛び出しを予測すること、
を特徴とする歩行者動作予測装置。 - 請求項1に記載の歩行者動作予測装置において、
検出された前記歩行者形状を時系列で記録し、記録した時系列の前記歩行者形状に基づいて歩行者の速度が連続であるか否かを判定し、当該判定の結果に基づいて歩行者の飛び出しを予測すること、
を特徴とする歩行者動作予測装置。 - 請求項1に記載の歩行者動作予測装置において、
歩行者の、前傾姿勢、上体の向き、脚の前後方向への開き、および脚の左右方向への開きのうち少なくとも1つを前記歩行者形状として取得すること、
を特徴とする歩行者動作予測装置。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE112011105330.4T DE112011105330T5 (de) | 2011-06-13 | 2011-06-13 | Fußgängerbewegungsvorhersagegerät |
| US14/125,862 US9507998B2 (en) | 2011-06-13 | 2011-06-13 | Pedestrian motion predicting device |
| PCT/JP2011/063515 WO2012172629A1 (ja) | 2011-06-13 | 2011-06-13 | 歩行者動作予測装置 |
| JP2013520341A JP5737397B2 (ja) | 2011-06-13 | 2011-06-13 | 歩行者動作予測装置 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2011/063515 WO2012172629A1 (ja) | 2011-06-13 | 2011-06-13 | 歩行者動作予測装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2012172629A1 true WO2012172629A1 (ja) | 2012-12-20 |
Family
ID=47356656
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2011/063515 Ceased WO2012172629A1 (ja) | 2011-06-13 | 2011-06-13 | 歩行者動作予測装置 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US9507998B2 (ja) |
| JP (1) | JP5737397B2 (ja) |
| DE (1) | DE112011105330T5 (ja) |
| WO (1) | WO2012172629A1 (ja) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014162538A1 (ja) * | 2013-04-03 | 2014-10-09 | トヨタ自動車株式会社 | 検出装置、検出方法、運転支援装置及び運転支援方法 |
| CN104933893A (zh) * | 2013-08-02 | 2015-09-23 | 本田技研工业株式会社 | 用于车辆与行人通信的系统和方法 |
| JP2016051247A (ja) * | 2014-08-29 | 2016-04-11 | マツダ株式会社 | 車両用歩行者検出装置 |
| WO2016098238A1 (ja) * | 2014-12-19 | 2016-06-23 | 株式会社日立製作所 | 走行制御装置 |
| WO2017056382A1 (ja) * | 2015-09-29 | 2017-04-06 | ソニー株式会社 | 情報処理装置、情報処理方法、及びプログラム |
| JP2019053647A (ja) * | 2017-09-19 | 2019-04-04 | 富士ゼロックス株式会社 | 行動推定装置及び行動推定プログラム |
| US11011062B2 (en) | 2016-07-07 | 2021-05-18 | Denso Corporation | Pedestrian detection apparatus and pedestrian detection method |
| JPWO2022024212A1 (ja) * | 2020-07-28 | 2022-02-03 | ||
| JP2023156709A (ja) * | 2022-04-13 | 2023-10-25 | トヨタ自動車株式会社 | 転換方向予測システム、移動システム、転換方向予測方法、及びプログラム |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9786178B1 (en) | 2013-08-02 | 2017-10-10 | Honda Motor Co., Ltd. | Vehicle pedestrian safety system and methods of use and manufacture thereof |
| US9855890B2 (en) * | 2014-12-11 | 2018-01-02 | Toyota Motor Engineering & Manufacturing North America, Inc. | Autonomous vehicle interaction with external environment |
| US9786177B2 (en) | 2015-04-10 | 2017-10-10 | Honda Motor Co., Ltd. | Pedestrian path predictions |
| JP6171046B1 (ja) * | 2016-04-26 | 2017-07-26 | 京セラ株式会社 | 電子機器、制御方法、及び制御プログラム |
| US9989966B2 (en) | 2016-05-20 | 2018-06-05 | Delphi Technologies, Inc. | Intersection cross-walk navigation system for automated vehicles |
| JP6334604B2 (ja) | 2016-05-24 | 2018-05-30 | 京セラ株式会社 | 車載装置、車両、報知システム、及び報知方法 |
| US10126136B2 (en) | 2016-06-14 | 2018-11-13 | nuTonomy Inc. | Route planning for an autonomous vehicle |
| US10309792B2 (en) | 2016-06-14 | 2019-06-04 | nuTonomy Inc. | Route planning for an autonomous vehicle |
| US11092446B2 (en) | 2016-06-14 | 2021-08-17 | Motional Ad Llc | Route planning for an autonomous vehicle |
| DE102016220450A1 (de) | 2016-10-19 | 2018-04-19 | Bayerische Motoren Werke Aktiengesellschaft | Vorrichtung, Fortbewegungsmittel und Verfahren zur Abschätzung einer Kollisionswahrscheinlichkeit zwischen einem Fortbewegungsmittel und einem Umgebungsobjekt |
| US10473470B2 (en) | 2016-10-20 | 2019-11-12 | nuTonomy Inc. | Identifying a stopping place for an autonomous vehicle |
| US10681513B2 (en) | 2016-10-20 | 2020-06-09 | nuTonomy Inc. | Identifying a stopping place for an autonomous vehicle |
| US10331129B2 (en) | 2016-10-20 | 2019-06-25 | nuTonomy Inc. | Identifying a stopping place for an autonomous vehicle |
| US10857994B2 (en) | 2016-10-20 | 2020-12-08 | Motional Ad Llc | Identifying a stopping place for an autonomous vehicle |
| US10272876B2 (en) * | 2016-12-19 | 2019-04-30 | Peiker Acustic GmbH & Co. KG, Valeo Peiker Telematics Product Line | Method of operating an ad hoc network to protect a passenger-as-a-pedestrian and system to protect a passenger-as-a-pedestrian |
| CN106515578A (zh) * | 2016-12-22 | 2017-03-22 | 百度在线网络技术(北京)有限公司 | 无人车驾驶状态的识别装置、识别方法及无人车 |
| KR101996419B1 (ko) * | 2016-12-30 | 2019-07-04 | 현대자동차주식회사 | 센서 융합 기반 보행자 탐지 및 보행자 충돌 방지 장치 및 방법 |
| KR101996418B1 (ko) | 2016-12-30 | 2019-07-04 | 현대자동차주식회사 | 센서 융합 기반 보행자 탐지 및 보행자 충돌 방지 장치 및 방법 |
| US10579788B2 (en) | 2017-08-17 | 2020-03-03 | Waymo Llc | Recognizing assigned passengers for autonomous vehicles |
| JP7347405B2 (ja) * | 2020-11-30 | 2023-09-20 | トヨタ自動車株式会社 | 運転支援システム |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002029346A (ja) * | 2000-07-14 | 2002-01-29 | Hiroyuki Yokozawa | 自動車の運転支援システム及び運転支援プログラムを記録した記録媒体 |
| JP2007257459A (ja) * | 2006-03-24 | 2007-10-04 | Honda Motor Co Ltd | 姿勢判別装置 |
| JP2007264778A (ja) * | 2006-03-27 | 2007-10-11 | Honda Motor Co Ltd | 歩行者認識装置 |
| JP2007279808A (ja) * | 2006-04-03 | 2007-10-25 | Honda Motor Co Ltd | 車両周辺監視装置 |
| JP2008282097A (ja) * | 2007-05-08 | 2008-11-20 | Toyota Central R&D Labs Inc | 衝突危険度推定装置及びドライバ支援装置 |
| JP2009244985A (ja) * | 2008-03-28 | 2009-10-22 | Toyota Central R&D Labs Inc | 運転支援装置及び歩行者検出装置 |
| JP2010102437A (ja) * | 2008-10-22 | 2010-05-06 | Toyota Central R&D Labs Inc | 歩行者飛び出し予測装置及びプログラム |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004029659A2 (en) * | 2002-06-14 | 2004-04-08 | Honda Giken Kogyo Kabushiki Kaisha | Pedestrian detection and tracking with night vision |
| WO2005050565A1 (ja) | 2003-11-20 | 2005-06-02 | Matsushita Electric Industrial Co., Ltd. | 移動物体検出装置及び移動物体検出方法 |
| JP2009012521A (ja) * | 2007-07-02 | 2009-01-22 | Nissan Motor Co Ltd | 車両の走行支援システム及び走行支援方法 |
| JP4470067B2 (ja) | 2007-08-07 | 2010-06-02 | 本田技研工業株式会社 | 対象物種別判定装置、車両 |
| JP2010079639A (ja) | 2008-09-26 | 2010-04-08 | Mazda Motor Corp | 車両の歩行者検出装置 |
| JP2010165003A (ja) | 2009-01-13 | 2010-07-29 | Toyota Central R&D Labs Inc | 歩行者認識支援装置および歩行者認識支援方法 |
-
2011
- 2011-06-13 US US14/125,862 patent/US9507998B2/en active Active
- 2011-06-13 DE DE112011105330.4T patent/DE112011105330T5/de active Pending
- 2011-06-13 JP JP2013520341A patent/JP5737397B2/ja active Active
- 2011-06-13 WO PCT/JP2011/063515 patent/WO2012172629A1/ja not_active Ceased
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002029346A (ja) * | 2000-07-14 | 2002-01-29 | Hiroyuki Yokozawa | 自動車の運転支援システム及び運転支援プログラムを記録した記録媒体 |
| JP2007257459A (ja) * | 2006-03-24 | 2007-10-04 | Honda Motor Co Ltd | 姿勢判別装置 |
| JP2007264778A (ja) * | 2006-03-27 | 2007-10-11 | Honda Motor Co Ltd | 歩行者認識装置 |
| JP2007279808A (ja) * | 2006-04-03 | 2007-10-25 | Honda Motor Co Ltd | 車両周辺監視装置 |
| JP2008282097A (ja) * | 2007-05-08 | 2008-11-20 | Toyota Central R&D Labs Inc | 衝突危険度推定装置及びドライバ支援装置 |
| JP2009244985A (ja) * | 2008-03-28 | 2009-10-22 | Toyota Central R&D Labs Inc | 運転支援装置及び歩行者検出装置 |
| JP2010102437A (ja) * | 2008-10-22 | 2010-05-06 | Toyota Central R&D Labs Inc | 歩行者飛び出し予測装置及びプログラム |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5983865B2 (ja) * | 2013-04-03 | 2016-09-06 | トヨタ自動車株式会社 | 検出装置及び運転支援装置 |
| WO2014162538A1 (ja) * | 2013-04-03 | 2014-10-09 | トヨタ自動車株式会社 | 検出装置、検出方法、運転支援装置及び運転支援方法 |
| CN104933893B (zh) * | 2013-08-02 | 2019-04-05 | 本田技研工业株式会社 | 用于车辆与行人通信的系统和方法 |
| CN104933893A (zh) * | 2013-08-02 | 2015-09-23 | 本田技研工业株式会社 | 用于车辆与行人通信的系统和方法 |
| JP2016051247A (ja) * | 2014-08-29 | 2016-04-11 | マツダ株式会社 | 車両用歩行者検出装置 |
| WO2016098238A1 (ja) * | 2014-12-19 | 2016-06-23 | 株式会社日立製作所 | 走行制御装置 |
| JPWO2016098238A1 (ja) * | 2014-12-19 | 2017-09-21 | 株式会社日立製作所 | 走行制御装置 |
| US10493985B2 (en) | 2014-12-19 | 2019-12-03 | Hitachi, Ltd. | Travel control device |
| WO2017056382A1 (ja) * | 2015-09-29 | 2017-04-06 | ソニー株式会社 | 情報処理装置、情報処理方法、及びプログラム |
| JPWO2017056382A1 (ja) * | 2015-09-29 | 2018-08-09 | ソニー株式会社 | 情報処理装置、情報処理方法、及びプログラム |
| US10949656B2 (en) | 2015-09-29 | 2021-03-16 | Sony Corporation | Information processing apparatus and information processing method |
| US11915522B2 (en) | 2015-09-29 | 2024-02-27 | Sony Corporation | Information processing apparatus and information processing method |
| US11011062B2 (en) | 2016-07-07 | 2021-05-18 | Denso Corporation | Pedestrian detection apparatus and pedestrian detection method |
| JP2019053647A (ja) * | 2017-09-19 | 2019-04-04 | 富士ゼロックス株式会社 | 行動推定装置及び行動推定プログラム |
| JP7110568B2 (ja) | 2017-09-19 | 2022-08-02 | 富士フイルムビジネスイノベーション株式会社 | 行動推定装置及び行動推定プログラム |
| JPWO2022024212A1 (ja) * | 2020-07-28 | 2022-02-03 | ||
| WO2022024212A1 (ja) * | 2020-07-28 | 2022-02-03 | 日本電気株式会社 | 画像処理装置、画像処理方法、及びプログラム |
| JP7420261B2 (ja) | 2020-07-28 | 2024-01-23 | 日本電気株式会社 | 画像処理装置、画像処理方法、及びプログラム |
| US12555381B2 (en) | 2020-07-28 | 2026-02-17 | Nec Corporation | Image processing apparatus, image processing method, and non-transitory computer-readable medium |
| JP2023156709A (ja) * | 2022-04-13 | 2023-10-25 | トヨタ自動車株式会社 | 転換方向予測システム、移動システム、転換方向予測方法、及びプログラム |
Also Published As
| Publication number | Publication date |
|---|---|
| JP5737397B2 (ja) | 2015-06-17 |
| US9507998B2 (en) | 2016-11-29 |
| JPWO2012172629A1 (ja) | 2015-02-23 |
| DE112011105330T5 (de) | 2014-03-06 |
| US20140112538A1 (en) | 2014-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5737397B2 (ja) | 歩行者動作予測装置 | |
| JP5780307B2 (ja) | 対象物変化検出装置および対象物変化検出方法 | |
| JP5786947B2 (ja) | 歩行者行動予測装置および歩行者行動予測方法 | |
| JP5197679B2 (ja) | 対象物検出装置及びプログラム | |
| US7139411B2 (en) | Pedestrian detection and tracking with night vision | |
| US8994823B2 (en) | Object detection apparatus and storage medium storing object detection program | |
| US10474884B2 (en) | Action determination device | |
| JP2011065338A (ja) | 対象物追跡装置及びプログラム | |
| JP6776719B2 (ja) | 移動体群検出プログラム、移動体群検出装置、及び移動体群検出方法 | |
| JP5838940B2 (ja) | 画像処理装置及び車両制御システム | |
| JP2012221162A (ja) | 対象物検出装置及びプログラム | |
| JP2013205410A (ja) | 車両用外界認識装置およびそれを用いた車両システム | |
| JP2012118683A (ja) | 歩行者認識装置 | |
| JP5832089B2 (ja) | 映像処理装置、映像処理方法およびプログラム | |
| JP2016015043A (ja) | 対象物認識装置 | |
| JP2013008315A (ja) | 歩行者認識装置 | |
| JP5258651B2 (ja) | 物体検出装置、物体検出方法、及び、プログラム | |
| KR101492366B1 (ko) | 차량 사고 감지 방법 및 그 장치 | |
| KR20140114650A (ko) | 이동 로봇의 경로계획 생성 장치 및 방법 | |
| JP5692024B2 (ja) | 対象物変化検出装置および対象物変化検出方法 | |
| JP5811951B2 (ja) | 対象物変化検出装置 | |
| KR101756916B1 (ko) | 행위 인식 장치 및 방법 | |
| JP2019191869A (ja) | 走行場面学習装置、走行場面推定装置、および走行場面推定システム | |
| JP5686119B2 (ja) | 対象物変化検出装置および対象物変化検出方法 | |
| Ansari et al. | ETLNet: An Efficient TCN-BiLSTM Network for Road Anomaly Detection Using Smartphone Sensors |
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: 11867830 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2013520341 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 14125862 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 1120111053304 Country of ref document: DE Ref document number: 112011105330 Country of ref document: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 11867830 Country of ref document: EP Kind code of ref document: A1 |