公开(公告)号：US12073563B2

公开(公告)日：2024-08-27

申请号：US17710807

申请日：2022-03-31

Applicant: Honda Motor Co., Ltd.

Inventor： Isht Dwivedi ,  Yi-Ting Chen ,  Behzad Dariush

IPC: G06T7/10 ,  G06T7/50 ,  G06T17/05 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06T7/10 ,  G06T7/50 ,  G06T17/05 ,  G06V10/7715 ,  G06V10/7747 ,  G06V10/82 ,  G06T2207/10028 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2210/56

Abstract: Systems and methods for bird's eye view (BEV) segmentation are provided. In one embodiment, a method includes receiving an input image from an image sensor on an agent. The input image is a perspective space image defined relative to the position and viewing direction of the agent. The method includes extracting features from the input image. The method includes estimating a depth map that includes depth values for pixels of the plurality of pixels of the input image. The method includes generating a 3D point map including points corresponding to the pixels of the input image. The method includes generating a voxel grid by voxelizing the 3D point map into a plurality voxels. The method includes generating a feature map by extracting feature vectors for pixels based on the points included in the voxels of the plurality of voxels and generating a BEV segmentation based on the feature map.

公开(公告)号：US11580743B2

公开(公告)日：2023-02-14

申请号：US17704324

申请日：2022-03-25

Applicant: Honda Motor Co., Ltd.

Inventor： Yi-Ting Chen ,  Behzad Dariush ,  Nakul Agarwal ,  Ming-Hsuan Yang

IPC: G06K9/62 ,  G06V20/40 ,  G06N3/08 ,  G06V20/56

Abstract: A system and method for providing unsupervised domain adaption for spatio-temporal action localization that includes receiving video data associated with a source domain and a target domain that are associated with a surrounding environment of a vehicle. The system and method also include analyzing the video data associated with the source domain and the target domain and determining a key frame of the source domain and a key frame of the target domain. The system and method additionally include completing an action localization model to model a temporal context of actions occurring within the key frame of the source domain and the key frame of the target domain and completing an action adaption model to localize individuals and their actions and to classify the actions based on the video data. The system and method further include combining losses to complete spatio-temporal action localization of individuals and actions.

公开(公告)号：US11155259B2

公开(公告)日：2021-10-26

申请号：US16386964

申请日：2019-04-17

Applicant: Honda Motor Co., Ltd.

Inventor： Yu Yao ,  Mingze Xu ,  Chiho Choi ,  Behzad Dariush

IPC: B60W30/09 ,  B60W30/095 ,  G06T7/246 ,  G05D1/02 ,  G06T7/73

Abstract: A system and method for egocentric-vision based future vehicle localization that include receiving at least one egocentric first person view image of a surrounding environment of a vehicle. The system and method also include encoding at least one past bounding box trajectory associated with at least one traffic participant that is captured within the at least one egocentric first person view image and encoding a dense optical flow of the egocentric first person view image associated with the at least one traffic participant. The system and method further include decoding at least one future bounding box associated with the at least one traffic participant based on a final hidden state of the at least one past bounding box trajectory encoding and the final hidden state of the dense optical flow encoding.

公开(公告)号：US11034357B2

公开(公告)日：2021-06-15

申请号：US16438365

申请日：2019-06-11

Applicant: Honda Motor Co., Ltd.

Inventor： Athmanarayanan Lakshmi Narayanan ,  Isht Dwivedi ,  Behzad Dariush

IPC: G06K9/62 ,  B60W40/06 ,  G06N3/08 ,  G06T7/11 ,  G06K9/00 ,  G06N3/04

Abstract: Systems and techniques for scene classification and prediction is provided herein. A first series of image frames of an environment from a moving vehicle may be captured. Traffic participants within the environment may be identified and masked based on a first convolutional neural network (CNN). Temporal classification may be performed to generate a series of image frames associated with temporal predictions based on a scene classification model based on CNNs and a long short-term memory (LSTM) network. Additionally, scene classification may occur based on global average pooling. Feature vectors may be generated based on different series of image frames and a fusion feature vector may be obtained by performing data fusion based on a first feature vector, a second feature vector, a third feature vector, etc. In this way, a behavior predictor may generate a predicted driver behavior based on the fusion feature.

公开(公告)号：US20200086879A1

公开(公告)日：2020-03-19

申请号：US16438365

申请日：2019-06-11

Applicant: Honda Motor Co., Ltd.

Inventor： Athmanarayanan Lakshmi Narayanan ,  Isht Dwivedi ,  Behzad Dariush

IPC: B60W40/06 ,  G06N3/08 ,  G06N3/04 ,  G06K9/00 ,  G06T7/11

Abstract: Systems and techniques for scene classification and prediction is provided herein. A first series of image frames of an environment from a moving vehicle may be captured. Traffic participants within the environment may be identified and masked based on a first convolutional neural network (CNN). Temporal classification may be performed to generate a series of image frames associated with temporal predictions based on a scene classification model based on CNNs and a long short-term memory (LSTM) network. Additionally, scene classification may occur based on global average pooling. Feature vectors may be generated based on different series of image frames and a fusion feature vector may be obtained by performing data fusion based on a first feature vector, a second feature vector, a third feature vector, etc. In this way, a behavior predictor may generate a predicted driver behavior based on the fusion feature.

公开(公告)号：US09342986B2

公开(公告)日：2016-05-17

申请号：US14190981

申请日：2014-02-26

Applicant: Honda Motor Co., Ltd.

Inventor： Behzad Dariush

IPC: G08G1/16

CPC classification number: G08G1/166

Abstract: A driver assistance system takes as input a number of different types of vehicle environment inputs including positions of objects in the vehicle's environment. The system identifies possible outcomes that may occur as a result of the positions of the objects in the environment. The possible outcomes include predicted positions for the objects involved in each outcome. The system uses the inputs to determine a likelihood of occurrence of each of the possible outcomes. The system also uses the inputs to determine a current risk value for objects as well as predicted risk values for objects for the possible outcomes. A total risk value can be determined by aggregating the current and predicted risk values of an object weighted by the likelihood of occurrence. Total risk values for objects can be used to determine how the driver assistance system responds to the inputs.

Abstract translation: 驾驶员辅助系统输入多种不同类型的车辆环境输入，包括车辆环境中物体的位置。 系统识别由于环境中物体的位置而可能发生的可能结果。 可能的结果包括每个结果涉及的对象的预测位置。 系统使用输入来确定每个可能结果发生的可能性。 该系统还使用输入来确定对象的当前风险值以及可能结果的对象的预测风险值。 总风险值可以通过汇总通过发生可能性加权的对象的当前和预测风险值来确定。 对象的总风险值可用于确定驾驶员辅助系统如何响应输入。

公开(公告)号：US20150094991A1

公开(公告)日：2015-04-02

申请号：US14203453

申请日：2014-03-10

Applicant: Honda Motor Co., Ltd.

Inventor： Chand T. John ,  Behzad Dariush

IPC: G06F17/50

CPC classification number: G06F17/5095 ,  G06F17/5009

Abstract: A computer-implemented method for interactive vehicle package design including receiving vehicle occupant package design model data including a task to be executed and receiving parameters defining a virtual human subject for executing the task, wherein the virtual human subject includes a plurality of degrees of freedom. The method including determining a plurality of motion descriptors of the virtual human subject including determining a manipulation over time of the degrees of freedom of the virtual human subject during accomplishment of the task and determining one or more performance metrics based on the motion descriptors. The method including generating a visual representation of the vehicle occupant package design model, the virtual human subject and the task to be executed based on at least one of the motion descriptors and the one or more performance metrics for output on a display.

Abstract translation: 一种用于交互式车辆包装设计的计算机实现方法，包括接收包括要执行的任务的车辆乘员包装设计模型数据，以及接收定义用于执行任务的虚拟人类对象的参数，其中所述虚拟人类对象包括多个自由度。 该方法包括确定虚拟人类对象的多个运动描述符，包括在完成任务期间确定虚拟人类受试者的自由度的时间上的操纵，并且基于运动描述符确定一个或多个性能度量。 该方法包括基于至少一个运动描述符和用于在显示器上输出的一个或多个性能度量来生成车辆乘员包装设计模型，虚拟人体对象和待执行的任务的视觉表示。

公开(公告)号：US20220017122A1

公开(公告)日：2022-01-20

申请号：US17160747

申请日：2021-01-28

Applicant: Honda Motor Co., Ltd.

Inventor： Srikanth Malla ,  Chiho Choi ,  Behzad Dariush

IPC: B60W60/00 ,  G06N3/04

Abstract: A system and method for providing social-stage spatio-temporal multi-modal future forecasting that include receiving environment data associated with a surrounding environment of an ego vehicle and implementing graph convolutions to obtain attention weights that are respectively associated with agents that are located within the surrounding environment. The system and method also include decoding multi modal trajectories and probabilities for each of the agents. The system and method further include controlling at least one vehicle system of the ego vehicle based on predicted trajectories associated with each of the agents and the rankings associated with probabilities that are associated with each of the predicted trajectories.

公开(公告)号：US20210264617A1

公开(公告)日：2021-08-26

申请号：US16917864

申请日：2020-06-30

Applicant: Honda Motor Co., Ltd.

Inventor： Isht Dwivedi ,  Chiho Choi ,  Srikanth Malla ,  Behzad Dariush

IPC: G06T7/246 ,  G05D1/02

Abstract: According to one aspect, composite field based single shot trajectory prediction may include receiving an image of an environment including a number of agents, extracting a set of features from the image, receiving the image of the environment, encoding a set of trajectories from the image, concatenating the set of features and the set of trajectories from the image to generate an interaction module input, receiving the interaction module input, encoding a set of interactions between the number of agents and between the number of agents and the environment, concatenating the set of interactions and a localization composite field map to generate a decoder input, receiving the decoder input, generating the localization composite field map and an association composite field map, and generating a set of trajectory predictions for the number of agents based on the localization composite field map and the association composite field map.

公开(公告)号：US11059493B2

公开(公告)日：2021-07-13

申请号：US16380586

申请日：2019-04-10

Applicant: HONDA MOTOR CO., LTD.

Inventor： Jun Hayakawa ,  Behzad Dariush

IPC: B60W40/105 ,  G06T7/246

Abstract: Systems and methods for estimating velocity of an autonomous vehicle and state information of a surrounding vehicle are provided. In some aspects, the system includes a memory that stores instructions for executing processes for estimating velocity of an autonomous vehicle and state information of the surrounding vehicle and a processor configured to execute the instructions. In various aspects, the processes include: receiving image data from an image capturing device; performing a ground plane estimation by predicting a depth of points on a road surface based on an estimated pixel-level depth; determining a three-dimensional (3D) bounding box of the surrounding vehicle; determining the state information of the surrounding vehicle based on the ground plane estimation and the 3D bounding box; and determining the velocity of the autonomous vehicle based on an immovable object relative to the autonomous vehicle. In some aspects, an operation of the autonomous vehicle may be controlled based on at least one of the state information or the velocity of the autonomous vehicles.