-
公开(公告)号：US20250037478A1
公开(公告)日：2025-01-30
申请号：US18917905
申请日：2024-10-16
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Arjun BHARGAVA , Chao FANG , Charles Christopher OCHOA , Kun-Hsin CHEN , Kuan-Hui LEE , Vitor GUIZILINI
Abstract: A method for generating a dense light detection and ranging (LiDAR) representation by a vision system of a vehicle includes generating, at a depth estimation network, a depth estimate of an environment depicted in an image captured by an image capturing sensor integrated with the vehicle. The method also includes generating, via a sparse depth network, one or more sparse depth estimates of the environment, each sparse depth estimate associated with a respective sparse representation of one or more sparse representations. The method further includes generating the dense LiDAR representation based on a dense depth estimate that is generated based on the depth estimate and the one or more sparse depth estimates. The method still further includes controlling an action of the vehicle based on the dense LiDAR representation.
-
公开(公告)号：US20240010225A1
公开(公告)日：2024-01-11
申请号：US17859945
申请日：2022-07-07
Inventor： Xiangru HUANG , Yue WANG , Vitor GUIZILINI , Rares Andrei AMBRUS , Adrien David GAIDON , Justin SOLOMON
CPC classification number: B60W60/001 , G06V20/58 , B60W2420/52 , B60W2420/42 , B60W2554/4049
Abstract: A method of representation learning for object detection from unlabeled point cloud sequences is described. The method includes detecting moving object traces from temporally-ordered, unlabeled point cloud sequences. The method also includes extracting a set of moving objects based on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method further includes classifying the set of moving objects extracted from on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method also includes estimating 3D bounding boxes for the set of moving objects based on the classifying of the set of moving objects.
-
公开(公告)号：US20220301207A1
公开(公告)日：2022-09-22
申请号：US17390760
申请日：2021-07-30
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Vitor GUIZILINI , Rares Andrei AMBRUS , Adrien David GAIDON , Igor VASILJEVIC , Gregory SHAKHNAROVICH
Abstract: A method for scale-aware depth estimation using multi-camera projection loss is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes training a scale-aware depth estimation model and an ego-motion estimation model according to the multi-camera photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the scale-aware depth estimation model and the ego-motion estimation model. The method also includes planning a vehicle control action of the ego vehicle according to the 360° point cloud of the scene surrounding the ego vehicle.
-
24.发明申请公开(公告)号：US20220262068A1
公开(公告)日：2022-08-18
申请号：US17734899
申请日：2022-05-02
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Vitor GUIZILINI , Adrian David GAIDON
Abstract: A method for three-dimensional (3D) scene reconstruction by an agent includes estimating an ego-motion of the agent based on a current image from a sequence of images and a previous image from the sequence of images. Each image in the sequence of images may be a two-dimensional (2D) image. The method also includes estimating a depth of the current image via a depth estimation model comprising a group of encoder layers and a group of decoder layers. The method further includes generating a 3D reconstruction of the current image based on the estimated ego-motion and the estimated depth. The method still further includes controlling an action of the agent based on the 3D reconstruction.
-
公开(公告)号：US20220148206A1
公开(公告)日：2022-05-12
申请号：US17581743
申请日：2022-01-21
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Vitor GUIZILINI , Sudeep PILLAI , Adrien David GAIDON , Rares A. AMBRUS , Igor VASILJEVIC
Abstract: A method for monocular depth/pose estimation in a camera agnostic network is described. The method includes projecting lifted 3D points onto an image plane according to a predicted ray vector based on a monocular depth model, a monocular pose model, and a camera center of a camera agnostic network. The method also includes predicting a warped target image from a predicted depth map of the monocular depth model, a ray surface of the predicted ray vector, and a projection of the lifted 3D points according to the camera agnostic network.
-
Patent Agency Ranking
公开(公告)号：US20210407117A1
公开(公告)日：2021-12-30
申请号：US16913238
申请日：2020-06-26
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Vitor GUIZILINI , Rares A. AMBRUS , Adrien David GAIDON
Abstract: Systems and methods for extracting ground plane information directly from monocular images using self-supervised depth networks are disclosed. Self-supervised depth networks are used to generate a three-dimensional reconstruction of observed structures. From this reconstruction the system may generate surface normals. The surface normals can be calculated directly from depth maps in a way that is much less computationally expensive and accurate than surface normals extraction from standard LiDAR data. Surface normals facing substantially the same direction and facing upwards may be determined to reflect a ground plane.
-
公开(公告)号：US20210398302A1
公开(公告)日：2021-12-23
申请号：US16908442
申请日：2020-06-22
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Vitor GUIZILINI , Adrien David GAIDON
Abstract: A method for scene reconstruction includes generating a depth estimate and a first pose estimate from a current image. The method also includes generating a second pose estimate based on the current image and one or more previous images in a sequence of images. The method further includes generating a warped image by warping each pixel in the current image based on the depth estimate, the first pose estimate, and the second pose estimate. The method still further includes controlling an action of an agent based on the second warped image.
-
公开(公告)号：US20210326601A1
公开(公告)日：2021-10-21
申请号：US17231905
申请日：2021-04-15
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Jiexiong TANG , Rares Andrei AMBRUS , Jie LI , Vitor GUIZILINI , Sudeep PILLAI , Adrien David GAIDON
Abstract: A method for keypoint matching includes determining a first set of keypoints corresponding to a current environment of the agent. The method further includes determining a second set of keypoints from a pre-built map of the current environment. The method still further includes identifying matching pairs of keypoints from the first set of keypoints and the second set of keypoints based on geometrical similarities between respective keypoints of the first set of keypoints and the second set of keypoints. The method also includes determining a current location of the agent based on the identified matching pairs of keypoints. The method further includes controlling an action of the agent based on the current location.
-
公开(公告)号：US20240135721A1
公开(公告)日：2024-04-25
申请号：US17964827
申请日：2022-10-12
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Rares Andrei AMBRUS , Sergey ZAKHAROV , Vitor GUIZILINI , Adrien David GAIDON
Abstract: A method for improving 3D object detection via object-level augmentations is described. The method includes recognizing, using an image recognition model of a differentiable data generation pipeline, an object in an image of a scene. The method also includes generating, using a 3D reconstruction model, a 3D reconstruction of the scene from the image including the recognized object. The method further includes manipulating, using an object level augmentation model, a random property of the object by a random magnitude at an object level to determine a set of properties and a set of magnitudes of an object manipulation that maximizes a loss function of the image recognition model. The method also includes training a downstream task network based on a set of training data generated based on the set of properties and the set of magnitudes of the object manipulation, such that the loss function is minimized.
-
30.发明公开公开(公告)号：US20230360243A1
公开(公告)日：2023-11-09
申请号：US18344750
申请日：2023-06-29
Applicant: TOYOTA RESEARCH INSTITUTE, INC.
Inventor： Vitor GUIZILINI , Rares Andrei AMBRUS , Adrien David GAIDON , Igor VASILJEVIC , Gregory SHAKHNAROVICH
IPC: G06T7/55 , G06T7/579 , G05D1/02 , B60R1/00 , G06T7/292 , G06T3/00 , G06T7/11 , G06T3/40 , G06N3/08 , B60W60/00
CPC classification number: G06T7/55 , G06T7/579 , G06F18/214 , G05D1/0246 , G06F18/2148 , B60R1/00 , G06T7/292 , H04N23/90 , G06T3/0012 , G06T7/11 , G06T3/40 , G06N3/08 , B60W60/001 , G05D1/0212 , G06T3/0093 , G06T2207/30244 , G06T2207/10028 , G06T2207/20084 , G06T2207/30252 , G06T2207/20081 , G05D2201/0213 , B60R2300/102 , B60W2420/42
Abstract: A method for multi-camera monocular depth estimation using pose averaging is described. The method includes determining a multi-camera photometric loss associated with a multi-camera rig of an ego vehicle. The method also includes determining a multi-camera pose consistency constraint (PCC) loss associated with the multi-camera rig of the ego vehicle. The method further includes adjusting the multi-camera photometric loss according to the multi-camera PCC loss to form a multi-camera PCC photometric loss. The method also includes training a multi-camera depth estimation model and an ego-motion estimation model according to the multi-camera PCC photometric loss. The method further includes predicting a 360° point cloud of a scene surrounding the ego vehicle according to the trained multi-camera depth estimation model and the ego-motion estimation model.
-
-
-
-
-
-
-
-
-
Search Results
39
records
(took 0.034 seconds)
