利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

12235 条记录 (耗时 0.031 秒)

    Scanner
    4.
    外观设计
    Scanner 有权

    公开(公告)号：USD1046157S1

    公开(公告)日：2024-10-08

    申请号：US29839411

    申请日：2022-05-20

    申请人： CANON MEDICAL SYSTEMS CORPORATION

    设计人： Seishiro Takano

    摘要： FIG. 1 is a perspective view of a scanner showing my new design;
    FIG. 2 is a front elevational view thereof;
    FIG. 3 is a rear elevational view thereof;
    FIG. 4 is a top plan view thereof;
    FIG. 5 is a bottom plan view thereof;
    FIG. 6 is a left-side elevational view thereof; and,
    FIG. 7 is a right-side elevational view thereof.

    Systems, apparatus, and methods for maintenance of stormwater management systems
    7.
    发明授权
    Systems, apparatus, and methods for maintenance of stormwater management systems 有权

    公开(公告)号：US12065821B2

    公开(公告)日：2024-08-20

    申请号：US17333292

    申请日：2021-05-28

    申请人： ADVANCED DRAINAGE SYSTEMS, INC.

    发明人： Gregory Spires ,  Brian Rustia ,  Evan Geno ,  Michael Kuehn

    IPC分类号： E03F5/10

    CPC分类号： E03F5/106

    摘要： Stormwater management systems, methods, and apparatuses for containing and filtering runoff may be provided. In one implementation, a flared end ramp for managing flow of material into a stormwater chamber may be provided. The flared end ramp may include an inlet end configured for connection with a pipe, a side wall of the flared end ramp having a rounded profile at the inlet end; an outlet end configured for placement within the stormwater chamber; and an inclined surface extending between the inlet end and the outlet end of the flared end ramp and configured to deliver material from the pipe into the stormwater chamber. The outlet end of the flared end ramp may have a larger width than the inlet end of the flared end ramp such that the inclined surface is angled laterally outward from the inlet end toward the outlet end.

    Symbol recognition from raster images of PandIDs using a single instance per symbol class
    10.
    发明授权
    Symbol recognition from raster images of PandIDs using a single instance per symbol class 有权

    公开(公告)号：US12039641B2

    公开(公告)日：2024-07-16

    申请号：US17722527

    申请日：2022-04-18

    申请人： Tata Consultancy Services Limited

    发明人： Shubham Singh Paliwal ,  Lovekesh Vig ,  Monika Sharma

    IPC分类号： G06T11/20 ,  G06N3/04 ,  G06T3/147 ,  G06T11/40

    CPC分类号： G06T11/203 ,  G06N3/04 ,  G06T3/147 ,  G06T11/40

    摘要： Traditional systems that enable extracting information from Piping and Instrumentation Diagrams (P&IDs) lack accuracy due to existing noise in the images or require a significant volume of annotated symbols for training if deep learning models that provide good accuracy are utilized. Conventional few-shot/one-shot learning approaches require a significant number of training tasks for meta-training prior. The present disclosure provides a method and system that utilizes the one-shot learning approach that enables symbol recognition using a single instance per symbol class which is represented as a graph with points (pixels) sampled along the boundaries of different symbols present in the P&ID and subsequently, utilizes a Graph Convolutional Neural Network (GCNN) or a GCNN appended to a Convolutional Neural Network (CNN) for symbol classification. Accordingly, given a clean symbol image for each symbol class, all instances of the symbol class may be recognized from noisy and crowded P&IDs.