-
公开(公告)号：EP4222719A1
公开(公告)日：2023-08-09
申请号：EP21816167.7
申请日：2021-11-19
IPC分类号： G06V20/69 , G06V10/762 , G06V10/764 , G06V10/774
-
公开(公告)号：EP4213107A1
公开(公告)日：2023-07-19
申请号：EP22207911.3
申请日：2022-11-16
发明人： DONDERICI, Burkay
IPC分类号： G06V10/774
摘要： The present technology pertains to obtaining sensor data and processed sensor data related to a base world scenario encountered by an AV entity. The sensor data and processed sensor data may be assessed to determine an importance value for the base world scenario. When the importance value is above a threshold, a closed course staging system may stage a re-creation of the base world scenario in a closed course environment (i.e., a closed course scenario). An AV may then interact with the closed course scenario. Sensor data and processed sensor data from the AV's interaction with the closed course scenario may then be added to training data used to train ML models for AVs.
-
公开(公告)号：EP4092632A1
公开(公告)日：2022-11-23
申请号：EP22150491.3
申请日：2022-01-06
发明人： QU, Shuhui , LEE, Janghwan , KANG, Yan
IPC分类号： G06V10/774 , G06V10/82 , G06V10/776 , G06T7/00
摘要： Systems and methods for classifying products are disclosed. A first data sample having a first portion and a second portion is identified from a training dataset. A first mask is generated based on the first data sample, where the first mask is associated with the first portion of the first data sample. A second data sample is generated based on a noise input. The first mask is applied to the second data sample for outputting a third portion of the second data sample. The third portion of the second data sample is combined with the second portion of the first data sample for generating a first combined data sample. Confidence and classification of the first combined data sample are predicted. The first combined data sample is added to the training dataset in response to predicting the confidence and the classification.
-
公开(公告)号：EP4089645A1
公开(公告)日：2022-11-16
申请号：EP22173310.8
申请日：2022-05-13
IPC分类号： G06V20/13 , G06V20/17 , G06V10/82 , G06K9/62 , G06V10/774
摘要： A system and method are disclosed for determining a classification and sub-classification of an aircraft. The system receives an aerial image of a geographic area that includes one or more aircrafts. The system inputs the aerial image into a machine learning model. The system receives an output from the machine learning model for each aircraft of the one or more aircrafts.
Based on the output for each aircraft, the system determines a set of geometric measurements.
The system compares the set of geometric measurements to a plurality of known sets of geometric measurements. Based on the comparison, the system identifies a known set of geometric measurements from the plurality of known sets of geometric measurements. The known set is mapped by a database to a sub-classification. The system outputs the sub-classification.-
45.发明公开
公开(公告)号：EP4060624A1
公开(公告)日：2022-09-21
申请号：EP22161966.1
申请日：2022-03-14
申请人： Ricoh Company, Ltd.
IPC分类号： G06V10/774 , G06V10/778 , G06V40/16 , G06V40/20 , G06V10/80
摘要： A learning apparatus (10) performs machine learning using line-of-sight information of an annotator. The learning apparatus includes input receiving means (13) for receiving an input of first label information to be given to a facial expression image indicating a face of a person. The learning apparatus includes inference means (18) for estimating second label information to be given to the facial expression image based on an interpolated image generated using the facial expression image and line-of-sight information indicating a direction of a line of sight of the annotator, the direction being detected at a time when the input is received. The learning apparatus includes loss calculation means (19) for calculating a difference between the first label information of which the input is received and the estimated second label information. The learning apparatus includes optimization means (20) for updating a parameter used for processing by the inference means (18) based on the calculated difference.
-
公开(公告)号：EP4027306A1
公开(公告)日：2022-07-13
申请号：EP21218499.8
申请日：2021-12-31
发明人： SHAH, Nirav , SANO, Yasuhito , HIROKI, Taniguchi
IPC分类号： G06V20/58 , G06V10/44 , G06V10/774
摘要： Aspects of the present invention relate to methods (40) of traffic light detection and classification. In particular, an aspect of the invention relates to a computer-implemented method (40) of identifying a vertical traffic light (111) in an image. The method (40) comprises: receiving the image from a vehicle camera (2); determining a feature map based on the received image using a convolutional neural network (13, 16); determining a bounding box proposal for the feature map using a region proposal network (14), wherein the bounding box proposal corresponds to a traffic light object (111), wherein the region proposal network (14) determines the bounding box proposal using a single set of anchor boxes (110), and wherein each anchor box (110) in the set of anchor boxes (110) has an aspect ratio configured such that a height of said anchor box (110) is greater than a width of said anchor box (110); and identifying the vertical traffic light (111) within the proposed bounding box using at least a region of interest pooling layer of the convolutional neural network (13, 16).
-
公开(公告)号：EP4027304A1
公开(公告)日：2022-07-13
申请号：EP21218497.2
申请日：2021-12-31
发明人： SHAH, Nirav , SANO, Yasuhito , HIROKI, Taniguchi
IPC分类号： G06V10/44 , G06V10/56 , G06V10/774 , G06V20/58
摘要： Aspects of the present invention relate to methods (60) of traffic light signal detection. In particular, an aspect of the invention relates to a computer-implemented method (60) of determining a status of a traffic light (111) in an image of the traffic light (111). The method (60) comprises: receiving an image of the traffic light (111); dividing the image of the traffic light (111) into at least two portions, including a proceed-signal portion (132) and a stop-signal portion (134); determining a first brightness value of a HSV colour representation of one of the proceed-signal portion (132) and the stop-signal portion (134); comparing the first brightness value to a first threshold; and identifying a first status of the traffic light (111) if the first brightness value is greater than or equal to the first threshold.
-
公开(公告)号：EP3975132A1
公开(公告)日：2022-03-30
申请号：EP21196868.0
申请日：2021-09-15
申请人： Apple Inc.
发明人： ZHU, Jingwen , SHARMA, Vinay , JIN, Jonghoon , GUPTA, Nitin , CHABERT, Floris , DAHLKAMP, Hendrik , NAHMANI, Muriel
IPC分类号： G06V10/44 , G06V10/774 , G06V40/16 , G06V10/26 , G06V20/52
摘要： Techniques are disclosed for determining the presence of a particular person based on facial characteristics. For example, a device may include a first image in a reference set of images based on determining that a face shown in the first image is not covered by a face covering. A trained model of the device may determine a first set of characteristics from the first image, whereby the trained model is trained utilizing simulated face coverings to match a partially covered face of a particular person with a non-covered face of the particular person. The device may also determine a second set of characteristics associated with a face of a second person based on a second image. The trained model may then determine a score corresponding to a level of similarity between both sets of characteristics, and then determine whether the first person is the second person based on the score.
-
公开(公告)号：EP4032025B1
公开(公告)日：2024-11-13
申请号：EP20786175.8
申请日：2020-09-19
IPC分类号： G06V10/771 , G06V10/776 , G06V10/772 , G06V10/774 , G06V10/82 , G06N3/006 , G06N3/084 , G06F18/2115 , G06F18/214 , G06F18/21 , G06F18/2321
-
公开(公告)号：EP3633549B1
公开(公告)日：2024-10-30
申请号：EP18810647.0
申请日：2018-03-16
发明人： WANG, Hao , LI, Zhifeng , JI, Xing , JIA, Fan , WANG, Yitong
IPC分类号： G06V10/774 , G06V10/776 , G06V10/82 , G06V40/16
-
-
-
-
-
-
-
-
-
搜索结果
274 条记录 (耗时 0.019 秒)
