WO2023045108A1 - 一种基于大规模高密度压阻薄膜的足迹统计分析方法 - Google Patents

一种基于大规模高密度压阻薄膜的足迹统计分析方法 Download PDF

Info

Publication number
WO2023045108A1
WO2023045108A1 PCT/CN2021/137587 CN2021137587W WO2023045108A1 WO 2023045108 A1 WO2023045108 A1 WO 2023045108A1 CN 2021137587 W CN2021137587 W CN 2021137587W WO 2023045108 A1 WO2023045108 A1 WO 2023045108A1
Authority
WO
WIPO (PCT)
Prior art keywords
footprint
area
pressure
adjacency matrix
gravity
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2021/137587
Other languages
English (en)
French (fr)
Inventor
王博
尚鹏
刘程祥
杨德龙
罗朝晖
张笑千
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
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 Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Publication of WO2023045108A1 publication Critical patent/WO2023045108A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/1036—Measuring load distribution, e.g. podologic studies
    • A61B5/1038—Measuring plantar pressure during gait
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Measuring devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor or mobility of a limb

Definitions

  • the invention relates to the technical field of medical rehabilitation, and more specifically, to a statistical analysis method of footprints based on large-scale high-density piezoresistive films.
  • Plantar pressure can provide valuable information for fall prediction, diagnosis and rehabilitation of various diseases, but the existing plantar pressure analysis technology cannot automatically identify the left and right foot positions in continuous gait, and cannot proceed to the next step dynamic gait analysis. And in terms of fall prediction, due to the limitation of equipment area, it is difficult to lay large-area equipment to collect plantar pressure data.
  • the existing plantar pressure monitoring is based on the plantar pressure detection technology under a single pressure film, which targets a small area of pressure data, and usually static data analysis, even for dynamic data, it is impossible to truly analyze dynamic gait the data below.
  • data analysis and recognition technology is in urgent need.
  • follow-up label analysis is usually used to analyze and process plantar pressure, including footprint pressure area labeling, left and right foot recognition, front and rear sole recognition, and gait direction recognition.
  • footprint pressure area labeling including footprint pressure area labeling, left and right foot recognition, front and rear sole recognition, and gait direction recognition.
  • the left and right feet have been determined on the hardware side, but there are problems such as large acquisition equipment and short wireless distance.
  • the size of the pressure film on the market is generally 400mm ⁇ 400mm.
  • the pressure film of this size can only realize the collection of plantar pressure data in situ, and cannot realize the collection and analysis of dynamic plantar pressure during real walking.
  • the existing pressure film collects plantar pressure data.
  • the purpose of the present invention is to overcome above-mentioned defective of prior art, provide a kind of footprint statistical analysis method based on large-scale high-density piezoresistive film, this method comprises the following steps:
  • Step S1 Use the piezoresistive film to build a pressure collection area, and collect the pressure signal during the target's walking process, where the piezoresistive film contains multiple force-sensitive point units, and use the set index for positioning for each force-sensitive point unit;
  • Step S2 Obtain the adjacency matrix of the plantar pressure image according to the collected pressure signal, each element of the adjacency matrix corresponds to the pressure level of the relevant force sensitive point unit, and each adjacency matrix corresponds to a footprint;
  • Step S3 Determine the direction of the footprint and the area of the inner and outer arches according to the area and orientation of the adjacency matrix
  • Step S4 Determine one or more of the center of gravity of the heel and forefoot, the type of footprint, the center of gravity of the footprint, and the step length of the footstep according to the area of the inner and outer arches.
  • the present invention has the advantages of replacing the work of manually obtaining the main parameters of the footprint data by using an automatic identification method; realizing the visualization of the footprint for the collected dynamic walking pressure, and then using statistical methods to distinguish the left footprint and the left footprint.
  • the present invention is able to obtain the direction and step size of the footsteps for fall prediction.
  • Fig. 1 is a flow chart of a footprint statistical analysis method based on a large-scale high-density piezoresistive film according to an embodiment of the present invention
  • Fig. 2 is a schematic diagram of a monolithic pressure film according to an embodiment of the present invention.
  • Fig. 3 is a schematic diagram of six spliced pressure films according to an embodiment of the present invention.
  • Fig. 4 is a flow chart of data processing according to one embodiment of the present invention.
  • Fig. 5 is a schematic diagram of plantar pressure visualization data according to an embodiment of the present invention.
  • Fig. 6 is a schematic diagram of the plantar pressure distribution and rotation angle of the left foot according to an embodiment of the present invention.
  • Fig. 7 is a vertical projection schematic diagram of the left foot pressure adjacency matrix according to an embodiment of the present invention.
  • Fig. 8 is a schematic diagram of the distribution of the plantar pressure of the right foot and the determination of the upper and lower arches according to an embodiment of the present invention
  • the provided footprint statistical analysis method based on large-scale high-density piezoresistive films includes the following steps.
  • Step S110 expanding the pressure collection area by using the piezoresistive film.
  • piezoresistive films can be used to expand the collection area.
  • FIG. 2 taking the piezoresistive film (Rouxi, RX-M3232L) as an example, its size is 400mm ⁇ 400mm, and it has 1024 force-sensitive point units.
  • the pressure acquisition area is expanded to 2400mm ⁇ 400mm (corresponding to 6144 force-sensitive point units) by using six piezoresistive films, as shown in Figure 3, by selecting the channel in the row (row) and the channel in the column (column) for positioning Each force sensitive point.
  • a digital-to-analog converter can be used to convert the measured voltage into digital data, and then, a data acquisition device can be designed to transmit the data to a computer or other data processing equipment.
  • step S120 the pressure data is obtained, and the adjacency matrix of the pressure data is identified according to the location of each force-sensitive point, and the area of the matrix is calculated, thereby determining the area of the arch of the foot.
  • the proposed footprint analysis method as shown in Figure 4, is used to distinguish left and right footprints, and obtain the main parameters of footprint analysis such as the direction and step length of the footprints.
  • the developed software can be used to receive data from the designed signal acquisition device through the serial port, and visualize the plantar pressure.
  • the multiple footprints on the piezoresistive film are shown in Figure 5, where a small square represents the force-sensitive point unit in the piezoresistive film, and the pressure values of different levels are represented by different colors, using a matrix of 32 ⁇ 192 (that is, corresponding to 6144 force Sensitive point unit) to calculate the relative position of the force sensitive point unit.
  • the visual image is updated at a set rate, such as about 12 frames per second, so that dynamic changes in the footprint can be captured over a range of walking speeds.
  • a set rate such as about 12 frames per second
  • the adjacency matrix (corresponding to the plantar pressure box) of the plantar pressure image is obtained by the above method, as shown in Figure 6, and then the angle R between the long side of the adjacency matrix and the x-axis is calculated to rotate the plantar pressure box to make it parallel to x-axis.
  • the vertical projection of the adjacency matrix is calculated to locate the position of the forefoot and hindpaw, and the change of the vertical projection value with respect to the number of columns is shown in Figure 7. It can be clearly seen from Fig. 7 that there are three peaks, of which the two largest peaks are produced by the pressure in the sole and heel area, and the smallest peak is produced by the pressure in the toe area.
  • Step S130 calculating the center of gravity of the forefoot and heel, the direction of the footprint, the center of gravity of the footprint, the category of the footprint, and the length of adjacent footprints based on the area of the arch of the foot.
  • left and right footprints can be identified based on their significant differences in geometry.
  • the footprint shown in FIG. 8 it can be identified that the position of the inner arch of the foot is above and the position of the outer arch of the foot is below, then the footprint is identified as a right footprint.
  • the location of the medial arch is below and the location of the lateral arch is above, then the footprint is identified as a left footprint. Therefore, the geometrical features of the arch of the foot are used to distinguish left and right footprints. Specifically, firstly, it is defined that the arch area is composed of the line connecting the two largest peaks and the long side of the adjacency matrix.
  • p(x, y) represents the pressure
  • x represents the abscissa
  • y represents the ordinate
  • ⁇ h represents the area of the heel.
  • the coordinates of the center of the heel area are expressed as (x b , y b ), and the calculation methods are shown in Formula 3 and Formula 4.
  • ⁇ b represents the area of the forefoot. According to the positions and attributes of the two center of gravity points, the direction of the plantar pressure matrix can be determined, that is, the forward direction of the foot or the direction of the footprint.
  • ⁇ c represents the area of the footprint, and the coordinates of the center of gravity of the footprint in the matrix are expressed as (x c , y c ), and the calculation method is shown in formula 5 and formula 6:
  • the calculation method of the center of gravity of the footprint in the next step (that is, the next footprint) is the same as formula 5 and formula 6, which is recorded as (x c+1 , y c+1 ).
  • the step size of two consecutive footprints is calculated by calculating the center distance of two adjacent adjacency matrices, which can be expressed as shown in Equation 7.
  • L s represents the length of two consecutive plantar pressures, that is, the current step size; x c+1 and x c represent the horizontal coordinates of the centers of two consecutive adjacency matrices; y c+1 and y c represent two consecutive adjacency
  • the longitudinal coordinate of the matrix center, the calculation method is the same as the center of gravity calculation method above.
  • the present invention has a higher recognition rate in the non-running state, can detect various features in real time in the normal walking state, and can extract accurate footprints for different people's feet and different walking speeds feature.
  • the present invention provides an automatic footprint recognition method for large-scale flexible sensors, which can accurately, real-time, and efficiently identify footprint position, footprint category, footprint center of gravity, front and rear soles, front and rear soles of gravity, footprint direction and footprint step length, etc. feature.
  • the present invention creatively proposes a method that can construct the direction of the plantar pressure according to the characteristics of the sole, which can be used for feature extraction of the real-time plantar pressure.
  • the invention has a wider application range, and realizes accurate footprint analysis for different target groups and different speeds.
  • the present invention can be a system, method and/or computer program product.
  • a computer program product may include a computer readable storage medium having computer readable program instructions thereon for causing a processor to implement various aspects of the present invention.
  • a computer readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device.
  • a computer readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Computer-readable storage media include: portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory), static random access memory (SRAM), compact disc read only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanically encoded device, such as a printer with instructions stored thereon A hole card or a raised structure in a groove, and any suitable combination of the above.
  • RAM random access memory
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • flash memory static random access memory
  • SRAM static random access memory
  • CD-ROM compact disc read only memory
  • DVD digital versatile disc
  • memory stick floppy disk
  • mechanically encoded device such as a printer with instructions stored thereon
  • a hole card or a raised structure in a groove and any suitable combination of the above.
  • computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., pulses of light through fiber optic cables), or transmitted electrical signals.
  • Computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or a network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • Computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or Source or object code written in any combination, including object-oriented programming languages—such as Smalltalk, C++, Python, etc., and conventional procedural programming languages—such as the “C” language or similar programming languages.
  • Computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as via the Internet using an Internet service provider). connect).
  • LAN local area network
  • WAN wide area network
  • an electronic circuit such as a programmable logic circuit, field programmable gate array (FPGA), or programmable logic array (PLA)
  • FPGA field programmable gate array
  • PDA programmable logic array
  • These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that when executed by the processor of the computer or other programmable data processing apparatus , producing an apparatus for realizing the functions/actions specified in one or more blocks in the flowchart and/or block diagram.
  • These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause computers, programmable data processing devices and/or other devices to work in a specific way, so that the computer-readable medium storing instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks in flowcharts and/or block diagrams.
  • each block in a flowchart or block diagram may represent a module, a portion of a program segment, or an instruction that includes one or more Executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by means of hardware, implementation by means of software, and implementation by a combination of software and hardware are all equivalent.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Dentistry (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Physiology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种基于大规模高密度压阻薄膜的足迹统计分析方法，包括：利用压阻薄膜构建压力采集区域，并采集目标行走过程中的压力信号，其中压阻薄膜包含多个力敏感点单元，针对每个力敏感点单元，采用设定的索引进行定位；根据所采集的压力信号，获得足底压力图像的邻接矩阵，该邻接矩阵的每个元素对应相关力敏感点单元的压力大小，每个邻接矩阵对应一个足迹；根据邻接矩阵的面积和朝向确定足迹的方向以及内外足弓面积；确定脚跟与前掌重心、足迹类别、足迹重心以及足迹步长中的一项或多项，其中根据内外足弓面积确定足迹类别。利用该方法能准确、实时、高效地提取足迹特征。

Description

一种基于大规模高密度压阻薄膜的足迹统计分析方法 技术领域
本发明涉及医疗康复技术领域，更具体地，涉及一种基于大规模高密度压阻薄膜的足迹统计分析方法。
背景技术
足底压力可为跌倒预测、多种疾病的诊断和康复治疗提供有价值的信息，但是现有的足底压力分析技术并不能在连续的步态下自动识别出左右脚位置，无法进行下一步的动态步态分析。并且在跌倒预测方面，由于设备面积的限制，很难铺设大面积的设备采集足底压力数据。
例如，现有的足底压力监测都是基于单个压力薄膜下的足底压力检测技术，针对的压力数据面积较小，而且通常是静态数据分析，即使针对动态数据，也无法真正分析动态步态下的数据。对于在动态步态下，数据分析与识别技术非常急缺。并且针对足底压力数据，通常采取后续标注分析方式对足底压力分析处理，包含足迹压力区域标注，左右脚识别，前后脚掌识别，步态方向识别，目前缺少自动化提取足迹特征的算法。此外，尽管在现有技术中，针对左右脚识别，存在一种可穿戴式薄膜鞋垫，在硬件端已经确定了左右脚，但是具有采集设备大，无线距离短等问题。
总之，现在市面上的压力薄膜尺寸一般是400mm×400mm，该尺寸的压力薄膜只能够实现原地的足底压力数据收集，无法实现真实行走时的动态足底压力的收集及分析。并且现有的压力薄膜采集足底压力数据，除了已经定义好左右脚的压力鞋垫，目前缺少自动识别左右脚的识别算法。
发明内容
本发明的目的是克服上述现有技术的缺陷，提供一种基于大规模高密度压阻薄膜的足迹统计分析方法，该方法包括以下步骤：
步骤S1：利用压阻薄膜构建压力采集区域，并采集目标行走过程中的压力信号，其中压阻薄膜包含多个力敏感点单元，针对每个力敏感点单 元，采用设定的索引进行定位；
步骤S2：根据所采集的压力信号，获得足底压力图像的邻接矩阵，该邻接矩阵的每个元素对应相关力敏感点单元的压力大下，每个邻接矩阵对应一个足迹；
步骤S3：根据所述邻接矩阵的面积和朝向确定足迹的方向以及内外足弓面积；
步骤S4：根据所述内外足弓面积确定脚跟与前掌重心、足迹类别、足迹重心以及足迹步长中的一项或多项。
与现有技术相比，本发明的优点在于，利用自动识别方式取代手工获取足迹数据主要参数的工作；对采集到的动态行走的压力，实现足迹的可视化，进而利用统计方法来区分左足迹和右足迹，用于步态动态分析。此外，本发明能够获得足迹的方向和步长，用于跌倒预测。
通过以下参照附图对本发明的示例性实施例的详细描述，本发明的其它特征及其优点将会变得清楚。
附图说明
被结合在说明书中并构成说明书的一部分的附图示出了本发明的实施例，并且连同其说明一起用于解释本发明的原理。
图1是根据本发明一个实施例的基于大规模高密度压阻薄膜的足迹统计分析方法的流程图；
图2是根据本发明一个实施例的单片压力薄膜示意图；
图3是根据本发明一个实施例的六片拼接的压力薄膜示意图；
图4是根据本发明一个实施例的数据处理流程图；
图5是根据本发明一个实施例的足底压力可视化数据示意图；
图6是根据本发明一个实施例的左脚的足底压力分布及旋转角示意图；
图7是根据本发明一个实施例的左脚压力邻接矩阵的垂直投影示意图；
图8是根据本发明一个实施例的右脚足底压力分布及上下足弓判断示意图；
附图中，the adjacency matrix of the footprint-足迹的邻接矩阵；center of  the ball of the foot-脚掌的重心；center of the footprint-足迹的重心；center of the heel-脚跟的重心；vertical projection-垂直投影；Column number-列号；arch area-弓形区域；medial arch area-内侧弓区；lateral arch area-外侧弓区。
具体实施方式
现在将参照附图来详细描述本发明的各种示例性实施例。应注意到：除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本发明的范围。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本发明及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论，但在适当情况下，所述技术、方法和设备应当被视为说明书的一部分。
在这里示出和讨论的所有例子中，任何具体值应被解释为仅仅是示例性的，而不是作为限制。因此，示例性实施例的其它例子可以具有不同的值。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步讨论。
结合图1和图4所示，所提供的基于大规模高密度压阻薄膜的足迹统计分析方法包括以下步骤。
步骤S110，利用压阻薄膜扩展压力采集区域。
为了采集目标真实行走时的动态足底压力，可采用多个压阻薄膜扩展采集区域。如图2所示，以压阻薄膜(Rouxi，RX-M3232L)为例，其尺寸是400mm×400mm，具有1024个力敏感点单元。通过采用六片压阻薄膜将压力采集区域扩展至2400mm×400mm(对应6144个力敏感点单元)，如图3所示，通过选择行(row)中的通道和列(column)中的通道定位每个力敏感点。在后续处理中，可利用数模转换器将测量的电压转换为数字数据，然后，可设计数据采集设备将数据传输到计算机或其他的数据处理设备。
步骤S120，获取压力数据，并根据对各个力敏感点的定位识别压力数据的邻接矩阵，计算矩阵面积，进而确定足弓面积。
在一个实施例中，提出的足迹分析方法如图4所示，用于区分左足迹和右足迹，并获得足迹的方向和步长等足迹分析的主要参数。
例如，在实际应用中，为获得足底的数据，可利用开发的软件通过串口从所设计的信号采集设备接收数据，并可视化足底压力。压阻薄膜上多个足迹如图5所示，其中一个小正方形表示压阻薄膜中的力敏感点单元，不同级别的压力值用不同的颜色表示，使用矩阵32×192(即对应6144个力敏感点单元)计算力敏感点单元的相对位置。
此外，视觉图像以设定的速率进行更新，例如以每秒约12帧的速度更新，从而可在一定的行走速度范围内捕捉足迹的动态变化。考虑到在压阻薄膜上行走时可能会捕获多幅图像，因此优选地在面积最大的压力面积上进一步分析，过滤掉面积小于阈值的足底压力区域。由于信号采集设备硬件中的电子干扰，图像上可能会显示一些小的激活区域，这可能会对图像产生干扰，因此采用阈值法滤除噪声。
通过上述方法获得足底压力图像的邻接矩阵(对应足底压力框)，如图6所示，然后计算邻接矩阵长边与x轴之间的角度R，以旋转足底压力框使其平行于x轴。计算邻接矩阵的垂直投影以定位前掌和后掌的位置，垂直投影值相对于列数的变化如图7所示。从图7中可清楚地看到，三个峰值，其中最大的两个峰值是由脚掌和脚跟区域的压力产生的，最小的峰值是由脚趾区域的压力产生。由于行走过程中脚印的动态变化，通过比较两个最大峰值来确定脚跟和脚掌的位置是不准确的。因此，前三列中的和值与后三列中的和值进行比较，以区分足迹的朝向，面积小的靠近脚掌，面积大的靠近脚跟。
步骤S130，基于足弓面积计算前掌和脚跟重心、足迹方向、足迹重心、足迹类别以及相邻足迹的长度。
如图6和图8所示，可根据其几何形状的显著差异来识别左右脚印。如图8所示的右脚印，可识别出内侧足弓的位置在上方，外侧足弓的位置在下方，则该脚印被识别为右脚印。相应地，若内侧足弓的位置在下方， 外侧足弓的位置在上方，则该足迹被标识为左侧足迹。因此，足弓的几何特征用于区分左右脚印。具体地，首先，定义了足弓面积由两个最大峰值的连线和邻接矩阵的长边构成。随后，从足弓区域提取两部分(上半部分和下半部分)，描述计算上半部分和下半部分面积，如以下伪代码所示。将上半部分和下半部分的面积进行比较，并假设内弓位于面积较大的部分，外弓位于面积较小的部分。
Figure PCTCN2021137587-appb-000001
获得脚跟和前掌(或称脚掌)的重心坐标之前，在邻接矩阵中脚跟和前掌的区域两个最大峰值之间寻找分割线，将整个足底压力区域分为前掌和脚跟。矩阵中脚跟重心的坐标表示为(x h，y h)，计算方法如公式1和公式2所示。
Figure PCTCN2021137587-appb-000002
Figure PCTCN2021137587-appb-000003
其中，p(x,y)表示压力，x表示横坐标，y表示纵坐标，Ω h表示脚跟的面积。脚跟区域中心的坐标表示为(x b，y b)，计算方法如公式3和公式4所示。
Figure PCTCN2021137587-appb-000004
Figure PCTCN2021137587-appb-000005
Ω b表示前掌的面积。根据两个重心点的位置和属性可确定足底压力矩阵的方向，即脚的前进方向或称足迹方向。
Ω c表示足迹的面积，矩阵中足迹重心的坐标表示为(x c，y c)，计算方法如公式5和公式6所示：
Figure PCTCN2021137587-appb-000006
Figure PCTCN2021137587-appb-000007
下一步(即下一足迹)的足迹重心计算方式同公式5和公式6，记为(x c+1，y c+1)。
通过计算两个相邻的邻接矩阵的中心距离来计算两个连续足迹的步长，可表示为如公式7所示。
Figure PCTCN2021137587-appb-000008
其中，L s表示两个连续的足底压力长度，即当前的步长；x c+1和x c表示两个连续邻接矩阵中心的水平坐标；y c+1和y c表示两个连续邻接矩阵中心的纵向坐标，计算方法如上的重心计算方法。
需说明的是，在不违背本发明精神和范围的前提下，本领域技术人员可对上述实施例进行适当的改变或变型。例如，在计算重心时，也可使用图形重心法，但是无法准确获取足迹方向；又如，采用更多数目的压阻薄膜来扩展压力采集区域；此外，所涉及的邻接矩阵旋转尽是为了在同一方向上进行数据分析，在实际应用中，只要将邻接矩阵作统一旋转即可，而不限制旋转的方向和角度。并且，对力敏感点单元的定位只要能唯一标识即可，不必须采用行号和列号进行定位。
为进一步验证本发明的效果，进行了实验。有三个实验者参与了实验，他们各自的脚长分别为A(265mm)、B(270mm)、C(285mm)，并且设计了四种速度，包括慢速行走(0.5～1.1m/s)、正常行走(1.1～1.5mm)、快速行走(1.5～1.8mm)、慢跑(1.8～2.1mm)，每种速度都采集了114组数据，共计1368个脚印数据。在各场景下，特征提取的准确率参见下表1。
表1：实验结果
Figure PCTCN2021137587-appb-000009
由表1可以看出，本发明在非跑步状态下有较高的识别率，能够在正常行走状态下实时检测出各项特征，并且对于不同人的脚和不同步行速度均能提取准确的足迹特征。
综上所述，本发明提供针对大规模柔性传感器的足迹自动识别方法，能够准确、实时、高效地识别足迹位置、足迹类别、足迹重心、前后脚掌、前后脚掌重心、足迹方向和足迹步长等特征。针对现有技术没有体现足底压力方向的方法，本发明创造性地提出一种可根据足底特征构造足底压力方向的方法，可用于实时足底压力的特征提取。本发明适用范围更广，针对不同目标人群、不同步速均实现了准确的足迹分析。
本发明可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本发明的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是但不限于电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过 电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本发明操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++、Python等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本发明的各个方面。
这里参照根据本发明实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本发明的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图 和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本发明的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。对于本领域技术人员来说公知的是，通过硬件方式实现、通过软件方式实现以及通过软件和硬件结合的方式实现都是等价的。
以上已经描述了本发明的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。本发明的范围由所附权利要求来限定。

Claims (10)

  1. 一种基于大规模高密度压阻薄膜的足迹统计分析方法，包括以下步骤：
    步骤S1：利用压阻薄膜构建压力采集区域，并采集目标行走过程中的压力信号，其中压阻薄膜包含多个力敏感点单元，针对每个力敏感点单元，采用设定的索引进行定位；
    步骤S2：根据所采集的压力信号，获得足底压力图像的邻接矩阵，该邻接矩阵的每个元素对应相关力敏感点单元的压力大下，每个邻接矩阵对应一个足迹；
    步骤S3：根据所述邻接矩阵的面积和朝向确定足迹的方向以及内外足弓面积；
    步骤S4：根据所述内外足弓面积确定脚跟与前掌重心、足迹类别、足迹重心以及足迹步长中的一项或多项。
  2. 根据权利要求1所述的方法，其特征在于，所述压力采集区域设有多片压阻薄膜，每片压阻薄膜具有行、列排列的多个力敏感点单元，对于每个力敏感点单元，采用行号和列号的组合进行定位。
  3. 根据权利要求1所述的方法，其特征在于，对于所述足底压力图像的邻接矩阵根据以下步骤进行可视化：
    采用一个正方形表示压阻薄膜中的一个力敏感点单元，不同级别的压力值用不同的颜色表示，使用一个位置矩阵表征力敏感点单元的相对位置；
    对于获得的视觉图像，以设定的速度进行更新，以捕捉足迹的动态变化。
  4. 根据权利要求3所述的方法，其特征在于，在步骤S3中，根据以下子步骤确定足迹的方向以及内外足弓面积：
    计算邻接矩阵长边与x轴之间的角度R，以旋转该邻接矩阵使其平行于x轴；
    计算邻接矩阵的垂直投影以定位前掌和后掌的位置，进而确定足迹的方向；
    根据邻接矩阵对应的几何形状差异识别足迹类别是左脚印或右脚印并计算内外足弓面积。
  5. 根据权利要求4所述的方法，其特征在于，在步骤S4中，根据以下子步骤确定脚跟与前掌重心、足底重心以及足迹步长：
    在邻接矩阵中脚跟和前掌的区域两个最大峰值之间寻找分割线，将整个足底压力区域分为前掌和脚跟，计算脚跟重心的坐标，表示为(x h，y h)：
    Figure PCTCN2021137587-appb-100001
    Figure PCTCN2021137587-appb-100002
    计算脚跟区域重心的坐标表示为(x b，y b)：
    Figure PCTCN2021137587-appb-100003
    Figure PCTCN2021137587-appb-100004
    计算足迹重心的坐标表示为(x c，y c)：
    Figure PCTCN2021137587-appb-100005
    Figure PCTCN2021137587-appb-100006
    通过计算两个相邻的邻接矩阵的重心距离来确定两个连续足迹的步长，表示为：
    Figure PCTCN2021137587-appb-100007
    其中，p(x,y)表示位置(x,y)处的压力，Ω c表示足迹的面积，Ω h表示脚跟的面积，Ω b表示前掌的面积，L s表示两个连续的足底压力长度，作为当前的步长；x c+1和x c表示两个连续邻接矩阵重心的水平坐标，y c+1和y c表示两个连续邻接矩阵重心的纵向坐标。
  6. 根据权利要求4所述的方法，其特征在于，以邻接矩阵平行于x轴为参考，如果识别出内侧足弓的位置在上方，外侧足弓的位置在下方，则将足迹类别确定为右脚印；若内侧足弓的位置在下方，外侧足弓的位置在上方，则将足迹类别确定为左侧脚印。
  7. 根据权利要求4所述的方法，其特征在于，所述内外足弓面积由邻接矩阵中脚跟和前掌区域的两个最大峰值的连线和邻接矩阵的长边构成。
  8. 根据权利要求1所述的方法，其特征在于，步骤S2还包括：对于获得的邻接矩阵，过滤掉面积小于设定阈值的足底压力区域。
  9. 一种计算机可读存储介质，其上存储有计算机程序，其中，该程序被处理器执行时实现根据权利要求1至8中任一项所述方法的步骤。
  10. 一种计算机设备，包括存储器和处理器，在所述存储器上存储有能够在处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现权利要求1至8中任一项所述的方法的步骤。
PCT/CN2021/137587 2021-09-26 2021-12-13 一种基于大规模高密度压阻薄膜的足迹统计分析方法 Ceased WO2023045108A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111126979.3 2021-09-26
CN202111126979.3A CN113951870A (zh) 2021-09-26 2021-09-26 一种基于大规模高密度压阻薄膜的足迹统计分析方法

Publications (1)

Publication Number Publication Date
WO2023045108A1 true WO2023045108A1 (zh) 2023-03-30

Family

ID=79462158

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/137587 Ceased WO2023045108A1 (zh) 2021-09-26 2021-12-13 一种基于大规模高密度压阻薄膜的足迹统计分析方法

Country Status (2)

Country Link
CN (1) CN113951870A (zh)
WO (1) WO2023045108A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN121003429A (zh) * 2025-08-08 2025-11-25 广州市花都区人民医院 一种用于糖尿病足患者的运动监护管理系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115661920B (zh) * 2022-10-10 2026-02-27 中国人民解放军军事科学院系统工程研究院 基于应力发光薄膜的步态识别身份认证方法
CN119761403B (zh) * 2025-03-03 2025-06-03 厦门盈趣科技股份有限公司 一种人流量检测方法、系统、设备及存储介质
CN120126222B (zh) * 2025-05-14 2025-08-26 北京华益精点生物技术有限公司 一种基于足底压力图像的步态分析方法及相关设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102921162A (zh) * 2012-10-27 2013-02-13 安徽埃力智能科技有限公司 自助式平衡与步态训练系统及方法
CN104434128A (zh) * 2014-12-25 2015-03-25 中国科学院合肥物质科学研究院 一种基于足底压力分布信息的左右脚动态识别方法
CN109443611A (zh) * 2018-11-15 2019-03-08 北京大学深圳研究生院 一种阵列式压力传感器和压力采集系统
US20200060580A1 (en) * 2017-03-22 2020-02-27 Steven Miller Custom foot orthotic and system and method for designing of a custom foot orthotic
CN111507209A (zh) * 2020-03-31 2020-08-07 湖北民族大学 基于足底压力分布的步态识别方法及系统
US20200375507A1 (en) * 2018-02-26 2020-12-03 Ochanomizu University Behavior determination device, behavior determination system, behavior determination method, and computer-readable storage medium
CN112766142A (zh) * 2021-01-15 2021-05-07 天津大学 足底压力图像处理方法、识别方法及步态分析系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4933365B2 (ja) * 2007-07-04 2012-05-16 株式会社アシックス 足関節の動的アライメントの評価システムおよび足関節の動的アライメントの評価方法
WO2013108306A1 (ja) * 2012-01-18 2013-07-25 テルモ株式会社 尖足度合い評価システム及び情報処理装置
US20190336040A1 (en) * 2016-08-05 2019-11-07 Chang Gung University Walking assist device
CN111127446B (zh) * 2019-12-26 2023-04-07 中国科学院合肥物质科学研究院 一种面向步态分析的足底压力图像分区方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102921162A (zh) * 2012-10-27 2013-02-13 安徽埃力智能科技有限公司 自助式平衡与步态训练系统及方法
CN104434128A (zh) * 2014-12-25 2015-03-25 中国科学院合肥物质科学研究院 一种基于足底压力分布信息的左右脚动态识别方法
US20200060580A1 (en) * 2017-03-22 2020-02-27 Steven Miller Custom foot orthotic and system and method for designing of a custom foot orthotic
US20200375507A1 (en) * 2018-02-26 2020-12-03 Ochanomizu University Behavior determination device, behavior determination system, behavior determination method, and computer-readable storage medium
CN109443611A (zh) * 2018-11-15 2019-03-08 北京大学深圳研究生院 一种阵列式压力传感器和压力采集系统
CN111507209A (zh) * 2020-03-31 2020-08-07 湖北民族大学 基于足底压力分布的步态识别方法及系统
CN112766142A (zh) * 2021-01-15 2021-05-07 天津大学 足底压力图像处理方法、识别方法及步态分析系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LIN QINQIN, RUOMING LI, YUANWEN GENG, HANG YUAN, XIAOLI YANG: "Characteristics and Changes of Plantar Pressure of Healthy Men Aged 3-35 Years Old During Natural Walking", CHINESE JOURNAL OF TISSUE ENGINEERING RESEARCH JUNE, vol. 25, no. 15, 5 November 2020 (2020-11-05), pages 2315 - 2320, XP093054261, ISSN: 2095-4344, DOI: 10.3969/j.issn.2095-4344.3804 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN121003429A (zh) * 2025-08-08 2025-11-25 广州市花都区人民医院 一种用于糖尿病足患者的运动监护管理系统

Also Published As

Publication number Publication date
CN113951870A (zh) 2022-01-21

Similar Documents

Publication Publication Date Title
WO2023045108A1 (zh) 一种基于大规模高密度压阻薄膜的足迹统计分析方法
US20230154580A1 (en) Anatomical location detection of features of a gastrointestinal tract of a patient
CN104376576B (zh) 一种目标跟踪方法及装置
CN109165540B (zh) 一种基于先验候选框选择策略的行人搜索方法和装置
CN104392223B (zh) 二维视频图像中的人体姿态识别方法
TWI660277B (zh) 資訊處理裝置及資訊處理方法
TWI667621B (zh) 人臉辨識方法
CN114549425B (zh) 医学影像的检测方法、装置、存储介质和计算机设备
CN113240718A (zh) 多目标识别及跟踪方法、系统、介质和计算设备
CN109003275A (zh) 焊缝缺陷图像的分割方法
CN112837241A (zh) 建图重影去除方法、设备及存储介质
CN112906816A (zh) 基于光微分与双通道神经网络的目标检测方法和装置
CN118882698A (zh) 一种egm2008模型的高程数据误差校正方法及系统
CN108154113A (zh) 基于全卷积网络热度图的跌倒事件检测方法
CN110245672B (zh) 基于快速视网膜特征点匹配及多尺度分割的浮选破碎气泡检测方法
CN108764343B (zh) 一种跟踪算法中的跟踪目标框的定位方法
CN115511883A (zh) 确定视网膜眼底血管的弯曲度的方法、设备和存储介质
WO2022230413A1 (ja) 検出装置、検出装置の制御方法、学習済モデルを生成するモデル生成装置によるモデル生成方法、情報処理プログラム、および記録媒体
CN108764183A (zh) 一种植物病害诊断方法、装置及存储介质
CN108876767B (zh) 一种甘蔗蔗节特征快速识别装置
CN116153516B (zh) 一种基于分布式计算的疾病大数据挖掘分析系统
CN118918135A (zh) 三维病灶的分割方法及装置、电子设备和存储介质
CN117741606A (zh) 一种目标物体速度测量方法及相关设备
CN114492937B (zh) 事件预警方法、装置、设备、存储介质和计算机产品
CN115331220B (zh) 基于目标检测和热图回归的宫颈念珠菌感染筛查方法

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: 21958219

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21958219

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 21958219

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 23.09.2024)

122 Ep: pct application non-entry in european phase

Ref document number: 21958219

Country of ref document: EP

Kind code of ref document: A1