技术领域Technical field
本发明属于计算机视觉领域，涉及人体姿态识别技术领域，具体涉及一种判断人体运动姿态的方法。The invention belongs to the field of computer vision, relates to the technical field of human body posture recognition, and specifically relates to a method for judging human body movement posture.
背景技术Background technique
随着人工智能技术的发展，文字识别，语音识别等技术已经逐步成熟，但在对人类姿态进行理解方面，仍然存在非常大的困难。With the development of artificial intelligence technology, text recognition, speech recognition and other technologies have gradually matured, but there are still great difficulties in understanding human gestures.
现有的人体姿态识别算法往往都是对人体所处的某一时刻的“状态”进行识别，这类方法能够很准确地识别出“举手”、“抬腿”等简单的静态姿态。但在自然的人际交流场景中，人类倾向于使用一系列的动作组合表示出更为复杂的含义。对于这种一连串动作组成的动态姿态进行识别，是当前人体姿态识别研究领域的研究重点与难点。Existing human body posture recognition algorithms often identify the "state" of the human body at a certain moment. This type of method can accurately identify simple static postures such as "raising hands" and "raising legs." But in natural interpersonal communication scenarios, humans tend to use a series of action combinations to express more complex meanings. Recognizing this dynamic posture composed of a series of actions is the focus and difficulty of current research in the field of human posture recognition.
现有的姿态识别方法主要包括2种，其一是基于动传感器的人体姿态识别，其二是基于图像分析的人体姿态识别；基于传感器的识别技术主要通过让研究人员携带传感器来进行采集相关运动数据，常用的传感器主要包括加速度计、磁阻传感器、陀螺仪等，利用传感器获取研究人员的运动信息后，结合机器学习的相关方法，对人的姿态做出识别，这种方法对姿态的识别结果主要受到特征提取方法即传感器使用和分类器选择的影响，对于姿态识别来说不够准确；基于图像的分析方法，系统通过提取研究人员的图像来作为研究分析的特征，目前基于图像的方法多采用堆图像高宽比、形状复杂性变化、离心率等方法分析图像的轮廓特征结合K-means或SVM来判别人的姿态类别，然而上述的传统方法只能进行单独的个体姿态识别，无法实现与标准动作的对比分析。Existing posture recognition methods mainly include two types, one is human posture recognition based on motion sensors, and the other is human posture recognition based on image analysis; sensor-based recognition technology mainly allows researchers to carry sensors to collect related movements. Data. Commonly used sensors mainly include accelerometers, magnetoresistive sensors, gyroscopes, etc. After using sensors to obtain the movement information of researchers, combined with related methods of machine learning, the human posture is recognized. This method can recognize the posture of the person. The results are mainly affected by the feature extraction method, that is, the use of sensors and the selection of classifiers, which are not accurate enough for gesture recognition; image-based analysis methods, the system extracts images of researchers as features for research analysis. Currently, there are many image-based methods Use heap image aspect ratio, shape complexity changes, eccentricity and other methods to analyze the contour features of the image and combine it with K-means or SVM to determine the posture category of others. However, the above-mentioned traditional methods can only perform individual individual posture recognition and cannot be realized. Comparative analysis with standard actions.
现有技术中，无论是在体育测试或是运动锻炼时，对被测试者所完成的动作是否标准的评价基本是通过采用人工判断方法得到的，计算机模型无法做出客观准确的评价。In the existing technology, whether it is during sports testing or exercise, the evaluation of whether the actions performed by the test subject are standard or not is basically obtained by using manual judgment methods, and computer models cannot make objective and accurate evaluations.
因此，亟需一种有效的识别人体运动姿态且能对运动姿态是否标准进行准确评价的方法。Therefore, there is an urgent need for a method that can effectively identify human movement postures and accurately evaluate whether the movement postures are standard.
发明内容Contents of the invention
有鉴于此，本发明的目的在于提供一种判断人体运动姿态的方法，用于精确计算人体运动姿态的关键参数，并根据关键参数判断出人体运动动作是否标准，然后做出动作调整方案。In view of this, the purpose of the present invention is to provide a method for judging the human body's movement posture, which is used to accurately calculate the key parameters of the human body's movement posture, and determine whether the human body's movement is standard based on the key parameters, and then make an action adjustment plan.
为达到上述目的，本发明提供如下技术方案：In order to achieve the above objects, the present invention provides the following technical solutions:
方案1：一种人体运动姿态关键参数的计算方法，包括以下步骤：Option 1: A method for calculating key parameters of human movement posture, including the following steps:
S1：获取动作视频，并对视频中每一帧图像进行处理；S1: Obtain the action video and process each frame of the video;
S2：根据骨架提取关节点数据，计算出能够描述人体姿态的关键参数，包括角度参数、高度参数及距离参数；S2: Extract joint point data based on the skeleton and calculate key parameters that can describe the human posture, including angle parameters, height parameters and distance parameters;
所述角度参数包括：肘关节的弯曲角度、膝关节的弯曲角度及腰部的弯曲角度；The angle parameters include: the bending angle of the elbow joint, the bending angle of the knee joint, and the bending angle of the waist;
所述高度参数包括：左右肘关节离地高度、左右膝关节离地高度及左右两侧腰部离地高度；The height parameters include: the height of the left and right elbow joints from the ground, the height of the left and right knee joints from the ground, and the height of the left and right waists from the ground;
所述距离参数包括：双脚之间的横向与纵向距离、手臂之间的横向与纵向距离，以及双膝之间的横向与纵向距离。The distance parameters include: the lateral and longitudinal distance between the feet, the lateral and longitudinal distance between the arms, and the lateral and longitudinal distance between the knees.
进一步，步骤S2中，所述角度参数主要是由三个相关关节点的数据进行计算，主要思路是由三个关节点构造出三角形，计算出三个关节点中两两关节点的距离即三角形的边长。Further, in step S2, the angle parameter is mainly calculated from the data of three related joint points. The main idea is to construct a triangle from the three joint points, and calculate the distance between two joint points among the three joint points, which is the triangle. side length.
进一步，步骤S2中，所述距离参数是根据关节点在水平及垂直方向上的投影所构造出的三角形，通过计算三角形的两直角边边长，得到关节点之间的横向距离与纵向距离。Further, in step S2, the distance parameter is a triangle constructed based on the projection of the joint points in the horizontal and vertical directions. By calculating the length of the two right-angled sides of the triangle, the lateral distance and the longitudinal distance between the joint points are obtained.
进一步，步骤S2中，所述高度参数是计算相关关节点间纵坐标距离差的绝对值。Further, in step S2, the height parameter is calculated as the absolute value of the ordinate distance difference between relevant joint points.
方案2：一种判断人体运动姿态的方法，具体包括以下步骤：Option 2: A method for judging human body movement posture, specifically including the following steps:
S31：通过所述的人体运动姿态关键参数的计算方法，得到锻炼者的姿态关键参数组Puser和标准动作的姿态关键参数组Pstandard；S31: Obtain the exerciser's posture key parameter group Puser and the standard action posture key parameter group Pstandard through the calculation method of the key parameters of human movement posture;
S32：计算出Puser及Pstandard参数组中按顺序一一对应的参数的差值differ；S32: Calculate the difference between the one-to-one corresponding parameters in the Puser and Pstandard parameter groups in order;
S33：设定锻炼者动作与标准动作的相差程度，根据动作相差程度给出姿态调整方案。S33: Set the difference between the exerciser's movements and the standard movements, and provide a posture adjustment plan based on the difference between the movements.
进一步，步骤S33中，所述姿态调整方案为：Further, in step S33, the attitude adjustment scheme is:
(1)角度参数的调整：(1)Adjustment of angle parameters:
当肘关节的弯曲角度为differ°时，将手臂向外/内侧移动约|differ|°，并保持身体其他各部位正确姿态不变；When the elbow joint bends at a different angle, move the arm outward/inward by about |differ|°, and keep the correct posture of other parts of the body unchanged;
当膝关节的弯曲角度为differ°时，将膝关节以上身体部位向上抬起/向下压约|differ|°，并保持身体其他各部位正确姿态不变；When the knee joint bends at a different angle, lift up/press down the body parts above the knee joint by about |differ|°, and keep the correct posture of other parts of the body unchanged;
当腰部的弯曲角度为differ°时，将腰部以上身体部位向背部/胸部方向移动约|differ|°，并保持身体其他各部位正确姿态不变；When the bending angle of the waist is differ°, move the body parts above the waist toward the back/chest direction by about |differ|°, and keep the correct posture of other parts of the body unchanged;
(2)距离参数的调整：(2) Adjustment of distance parameters:
当双脚之间的横向与纵向距离为differ cm时，将左右脚均向外/内侧平移约|differ|/2cm，并保持身体其他各部位正确姿态不变；When the lateral and vertical distance between the feet is differ cm, move both left and right feet outward/inward by about |differ|/2cm, and keep the correct posture of other parts of the body unchanged;
当手臂之间的横向与纵向距离为differ cm时，将左右手臂均向外/内侧平移约|differ|/2cm，并保持身体其他各部位正确姿态不变；When the horizontal and vertical distance between the arms is differ cm, move both left and right arms outward/inward by about |differ|/2cm, and keep the correct posture of other parts of the body unchanged;
当双膝之间的横向与纵向距离为differ cm时，将左右膝关节均向外/内侧平移约|differ|/2cm，并保持身体其他各部位正确姿态不变；When the lateral and vertical distance between the knees is differ cm, move the left and right knee joints outward/inward by about |differ|/2cm, and keep the correct posture of other parts of the body unchanged;
(3)高度参数的调整：(3) Adjustment of height parameters:
当肘关节离地高度为differ cm时，将左右肘关节向上/下平移约|differ|cm,并保持身体其他各部位正确姿态不变；When the height of the elbow joint from the ground is differ cm, move the left and right elbow joints up/down about |differ|cm, and keep the correct posture of other parts of the body unchanged;
当膝关节离地高度为differ cm时，将左右膝关节向上/下平移约|differ|cm,并保持身体其他各部位正确姿态不变；When the height of the knee joint from the ground is differ cm, move the left and right knee joints up/down about |differ|cm, and keep the correct posture of other parts of the body unchanged;
当腰部离地高度为differ cm时，将腰部向上/下平移约|differ|cm,并保持身体其他各部位正确姿态不变。When the height of the waist from the ground is differ cm, translate the waist up/down about |differ|cm, and keep the correct posture of other parts of the body unchanged.
本发明的有益效果在于：本发明能精确计算出人体运动姿态的关键参数，并根据关键参数判断出人体运动动作是否标准，然后做出有效的动作调整方案；为锻炼者提供了高效的运动参考，便于锻炼者及时调整姿态，提高锻炼的安全性和健康性。The beneficial effects of the present invention are: the present invention can accurately calculate the key parameters of the human body's movement posture, and judge whether the human body's movement is standard based on the key parameters, and then make an effective movement adjustment plan; it provides an efficient movement reference for exercisers , to facilitate exercisers to adjust their posture in time and improve the safety and health of exercise.
本发明的其他优点、目标和特征在某种程度上将在随后的说明书中进行阐述，并且在某种程度上，基于对下文的考察研究对本领域技术人员而言将是显而易见的，或者可以从本发明的实践中得到教导。本发明的目标和其他优点可以通过下面的说明书来实现和获得。Other advantages, objects, and features of the present invention will, to the extent that they are set forth in the description that follows, and to the extent that they will become apparent to those skilled in the art upon examination of the following, or may be derived from This invention is taught by practicing it. The objects and other advantages of the invention may be realized and obtained by the following description.
附图说明Description of the drawings
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作优选的详细描述，其中：In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings, in which:
图1为人体姿势的角度参数示意图；Figure 1 is a schematic diagram of the angle parameters of human posture;
图2为人体姿势的距离参数示意图；Figure 2 is a schematic diagram of distance parameters of human posture;
图3为人体姿势的高度参数示意图；Figure 3 is a schematic diagram of height parameters of human posture;
图4为计算角度参数时关节点三角形示意图；Figure 4 is a schematic diagram of the joint point triangle when calculating angle parameters;
图5为计算距离参数时关节点三角形示意图；Figure 5 is a schematic diagram of the joint point triangle when calculating distance parameters;
图6为计算高度参数是的关节点示意图；Figure 6 is a schematic diagram of joint points for calculating height parameters;
图7为某个人体姿态关节点示意图。Figure 7 is a schematic diagram of the joint points of a human body posture.
具体实施方式Detailed ways
以下通过特定的具体实例说明本发明的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本发明的其他优点与功效。本发明还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本发明的精神下进行各种修饰或改变。需要说明的是，以下实施例中所提供的图示仅以示意方式说明本发明的基本构想，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。The following describes the embodiments of the present invention through specific examples. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. The following embodiments and the features in the embodiments can be combined with each other as long as there is no conflict.
其中，附图仅用于示例性说明，表示的仅是示意图，而非实物图，不能理解为对本发明的限制；为了更好地说明本发明的实施例，附图某些部件会有省略、放大或缩小，并不代表实际产品的尺寸；对本领域技术人员来说，附图中某些公知结构及其说明可能省略是可以理解的。The drawings are only for illustrative purposes, and represent only schematic diagrams rather than actual drawings, which cannot be understood as limitations of the present invention. In order to better illustrate the embodiments of the present invention, some components of the drawings will be omitted. The enlargement or reduction does not represent the size of the actual product; it is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.
本发明实施例的附图中相同或相似的标号对应相同或相似的部件；在本发明的描述中，需要理解的是，若有术语“上”、“下”、“左”、“右”、“前”、“后”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此附图中描述位置关系的用语仅用于示例性说明，不能理解为对本发明的限制，对于本领域的普通技术人员而言，可以根据具体情况理解上述术语的具体含义。In the drawings of the embodiments of the present invention, the same or similar numbers correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms "upper", "lower", "left" and "right" The orientation or positional relationship indicated by "front", "rear", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must be It has a specific orientation and is constructed and operated in a specific orientation. Therefore, the terms describing the positional relationships in the drawings are only for illustrative purposes and cannot be understood as limitations of the present invention. For those of ordinary skill in the art, they can determine the specific position according to the specific orientation. Understand the specific meaning of the above terms.
请参阅图1～图7，本发明设计了一种判断人体运动姿态的方法，包括姿态关键参数计算阶段和判断人体运动姿态是否标准阶段。Please refer to Figures 1 to 7. The present invention designs a method for judging human body movement posture, which includes a stage of calculating key posture parameters and a stage of determining whether the human body movement posture is standard.
1、姿态关键参数计算阶段1. Calculation stage of key posture parameters
为了让锻炼者能够更直观的了解到自身动作与标准动作的差异，本实施例将会对从标准动作视频与测试视频中提取出的每一帧图像进行处理。通过在骨架提取阶段所得到的关节点数据，计算出能够描述人体姿态的关键参数，包括角度参数、高度参数及距离参数，具体的参数如表1所示。In order to allow exercisers to more intuitively understand the difference between their own movements and standard movements, this embodiment will process each frame of image extracted from the standard movement video and the test video. Through the joint point data obtained in the skeleton extraction stage, the key parameters that can describe the human posture are calculated, including angle parameters, height parameters and distance parameters. The specific parameters are shown in Table 1.
表1人体姿态关键参数表Table 1 Key parameters of human body posture
以上参数的具体含义如图1～图3所示。The specific meanings of the above parameters are shown in Figures 1 to 3.
根据骨架提取阶段获取到的关节数据点，可以得到以上15个人体姿态关键参数的计算公式。其中角度参数包括肘关节的弯曲角度、膝关节的弯曲角度及腰部的弯曲角度，角度参数主要是由三个相关关节点的数据进行计算，主要思路是由三个关节点构造出三角形，如图4所示。Based on the joint data points obtained in the skeleton extraction stage, the calculation formulas for the above 15 key parameters of human posture can be obtained. The angle parameters include the bending angle of the elbow joint, the bending angle of the knee joint and the bending angle of the waist. The angle parameters are mainly calculated from the data of three related joint points. The main idea is to construct a triangle from the three joint points, as shown in the figure 4 shown.
根据图4所示的三角形，计算出三个关节点中两两关节点的距离即三角形的边长A,B,C，如下式所示：According to the triangle shown in Figure 4, calculate the distance between two of the three joint points, that is, the side lengths A, B, and C of the triangle, as shown in the following formula:
其中，(xa,ya)、(xb,yb)、(xc,yc)分别表示三个关节点的坐标。Among them, (xa ,ya ), (xb ,yb ), (xc ,yc ) respectively represent the coordinates of the three joint points.
再利用余弦定理公式计算出角度α，如下式所示：Then use the cosine theorem formula to calculate the angle α, as shown in the following formula:
α＝arccosαα=arccosα
人体姿态关键参数中的距离参数主要包括双脚之间的横向与纵向距离、手臂之间的横向与纵向距离及双膝之间的横向与纵向距离。由于在大多数实际情况中，双脚、双手肘关节与双膝并不处于同一条水平直线上，导致其距离的计算并不能简单的直接使用两点间距离公式进行计算，而是参考角度计算的思路构造出三角形，通过计算三角形的边长得到关节点之间的距离。The distance parameters among the key parameters of human posture mainly include the horizontal and vertical distance between the feet, the horizontal and vertical distance between the arms, and the horizontal and vertical distance between the knees. Since in most practical situations, the feet, elbow joints and knees are not on the same horizontal straight line, the distance cannot be calculated simply by using the distance formula between two points, but by referring to the angle calculation. The idea is to construct a triangle, and get the distance between the joint points by calculating the side lengths of the triangle.
由图5所示为根据关节点在水平及垂直方向上的投影所构造出的三角形，由图5可知通过计算三角形的两直角边边长，即可得到关节点之间的横向距离HD与纵向距离VD。Figure 5 shows a triangle constructed based on the projection of the joint points in the horizontal and vertical directions. It can be seen from Figure 5 that by calculating the length of the two right-angled sides of the triangle, the lateral distance HD and the longitudinal distance between the joint points can be obtained. Distance VD.
由图5可知，关节点之间的横向距离HD与纵向距离VD计算公式分别为：As can be seen from Figure 5, the calculation formulas for the horizontal distance HD and the longitudinal distance VD between joint points are:
HD＝|x2-x1|HD＝|x2 -x1 |
VD＝|y2-y1|VD＝|y2 -y1 |
人体姿态关键参数中的高度参数主要包括肘关节离地高度、膝关节离地高度及腰部离地高度，其中所有的高度参数均由人体右侧与左侧两部分组成，如图6所示，即肘关节离地高度包括左手肘关节离地高度与右手肘关节离地高度、膝关节离地高度包括左膝关节离地高度与右膝关节离地高度、腰部离地高度包括左侧腰部离地高度与右侧腰部离地高度。The height parameters among the key parameters of human posture mainly include the height of the elbow joint from the ground, the height of the knee joint from the ground, and the height of the waist from the ground. All height parameters are composed of the right and left parts of the human body, as shown in Figure 6. That is, the elbow joint height from the ground includes the left elbow joint height from the ground and the right elbow joint height from the ground, the knee joint height from the ground includes the left knee joint height from the ground and the right knee joint height from the ground, and the waist height from the ground includes the left waist height from the ground. The ground height and the right waist height from the ground.
高度参数的计算相对角度与距离参数的计算来说比较简单，直接计算相关关节点间纵坐标距离差的绝对值即可。The calculation of the height parameter is relatively simple compared to the calculation of the angle and distance parameters. Simply calculate the absolute value of the ordinate distance difference between the relevant joint points.
图7为某个人体姿态的关节点示意图，其中坐标角标r表示该关节点属于身体右侧，l表示该关节点属于身体左侧。Figure 7 is a schematic diagram of the joint points of a certain human body posture. The coordinate index r indicates that the joint point belongs to the right side of the body, and l indicates that the joint point belongs to the left side of the body.
由图7可以很容易得出左手肘关节离地高度Hzl与右手肘关节离地高度Hzr、左膝关节离地高度Hxl与右膝关节离地高度Hxr、左侧腰部离地高度Hyl与右侧腰部离地高度Hyr的计算公式如下式所示：From Figure 7, it can be easily concluded that the height of the left elbow joint from the ground Hzl and the height of the right elbow joint from the ground Hzr , the height of the left knee joint from the ground Hxl and the height of the right knee joint Hxr , and the height of the left waist from the ground The calculation formula of Hyl and the right waist height Hyr from the ground is as follows:
Hzl＝|yl1-yl4|Hzl =|yl1 -yl4 |
Hzr＝|yr1-yr4|Hzr =|yr1 -yr4 |
Hxl＝|yl3-yl4|Hxl =|yl3 -yl4 |
Hxr＝|yr3-yr4|Hxr =|yr3 -yr4 |
Hyl＝|yl2-yl4|Hyl =|yl2 -yl4 |
Hyr＝|yr2-yr4|Hyr =|yr2 -yr4 |
通过以上的计算公式，可以得到人体姿态的关键参数值，通过比较测试视频关键图像帧与标准视频关键图像帧中的人体姿态的角度参数值、距离参数值及高度参数值，可以准确的得出锻炼者动作与标准库中动作存在差异的身体部位，并且可以对存在差异的身体部分进行量化。假设某锻炼者肘关节弯曲角度相对标准库中人体肘关节弯曲角度较大，则可以输出文字提示用户，如：肘关节弯曲角度过大，建议减小肘关节的弯曲角度。Through the above calculation formula, the key parameter values of the human posture can be obtained. By comparing the angle parameter values, distance parameter values and height parameter values of the human posture in the test video key image frame and the standard video key image frame, it can be accurately obtained The body parts where the exerciser's movements differ from those in the standard library, and the body parts where the differences exist can be quantified. Assuming that the bending angle of an exerciser's elbow joint is larger than the bending angle of the human elbow joint in the standard library, text can be output to prompt the user, for example: the bending angle of the elbow joint is too large, it is recommended to reduce the bending angle of the elbow joint.
2、判断人体运动姿态是否标准阶段2. Determine whether the human body movement posture is in the standard stage
为了让锻炼者更加直观的了解到自身运动姿态所存在的具体问题，本实施例将会对姿态关键参数计算阶段所得到的结果进行处理，设定阈值，生成详细的文字描述，具体实现方案如下：In order to allow exercisers to more intuitively understand the specific problems of their own movement postures, this embodiment will process the results obtained in the calculation phase of key posture parameters, set thresholds, and generate detailed text descriptions. The specific implementation plan is as follows :
第一步，假设通过姿态关键参数计算环节，得到锻炼者与标准库视频关键图像帧中人体姿态关键参数分别为：In the first step, it is assumed that through the calculation of key posture parameters, the key parameters of the human posture in the key image frames of the exerciser and the standard library video are obtained:
Puser＝{αzu,αxu,αyu,hdfu,vdfu,hdau,vdau,hdku,vdku,hzlu,hzru,hxlu,hxru,hylu,hyru}Puser ={αzu ,αxu ,αyu ,hdfu ,vdfu ,hdau ,vdau ,hdku ,vdku ,hzlu ,hzru ,hxlu ,hxru ,hylu ,hyru }
Pstandard＝{αzs,αxs,αys,hdfs,vdfs,hdas,vdas,hdks,vdks,hzls,hzrs,hxls,hxrs,hyls,hyrs}Pstandard ={αzs ,αxs ,αys ,hdfs ,vdfs ,hdas ,vdas ,hdks ,vdks ,hzls ,hzrs ,hxls ,hxrs ,hyls ,hyrs }
其中，Puser表示锻炼者的姿态关键参数组，Pstandard表示标准动作的姿态关键参数组，其中具体的参数含义请节姿态关键参数计算阶段的说明。Among them, Puser represents the exerciser's posture key parameter group, and Pstandard represents the posture key parameter group of the standard movement. For the specific meaning of the parameters, please refer to the description of the posture key parameter calculation stage.
首先计算Puser及Pstandard参数组中按顺序一一对应的参数的差值differ，差值的通用计算公式为：First, calculate the difference between the parameters corresponding to each other in sequence in the Puser and Pstandard parameter groups. The general calculation formula for the difference is:
differ＝xu-xsdiffer＝xu -xs
其中，xu表示Puser参数组中的参数值，xs表示Pstandard参数组中的参数值。Among them, xu represents the parameter value in the Puser parameter group, and xs represents the parameter value in the Pstandard parameter group.
第二步，设定不同程度说明文字对应的输出阈值，此处的不同程度说明文字是指锻炼者动作与标准动作的相差程度，如：稍大、比较大、较大及过大等。根据计算出差值differ的大小，输出不同程度的说明文字，文字说明应该指出存在差异的身体部位、对差异的具体描述(与标准动作的相差程度)及调整方案，如：上肢左侧肘关节的弯曲角度稍小，应将前臂向外侧移动大约5°、下肢右侧膝关节离地高度比较高，应将膝关节向下压约10cm、腰部弯曲角度较大，应将上半身向下弯曲约15°等。锻炼者可以设定健身的级别，可选项为高级，中级与初级，等级越低，则不同程度说明文字对应的输出阈值越高，下面将会以初级锻炼者为例，给出具体的输出说明文字与对应阈值及调整方案，而对于中级与高级锻炼者，其输出说明文字与调整方案与初级锻炼者相同，唯一不同之处即阈值的取值不同。The second step is to set the output thresholds corresponding to different levels of explanatory text. The different levels of explanatory text here refer to the degree of difference between the exerciser's movements and the standard movements, such as: slightly larger, relatively larger, larger, and too large, etc. According to the calculated difference value, different levels of explanatory text are output. The text description should point out the body parts with differences, a specific description of the difference (the degree of difference from the standard movement) and the adjustment plan, such as: left elbow joint of the upper limb The bending angle is slightly smaller, the forearm should be moved to the outside by about 5°, the right knee joint of the lower limb is relatively high from the ground, the knee joint should be pressed down about 10cm, the waist bending angle is larger, the upper body should be bent downward about 15° etc. The exerciser can set the level of fitness. The options are advanced, intermediate and elementary. The lower the level, the higher the output threshold corresponding to the different levels of explanatory text. The following will take the elementary exerciser as an example to give specific output instructions. Text and corresponding threshold value and adjustment plan. For intermediate and advanced exercisers, the output description text and adjustment plan are the same as those for beginner exercisers. The only difference is that the value of the threshold is different.
对于初级的锻炼者，在其动作与标准动作相差比较大的情况下，才会输出说明文字，提示锻炼者的动作有误并给出调整方案，输出阈值如表2所示；For junior exercisers, when their movements are significantly different from the standard movements, explanatory text will be output to remind the exerciser that their movements are incorrect and provide an adjustment plan. The output thresholds are shown in Table 2;
表2输出说明文字与对应阈值表(初级)Table 2 Output description text and corresponding threshold table (elementary)
对于中级与高级锻炼者，其阈值如表3所示；For intermediate and advanced exercisers, the thresholds are shown in Table 3;
表3中级与高级锻炼者阈值参数表Table 3 Threshold parameter table for intermediate and advanced exercisers
根据表2的阈值及说明文字，可以给出锻炼者对应的调整方案，详细的调整方案如表4所示,调整方案详细的指出了锻炼者应该如何调整自身的姿态。According to the thresholds and explanatory text in Table 2, the exerciser's corresponding adjustment plan can be given. The detailed adjustment plan is shown in Table 4. The adjustment plan points out in detail how the exerciser should adjust his or her posture.
表4姿态调整方案表Table 4 Posture adjustment plan table
根据表2、表3及表4，本实施例可以给出不同等级的锻炼者自身运动姿态存在的问题以及对应的详细调整方案，下面列举两种情况进行举例说明：According to Table 2, Table 3 and Table 4, this embodiment can provide the problems existing in exercise postures of different levels of exercisers and the corresponding detailed adjustment plans. Two situations are listed below for illustration:
1)初级锻炼者，通过计算得到该锻炼者双脚横向距离hdfu与对应标准动作的双脚横向距离hdfs差值differ为-7cm，则根据differ值，提示该锻炼者存在差异的身体部位的说明文字为：双脚之间的横向距离稍小，给出对应的调整方案为：将左右脚均向外侧平移约3.5cm，移动过程中注意保持身体各部位正确姿态不变。1) For beginner exercisers, the difference between the lateral distance hdfu of the exerciser’s feet and the lateral distance hdfs of the feet corresponding to the standard movement is calculated to be -7cm. Based on the difference value, the exerciser will be prompted for different body parts. The description reads: The lateral distance between the feet is slightly smaller. The corresponding adjustment plan is: move both left and right feet outward about 3.5cm. During the movement, pay attention to keeping the correct posture of each part of the body unchanged.
1)中级锻炼者，通过计算得到该锻炼者腰部的弯曲角度αyu与对应标准动作的腰部的弯曲角度αys差值differ为13°，则根据differ值，提示该锻炼者存在差异的身体部位的说明文字为：腰部的弯曲角度较大，给出对应的调整方案为：将腰部以上身体部位向胸部方向移动约13°，移动过程中注意保持身体各部位正确姿态不变。1) For an intermediate exerciser, the difference between the bending angle αyu of the exerciser's waist and the bending angle αys of the waist corresponding to the standard movement is calculated to be 13°. Based on the difference value, the exerciser is prompted for the body parts with differences. The description reads: The bending angle of the waist is large. The corresponding adjustment plan is: move the body parts above the waist towards the chest by about 13°. During the movement, pay attention to keeping the correct posture of each part of the body unchanged.
最后说明的是，以上实施例仅用以说明本发明的技术方案而非限制，尽管参照较佳实施例对本发明进行了详细说明，本领域的普通技术人员应当理解，可以对本发明的技术方案进行修改或者等同替换，而不脱离本技术方案的宗旨和范围，其均应涵盖在本发明的权利要求范围当中。Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified. Modifications or equivalent substitutions without departing from the purpose and scope of the technical solution shall be included in the scope of the claims of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379043.5ACN112990089B (en) | 2021-04-08 | 2021-04-08 | A method for judging human body movement posture |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379043.5ACN112990089B (en) | 2021-04-08 | 2021-04-08 | A method for judging human body movement posture |
| Publication Number | Publication Date |
|---|---|
| CN112990089A CN112990089A (en) | 2021-06-18 |
| CN112990089Btrue CN112990089B (en) | 2023-09-26 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110379043.5AExpired - Fee RelatedCN112990089B (en) | 2021-04-08 | 2021-04-08 | A method for judging human body movement posture |
| Country | Link |
|---|---|
| CN (1) | CN112990089B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093029A (en)* | 2021-11-23 | 2022-02-25 | 上海市青少年校外活动营地--东方绿舟 | Method and device for analyzing group queue training |
| CN114974506B (en)* | 2022-05-17 | 2024-05-03 | 重庆大学 | Human body posture data processing method and system |
| CN115005812B (en)* | 2022-05-30 | 2024-06-25 | 哈尔滨工业大学（威海） | Human body motion detection method, human body upper limb motion detection method based on space triangle and consistency evaluation method |
| CN115005811B (en)* | 2022-05-30 | 2024-08-20 | 哈尔滨工业大学（威海） | Human body movement angle measuring method |
| CN116823953A (en)* | 2023-07-19 | 2023-09-29 | 咪咕新空文化科技(厦门)有限公司 | Attitude adjustment method, device, electronic equipment and readable storage medium |
| CN118394221B (en)* | 2024-06-24 | 2024-09-24 | 湖南美创数字科技有限公司 | Interaction method and system based on somatosensory capture |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10261090A (en)* | 1997-03-19 | 1998-09-29 | Tokyo Electric Power Co Inc:The | Motion capture system |
| CN105608467A (en)* | 2015-12-16 | 2016-05-25 | 西北工业大学 | Kinect-based non-contact type student physical fitness evaluation method |
| CN108537284A (en)* | 2018-04-13 | 2018-09-14 | 东莞松山湖国际机器人研究院有限公司 | Pose assessment scoring method and system based on computer vision deep learning algorithm |
| CN110245623A (en)* | 2019-06-18 | 2019-09-17 | 重庆大学 | A real-time human motion posture correction method and system |
| CN110321754A (en)* | 2018-03-28 | 2019-10-11 | 西安铭宇信息科技有限公司 | A kind of human motion posture correcting method based on computer vision and system |
| CN110969114A (en)* | 2019-11-28 | 2020-04-07 | 四川省骨科医院 | Human body action function detection system, detection method and detector |
| CN111883229A (en)* | 2020-07-31 | 2020-11-03 | 焦点科技股份有限公司 | Intelligent movement guidance method and system based on visual AI |
| CN111931733A (en)* | 2020-09-25 | 2020-11-13 | 西南交通大学 | Human body posture detection method based on depth camera |
| CN112184898A (en)* | 2020-10-21 | 2021-01-05 | 安徽动感智能科技有限公司 | Digital human body modeling method based on motion recognition |
| CN112200074A (en)* | 2020-10-09 | 2021-01-08 | 广州健康易智能科技有限公司 | A method and terminal for attitude comparison |
| CN112329513A (en)* | 2020-08-24 | 2021-02-05 | 苏州荷露斯科技有限公司 | High frame rate 3D (three-dimensional) posture recognition method based on convolutional neural network |
| CN112381002A (en)* | 2020-11-16 | 2021-02-19 | 深圳技术大学 | Human body risk posture identification method and system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7196645B2 (en)* | 2019-01-31 | 2022-12-27 | コニカミノルタ株式会社 | Posture Estimation Device, Action Estimation Device, Posture Estimation Program, and Posture Estimation Method |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10261090A (en)* | 1997-03-19 | 1998-09-29 | Tokyo Electric Power Co Inc:The | Motion capture system |
| CN105608467A (en)* | 2015-12-16 | 2016-05-25 | 西北工业大学 | Kinect-based non-contact type student physical fitness evaluation method |
| CN110321754A (en)* | 2018-03-28 | 2019-10-11 | 西安铭宇信息科技有限公司 | A kind of human motion posture correcting method based on computer vision and system |
| CN108537284A (en)* | 2018-04-13 | 2018-09-14 | 东莞松山湖国际机器人研究院有限公司 | Pose assessment scoring method and system based on computer vision deep learning algorithm |
| CN110245623A (en)* | 2019-06-18 | 2019-09-17 | 重庆大学 | A real-time human motion posture correction method and system |
| CN110969114A (en)* | 2019-11-28 | 2020-04-07 | 四川省骨科医院 | Human body action function detection system, detection method and detector |
| CN111883229A (en)* | 2020-07-31 | 2020-11-03 | 焦点科技股份有限公司 | Intelligent movement guidance method and system based on visual AI |
| CN112329513A (en)* | 2020-08-24 | 2021-02-05 | 苏州荷露斯科技有限公司 | High frame rate 3D (three-dimensional) posture recognition method based on convolutional neural network |
| CN111931733A (en)* | 2020-09-25 | 2020-11-13 | 西南交通大学 | Human body posture detection method based on depth camera |
| CN112200074A (en)* | 2020-10-09 | 2021-01-08 | 广州健康易智能科技有限公司 | A method and terminal for attitude comparison |
| CN112184898A (en)* | 2020-10-21 | 2021-01-05 | 安徽动感智能科技有限公司 | Digital human body modeling method based on motion recognition |
| CN112381002A (en)* | 2020-11-16 | 2021-02-19 | 深圳技术大学 | Human body risk posture identification method and system |
| Title |
|---|
| A New Kinect-Based Posture Recognition Method in Physical Sports Training Based on Urban Data;Dianchen He等;Wireless Communications and Mobile Computing;第1-9页* |
| 基于3D打印与光纤光栅传感技术的新型人体姿态识别系统;韩艳杰;中国优秀硕士学位论文全文数据库 信息科技辑(第1期);第I140-1175页* |
| 基于Kinect的体育运动自训练系统;李鑫等;计算机技术与发展(第4期);第128-133页* |
| 基于运动传感的人体姿态实时捕获系统研究;李杰;中国优秀硕士学位论文全文数据库 信息科技辑(第2期);第I138-4090页* |
| Publication number | Publication date |
|---|---|
| CN112990089A (en) | 2021-06-18 |
| Publication | Publication Date | Title |
|---|---|---|
| CN112990089B (en) | A method for judging human body movement posture | |
| US12183109B2 (en) | Modeling method and modeling device for human body model, electronic device, and storage medium | |
| CN110969114B (en) | Human body action function detection system, detection method and detector | |
| CN112861624A (en) | Human body posture detection method, system, storage medium, equipment and terminal | |
| CN102043952B (en) | A Eye Tracking Method Based on Dual Light Sources | |
| CN106650687A (en) | Posture correction method based on depth information and skeleton information | |
| CN112749684A (en) | Cardiopulmonary resuscitation training and evaluating method, device, equipment and storage medium | |
| CN107491648A (en) | Hand recovery training method based on Leap Motion motion sensing control devices | |
| CN115227234B (en) | A camera-based cardiopulmonary resuscitation compression action evaluation method and system | |
| CN109766782B (en) | Real-time body motion recognition method based on SVM | |
| CN111883229A (en) | Intelligent movement guidance method and system based on visual AI | |
| CN112668531A (en) | Motion posture correction method based on motion recognition | |
| CN114092854B (en) | Intelligent rehabilitation auxiliary training system for spinal degenerative diseases based on deep learning | |
| CN110263745A (en) | A kind of method and device of pupil of human positioning | |
| KR20220120731A (en) | Method and device for providing affordance healthcare contents using mirror type display | |
| He et al. | A New Kinect‐Based Posture Recognition Method in Physical Sports Training Based on Urban Data | |
| CN112818800A (en) | Physical exercise evaluation method and system based on human skeleton point depth image | |
| Memon | On assisted living of paralyzed persons through real-time eye features tracking and classification using Support Vector Machines | |
| CN116363759A (en) | A human sitting posture detection method based on 3D skeleton points | |
| CN116386137A (en) | A mobile terminal design method for lightweight recognition of Tai Chi movements | |
| CN115240247A (en) | A recognition method and system for motion and gesture detection | |
| Omidokun et al. | Leveraging digital perceptual technologies for remote perception and analysis of human biomechanical processes: A contactless approach for workload and joint force assessment | |
| Piraintorn et al. | Stroke rehabilitation based on intelligence interaction system | |
| CN116343325A (en) | Intelligent auxiliary system for household body building | |
| CN115251905A (en) | Breast cancer postoperative rehabilitation state assessment method and system |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20230926 |