-
公开(公告)号：US20230350050A1
公开(公告)日：2023-11-02
申请号：US17731021
申请日：2022-04-27
IPC分类号： G01S13/86 , G01S13/931 , G01S13/89
CPC分类号： G01S13/867 , G01S13/931 , G01S13/89
摘要： The disclosure generally relates to methods for gathering radar measurements, wherein the radar measurements includes one or more angular uncertainties, generating a two dimensional radar uncertainty cloud, wherein the radar uncertainty cloud includes one or more shaded regions that each represent an angular uncertainty, capturing image data, wherein the image data includes one or more targets within a region of interest, and fusing the two dimensional radar uncertainty cloud with the image data to overlay the one or more regions of uncertainty over a target.
-
公开(公告)号：US11776281B2
公开(公告)日：2023-10-03
申请号：US17130435
申请日：2020-12-22
发明人： Kun-Hsin Chen , Kuan-Hui Lee , Jia-En Pan , Sudeep Pillai
IPC分类号： G06V20/00 , G06V20/58 , G06T7/246 , G06V30/262 , G06F18/21 , G06F18/24 , G06N3/044 , G06N3/045 , G08G1/095
CPC分类号： G06V20/584 , G06F18/21 , G06F18/24 , G06N3/044 , G06N3/045 , G06T7/248 , G06V30/274 , G06T2207/10016 , G06T2207/20084 , G06T2207/30252 , G08G1/095
摘要： A traffic light classification system for a vehicle includes an image capture device to capture an image of a scene that includes a traffic light with multiple light signals, a processor, and a memory communicably coupled to the processor and storing a first neural network module including instructions that when executed by the processor cause the processor to determine, based on inputting the image into a neural network, a semantic keypoint for each light signal in the traffic light, and determine, based on each semantic keypoint, a classification state of each light signal.
-
33.发明授权公开(公告)号：US11610314B2
公开(公告)日：2023-03-21
申请号：US16858373
申请日：2020-04-24
发明人： Kuan-Hui Lee , Jie Li , Adrien David Gaidon
摘要： Systems and methods for panoptic segmentation of an image of a scene, comprising: receiving a synthetic data set as simulation data set in a simulation domain, the simulation data set comprising a plurality of synthetic data objects; disentangling the synthetic data objects by class for a plurality of object classes; training each class of the plurality of classes separately by applying a Generative Adversarial Network (GAN) to each class from the data set in the simulation domain to create a generated instance for each class; combining the generated instances for each class with labels for the objects in each class to obtain a fake instance of an object; fusing the fake instances to create a fused image; and applying a GAN to the fused image and a corresponding real data set in a real-world domain to obtain an updated data set. The process can be repeated across multiple iterations.
-
公开(公告)号：US11604936B2
公开(公告)日：2023-03-14
申请号：US16827252
申请日：2020-03-23
申请人： TOYOTA RESEARCH INSTITUTE, INC. , THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIVERSITY
发明人： Boxiao Pan , Haoye Cai , De-An Huang , Kuan-Hui Lee , Adrien David Gaidon , Ehsan Adeli-Mosabbeb , Juan Carlos Niebles Duque
摘要： A method for scene perception using video captioning based on a spatio-temporal graph model is described. The method includes decomposing the spatio-temporal graph model of a scene in input video into a spatial graph and a temporal graph. The method also includes modeling a two branch framework having an object branch and a scene branch according to the spatial graph and the temporal graph to learn object interactions between the object branch and the scene branch. The method further includes transferring the learned object interactions from the object branch to the scene branch as privileged information. The method also includes captioning the scene by aligning language logits from the object branch and the scene branch according to the learned object interactions.
-
公开(公告)号：US20220392089A1
公开(公告)日：2022-12-08
申请号：US17489231
申请日：2021-09-29
摘要： Systems and methods described herein relate to jointly training a machine-learning-based monocular optical flow, depth, and scene flow estimator. One embodiment processes a pair of temporally adjacent monocular image frames using a first neural network structure to produce an optical flow estimate and to extract, from at least one image frame in the pair of temporally adjacent monocular image frames, a set of encoded image context features; triangulates the optical flow estimate to generate a depth map; extracts a set of encoded depth context features from the depth map using a depth context encoder; and combines the set of encoded image context features and the set of encoded depth context features to improve performance of a second neural network structure in estimating depth and scene flow.
-
公开(公告)号：US20220284222A1
公开(公告)日：2022-09-08
申请号：US17192443
申请日：2021-03-04
发明人： Jia-En Pan , Kuan-Hui Lee , Chao Fang , Kun-Hsin Chen , Arjun Bhargava , Sudeep Pillai
摘要： In one embodiment, a vehicle light classification system captures a sequence of images of a scene that includes a front/rear view of a vehicle with front/rear-side lights, determines semantic keypoints, in the images and associated with the front/rear-side lights, based on inputting the images into a first neural network, obtains multiple difference images that are each a difference between successive images from among the sequence of images, the successive images being aligned based on their respective semantic keypoints, and determines a classification of the front/rear-side lights based at least in part on the difference images by inputting the difference images into a second neural network.
-
37.发明申请公开(公告)号：US20220261583A1
公开(公告)日：2022-08-18
申请号：US17177516
申请日：2021-02-17
发明人： Kun-Hsin Chen , Peiyan Gong , Sudeep Pillai , Arjun Bhargava , Shunsho Kaku , Hai Jin , Kuan-Hui Lee
摘要： Systems, methods, computer-readable media, techniques, and methodologies are disclosed for performing end-to-end, learning-based keypoint detection and association. A scene graph of a signalized intersection is constructed from an input image of the intersection. The scene graph includes detected keypoints and linkages identified between the keypoints. The scene graph can be used along with a vehicle's localization information to identify which keypoint that represents a traffic signal is associated with the vehicle's current travel lane. An appropriate vehicle action may then be determined based on a transition state of the traffic signal keypoint and trajectory information for the vehicle. A control signal indicative of this vehicle action may then be output to cause an autonomous vehicle, for example, to implement the appropriate vehicle action.
-
38.发明申请公开(公告)号：US20190147582A1
公开(公告)日：2019-05-16
申请号：US15893864
申请日：2018-02-12
发明人： Kuan-Hui Lee , German Ros , Adrien D. Gaidon , Jie Li
摘要： Systems and method for generating photorealistic images include training a generative adversarial network (GAN) model by jointly learning a first generator, a first discriminator, and a set of predictors through an iterative process of optimizing a minimax objective. The first discriminator learns to determine a synthetic-to-real image from a real image. The first generator learns to generate the synthetic-to-real image from a synthetic image such that the first discriminator determines the synthetic-to-real image is real. The set of predictors learn to predict at least one of a semantic segmentation labeled data and a privileged information from the synthetic-to-real image based on at least one of a known semantic segmentation labeled data and a known privileged information corresponding to the synthetic image. Once trained, the GAN model may generate one or more photorealistic images using the trained GAN model.
-
公开(公告)号：US20180217233A1
公开(公告)日：2018-08-02
申请号：US15420099
申请日：2017-01-31
发明人： Kuan-Hui Lee
CPC分类号： G01S7/4802 , G01S17/936 , G06K9/00201 , G06K9/00805 , G06K9/6255 , G06N20/00
摘要： System, methods, and other embodiments described herein relate to estimating an object from acquired data that is a partial observation of the object. In one embodiment, a method includes accessing, from a database, object data that is a three-dimensional representation of a known object. The method includes transforming the object data to produce partial data that is a partial representation of the known object with a relative fewer number of data points than the object data. The method includes training an observation model by using the partial data that is linked to the known object to represent relationships between the object data and the partial data that provide for estimating the known object from the obscured data of a partially observed object that is unknown.
-
公开(公告)号：US12087063B2
公开(公告)日：2024-09-10
申请号：US17731433
申请日：2022-04-28
CPC分类号： G06V20/584 , B60W60/0027 , G06V10/255 , G06V20/588 , B60W2420/403
摘要： System, methods, and other embodiments described herein relate to detection of traffic lights corresponding to a driving lane from views captured by multiple cameras. In one embodiment, a method includes estimating, by a first model using images from multiple cameras, positions and state confidences of traffic lights corresponding to a driving lane of a vehicle. The method also includes aggregating, by a second model, the state confidences and a multi-view stereo composition from geometric representations associated with the positions of the traffic lights. The method also includes assigning, by the second model according to the aggregating, a relevancy score computed for a candidate traffic light of the traffic lights to the driving lane. The method also includes executing a task by the vehicle according to the relevancy score.
-
-
-
-
-
-
-
-
-
搜索结果
51 条记录 (耗时 0.027 秒)
