会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明公开
    • PROCÉDÉ DE DÉTERMINATION D'UN PLAN DU SOL À PARTIR D'UNE IMAGE DE PROFONDEUR
    • VERFAHREN ZUR BESTIMMUNG EINER GRUNDEBENE AUS EINEM TIEFENBILD
    • EP2828825A1
    • 2015-01-28
    • EP13709900.8
    • 2013-03-15
    • Commissariat à l'Énergie Atomique et aux Énergies Alternatives
    • ALLEZARD, NicolasHERVIEU, AlexandreLUCAT, Laurent
    • G06T7/00
    • G06T7/0051G06K9/00201G06T7/50G06T7/75G06T2207/10021G06T2207/10028G06T2207/30252
    • The invention relates to the field of image processing applied to the detection of targets and, more precisely, to the field of the estimation of the ground plane in images. It relates to a method of determining a triplet of parameters defining a ground plane on the basis of a depth image. The method of determining the ground plane comprises in particular a step of determining several triplets of parameters each defining a ground plane, a step of spatial filtering of the parameters and a step of temporal filtering of the parameters. According to the invention, the temporal filtering of the parameters is dependent on an indicator R
      3d representative of the quality of the data of the depth image which are available for the determination of the ground plane. The temporal filtering of the parameters may also be dependent on an indicator R
      pl representative of the quality of the ground plane determined after spatial filtering. Likewise, the spatial filtering may also be parameterized as a function of the indicators R
      3d and R
      pl . Globally, the invention implements the idea according to which the more the plane estimated for a depth image makes it possible to "explain" the points of this image, the more accurately the planes of the subsequent images may be determined. In particular, for the spatial filtering, this involves a ground plane search in a more limited space and, for the temporal filtering, a less significant consideration of the ground planes estimated previously.
    • 确定基于深度图像定义接地平面的参数的三元组的方法包括确定参数的多个三元组,各自定义接地平面,参数的空间滤波以及参数的时间滤波。 时间滤波取决于可用于确定地平面的深度图像数据的质量指标。 时间滤波取决于空间滤波后确定的接地平面的质量指标。 类似地,空间滤波可以被参数化为两个指标的函数。 在全球范围内,深度图像的估计平面越多,可以“解释”该图像中的点,确定后续图像的平面越准确。 对于空间滤波,在更有限的空间中搜索接地平面,并且对于时间滤波,先前估计的接地平面被认为是较小的程度。
    • 3. 发明公开
    • PROCEDE ET SYSTEME DE DETECTION D'EVENEMENTS DE NATURE CONNUE
    • EP3198523A1
    • 2017-08-02
    • EP15767185.0
    • 2015-09-24
    • Commissariat à l'Énergie Atomique et aux Énergies Alternatives
    • CHAN-HON-TONG, AdrienLUCAT, Laurent
    • G06K9/00
    • G06K9/00201G06K9/00221G06K9/00302G06K9/00335G06K9/00362G06K9/00711
    • The invention relates to a method for detecting events in a signal received on a detection sensor (22) connected to a processor (20) comprising at least the following steps, given {E
      e }
      e=1..Ne natural events, a voting field D consisting of I subfields D
      i ={ [d
      i , d
      i+1 [ } where i=1...I and a dictionary of micro-events {m
      i }
      i=1..M : initializing, at an identical value, a table S containing score values, S[e][p], where p is a space or time position index (p ∈ D); detecting one or more micro-events m
      n (n=1..N), located at t
      n (n=1..N), (20), corresponding to the quantification of a local observation O
      n in the signal; for each micro-event m
      n located at t
      n , for each event type "e", and for each subfield D
      i , updating the table S[e][t
      n + p] by adding a constant value for all the locations p ∈ D
      i , (31); and determining a set of events associated with an observation in the signal from table S, (32) and detecting the likeliest event associated with an observation of the signal.
    • 本发明涉及一种用于检测在连接到处理器(20)的检测传感器(22)上接收到的信号中的事件的方法,该方法包括至少以下步骤,给定{Ee} = 1..Ne自然事件,投票场 D由I个子域组成Di = {[di,di + 1]}其中i = 1 ... I和一个微事件字典{mi} i = 1..M:以相同的值初始化一个表 S包含分数值S [e] [p],其中p是空间或时间位置索引(p∈D); 检测位于tn(n = 1..N),(20)处的一个或多个微事件mn(n = 1..N),对应于信号中的局部观察On的量化; 对于位于tn的每个微事件mn,针对每个事件类型“e”,并且对于每个子字段Di,通过为所有位置p∈Di添加常数值来更新表S [e] [tn + p] 31); 以及确定与来自表S(32)的信号中的观察值相关联的一组事件并检测与信号观察相关联的最可能事件。