-
公开(公告)号：US20190050693A1
公开(公告)日：2019-02-14
申请号：US15676682
申请日：2017-08-14
Applicant: Ehsan Taghavi
Inventor： Ehsan Taghavi
Abstract: Methods and systems for generating an annotated dataset for training a deep tracking neural network, and training of the neural network using the annotated dataset. For each object in each frame of a dataset, one or more likelihood functions are calculated to correlate feature score of the object with respective feature scores each associated with one or more previously assigned target identifiers (IDs) in a selected range of frames. A target ID is assigned to the object by assigning a previously assigned target ID associated with a calculated highest likelihood or assigning a new target ID. Track management is performed according to a predefined track management scheme to assign a track type to the object. This is performed for all objects in all frames of the dataset. The resulting annotated dataset contains target IDs and track types assigned to all objects in all frames.
-
公开(公告)号：US20240078787A1
公开(公告)日：2024-03-07
申请号：US17902728
申请日：2022-09-02
Applicant: Ehsan TAGHAVI , Ryan RAZANI , Bingbing LIU
Inventor： Ehsan TAGHAVI , Ryan RAZANI , Bingbing LIU
IPC: G06V10/764 , G06T7/73 , G06T15/20 , G06V10/25 , G06V10/26 , G06V10/74 , G06V10/762 , G06V20/58
CPC classification number: G06V10/764 , G06T7/73 , G06T15/205 , G06V10/25 , G06V10/26 , G06V10/74 , G06V10/762 , G06V20/58
Abstract: Method and system for processing a point cloud frame representing a real-world scene that includes one or more objects, including assigning data-element-level classification labels to data elements that each respectively represent one or more points included in the point cloud frame, estimating an approximate position of a first object instance represented in the point cloud frame, assigning an object-instance-level classification label to the first object instance, selecting, for the first object instance, a subgroup of the data elements based on the approximate position, selecting from the subgroup a first cluster of data elements that have assigned data-element-level classification labels that match the object-instance-level classification label assigned to the first object instance, and outputting an object instance list that indicates, for the first object instance, the first cluster of data elements, and the object-instance-level classification label assigned to the first object instance.
-
公开(公告)号：US11815897B2
公开(公告)日：2023-11-14
申请号：US16871711
申请日：2020-05-11
Applicant: Amirhosein Nabatchian , Ehsan Taghavi
Inventor： Amirhosein Nabatchian , Ehsan Taghavi
IPC: G05D1/02 , B60W60/00 , G06T7/20 , G06V20/56 , G06F18/25 , G06F18/214 , G06V10/82 , G01S17/42 , G01S17/931
CPC classification number: G05D1/0214 , B60W60/001 , G05D1/0221 , G05D1/0278 , G06F18/214 , G06F18/25 , G06T7/20 , G06V10/82 , G06V20/56 , B60W2556/50 , G01S17/42 , G01S17/931 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084 , G06T2207/30241 , G06T2207/30252
Abstract: A system and method for generating an importance occupancy grid map (OGM) for a vehicle are disclosed. The method includes: receiving a three-dimensional (3D) point cloud; receiving a binary map, the binary map associated with a set of GPS coordinates of the vehicle; receiving information representative of a planned path for the vehicle; and generating an importance OGM based on the 3D point cloud, the binary map, and the planned path for the vehicle using a map generation module.
-
公开(公告)号：US20230410530A1
公开(公告)日：2023-12-21
申请号：US17827963
申请日：2022-05-30
Applicant: Ehsan TAGHAVI , Ryan RAZANI , Bingbing LIU
Inventor： Ehsan TAGHAVI , Ryan RAZANI , Bingbing LIU
IPC: G06V20/58 , G06V10/26 , G06V10/762 , G06V10/764 , G01S17/89 , B60W30/00
CPC classification number: G06V20/58 , G06V10/26 , G06V10/762 , B60W2420/52 , G01S17/89 , B60W30/00 , G06V10/764
Abstract: Devices, systems, methods, and media are disclosed for performing an object detection task comprising: obtaining a semantic segmentation map representing a real-world space, the semantic segmentation map including an array of elements that each represent a respective location in the real-world space and are assigned a respective element classification label; clustering groups of the elements based on the assigned respective element classification labels to identify at least a first cluster of elements that have each been assigned the same respective element classification label; generating, based on a location of the first cluster within the semantic segmentation map, at least one anchor that defines a respective probable object location of a first dynamic object; and generating, based on the semantic segmentation map and the at least one anchor, a respective bounding box and object instance classification label for the first dynamic object.
-
公开(公告)号：US11676005B2
公开(公告)日：2023-06-13
申请号：US16191011
申请日：2018-11-14
Applicant: Ehsan Nezhadarya , Ehsan Taghavi , Bingbing Liu
Inventor： Ehsan Nezhadarya , Ehsan Taghavi , Bingbing Liu
IPC: G06N3/08
CPC classification number: G06N3/08
Abstract: Methods and systems for deep neural networks using dynamically selected feature-relevant points from a point cloud are described. A plurality of multidimensional feature vectors arranged in a point-feature matrix are received. Each row of the point-feature matrix corresponds to a respective one of the multidimensional feature vectors, and each column of the point-feature matrix corresponds to a respective feature. Each multidimensional feature vector represents a respective unordered point from a point cloud and each multidimensional feature vector includes a respective plurality of feature-correlated values, each feature-correlated value represents a correlation extent of the respective feature. A reduced-max matrix having a selected plurality of feature-relevant vectors is generated. The feature-relevant vectors are selected by, for each respective feature, identifying a respective multidimensional feature vector in the point-feature matrix having a maximum feature-correlated value associated with the respective feature. The reduced-max matrix is output to at least one neural network layer.
-
Patent Agency Ranking
公开(公告)号：US11410388B1
公开(公告)日：2022-08-09
申请号：US17203407
申请日：2021-03-16
Applicant: Ehsan Taghavi , Yuan Ren , Bingbing Liu
Inventor： Ehsan Taghavi , Yuan Ren , Bingbing Liu
Abstract: Devices, systems, methods, and media are described for adaptive scene augmentation of a point cloud frame for inclusion in a labeled point cloud dataset used for training a machine learned model for a prediction task for point cloud frames, such as object detection or segmentation. A formal method is described for generating new point cloud frames based on pre-existing annotated large-scale labeled point cloud frames included in a point cloud dataset to generate new, augmented point cloud frames. A policy is generated for large-scale data augmentation using detailed quantitative metrics such as confusion matrices. The policy is a detailed and stepwise set of rules, procedures, and/or conditions that may be used to generate augmented data specifically targeted to mitigate the existing inaccuracies in the trained model. The augmented point cloud frames may then be used to further train the model to improve the prediction accuracy of the model.
-
7.发明申请公开(公告)号：US20220012466A1
公开(公告)日：2022-01-13
申请号：US16926096
申请日：2020-07-10
Applicant: Ehsan TAGHAVI , Amirhosein NABATCHIAN , Bingbing LIU
Inventor： Ehsan TAGHAVI , Amirhosein NABATCHIAN , Bingbing LIU
Abstract: A system and method for generating a bounding box for an object in proximity to a vehicle are disclosed. The method includes: receiving a three-dimensional (3D) point cloud representative of an environment; receiving a two-dimensional (2D) image of the environment; processing the 3D point cloud to identify an object cluster of 3D data points for a 3D object in the 3D point cloud; processing the 2D image to detect a 2D object in the 2D image and generate information regarding the 2D object from the 2D image; and when the 3D object and the 2D object correspond to the same object in the environment: generating a bird's eye view (BEV) bounding box for the object based on the object cluster of 3D data points and the information from the 2D image.
-
公开(公告)号：US20210347378A1
公开(公告)日：2021-11-11
申请号：US16871711
申请日：2020-05-11
Applicant: Amirhosein NABATCHIAN , Ehsan TAGHAVI
Inventor： Amirhosein NABATCHIAN , Ehsan TAGHAVI
Abstract: A system and method for generating an importance occupancy grid map (OGM) for a vehicle are disclosed. The method includes: receiving a three-dimensional (3D) point cloud; receiving a binary map, the binary map associated with a set of GPS coordinates of the vehicle; receiving information representative of a planned path for the vehicle; and generating an importance OGM based on the 3D point cloud, the binary map, and the planned path for the vehicle using a map generation module.
-
9.发明申请公开(公告)号：US20200151557A1
公开(公告)日：2020-05-14
申请号：US16191011
申请日：2018-11-14
Applicant: Ehsan Nezhadarya , Ehsan Taghavi , Bingbing Liu
Inventor： Ehsan Nezhadarya , Ehsan Taghavi , Bingbing Liu
IPC: G06N3/08
Abstract: Methods and systems for deep neural networks using dynamically selected feature-relevant points from a point cloud are described. A plurality of multidimensional feature vectors arranged in a point-feature matrix are received. Each row of the point-feature matrix corresponds to a respective one of the multidimensional feature vectors, and each column of the point-feature matrix corresponds to a respective feature. Each multidimensional feature vector represents a respective unordered point from a point cloud and each multidimensional feature vector includes a respective plurality of feature-correlated values, each feature-correlated value represents a correlation extent of the respective feature. A reduced-max matrix having a selected plurality of feature-relevant vectors is generated. The feature-relevant vectors are selected by, for each respective feature, identifying a respective multidimensional feature vector in the point-feature matrix having a maximum feature-correlated value associated with the respective feature. The reduced-max matrix is output to at least one neural network layer.
-
公开(公告)号：US10592786B2
公开(公告)日：2020-03-17
申请号：US15676682
申请日：2017-08-14
Applicant: Ehsan Taghavi
Inventor： Ehsan Taghavi
Abstract: Methods and systems for generating an annotated dataset for training a deep tracking neural network, and training of the neural network using the annotated dataset. For each object in each frame of a dataset, one or more likelihood functions are calculated to correlate feature score of the object with respective feature scores each associated with one or more previously assigned target identifiers (IDs) in a selected range of frames. A target ID is assigned to the object by assigning a previously assigned target ID associated with a calculated highest likelihood or assigning a new target ID. Track management is performed according to a predefined track management scheme to assign a track type to the object. This is performed for all objects in all frames of the dataset. The resulting annotated dataset contains target IDs and track types assigned to all objects in all frames.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.019 seconds)
