公开(公告)号：US12116007B2

公开(公告)日：2024-10-15

申请号：US17116422

申请日：2020-12-09

申请人： Waymo LLC

发明人： Jared Russell ,  Jens-Steffen Gutmann ,  Ioan-Alexandru Sucan

IPC分类号： B60W60/00 ,  B60W30/08 ,  G01C21/36 ,  G06V20/58

CPC分类号： B60W60/001 ,  B60W30/08 ,  G01C21/3602 ,  G06V20/582 ,  G06V20/584 ,  B60W2030/082 ,  B60W2420/408 ,  B60W2554/4049

摘要： Aspects of the disclosure provide a method of generating and following planned trajectories for an autonomous vehicle. For instance, a baseline for a planned trajectory that the autonomous vehicle can use to follow a route to a destination may be determined. A stopping point corresponding to a traffic control that will cause the autonomous vehicle to come to a stop using the baseline may be determined. Sensor data identifying objects and their locations may be received. A plurality of constraints may be generated based on the sensor data. A planned trajectory may be generated using the baseline, the stopping point, and the plurality of constraints, wherein constraints beyond the stopping point are ignored.

公开(公告)号：US20240331404A1

公开(公告)日：2024-10-03

申请号：US18191939

申请日：2023-03-29

申请人： Siemens Mobility, Inc.

发明人： Benjamin Planche

IPC分类号： G06V20/58 ,  B61L5/18 ,  G06V10/44 ,  G06V10/82

CPC分类号： G06V20/584 ,  B61L5/18 ,  G06V10/454 ,  G06V10/82

摘要： A system for visual inspection of signal lights at a railroad crossing includes a data source comprising a stream of images, the stream of images including images of signal lights at a railroad crossing, an inspection module configured via computer executable instructions to receive the stream of images, detect signal lights and light instances in the stream of images, encode global information relevant to ambient luminosity and return a first feature vector, encode patch information of luminosity of detected signal lights and return a second feature vector, concatenate the first feature vector with the second feature vector and return a concatenated feature vector, and decode the concatenated feature vector and provide status of the signal lights.

公开(公告)号：US20240320988A1

公开(公告)日：2024-09-26

申请号：US18599015

申请日：2024-03-07

申请人： TuSimple, Inc.

发明人： Long SHA ,  Lezhou FENG ,  Pengfei CHEN ,  Panqu WANG

IPC分类号： G06V20/58 ,  G06T7/90 ,  G06V10/25 ,  G06V10/44 ,  G06V10/60 ,  G06V10/80

CPC分类号： G06V20/584 ,  G06T7/90 ,  G06V10/25 ,  G06V10/44 ,  G06V10/60 ,  G06V10/806 ,  G06T2207/20132 ,  G06V2201/07

摘要： Techniques are described for performing image processing on images of cameras located on or in a vehicle. An example technique includes receiving a first set of images obtained by a first camera and a second set of images obtained by a second camera; determining, for each image in the first set, a first set of features of a first object; determining, for each image in the second set, a second set of features of a second object; obtaining a third set of features of an object by combining the first set of features and the second set of features; obtaining a fourth set of features of the object by including one or more features of a light signal of the object; determining characteristic(s) indicated by the light signal; and causing a vehicle to perform a driving related operation based on the characteristic(s) of the object.

公开(公告)号：US20240312224A1

公开(公告)日：2024-09-19

申请号：US18583975

申请日：2024-02-22

申请人： DENSO TEN Limited

发明人： Yuki MATSUMOTO ,  Naoshi Kakita ,  Takashi Kono ,  Shota Kinoshita ,  Yasutaka Nishijima

IPC分类号： G06V20/58 ,  G06T7/11

CPC分类号： G06V20/584 ,  G06T7/11

摘要： An image processing apparatus includes a controller configured to: (i) perform image recognition of a camera image to identify a signal region in which a traffic light exists in the camera image, the traffic light including an arrow light; (ii) identify a candidate region of the signal region, the candidate region satisfying (a) a first condition related to a color component of the arrow light and (b) a second condition related to a luminance component of the arrow light; and (iii) determine that the arrow light of the traffic light is turned on when a size of the candidate region that has been identified is smaller than a predetermined size.

公开(公告)号：US20240312223A1

公开(公告)日：2024-09-19

申请号：US18583093

申请日：2024-02-21

申请人： DENSO TEN Limited

发明人： Naoshi KAKITA ,  Takashi KONO ,  Yuki MATSUMOTO ,  Shota KINOSHITA ,  Yasutaka NISHIJIMA

IPC分类号： G06V20/58 ,  G06V10/56 ,  G06V10/60

CPC分类号： G06V20/584 ,  G06V10/56 ,  G06V10/60

摘要： An image processing apparatus that identifies a light emitting state of a traffic light having a green light, a yellow light and a red light from a camera image includes a controller configured to: (i) detect, from the camera image, each of green pixels, yellow pixels, and red pixels of the green, yellow and red lights of the traffic light; (ii) identify a light emitting region and non-light emitting regions from the green pixels, the yellow pixels and the red pixels that have been detected by comparing the detected pixels to predetermined threshold values; and (iii) determine the light emitting state of the traffic light according to results of relative comparison of luminance and saturation between the light emitting region and the non-light emitting regions that have been identified.

公开(公告)号：US20240312063A1

公开(公告)日：2024-09-19

申请号：US18585116

申请日：2024-02-23

申请人： DENSO TEN Limited

发明人： Shota KINOSHITA ,  Naoshi Kakita ,  Takashi Kono ,  Yuki Matsumoto ,  Yasutaka Nishijima

IPC分类号： G06T7/90 ,  G06V10/56 ,  G06V10/77 ,  G06V20/58

CPC分类号： G06T7/90 ,  G06V10/56 ,  G06V10/7715 ,  G06V20/584

摘要： An image processing apparatus includes a controller that determines a light color of a traffic light from a camera image. The controller is configured to: (i) perform image recognition of the camera image to identify a signal region in which the traffic light exists in the camera image; (ii) set a plurality of different spatial intervals between detectors that detect pixels in the signal region having respective color components of respective lights included in the traffic light; (iii) generate a plurality of feature maps indicating a feature amount for an arrangement pattern of each of the respective color components based on detections of the signal region by the detectors using the plurality of different spatial intervals; and (iv) determine the light color of the traffic light based on the plurality of feature maps.

公开(公告)号：US12092742B2

公开(公告)日：2024-09-17

申请号：US18452322

申请日：2023-08-18

申请人： NVIDIA Corporation

发明人： Lin Yang ,  Mark Damon Wheeler

IPC分类号： G01S17/89 ,  B60R11/04 ,  G01C11/02 ,  G01C21/00 ,  G01C21/30 ,  G01S17/86 ,  G01S17/90 ,  G01S17/931 ,  G05D1/00 ,  G06F16/174 ,  G06T9/00 ,  G06T9/20 ,  G06V20/56 ,  G06V20/58 ,  H04N19/17

CPC分类号： G01S17/89 ,  G01C21/30 ,  G01C21/3841 ,  G01C21/3848 ,  G01C21/3867 ,  G01S17/86 ,  G01S17/90 ,  G01S17/931 ,  G06T9/001 ,  G06T9/20 ,  G06V20/582 ,  G06V20/584 ,  G06V20/588 ,  H04N19/17 ,  B60R11/04 ,  G01C11/025 ,  G05D1/0274 ,  G06F16/1744

摘要： Embodiments relate to methods for efficiently encoding sensor data captured by an autonomous vehicle and building a high definition map using the encoded sensor data. The sensor data can be LiDAR data which is expressed as multiple image representations. Image representations that include important LiDAR data undergo a lossless compression while image representations that include LiDAR data that is more error-tolerant undergo a lossy compression. Therefore, the compressed sensor data can be transmitted to an online system for building a high definition map. When building a high definition map, entities, such as road signs and road lines, are constructed such that when encoded and compressed, the high definition map consumes less storage space. The positions of entities are expressed in relation to a reference centerline in the high definition map. Therefore, each position of an entity can be expressed in fewer numerical digits in comparison to conventional methods.

公开(公告)号：US20240290110A1

公开(公告)日：2024-08-29

申请号：US18411370

申请日：2024-01-12

申请人： Anhui NIO Autonomous Driving Technology Co., Ltd.

发明人： Zhipeng Ge

IPC分类号： G06V20/58 ,  B60W60/00 ,  G06T7/70 ,  G06T7/90

CPC分类号： G06V20/584 ,  B60W60/001 ,  G06T7/70 ,  G06T7/90 ,  B60W2420/403 ,  B60W2555/60 ,  G06T2207/30252

摘要： A traffic light perception method, a vehicle control method, a device, a medium and a vehicle are provided to solve the problem of accurately sensing a status of a traffic light. The method includes: sensing and recognizing a current image frame of the traffic light to obtain a lamp head shape and a color of a currently lit single light in the traffic light; determining a traffic indication direction of a virtual light corresponding to the traffic light based on the lamp head shape of the single light; and determining a color of the traffic indication direction based on the color of the single light, to form a virtual light. According to the above method, a status of a traffic light can be accurately obtained without relying on a high-definition map, which improves the safety and reliability of vehicle driving.

公开(公告)号：US12073632B2

公开(公告)日：2024-08-27

申请号：US16872095

申请日：2020-05-11

申请人： TOYOTA RESEARCH INSTITUTE, INC.

发明人： Kun-Hsin Chen ,  Dennis I. Park ,  Jie Li

IPC分类号： G06V20/58 ,  G06F18/21 ,  G06F18/214 ,  G06N20/00

CPC分类号： G06V20/584 ,  G06F18/2148 ,  G06F18/217 ,  G06N20/00

摘要： Systems and methods are provided for developing/leveraging a hierarchical ontology in traffic light perception. A hierarchical ontology representative of various traffic light characteristic (e.g., states, transitions, colors, shapes, etc.) allow for structured and/or automated annotation (in supervised machine learning), as well as the ability to bootstrap traffic light prediction. Further still, the use of a hierarchical ontology provides the ability to accommodate both coarse and fine-grained model prediction, as well as the ability to generate models that are applicable to different traffic light systems used, e.g., in different geographical regions and/or contexts.

公开(公告)号：US12072442B2

公开(公告)日：2024-08-27

申请号：US17456045

申请日：2021-11-22

申请人： NVIDIA Corporation

发明人： Tommi Koivisto ,  Pekka Janis ,  Tero Kuosmanen ,  Timo Roman ,  Sriya Sarathy ,  William Zhang ,  Nizar Assaf ,  Colin Tracey

IPC分类号： G06V10/46 ,  B60W50/00 ,  G01S7/41 ,  G05D1/00 ,  G06F16/35 ,  G06F18/21 ,  G06F18/214 ,  G06F18/23 ,  G06F18/2413 ,  G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  G06N20/00 ,  G06V10/20 ,  G06V10/44 ,  G06V10/762 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V20/58 ,  G01S7/48 ,  G01S13/86 ,  G01S13/931 ,  G01S17/931 ,  G06N3/047 ,  G06N3/048

CPC分类号： G01S7/417 ,  B60W50/00 ,  G05D1/0246 ,  G06F16/35 ,  G06F18/214 ,  G06F18/217 ,  G06F18/23 ,  G06F18/2414 ,  G06N3/044 ,  G06N3/045 ,  G06N3/084 ,  G06N20/00 ,  G06V10/255 ,  G06V10/454 ,  G06V10/46 ,  G06V10/762 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V20/58 ,  G06V20/584 ,  G01S7/412 ,  G01S7/4802 ,  G01S13/867 ,  G01S2013/9318 ,  G01S2013/9323 ,  G01S17/931 ,  G06N3/047 ,  G06N3/048

摘要： In various examples, detected object data representative of locations of detected objects in a field of view may be determined. One or more clusters of the detected objects may be generated based at least in part on the locations and features of the cluster may be determined for use as inputs to a machine learning model(s). A confidence score, computed by the machine learning model(s) based at least in part on the inputs, may be received, where the confidence score may be representative of a probability that the cluster corresponds to an object depicted at least partially in the field of view. Further examples provide approaches for determining ground truth data for training object detectors, such as for determining coverage values for ground truth objects using associated shapes, and for determining soft coverage values for ground truth objects.