WO2018171016A1 - 压力和高度数据整合方法及系统 - Google Patents

压力和高度数据整合方法及系统 Download PDF

Info

Publication number
WO2018171016A1
WO2018171016A1 PCT/CN2017/084092 CN2017084092W WO2018171016A1 WO 2018171016 A1 WO2018171016 A1 WO 2018171016A1 CN 2017084092 W CN2017084092 W CN 2017084092W WO 2018171016 A1 WO2018171016 A1 WO 2018171016A1
Authority
WO
WIPO (PCT)
Prior art keywords
distribution
pressure
distribution mode
data
height data
Prior art date
Application number
PCT/CN2017/084092
Other languages
English (en)
French (fr)
Inventor
辛志宇
闵苏
Original Assignee
魔玛智能科技（上海）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 魔玛智能科技（上海）有限公司 filed Critical 魔玛智能科技（上海）有限公司
Publication of WO2018171016A1 publication Critical patent/WO2018171016A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/251—Fusion techniques of input or preprocessed data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features

Definitions

  • the present invention relates to computers and intelligent systems, and in particular to a method and system for integrating pressure and altitude data.
  • the surface involved in the interaction with the contact object needs to collect and process the surface force state data and the deformation state data, and then judge the state and behavior of the contact object. Identification.
  • the patent document CN106039585A (Application No. 201610443676.7) discloses "a smart mattress with posture sensing and physiotherapy sleep function", including a mattress substrate, a flexible array force sensor layer, a heat insulation layer, and a far infrared heat. Layer, protective layer, knitted fabric layer, signal acquisition control module, intelligent terminal and cloud server. Smart mattress monitors and evaluates user sleep quality by collecting and analyzing pressure distribution data information, and performs infrared rehabilitation on specific parts of users according to needs. Physiotherapy to improve the quality of sleep for users.
  • This patent document reflects a commonly used method in which a uniform pressure sensor array is used to obtain a pressure data set and perform calculation processing.
  • this method is complicated in arrangement, high in cost, and flexible in adapting to actual needs.
  • only distributed pressure data sets often do not fully reflect the surface condition and its relationship with the contact object.
  • the corresponding set of height deformation data collectively reflects the surface condition and its relationship with the contact object, thereby more accurately determining and identifying the surface state and the behavior and state of the contact object.
  • a method for integrating pressure and height data according to the present invention includes:
  • Hybrid distribution data collection step for the same surface area, the pressure data is collected according to the first distribution mode, and the height data is collected according to the second distribution mode, wherein the first distribution mode is different from the second distribution mode.
  • any of the following distribution modes are employed:
  • the first distribution mode is a multi-sub-region distribution mode
  • the second distribution mode is a multi-point distribution mode
  • the first distribution mode is a multi-point distribution mode
  • the second distribution mode is a multi-sub-region distribution mode.
  • the first distribution mode is a multi-sub-area distribution manner arranged in a linear direction
  • the second distribution mode is a grid lattice distribution mode
  • Feature acquisition step acquiring a force condition feature according to the pressure data, and acquiring a morphological condition feature according to the height data;
  • the identification step identifying the state of the surface region according to the characteristics of the force condition and the morphological condition, and obtaining the recognition result;
  • Contrast step By comparing the instantaneous surface area state with the diachronic surface area state, the behavior of the contact object of the surface area is obtained.
  • the data fusion step performed before the feature acquisition step is further included;
  • the pressure data collected according to the first distribution manner is merged with the height data collected according to the second distribution manner to obtain mixed lattice pressure data;
  • the pressure data on which the feature of the force condition is acquired in the feature acquisition step uses mixed lattice pressure data.
  • a pressure and height data integration system includes:
  • the mixed distribution data collecting device collects pressure data according to the first distribution manner for the same surface area, and collects the height data according to the second distribution manner, wherein the first distribution manner is different from the second distribution manner.
  • any of the following distribution modes are employed:
  • the first distribution mode is a multi-sub-region distribution mode
  • the second distribution mode is a multi-point distribution mode
  • the first distribution mode is a multi-point distribution mode
  • the second distribution mode is a multi-sub-region distribution mode.
  • the first distribution mode is a multi-sub-area distribution manner arranged in a linear direction
  • the second distribution mode is a grid lattice distribution mode
  • Feature acquisition device acquiring a force condition feature according to the pressure data, and acquiring a morphological condition feature according to the height data;
  • the identification device identifies the state of the surface region according to the characteristics of the force condition and the morphological condition, and obtains the recognition result;
  • Contrast device the surface is obtained by comparing the state of the immediate surface area with the state of the surface area over time. The behavior of the contact object in the area.
  • the pressure data collected according to the first distribution manner is merged with the height data collected according to the second distribution manner to obtain mixed lattice pressure data;
  • the pressure data according to the feature acquisition device for acquiring the force condition feature uses mixed lattice pressure data.
  • the present invention has the following beneficial effects:
  • the invention adopts a pressure and height data acquisition device with a mixed distribution of collection points to realize complex data collection requirements for describing the state and relationship of the surface and its contact objects.
  • the present invention processes, combines, and compares the pressure and height data collected by the hybrid distribution to obtain a plurality of features describing key regions and nodes of the surface state.
  • the present invention calculates the mutual relationship between the above features to realize the judgment and recognition of the surface human body state and behavior.
  • FIG 1 and 2 are flow charts of two preferred embodiments of the pressure and height data integration method provided by the present invention.
  • the invention provides a method for integrating pressure and height data, comprising:
  • Hybrid distribution data collection step collecting pressure data according to a first distribution manner for the same surface area, and collecting height data according to a second distribution manner, wherein the first distribution manner is different from the second distribution manner;
  • Data fusion step in the data preprocessing stage, the pressure data collected according to the first distribution mode is merged with the height data collected according to the second distribution manner to obtain mixed lattice pressure data; the meaning of the data fusion step is mainly Therefore, if conventionally, it is more necessary to arrange two sets of array sensor systems corresponding to pressure and height in the same area, the complexity and cost of implementation are very high.
  • Feature acquisition step acquiring a force condition feature according to the mixed lattice pressure data, and acquiring a morphological condition feature according to the height data;
  • the identification step identifying the state of the surface region according to the characteristics of the force condition and the morphological condition, and obtaining the recognition result;
  • Contrast step By comparing the instantaneous surface area state with the diachronic surface area state, the behavior of the contact object of the surface area is obtained.
  • the pressure data and the height data collected in the hybrid distribution data collection step are not only for the same surface area, but also the acquisition time of the pressure data and the height data are in the same time period, for example, the same traversal period, that is, synchronization. Or at the same time.
  • Pressure data and height data are collected in the same surface area and in the same time period by different first distribution patterns and second distribution patterns, respectively, to reflect the stress state and deformation state of the surface region, thereby realizing the mixed distribution.
  • the surface area refers in particular to an area that is in direct contact with the human body or in indirect contact with the human body by a fabric such as clothing.
  • the surface area may be a mattress surface or a cushion surface, a recliner surface or a pillow surface.
  • the surface area may be the entire support surface of the furniture such as a smart bed, a reclining chair, or the like, or may be a partial area in the entire support surface.
  • the hybrid distribution data collection step may be performed independently or in association with each other for the plurality of surface regions, and then subsequent feature acquisition steps, identification steps, and comparison steps are performed accordingly.
  • the pressure data and the height data are for the same surface area and the acquisition time is at the same time period
  • the pressure data and the height data both include a position attribute and a time attribute, wherein the time attribute is marked by a time stamp.
  • Time information such as date and time of pressure data or height data collection.
  • the first distribution mode is a multi-sub-area distribution mode
  • the second distribution mode is a multi-point distribution mode
  • the first distribution mode is a multi-point distribution mode
  • the second distribution mode is a multi-sub-area distribution mode.
  • the first distribution mode is a multi-sub-area distribution manner arranged in a linear direction
  • the second distribution mode is a grid lattice distribution mode.
  • the sub-area may be a part of the surface area. When the sub-area is divided, the plurality of sub-areas may not overlap each other, and the plurality of sub-areas may overlap.
  • the main focus of the pressure data is the data change along the height direction of the human body, so the linear direction can be For the height of the human body.
  • a plurality of sub-areas may be arranged along the width direction of the human body.
  • height data reflecting surface area deformation needs to be presented in a matrix to capture the three-dimensional features of the human body's lying posture. The pressure in the sub-area can be reflected by the air bag in the mattress to a pressure in the sub-area.
  • the second point that needs to be more specifically explained is that in order to accurately identify the human body object, the state of the human body in the surface area or the lying behavior of the human body, the pressure data and the height data collection point adopt different mixed distribution modes in the two-dimensional area of the surface.
  • the pressure data acquisition points or collection areas are arranged along the length direction, reflecting changes in pressure data in successive longitudinal regions.
  • the height data collection point uses the grid lattice distribution to reflect the deformation of the two-dimensional surface area in the height direction; due to the mixing and comparison of the pressure data, the grid lattice distribution can be spaced apart at the maximum spacing. The number of sensors required is reduced, which greatly reduces the actual cost of the technical solution.
  • the maximum spacing refers to the maximum distributed separation distance between the array distribution sensors on the physical space plane when the acquired data can meet the requirements for describing the surface requirements.
  • the pressure data can be collected by a pressure sensor, and the height data can be collected by a height measuring device, or converted into height data by pressure data collected by a pressure sensor distributed in a lattice. Therefore, the height data collected according to the second distribution manner may be converted by the pressure data collected according to the second distribution manner, and the height data may not be directly collected, wherein the pressure data may be linear with the height data. Related. Similarly, it is not necessarily the pressure data collected directly, but it can also be obtained by collecting data different from the pressure data.
  • the original collected pressure data and height data are pre-processed, for example, statistically cleaning the abnormal values in the vacancy and the collected data at the collection time, and simultaneously performing the above pressure data and height data.
  • the standardization process is performed, and the data output after processing is saved in a specific data structure including a time stamp and a positional relationship.
  • the eigenvalues are solved for the pressure data and the height data of the surface region containing the positional relationship in the same traversal cycle, and the pressure feature value and the distribution feature value of the surface region are obtained, and the height feature value of the surface region is obtained at the same time.
  • the height geometric feature value especially the key feature value of the height direction, obtains the characteristic value of the stress state and the deformation state characteristic value of the surface area, and saves it.
  • the pressure data is specifically the lattice pressure data after the integration process.
  • identifying step and the comparing step determining whether the contact object belongs to the human body and marking according to the weight, height and weight distribution of the lying body on the surface based on the mixed lattice pressure data, and simultaneously identifying and marking the human body part and the lying posture For user object recognition and recognition of user behavior such as turning over, going to bed, and the like.
  • the present invention provides a pressure and altitude data integration system comprising:
  • Hybrid distribution data collection device collecting pressure data according to a first distribution manner for the same surface area, and collecting height data according to a second distribution manner, wherein the first distribution manner is different from the second distribution manner;
  • Feature acquisition device acquiring a force condition feature according to the pressure data, and acquiring a morphological condition feature according to the height data;
  • the identification device identifies the state of the surface region according to the characteristics of the force condition and the morphological condition, and obtains the recognition result;
  • Contrast device The behavior of the contact object of the surface region is obtained by comparing the state of the instant surface region with the state of the surface region over time.
  • the pressure and altitude data integration system further includes a data fusion device that is executed prior to the feature acquisition device;
  • the pressure data collected according to the first distribution manner is merged with the height data collected according to the second distribution manner to obtain mixed lattice pressure data;
  • the pressure data according to the feature acquisition device for acquiring the force condition feature uses mixed lattice pressure data.
  • the first distribution mode and the second distribution mode adopt any one of the following distribution modes:
  • the first distribution mode is a multi-sub-region distribution mode
  • the second distribution mode is a multi-point distribution mode
  • the first distribution mode is a multi-point distribution mode
  • the second distribution mode is a multi-sub-region distribution mode.
  • the first distribution mode is a distribution pattern of multiple sub-regions arranged in a straight line direction
  • the second distribution mode is a grid lattice distribution mode.
  • the invention accurately reflects the surface state and its complex relationship with the contact object from the two dimensions of pressure and deformation height, and realizes accurate judgment and recognition of the state and behavior of the contact object, thereby greatly reducing the density of the sampling point arrangement.
  • the system layout scheme can be flexibly adjusted according to actual needs to obtain better recognition results.
  • the method and system provided by the present invention can be applied to smart furniture, and thus the present invention provides smart furniture, such as a smart bed, a smart chair, a smart pad, and the like that can support the human body.
  • the system provided by the present invention and its various devices can be fully implemented by logically programming the method steps, except that the system provided by the present invention and its various devices, modules, and units are implemented in a purely computer readable program code.
  • Modules and units implement the same functions in the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules and units provided by the present invention can be regarded as a hardware component, and the devices, modules and units included therein for implementing various functions can also be regarded as hardware components.
  • the device, module, and unit for implementing various functions can also be regarded as a software module that can be both a method and a hardware component.

Abstract

本发明提供了一种压力和高度数据整合方法及系统，其针对同一表面区域，按照第一分布方式采集压力数据，并按照第二分布方式采集高度数据，其中，第一分布方式不同于第二分布方式。本发明采用采集点混合分布的压力和高度数据采集装置，实现描述表面及其接触对象状态和相互关系的复杂数据采集要求；本发明对混合分布采集的压力和高度数据进行处理、合并、比对，获得描述表面状态关键区域和节点的多个特征；本发明对上述特征间的相互关系进行运算，实现对表面人体状态和行为进行判断和识别。

Description

压力和高度数据整合方法及系统 技术领域
本发明涉及计算机及智能系统，具体地，涉及压力和高度数据整合方法及系统。
背景技术
在人机交互系统中，涉及与接触对象存在相互作用关系的表面，出于设计要求，需要对表面受力状态数据和形变状态数据进行采集和处理，进而对接触对象的状态和行为进行判断和识别。
针对上述需求，专利文献CN106039585A(申请号201610443676.7)公开了“一种具有体位感知和理疗助眠功能的智能床垫”，包括床垫基板、柔性阵列力敏传感器层、隔热层、远红外电热层、保护层、针织物层、信号采集控制模块、智能终端和云服务器，智能床垫通过采集和分析压力分布数据信息对用户睡眠质量进行监测和评估，并根据需要对用户特定部位进行红外康复理疗，提高用户睡眠质量。
该专利文献反映的是常用的方法，即采用均布式的压力传感器阵列来获得压力数据集合并进行计算处理。但这种方法布置复杂、成本较高、适应实际需求的灵活性较差。特别是，在一些可自主调节适应的表面支撑系统中，由于存在主动和被动的复杂变化因素，只有分布式的压力数据集合往往并不能完全反映表面状况及其与接触对象的相互关系，需要与之相对应的高度形变数据集合来共同反映表面状况及其与接触对象的相互关系，从而对表面状态及其接触对象的行为和状态进行更准确的判断和识别。
发明内容
针对现有技术中的缺陷，本发明的目的是提供一种压力和高度数据整合方法及系统。
根据本发明提供的一种压力和高度数据整合方法，包括：
混合分布数据采集步骤：针对同一表面区域，按照第一分布方式采集压力数据，并按照第二分布方式采集高度数据，其中，第一分布方式不同于第二分布方式。
优选地，采用如下任一种分布方式：
-第一分布方式为多子区域分布方式，第二分布方式为多点分布方式；
-第一分布方式为多点分布方式，第二分布方式为多子区域分布方式。
优选地，第一分布方式为沿直线方向排布的多子区域分布方式，第二分布方式为网格点阵分布方式。
优选地，包括：
特征获取步骤：根据压力数据获取受力状况特征，并根据高度数据获取形态状况特征；
识别步骤：根据受力状况特征、形态状况特征对表面区域状态进行识别，得到识别结果；
对比步骤：通过将即时的表面区域状态与历时的表面区域状态进行对比，得到表面区域的接触对象的行为。
优选地，还包括在所述特征获取步骤之前执行的数据融合步骤；
在所述数据融合步骤中，将所述按照第一分布方式采集到的压力数据与按照第二分布方式采集高度数据进行融合，得到混合点阵压力数据；
所述特征获取步骤中为获取受力状况特征所根据的压力数据采用混合点阵压力数据。
根据本发明提供的一种压力和高度数据整合系统，包括：
混合分布数据采集装置：针对同一表面区域，按照第一分布方式采集压力数据，并按照第二分布方式采集高度数据，其中，第一分布方式不同于第二分布方式。
优选地，采用如下任一种分布方式：
-第一分布方式为多子区域分布方式，第二分布方式为多点分布方式；
-第一分布方式为多点分布方式，第二分布方式为多子区域分布方式。
优选地，第一分布方式为沿直线方向排布的多子区域分布方式，第二分布方式为网格点阵分布方式。
优选地，包括：
特征获取装置：根据压力数据获取受力状况特征，并根据高度数据获取形态状况特征；
识别装置：根据受力状况特征、形态状况特征对表面区域状态进行识别，得到识别结果；
对比装置：通过将即时的表面区域状态与历时的表面区域状态进行对比，得到表面 区域的接触对象的行为。
优选地，还包括在所述特征获取装置之前执行的数据融合装置；
在所述数据融合装置中，将所述按照第一分布方式采集到的压力数据与按照第二分布方式采集高度数据进行融合，得到混合点阵压力数据；
所述特征获取装置中为获取受力状况特征所根据的压力数据采用混合点阵压力数据。
与现有技术相比，本发明具有如下的有益效果：
1、本发明采用采集点混合分布的压力和高度数据采集装置，实现描述表面及其接触对象状态和相互关系的复杂数据采集要求。
2、本发明对混合分布采集的压力和高度数据进行处理、合并、比对，获得描述表面状态关键区域和节点的多个特征。
3、本发明对上述特征间的相互关系进行运算，实现对表面人体状态和行为进行判断和识别。
附图说明
通过阅读参照以下附图对非限制性实施例所作的详细描述，本发明的其它特征、目的和优点将会变得更明显：
图1、图2为本发明提供的压力和高度数据整合方法的两种优选方案的流程图。
具体实施方式
下面结合具体实施例对本发明进行详细说明。以下实施例将有助于本领域的技术人员进一步理解本发明，但不以任何形式限制本发明。应当指出的是，对本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变化和改进。这些都属于本发明的保护范围。
本发明提供一种压力和高度数据整合方法，包括：
混合分布数据采集步骤：针对同一表面区域，按照第一分布方式采集压力数据，并按照第二分布方式采集高度数据，其中，第一分布方式不同于第二分布方式；
数据融合步骤：在数据预处理阶段，将所述按照第一分布方式采集到的压力数据与按照第二分布方式采集高度数据进行融合，得到混合点阵压力数据；所述数据融合步骤的意义主要在于，如果按照常规方法，更需要在同一区域布置两套分别对应于压力和高度的阵列传感器系统，其实现的复杂程度和成本非常高。
特征获取步骤：根据混合点阵压力数据获取受力状况特征，并根据高度数据获取形态状况特征；
识别步骤：根据受力状况特征、形态状况特征对表面区域状态进行识别，得到识别结果；
对比步骤：通过将即时的表面区域状态与历时的表面区域状态进行对比，得到表面区域的接触对象的行为。
具体地，所述混合分布数据采集步骤中采集的压力数据和高度数据，不仅针对的是同一表面区域，而且压力数据和高度数据的采集时间位于同一时间段内，例如同一个遍历周期，即同步或者同时。在同一表面区域且同一时间段内采用不同的第一分布方式、第二分布方式分别采集压力数据、高度数据，反映该表面区域的受力状况、形变状况，从而实现了混合分布。所述表面区域尤其是指与人体直接接触或者与人体被衣物等织物相隔间接接触的区域。例如表面区域可以是床垫表面，也可以是坐垫表面、躺椅表面或者枕头表面。进一步地，所述表面区域可以是智能床、躺椅等家具的整个支撑面，也可以是整个支撑面中的局部区域，当整个支撑面被划分出多个局部区域时，就存在多个表面区域，针对这多个表面区域可以彼此独立或者关联地执行所述混合分布数据采集步骤，然后相应地执行后续的特征获取步骤、识别步骤、对比步骤。
更为具体地，由于压力数据和高度数据是针对同一表面区域且采集时间位于同一时间段，因此所述压力数据和高度数据均包括位置属性和时间属性，其中，时间属性通过时间戳标记，反应压力数据或高度数据采集的日期和时刻点等时间信息。
下面对本发明中的各个步骤分别进行举例以对其优选的实施方式进行说明。
在混合分布数据采集步骤中，第一分布方式为多子区域分布方式，第二分布方式为多点分布方式；或者，第一分布方式为多点分布方式，第二分布方式为多子区域分布方式。进一步地，第一分布方式为沿直线方向排布的多子区域分布方式，第二分布方式为网格点阵分布方式。子区域可以是表面区域的局部，划分子区域时，多个子区域之间可以互不重叠，多个子区域之间也可以存在重叠。
需要更具体说明的第一点是：对于人体躺卧的床、椅等家具所具有的可形变支撑表面，压力数据的主要关注方向是沿人体身高方向的数据变化，因此所述直线方向可以即为人体身高方向。但不排除，也可以沿人体宽度方向布置多个子区域。与压力数据不同的是，反映表面区域形变的高度数据需要以点阵方式呈现，以捕捉人体躺卧姿态的三维特征。子区域的压力可以通过床垫中的气包反应出一个所属子区域的压力。
需要更具体说明的第二点是：为了准确识别人体对象、人体在表面区域状态或者人体躺卧行为，压力数据和高度数据采集点在表面二维区域内采用了不同的混合分布方式。压力数据采集点或者采集区域沿长度方向布置，反映了连续的纵向区域的压力数据变化。而高度数据采集点则采用网格点阵分布，以反映二维表面区域在高度方向的形变变化；由于有压力数据的混合及比对，这种网格点阵分布可以在最大间距上间隔分布，所需传感器数量减少，大大降低了技术方案实现的实际成本。
进一步地，阵列传感器的布置密度增加能提高对表面描述的精度，但会提高复杂程度和增加实现成本。最大间距是指阵列分布传感器之间，在采集数据能够满足实现描述表面要求情况下的、在物理空间平面上的最大分布间隔距离。
进一步地，压力数据可以通过压力传感器进行采集，高度数据可以通过高度测量装置采集，或者通过点阵分布的压力传感器所采集得到压力数据转化为高度数据。因此，所述按照第二分布方式采集得到的高度数据，可以是由按照第二分布方式采集得到的压力数据转化得到，并不一定是直接采集得到高度数据，其中，压力数据可以与高度数据线性相关。同样的，并不一定是直接采集的压力数据，也可以通过与压力数据不同的采集数据转化得到。
在所述特征获取步骤中，先对原始采集到的压力数据和高度数据进行预处理，例如对在采集时刻上空缺和采集数据中的异常值进行统计清洗处理，同时对上述压力数据和高度数据进行标准化处理，处理后输出的数据按包含时间戳和位置关系的特定数据结构进行保存。在解算特征时，对同一遍历周期内的含有位置关系的表面区域的压力数据和高度数据进行特征值解算，获得表面区域的压力特征值及分布特征值，同时获得表面区域的高度特征值及高度几何特征值，尤其是高度方向关键节点特征值，得到描述表面区域的受力状况特征值和形变状况特征值，进行保存。进一步地，在所述特征获取步骤中，压力数据具体为整合处理后的点阵压力数据。
在所述识别步骤和对比步骤中，基于混合点阵压力数据对表面躺卧人体的体重、身高及体重分布来判断接触对象是否属于人体并标记，同时对人体部位、躺卧姿态进行识别和标记，用于用户对象识别以及用户行为的识别例如翻身、上下床等行为。
与所述压力和高度数据整合方法相应地，本发明提供一种压力和高度数据整合系统，包括：
混合分布数据采集装置：针对同一表面区域，按照第一分布方式采集压力数据，并按照第二分布方式采集高度数据，其中，第一分布方式不同于第二分布方式；
特征获取装置：根据压力数据获取受力状况特征，并根据高度数据获取形态状况特征；
识别装置：根据受力状况特征、形态状况特征对表面区域状态进行识别，得到识别结果；
对比装置：通过将即时的表面区域状态与历时的表面区域状态进行对比，得到表面区域的接触对象的行为。
在优选例中，所述压力和高度数据整合系统，还包括在所述特征获取装置之前执行的数据融合装置；
在所述数据融合装置中，将所述按照第一分布方式采集到的压力数据与按照第二分布方式采集高度数据进行融合，得到混合点阵压力数据；
所述特征获取装置中为获取受力状况特征所根据的压力数据采用混合点阵压力数据。
具体地，第一分布方式、第二分布方式采用如下任一种分布方式：
-第一分布方式为多子区域分布方式，第二分布方式为多点分布方式；
-第一分布方式为多点分布方式，第二分布方式为多子区域分布方式。
第一分布方式为沿直线方向排布的多子区域分布方式，第二分布方式为网格点阵分布方式。
本发明从压力和形变高度这两种维度准确反映了表面状态及其与接触对象的复杂关系，实现了对接触对象的状态和行为进行准确的判断和识别，极大降低了采样点布置的密度，可以根据实际需要灵活调整系统布置方案，获得更好的识别效果。本发明提供的方法和系统可以应用于智能家具中，因此本发明提供了智能家具，例如智能床、智能椅、智能垫等能够支撑人体的家具。
本领域技术人员知道，除了以纯计算机可读程序代码方式实现本发明提供的系统及其各个装置、模块、单元以外，完全可以通过将方法步骤进行逻辑编程来使得本发明提供的系统及其各个装置、模块、单元以逻辑门、开关、专用集成电路、可编程逻辑控制器以及嵌入式微控制器等的形式来实现相同功能。所以，本发明提供的系统及其各项装置、模块、单元可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置、模块、单元也可以视为硬件部件内的结构；也可以将用于实现各种功能的装置、模块、单元视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
以上对本发明的具体实施例进行了描述。需要理解的是，本发明并不局限于上述特定实施方式，本领域技术人员可以在权利要求的范围内做出各种变化或修改， 这并不影响本发明的实质内容。在不冲突的情况下，本申请的实施例和实施例中的特征可以任意相互组合。

Claims (10)

  1. 一种压力和高度数据整合方法，其特征在于，包括：
    混合分布数据采集步骤：针对同一表面区域，按照第一分布方式采集压力数据，并按照第二分布方式采集高度数据，其中，第一分布方式不同于第二分布方式。
  2. 根据权利要求1所述的压力和高度数据整合方法，其特征在于，采用如下任一种分布方式：
    -第一分布方式为多子区域分布方式，第二分布方式为多点分布方式；
    -第一分布方式为多点分布方式，第二分布方式为多子区域分布方式。
  3. 根据权利要求2所述的压力和高度数据整合方法，其特征在于，第一分布方式为沿直线方向排布的多子区域分布方式，第二分布方式为网格点阵分布方式。
  4. 根据权利要求1所述的压力和高度数据整合方法，其特征在于，包括：
    特征获取步骤：根据压力数据获取受力状况特征，并根据高度数据获取形态状况特征；
    识别步骤：根据受力状况特征、形态状况特征对表面区域状态进行识别，得到识别结果；
    对比步骤：通过将即时的表面区域状态与历时的表面区域状态进行对比，得到表面区域的接触对象的行为。
  5. 根据权利要求4所述的压力和高度数据整合方法，其特征在于，还包括在所述特征获取步骤之前执行的数据融合步骤；
    在所述数据融合步骤中，将所述按照第一分布方式采集到的压力数据与按照第二分布方式采集高度数据进行融合，得到混合点阵压力数据；
    所述特征获取步骤中为获取受力状况特征所根据的压力数据采用混合点阵压力数据。
  6. 一种压力和高度数据整合系统，其特征在于，包括：
    混合分布数据采集装置：针对同一表面区域，按照第一分布方式采集压力数据，并按照第二分布方式采集高度数据，其中，第一分布方式不同于第二分布方式。
  7. 根据权利要求6所述的压力和高度数据整合系统，其特征在于，采用如下任一种分布方式：
    -第一分布方式为多子区域分布方式，第二分布方式为多点分布方式；
    -第一分布方式为多点分布方式，第二分布方式为多子区域分布方式。
  8. 根据权利要求7所述的压力和高度数据整合系统，其特征在于，第一分布方式为沿直线方向排布的多子区域分布方式，第二分布方式为网格点阵分布方式。
  9. 根据权利要求6所述的压力和高度数据整合系统，其特征在于，包括：
    特征获取装置：根据压力数据获取受力状况特征，并根据高度数据获取形态状况特征；
    识别装置：根据受力状况特征、形态状况特征对表面区域状态进行识别，得到识别结果；
    对比装置：通过将即时的表面区域状态与历时的表面区域状态进行对比，得到表面区域的接触对象的行为。
  10. 根据权利要求9所述的压力和高度数据整合系统，其特征在于，还包括在所述特征获取装置之前执行的数据融合装置；
    在所述数据融合装置中，将所述按照第一分布方式采集到的压力数据与按照第二分布方式采集高度数据进行融合，得到混合点阵压力数据；
    所述特征获取装置中为获取受力状况特征所根据的压力数据采用混合点阵压力数据。
PCT/CN2017/084092 2017-03-20 2017-05-12 压力和高度数据整合方法及系统 WO2018171016A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710167203.3 2017-03-20
CN201710167203.3A CN107169501B (zh) 2017-03-20 2017-03-20 压力和高度数据整合方法及系统

Publications (1)

Publication Number Publication Date
WO2018171016A1 true WO2018171016A1 (zh) 2018-09-27

Family

ID=59848789

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/084092 WO2018171016A1 (zh) 2017-03-20 2017-05-12 压力和高度数据整合方法及系统

Country Status (2)

Country Link
CN (1) CN107169501B (zh)
WO (1) WO2018171016A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108108104A (zh) * 2017-11-09 2018-06-01 魔玛智能科技（上海）有限公司 可视化控制系统及其工作方法
CN110840156A (zh) * 2019-09-23 2020-02-28 赵树龙 智能床垫

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8057388B1 (en) * 2003-04-25 2011-11-15 The United States Of America As Represented By The Secretary Of The Navy Microsensor array system
CN103745018A (zh) * 2014-02-11 2014-04-23 天津市星际空间地理信息工程有限公司 一种多平台点云数据融合方法
CN104886975A (zh) * 2015-06-09 2015-09-09 安徽机电职业技术学院 一种适应人体曲线的床垫及其高度调节方法
CN104905921A (zh) * 2015-06-15 2015-09-16 杨松 垫体和垫体的控制方法
CN105686526A (zh) * 2015-07-28 2016-06-22 广州知途鸟智能科技有限公司 乘坐运载工具所用的智能护枕

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102551732A (zh) * 2011-12-22 2012-07-11 西北工业大学 一种非觉察状态下完成睡姿检测的装置及方法
DK2745745T3 (da) * 2012-12-19 2020-01-20 Starsprings Ab Seng med automatisk justerbare egenskaber
CN104799613B (zh) * 2015-03-25 2017-10-24 安徽农业大学 一种无干扰识别和记录睡眠行为的健康分区床垫及应用
CN104732250B (zh) * 2015-03-25 2018-09-25 安徽农业大学 一种无干扰睡眠的睡姿和睡眠行为测试识别方法
CN204520112U (zh) * 2015-04-21 2015-08-05 李同强 自动调节高度的枕头

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8057388B1 (en) * 2003-04-25 2011-11-15 The United States Of America As Represented By The Secretary Of The Navy Microsensor array system
CN103745018A (zh) * 2014-02-11 2014-04-23 天津市星际空间地理信息工程有限公司 一种多平台点云数据融合方法
CN104886975A (zh) * 2015-06-09 2015-09-09 安徽机电职业技术学院 一种适应人体曲线的床垫及其高度调节方法
CN104905921A (zh) * 2015-06-15 2015-09-16 杨松 垫体和垫体的控制方法
CN105686526A (zh) * 2015-07-28 2016-06-22 广州知途鸟智能科技有限公司 乘坐运载工具所用的智能护枕

Also Published As

Publication number Publication date
CN107169501A (zh) 2017-09-15
CN107169501B (zh) 2020-07-03

Similar Documents

Publication Publication Date Title
CN108243620A (zh) 用于检测压力的柔性导电装置及系统
CN105451643B (zh) 自动连续患者移动监测
WO2018171016A1 (zh) 压力和高度数据整合方法及系统
WO2008032661A1 (fr) Procédé de mesure de valeur de distribution et système de mesure utilisant un capteur de valeur de distribution pour celui-ci
CN108209863A (zh) 非穿戴式睡姿监测装置及其床品
CN105556567B (zh) 用于脊椎位置探测的方法和系统
CN105631515A (zh) 人流计数系统
CN101199370A (zh) 机器人服装触觉传感信息融合数据处理方法
Li et al. Sleep posture classification with multi-stream CNN using vertical distance map
WO2018171017A1 (zh) 分布式压力和高度混合测量控制系统与方法
Pugach et al. Neural learning of the topographic tactile sensory information of an artificial skin through a self-organizing map
Chao et al. Method of recognizing sleep postures based on air pressure sensor and convolutional neural network: For an air spring mattress
CN205924026U (zh) 一种人体活动量检测系统
CN106725457A (zh) 一种基于脑机人工智能技术的住院病人监测系统
JP2020074860A (ja) 内部構造推定装置、方法、及び、プログラム
Akhund et al. Iot based low-cost posture and bluetooth controlled robot for disabled and virus affected people
Lee et al. Recognition algorithm for sleep postures using a smart fabric pad with multiple pressure sensors
Salleh et al. The using of 3D handheld scanner to develop a pressure garment model
Wasza et al. Sparse principal axes statistical surface deformation models for respiration analysis and classification
Xiong et al. FVSight: A Novel Multimodal Tactile Sensor for Robotic Object Perception
Boughorbel et al. Pressure-sensor system for sleeping-posture classification
Ziaratnia et al. Multimodal Deep Learning for Remote Stress Estimation Using CCT-LSTM
Mijović et al. Investigating brain dynamics in industrial environment–integrating mobile EEG and kinect for cognitive state detection of a worker
Kulon et al. Rule-based algorithm for the classification of sitting postures in the sagittal plane from the Cardiff Body Match measurement system
Wang et al. Development of a percentile based three-dimensional model of the buttocks in computer system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17902336

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC , EPO FORM 1205A DATED 10.01.2020.

122 Ep: pct application non-entry in european phase

Ref document number: 17902336

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 10/01/2020)