公开(公告)号：WO2022001811A1

公开(公告)日：2022-01-06

申请号：PCT/CN2021/102030

申请日：2021-06-24

Applicant: 浙江网商银行股份有限公司

Inventor： 顾欣欣 ,  甘利民 ,  汪佳 ,  孙剑哲 ,  余泉 ,  孙晓冬

IPC: G06Q40/02 ,  G06Q50/02 ,  G06K9/00 ,  G06K9/62 ,  G06K9/6267 ,  G06Q40/025 ,  G06V20/188

Abstract: 本说明书实施例提供了授信额度处理方法及装置、作物识别方法及装置，其中，一种授信额度处理方法包括：获取目标用户的作物地块的地块信息；以所述地块信息中包含的地块坐标信息和时间信息为入参，调用作物识别接口进行作物种类识别；根据所述作物识别接口返回的作物种类分布，以及所述地块信息中包含的目标作物种类，确定所述地块信息的置信度；基于所述置信度、所述地块信息以及所述目标作物种类对应的作物属性，确定所述目标用户的授信额度。

公开(公告)号：WO2022000861A1

公开(公告)日：2022-01-06

申请号：PCT/CN2020/121512

申请日：2020-10-16

Applicant: 苏州科达科技股份有限公司

Inventor： 郭腾伟 ,  晋兆龙 ,  邹文艺

IPC: G06T1/00 ,  G06K9/6223 ,  G06K9/6267 ,  G06T1/0021 ,  G06T2201/0065

Abstract: 本申请涉及一种图像篡改区域的定位方法、装置及存储介质，属于图像处理技术领域，该方法包括：对目标图像进行离散小波变换，得到目标图像的对角小波系数矩阵；对对角小波系数矩阵按照不同尺寸进行多次分块，得到每次分块对应的分块系数集；分别对各个分块系数集中的各个分块系数进行噪声估计，得到各个分块系数对应的分块噪声值；结合多次分块对应的各个分块噪声值确定目标图像中的篡改区域；可以解决现有的图像篡改检测方法的适用场景受限的问题；由于图像篡改区域的噪声分布通常与正常区域的噪声分布不同，因此，通过对各个区域的噪声进行估计以检测篡改区域，可以扩大图像篡改检测方法的适用范围，并提高定位篡改区域的准确性。

公开(公告)号：WO2021263035A1

公开(公告)日：2021-12-30

申请号：PCT/US2021/038971

申请日：2021-06-24

Applicant: MAGIC LEAP, INC.

Inventor： MAHENDRAN, Siddharth ,  BANSAL, Nitin ,  SEKHAR, Nitesh ,  GANGWAR, Manushree ,  GUPTA, Khushi ,  SINGHAL, Prateek

IPC: G06K9/62 ,  G06N3/08 ,  G06K9/46 ,  G06T7/00 ,  G06T19/00 ,  G06K9/6261 ,  G06K9/6267 ,  G06N3/04 ,  G06T19/006 ,  G06T2207/20084 ,  G06T7/60 ,  G06T7/73

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for object recognition neural network for amodal center prediction. One of the methods includes receiving an image of an object captured by a camera. The image of the object is processed using an object recognition neural network that is configured to generate an object recognition output. The object recognition output includes data defining a predicted two-dimensional amodal center of the object, wherein the predicted two-dimensional amodal center of the object is a projection of a predicted three-dimensional center of the object under a camera pose of the camera that captured the image.

公开(公告)号：WO2021261836A1

公开(公告)日：2021-12-30

申请号：PCT/KR2021/007562

申请日：2021-06-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： AHN, Youngchun

IPC: H04N21/44 ,  H04N21/434 ,  H04N21/466 ,  G06K9/32 ,  G06K9/00 ,  G06K9/6232 ,  G06K9/6267 ,  G06N3/08 ,  G06V10/44 ,  G06V10/56 ,  G06V20/635 ,  G06V2201/02 ,  G06V30/10 ,  G06V30/245

Abstract: An image detection apparatus includes: a display outputting an image; a memory storing one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: detect, by using a neural network, an additional information area in a first image output on the display; obtain style information of the additional information area from the additional information area; and detect, in a second image output on the display, an additional information area having style information different from the style information by using a model that has learned an additional information area having new style information generated based on the style information.

公开(公告)号：WO2021243787A1

公开(公告)日：2021-12-09

申请号：PCT/CN2020/099945

申请日：2020-07-02

Applicant: 中国科学院自动化研究所

Inventor： 张兆翔 ,  谭铁牛 ,  宋纯锋 ,  樊峻菘

IPC: G06K9/34 ,  G06K9/6256 ,  G06K9/6267 ,  G06K9/6292 ,  G06N3/0454 ,  G06N3/08 ,  G06V10/267

Abstract: 一种基于类内判别器的弱监督图像语义分割方法、系统、装置，旨在解决弱监督采用的粗略标注带来的语义分割不准确的问题。本方法包括：为每个图像级的类别构建两级类内判别器，用以判断所属该图像类别的各像素点属于目标前景或是背景，并使用弱监督的数据进行训练；基于该类内判别器生成像素级的图像类别标签，生成语义分割结果并输出；还可以使用该标签进行图像语义分割模块或网络的训练，得到最终用于无标签输入图像的语义分割的模型。本方法充分挖掘隐含在特征编码中的类内图像信息，准确区分前景与背景像素，在仅依赖图像级标注的情况下，显著地提高弱监督语义分割模型的性能。

公开(公告)号：WO2021239533A1

公开(公告)日：2021-12-02

申请号：PCT/EP2021/063258

申请日：2021-05-19

Applicant: SARTORIUS STEDIM DATA ANALYTICS AB

Inventor： SJÖGREN, Rickard ,  EDLUND, Christoffer ,  SEHLSTEDT, Mattias

IPC: G06K9/00 ,  G06K9/62 ,  G06K9/6267 ,  G06V10/82 ,  G06V20/48 ,  G06V20/49 ,  G06V20/695 ,  G06V20/698

Abstract: A computer-implemented method is provided for analyzing videos of a living system captured with microscopic imaging. The method comprises: obtaining (S10) a base dataset including one or more videos captured with microscopic imaging, at least one of the one or more videos including a cellular event; cropping out (S30), from the base dataset, sub-videos including one or more objects of interest that may be involved in the cellular event; receiving (S40) information indicating a plurality of sub-videos selected from among the sub-videos that are cropped out from the base dataset, the plurality of selected sub-videos including the cellular event; training (S50) an artificial neural network, ANN, model, using the plurality of selected sub-videos as training data, to perform unsupervised video alignment; obtaining (S602) a query sub-video, the query sub-video being: one of the sub-videos that are cropped out from the base dataset, or a sub-video cropped out from a video that is captured with microscopic imaging and that is not included in the base dataset; aligning (S604), using the trained ANN model, the query sub-video with a reference sub-video that is one of the plurality of selected sub-videos; and determining (S606), according to a result of the aligning, whether or not the query sub-video includes the cellular event.

公开(公告)号：WO2021231355A1

公开(公告)日：2021-11-18

申请号：PCT/US2021/031682

申请日：2021-05-11

Applicant: WAYMO LLC

Inventor： MCCOOL, Courtney ,  COOPER, Roshni ,  YANG, Timothy ,  WANG, Yuchi

IPC: B60W60/00 ,  B60W40/02 ,  B60W50/00 ,  B60W60/0011 ,  B60W60/0027 ,  G06K9/00791 ,  G06K9/6267

Abstract: Aspects of the disclosure provide methods for controlling a first vehicle (100) having an autonomous driving mode. In one instance, sensor data generated by one or more sensors of the first vehicle may be received. A splash and characteristics of the splash may be detected from the sensor data using a classifier. A severity of a puddle (680), (682) may be determined based on the characteristics of the splash and a speed of a second vehicle (670), (672) that caused the splash. The first vehicle may be controlled based on the severity. In another instance, a location of a puddle relative to a tire (870) of a second vehicle is estimated using sensor data generated by one or more sensors of the first vehicle. A severity of the puddle may be determined based on the estimated location. The first vehicle may be controlled based on the severity.

公开(公告)号：WO2021231230A1

公开(公告)日：2021-11-18

申请号：PCT/US2021/031415

申请日：2021-05-07

Applicant: ECHONOUS, INC.

Inventor： COOK, Matthew ,  LU, Allen

IPC: A61B8/08 ,  A61B8/00 ,  G16H30/40 ,  G16H50/20 ,  G06N20/00 ,  A61B8/14 ,  A61B8/463 ,  A61B8/469 ,  A61B8/5215 ,  G06K9/6267 ,  G06N3/0454 ,  G06N3/08 ,  G06T11/00 ,  G06T2207/10132 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30004 ,  G06T2210/12 ,  G06T7/0012 ,  G16H30/20 ,  G16H50/50

Abstract: A facility for processing a medical imaging image is described. The facility applies to the image a first machine learning model trained to recognize a view to which an image corresponds, and a second machine learning model trained to identify any of a set of anatomical features visualized in an image. The facility accesses a list of permitted anatomical features for images corresponding to the recognized view, and filters the identified anatomical features to exclude any not on the accessed list. The facility causes the accessed image to be displayed, overlaid with a visual indication of each of the filtered identified anatomical features.

公开(公告)号：WO2021195563A1

公开(公告)日：2021-09-30

申请号：PCT/US2021/024483

申请日：2021-03-26

Applicant: DIGIMARC CORPORATION

Inventor： FILLER, Tomas ,  HOLUB, Vojtech ,  SHARMA, Ravi K. ,  RODRIGUEZ, Tony F. ,  ALATTAR, Osama M. ,  ALATTAR, Adnan M. ,  LORD, John D. ,  JOHNSON, Brian ,  RUOTOLO, Brian ,  RHOADS, Geoffrey B. ,  BRUNK, Hugh L. ,  SEDIGHIANARAKI, Vahid

IPC: G06K9/00 ,  B07C2501/0054 ,  B07C5/3416 ,  B07C5/3422 ,  B65G47/493 ,  G05B13/027 ,  G06K9/6217 ,  G06K9/6267 ,  G06K9/6293 ,  G06T1/0014 ,  G06T1/0021 ,  G06T2207/10024 ,  G06T2207/10048 ,  G06T2207/20084 ,  G06T2207/30108 ,  G06T7/0004 ,  G06T7/90 ,  G06V10/454 ,  G06V10/58 ,  G06V10/82 ,  G06V2201/06 ,  G06V30/224 ,  H04N5/2256 ,  H04N5/2353 ,  H04N7/18

Abstract: Images depicting items in a waste flow on a conveyor belt are provided to two analysis systems. The first system processes images to decode digital watermark payload data found on certain of the items (e.g., plastic containers). This payload data is used to look up corresponding attribute metadata for the items in a database, such as the type of plastic in each item, and whether the item was used as a food container or not. The second analysis system can be a spectroscopy system that determines the type of plastic in each item by its absorption characteristics. When the two systems conflict in identifying the plastic type, a sorting logic processor applies a rule set to arbitrate the conflict and determine which plastic type is most likely. The item is then sorted into one of several different bins depending on a combination of the final plastic identification, and whether the item was used as a food container or not. A variety of other features and arrangements are also detailed.

公开(公告)号：WO2021189959A1

公开(公告)日：2021-09-30

申请号：PCT/CN2020/135333

申请日：2020-12-10

Applicant: 平安科技（深圳）有限公司

Inventor： 周鑫 ,  徐尚良 ,  章古月 ,  陈凯星

IPC: G06T7/00 ,  G06K9/4676 ,  G06K9/6267 ,  G06N3/0454 ,  G06N3/08 ,  G06T2207/20016 ,  G06T2207/30016 ,  G06T7/0012 ,  G06T7/10

Abstract: 涉及人工智能技术领域，一种大脑中线识别方法、装置、计算机设备及存储介质，所述方法包括：通过对与用户标识码关联的脑部图像进行图像预处理得到待识别图像；通过多尺度深度网络模型进行中线特征提取，生成待处理特征图和分类识别结果；通过特征金字塔网络模型对所有待处理特征图进行特征融合，生成融合特征图组；运用双线性插值法，通过加权融合模型对所有融合特征图组进行插值及加权融合，生成待分割特征图像，并对待分割特征图像进行中线分割，得到大脑中线分割识别结果；并合成得到大脑中线图像，输出最终识别结果。该方法自动识别出大脑中线并标明，适用于智慧医疗等领域，可进一步推动智慧城市的建设。