CN107371307B - A kind of lamp effect control method and system based on gesture identification - Google Patents
A kind of lamp effect control method and system based on gesture identification Download PDFInfo
- Publication number
- CN107371307B CN107371307B CN201710577064.1A CN201710577064A CN107371307B CN 107371307 B CN107371307 B CN 107371307B CN 201710577064 A CN201710577064 A CN 201710577064A CN 107371307 B CN107371307 B CN 107371307B
- Authority
- CN
- China
- Prior art keywords
- image
- hand
- gray value
- brightness
- lamp
- 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.)
- Active
Links
- 230000000694 effects Effects 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000000605 extraction Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims 2
- 230000001795 light effect Effects 0.000 claims 2
- 230000007423 decrease Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 4
- 230000003750 conditioning effect Effects 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000001143 conditioned effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004148 unit process Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B47/00—Circuit arrangements for operating light sources in general, i.e. where the type of light source is not relevant
- H05B47/10—Controlling the light source
- H05B47/105—Controlling the light source in response to determined parameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
本发明公开了一种基于手势识别的灯效控制方法及系统，首先获取图像拍摄模块所拍摄的包含手部的图像，然后提取出所述图像中手部的图像，根据提取出的手部的图像，识别出手部的张开程度，并根据手部张开程度的变化生成用于调整来灯的亮度的控制指令。实施本发明的基于手势识别的灯效控制方法及系统，操作人员可以在不携带任何遥控装置的前提下，实现对灯的亮度的调节，方便简单。
The invention discloses a lighting effect control method and system based on gesture recognition. Firstly, an image including a hand captured by an image capturing module is acquired, and then the image of the hand in the image is extracted. The image recognizes the degree of hand opening, and generates a control command for adjusting the brightness of the incoming light according to the change of the hand opening degree. By implementing the lighting effect control method and system based on gesture recognition of the present invention, the operator can adjust the brightness of the lamp without carrying any remote control device, which is convenient and simple.
Description
技术领域technical field
本发明涉及灯具领域，更具体地说灯具的等效控制领域，涉及一种基于手势识别的灯效控制方法及系统。The present invention relates to the field of lamps, more specifically to the field of equivalent control of lamps, and relates to a method and system for controlling lamp effects based on gesture recognition.
背景技术Background technique
灯作为人们日常生活、工作中不可或缺的一部分，除了进行必须的开关之外，很多时候还需要进行亮度的调节，将灯置于不同的亮度。对灯的亮度进行调节，目前的主要方式是通过手动调节开关，通过将开关调整至不同的档位或者开度来调整灯的亮度。然而，通过手动调节开关的方式操作人员必须处于开关处才能进行操作，有时候使用起来并不便利。As an indispensable part of people's daily life and work, lamps need to be adjusted in brightness in addition to necessary switches, and the lamps are placed at different brightnesses. To adjust the brightness of the lamp, the current main method is to manually adjust the switch, and adjust the brightness of the lamp by adjusting the switch to different gear positions or opening degrees. However, by manually adjusting the switch, the operator must be at the switch to perform the operation, which is inconvenient to use sometimes.
为了解决上述问题，现有技术中提供了一种手持遥控装置来解决上述问题的方法，操作人员通过触发手持遥控装置上的开关，实现对灯的亮度进行调节。然而，一方面手持遥控装置容易丢失，另一方面手持遥控装置需要占住操作者的一只手，在某些场合也十分不便利，如在需要与人进行握手、拥抱等交互时。In order to solve the above problems, a hand-held remote control device is provided in the prior art to solve the above-mentioned problems. The operator can adjust the brightness of the lamp by triggering a switch on the hand-held remote control device. However, on the one hand, the hand-held remote control device is easy to lose, and on the other hand, the hand-held remote control device needs to occupy one hand of the operator, which is very inconvenient in some occasions, such as when it is necessary to interact with people such as shaking hands or hugging.
发明内容Contents of the invention
本发明要解决的技术问题在于，针对上述的对灯的亮度进行调节时采用手动调节方式以及手持遥控装置调节开关方式，使用不便利以及手持遥控装置易丢失的技术缺陷，提供了一种基于手势识别的灯效控制方法及系统。The technical problem to be solved by the present invention is to provide a gesture-based The identified lighting effect control method and system.
根据本发明的第一方面，本发明为解决其技术问题，提供了一种基于手势识别的灯效控制系统，包括：According to the first aspect of the present invention, in order to solve its technical problem, the present invention provides a lighting effect control system based on gesture recognition, including:
图像获取模块，用于获取图像拍摄模块所拍摄的包含操作者的手部的图像；An image acquisition module, configured to acquire an image of the operator's hand captured by the image capture module;
手部提取模块，用于提取出所述图像中手部的图像；The hand extraction module is used to extract the image of the hand in the image;
动作识别模块，用于根据提取出的手部的图像，识别出手部的张开程度；The action recognition module is used to recognize the degree of opening of the hand according to the image of the extracted hand;
亮度调整模块，用于根据手部张开程度的变化生成用于调整来灯的亮度的控制指令。The brightness adjustment module is used to generate a control instruction for adjusting the brightness of the incoming light according to the change of the hand opening degree.
在本发明的基于手势识别的灯效控制系统中，上述控制指令作用于灯时满足：当手部张开程度增大时，灯的亮度增大，当手部的张开程度增小时，灯的亮度减小。In the lighting effect control system based on gesture recognition of the present invention, when the above-mentioned control command acts on the lamp, it satisfies: when the degree of hand opening increases, the brightness of the light increases, and when the degree of hand opening increases, the brightness of the light increases. brightness decreases.
在本发明的基于手势识别的灯效控制系统中，手部从完全闭合到完全张开的每一个张开程度分别与灯从最小亮度到最大亮度的每一个亮度一一对应；或者，In the lighting effect control system based on gesture recognition of the present invention, each degree of opening of the hand from fully closed to fully opened corresponds to each brightness of the lamp from minimum brightness to maximum brightness; or,
手部从完全闭合到完全张开的每一个张开程度的变化分别与亮度最小变化量到亮度最小变化量的每一个变化量一一对应。Each change in the degree of opening of the hand from fully closed to fully opened corresponds to each change from the minimum change in brightness to the minimum change in brightness.
在本发明的基于手势识别的灯效控制系统中，还包括：In the lighting effect control system based on gesture recognition of the present invention, it also includes:
颜色调整模块，用于在张开程度的变化速度大于预设值时，生成切换灯的颜色的控制指令。The color adjustment module is configured to generate a control instruction for switching the color of the lamp when the change speed of the opening degree is greater than a preset value.
在本发明的基于手势识别的灯效控制系统中，手部提取模块包含：In the lighting effect control system based on gesture recognition of the present invention, the hand extraction module includes:
灰度化处理处理模块，用于将拍摄的图像进行灰度化处理；A grayscale processing module, configured to perform grayscale processing on the captured image;
类间方差遍历模块，用于根据下述公式，计算出灰度化处理后图像中每一个像素的灰度值的类间方差，得出使得类间方差最大的灰度值；The inter-class variance traversal module is used to calculate the inter-class variance of the gray value of each pixel in the image after grayscale processing according to the following formula, so as to obtain the gray value that makes the inter-class variance the largest;
g＝ω1×ω2×(μ1-μ2)2，g＝ω 1 ×ω 2 ×(μ 1 -μ 2 ) 2 ,
式中，g为类间方差，ω1为灰度化处理后图像中灰度值大于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ1灰度化处理后图像中灰度值大于当前选定的灰度值的像素的平均灰度值，ω2为灰度化处理后图像中灰度值小于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ2灰度化处理后图像中灰度值小于当前选定的灰度值的像素的平均灰度值；In the formula, g is the variance between classes, ω 1 is the ratio of the number of pixels whose gray value is greater than the currently selected gray value in the image to the number of pixels in the entire image after gray scale processing, μ 1 after gray scale processing The average gray value of the pixels whose gray value is greater than the currently selected gray value in the image, ω2 is the number of pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing, accounting for the entire image The ratio of the number of pixels, μ 2 the average gray value of the pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing;
二值化处理模块，用于以得出的使得类间方差最大的灰度值作为分割阈值，将灰度化处理后的图像进行二值化处理，得出手部的图像。The binarization processing module is used to use the obtained gray value that maximizes the variance between classes as a segmentation threshold, and perform binarization processing on the gray-scale processed image to obtain an image of the hand.
根据本发明的另一方面，本发明为解决其技术问题，还提供了一种基于手势识别的灯效控制方法，包括：According to another aspect of the present invention, in order to solve its technical problem, the present invention also provides a lighting effect control method based on gesture recognition, including:
图像获取步骤：获取图像拍摄模块所拍摄的包含操作者的操作者的手部的图像；Image acquiring step: acquiring an image of the operator's hand captured by the image capturing module;
手部提取步骤：提取出所述图像中手部的图像；Hand extraction step: extract the image of the hand in the image;
动作识别步骤：根据提取出的手部的图像，识别出手部的张开程度；Action recognition step: According to the image of the extracted hand, identify the degree of opening of the hand;
亮度调整步骤：根据手部张开程度的变化生成用于调整来灯的亮度的控制指令。Brightness adjustment step: generating a control instruction for adjusting the brightness of the incoming light according to the change of the hand opening degree.
在本发明的基于手势识别的灯效控制系统中，上述控制指令作用于灯时满足：当手部张开程度增大时，灯的亮度增大，当手部的张开程度增小时，灯的亮度减小。In the lighting effect control system based on gesture recognition of the present invention, when the above-mentioned control command acts on the lamp, it satisfies: when the degree of hand opening increases, the brightness of the light increases, and when the degree of hand opening increases, the brightness of the light increases. brightness decreases.
在本发明的基于手势识别的灯效控制系统中，手部从完全闭合到完全张开的每一个张开程度分别与灯从最小亮度到最大亮度的每一个亮度一一对应；或者，手部由完全张开到完全闭合至由完全闭合到完全张开每一个张开程度的变化分别与亮度零变化量到亮度最小变化量的每一个变化量一一对应。In the lighting effect control system based on gesture recognition of the present invention, each opening degree of the hand from fully closed to fully opened corresponds to each brightness of the lamp from the minimum brightness to the maximum brightness; or, the hand Each change in degree of opening from fully open to fully closed to fully closed to fully open corresponds to each change from zero brightness change to minimum brightness change.
在本发明的基于手势识别的灯效控制系统中，还包括：In the lighting effect control system based on gesture recognition of the present invention, it also includes:
颜色调整步骤，用于在张开程度的变化速度大于预设值时，生成切换灯的颜色的控制指令。The color adjustment step is used to generate a control instruction for switching the color of the lamp when the change speed of the opening degree is greater than a preset value.
在本发明的基于手势识别的灯效控制系统中，手部提取步骤包含：In the lighting effect control system based on gesture recognition of the present invention, the hand extraction step includes:
灰度化处理处理步骤，用于将拍摄的图像进行灰度化处理；The grayscale processing step is used to perform grayscale processing on the captured image;
类间方差遍历步骤，用于根据下述公式，计算出灰度化处理后图像中每一个像素的灰度值的类间方差，得出使得类间方差最大的灰度值；The inter-class variance traversal step is used to calculate the inter-class variance of the gray value of each pixel in the image after grayscale processing according to the following formula, so as to obtain the gray value that makes the inter-class variance the largest;
g＝ω1×ω2×(μ1-μ2)2，g＝ω 1 ×ω 2 ×(μ 1 -μ 2 ) 2 ,
式中，g为类间方差，ω1为灰度化处理后图像中灰度值大于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ1灰度化处理后图像中灰度值大于当前选定的灰度值的像素的平均灰度值，ω2为灰度化处理后图像中灰度值小于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ2灰度化处理后图像中灰度值小于当前选定的灰度值的像素的平均灰度值；In the formula, g is the variance between classes, ω 1 is the ratio of the number of pixels whose gray value is greater than the currently selected gray value in the image to the number of pixels in the entire image after gray scale processing, μ 1 after gray scale processing The average gray value of the pixels whose gray value is greater than the currently selected gray value in the image, ω2 is the number of pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing, accounting for the entire image The ratio of the number of pixels, μ 2 the average gray value of the pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing;
二值化处理步骤，用于以得出的使得类间方差最大的灰度值作为分割阈值，将灰度化处理后的图像进行二值化处理，得出手部的图像。The binarization processing step is used to use the obtained gray value that maximizes the inter-class variance as a segmentation threshold, and perform binarization processing on the gray-scale processed image to obtain an image of the hand.
本发明的基于手势识别的灯效控制方法及系统，首先获取图像拍摄模块所拍摄的包含手部的图像，然后提取出所述图像中手部的图像，根据提取出的手部的图像，识别出手部的张开程度，并根据手部张开程度的变化生成用于调整来灯的亮度的控制指令。实施本发明的基于手势识别的灯效控制方法及系统，操作人员可以在不携带任何遥控装置的前提下，实现对灯的亮度的调节，方便简单，且算法简单，运算速度快，制作的成本教低。The lighting effect control method and system based on gesture recognition of the present invention first acquires the image including the hand captured by the image capture module, then extracts the image of the hand in the image, and recognizes the The degree of opening of the hand, and generate a control command for adjusting the brightness of the incoming light according to the change of the degree of hand opening. By implementing the lighting effect control method and system based on gesture recognition of the present invention, the operator can adjust the brightness of the lamp without carrying any remote control device, which is convenient and simple, and the algorithm is simple, the calculation speed is fast, and the production cost is low. Teach low.
附图说明Description of drawings
下面将结合附图及实施例对本发明作进一步说明，附图中：The present invention will be further described below in conjunction with accompanying drawing and embodiment, in the accompanying drawing:
图1是本发明的基于手势识别的灯效控制系统一优选实施例的原理框图；Fig. 1 is a functional block diagram of a preferred embodiment of the lighting effect control system based on gesture recognition of the present invention;
图2是本发明的基于手势识别的灯效控制方法一优选实施例的流程图。FIG. 2 is a flow chart of a preferred embodiment of the lighting effect control method based on gesture recognition in the present invention.
具体实施方式Detailed ways
为了对本发明的技术特征、目的和效果有更加清楚的理解，现对照附图详细说明本发明的具体实施方式。In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.
如图1所示，其本发明的基于手势识别的灯效控制系统一优选实施例的原理框图。在本实施例的灯效控制系统具有手势识别端1和灯效控制端2，手势控制端1具有依次连接的图像拍摄模块11、手部提取模块12、动作识别模块13、亮度调整模块14以及蓝牙模块一15。灯效控制端2具有连接的蓝牙模块二22与灯效控制模块21。蓝牙模块一15与蓝牙模块二22可通信连接。As shown in FIG. 1 , it is a functional block diagram of a preferred embodiment of the lighting effect control system based on gesture recognition of the present invention. The lighting effect control system in this embodiment has a gesture recognition terminal 1 and a lighting effect control terminal 2. The gesture control terminal 1 has an image capture module 11, a hand extraction module 12, an action recognition module 13, a brightness adjustment module 14 and Bluetooth module one 15 . The lighting effect control terminal 2 has a connected Bluetooth module 2 22 and a lighting effect control module 21 . The first bluetooth module 15 and the second bluetooth module 22 are communicably connected.
在本实施例中，图像拍摄模块11在本实施例采用固定拍摄角度的摄像头，摄像头拍摄包含灯效操作人员的手部的图像，拍摄时将摄像头的拍摄范围内任意出现的人员的手部均视作操作者的手部进行拍摄，拍摄的手部图像均视作有效图像。在本发明的另一实施例中，图像拍摄模块11为云台摄像机，云台摄像机根据预先设置的人员图像，自动跟踪对应人员，拍摄该人员的手势进行处理，而将拍摄的其他人员的手部图像视为无效图像，无效图像不参与控制指令的产生或者作用。In this embodiment, the image capturing module 11 adopts a camera with a fixed shooting angle in this embodiment, and the camera captures an image including the hands of the lighting effect operator. It is regarded as the operator's hand for shooting, and the captured hand images are all regarded as valid images. In another embodiment of the present invention, the image capture module 11 is a pan-tilt camera, and the pan-tilt camera automatically tracks the corresponding person according to the preset personnel image, and takes pictures of the gestures of the personnel for processing, while the hand gestures of other personnel photographed will be processed. The external image is regarded as an invalid image, and the invalid image does not participate in the generation or function of the control command.
手部提取模块12具有信号调理电路以及与信号调理电路连接的手部提取单元。信号调理电路连接图像拍摄模块11，对图像拍摄模块11拍摄的图像进行调理，将信号放大至预设的范围，然后再进行滤波处理，滤除其中的噪声后传输至与手部提取单元，手部提取单元将调理后的图像进行处理，提取出手部的图像。The hand extraction module 12 has a signal conditioning circuit and a hand extraction unit connected to the signal conditioning circuit. The signal conditioning circuit is connected to the image capturing module 11, adjusts the image captured by the image capturing module 11, amplifies the signal to a preset range, and then performs filtering processing, and then transmits to the hand extraction unit after filtering out the noise therein. The hand extraction unit processes the conditioned image to extract an image of the hand.
动作识别模块13连接手部提取模块12，根据提取出的手部的图像，识别出手部的张开程度。The action recognition module 13 is connected to the hand extraction module 12, and recognizes the degree of opening of the hand according to the extracted hand image.
亮度调整模块14根据手部在张开程度的变化来生成用于控制灯的亮度的控制指令。控制指令生成后，与亮度调整模块14连接的蓝牙模块一15将控制指令发送出去。手部在张开过程中，张开程度逐渐增大；手部在握紧过程中，张开程度逐渐减小。The brightness adjustment module 14 generates a control instruction for controlling the brightness of the lamp according to the change of the hand opening degree. After the control command is generated, the Bluetooth module 1 15 connected to the brightness adjustment module 14 sends out the control command. In the process of opening the hand, the degree of opening gradually increases; in the process of clenching, the degree of opening gradually decreases.
蓝牙模块二22接收到上述的控制指令后，传送至与其连接的灯效控制装置21，灯效控制装置21响应上述控制指令，而调整灯的亮度，将亮度调大或者调小。Bluetooth module 2 22 receives the above-mentioned control command and transmits it to the lighting effect control device 21 connected to it. The lighting effect control device 21 responds to the above-mentioned control command and adjusts the brightness of the lamp to increase or decrease the brightness.
在本发明的另一实施例中，手势控制端1和灯效控制端2可以不采用本发明的两个蓝牙模块进行传输，而采用其他的传输方式，即上述的两个蓝牙模块可以被下述的任意一种模块所同时代替：RS232通信模块、RS485通信模块、RS422通信模块、SPI(SerialPeripheral Interface)通信模块、IIC(Inter-Integrated Circuit)通信模块、Zigbee通信模块及NRF通信模块。In another embodiment of the present invention, the gesture control terminal 1 and the lighting effect control terminal 2 may not use the two bluetooth modules of the present invention for transmission, but use other transmission methods, that is, the above two bluetooth modules can be downloaded Any one of the above modules can be replaced at the same time: RS232 communication module, RS485 communication module, RS422 communication module, SPI (Serial Peripheral Interface) communication module, IIC (Inter-Integrated Circuit) communication module, Zigbee communication module and NRF communication module.
手部提取模块12将处理后的图像进行处理，提取出手部的图像可通过下述的模块进行实现。The hand extraction module 12 processes the processed image, and extracting the image of the hand can be realized by the following modules.
灰度化处理处理模块，将拍摄的调理后的图像进行灰度化处理。摄像头采集到的图像信息为RGB彩图，为了降低计算量，首先将RGB图像进行灰度化处理，经处理后的每一个像素的像素值为：The grayscale processing module is configured to perform grayscale processing on the captured and conditioned image. The image information collected by the camera is an RGB color image. In order to reduce the amount of calculation, the RGB image is first processed in grayscale. The pixel value of each pixel after processing is:
Gray＝R*0.299+G*0.587+B*0.114Gray＝R*0.299+G*0.587+B*0.114
其中，Gray为灰度化处理后形成的灰度图的像素值，R、G、B分别为灰度化处理之前的彩图中红、绿、蓝所对应的像素值。Among them, Gray is the pixel value of the grayscale image formed after the grayscale processing, and R, G, and B are the pixel values corresponding to red, green, and blue in the color image before the grayscale processing, respectively.
类间方差遍历模块，用于根据下述公式，计算出灰度化处理后图像中每一个像素的灰度值的类间方差，得出使得类间方差最大的灰度值 The inter-class variance traversal module is used to calculate the inter-class variance of the gray value of each pixel in the image after grayscale processing according to the following formula, and obtain the gray value that maximizes the inter-class variance
g＝ω1×ω2×(μ1-μ2)2，g＝ω 1 ×ω 2 ×(μ 1 -μ 2 ) 2 ,
式中，g为类间方差，ω1为灰度化处理后图像中灰度值大于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ1灰度化处理后图像中灰度值大于当前选定的灰度值的像素的平均灰度值，ω2为灰度化处理后图像中灰度值小于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ2灰度化处理后图像中灰度值小于当前选定的灰度值的像素的平均灰度值；In the formula, g is the variance between classes, ω 1 is the ratio of the number of pixels whose gray value is greater than the currently selected gray value in the image to the number of pixels in the entire image after gray scale processing, μ 1 after gray scale processing The average gray value of the pixels whose gray value is greater than the currently selected gray value in the image, ω2 is the number of pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing, accounting for the entire image The ratio of the number of pixels, μ 2 the average gray value of the pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing;
二值化处理模块连接类间方差遍历模块，并连接动作识别模块的第二处理器，以得出的使得类间方差最大的灰度值作为分割阈值，将灰度化处理后的图像进行二值化处理，然后进行膨胀操作和腐蚀操作滤除背景，得出手部的图像。在本实施例中，灰度值小于的像素被二值化为“0”，否则被二值化为“1”，所有二值化为“1”的像素组成本发明的手部的图像，而二值化为“0”的像素组成本发明的手背所处的背景的图像。The binarization processing module is connected to the inter-class variance traversal module, and is connected to the second processor of the action recognition module, and the obtained gray value that makes the inter-class variance the largest is used as the segmentation threshold, and the gray-scale processed image is binarized. Value processing, and then perform expansion and erosion operations to filter out the background to obtain the image of the hand. In this embodiment, the gray value is less than The pixel is binarized to "0", otherwise it is binarized to "1", all the pixels binarized to "1" form the image of the hand of the present invention, and the pixels binarized to "0" An image of the background on which the back of the hand sits that make up the invention.
动作识别模块13根据提取出的手部的图像，识别出手部的张开程度。为了减少被发明中的面积的计算误差，在二值化处理后，还可以采用膨胀操作和腐蚀操作，滤除背景中的噪声，即滤除二值化为“0”的像素所包围的少量的“1”。然后对二值化处理后的图像进行求和，等效于对手部的图像的区域进行求和，将所有的“1”相加起来得出和，和的大小代表手部的张开程度，和的变化速度也能反映手部的张开程度的变化速度，和变化越快，张开程度的变化越大，和变化越慢，张开程度的变化越小。优选的，张开程度＝(手部当前对应的和-手部对应的最小和)/(手部对应的最大和-手部对应的最小和)，其中手部对应的最大和与手部对应的最大和通过预设方式得到，既可以成年人的平均值，可以事先针对不同操作者进行采集。The action recognition module 13 recognizes the degree of opening of the hand according to the extracted hand image. In order to reduce the calculation error of the area being invented, after the binarization process, expansion operation and erosion operation can also be used to filter out the noise in the background, that is, to filter out a small amount of pixels surrounded by binarized to "0" 1". Then sum the binarized images, which is equivalent to summing the area of the hand image, adding all "1" to get the sum, and the size of the sum represents the degree of opening of the hand. The change speed of and can also reflect the change speed of the degree of opening of the hand, the faster the change of and, the greater the change of the degree of opening, and the slower the change of and, the smaller the change of the degree of opening. Preferably, the degree of opening=(the current corresponding sum of the hand-the minimum sum corresponding to the hand)/(the maximum sum corresponding to the hand-the minimum sum corresponding to the hand), wherein the maximum sum corresponding to the hand corresponds to the hand The maximum sum of is obtained by a preset method, which can be the average value of adults, and can be collected for different operators in advance.
亮度调整模块14根据手部张开程度的变化生成用于调整来灯的亮度的控制指令，控制指令作用于灯时满足：当手部张开程度增大时，灯的亮度增大，当手部的张开程度增小时，灯的亮度减小。灯的亮度被调大到最大值后，手部继续张开，灯的亮度不再增加；灯的亮度被调到最小亮度后，手部继续闭合，亮度不再减小。实现上述控制指令的方式有两种：1、手部从完全闭合(握拳)到完全张开(手指伸直)的每一个张开程度分别与灯从最小亮度(如灯关闭)到最大亮度(如灯光饱和)的每一个亮度一一对应，优选的这个过程中的张开程度与灯的亮度成正比例；2、手部由完全张开到完全闭合至由完全闭合到完全张开每一个张开程度的变化分别与亮度零变化量到亮度最小变化量的每一个变化量一一对应，即手部从张开到完全闭合对应最小变化量，如-30％(亮度减小30％)，手部完全闭合到完全张开对应最大变化量(亮度增加30％)，如某次手部有手部完全闭合到张开50％，则亮度变大15％，当需要多次调整的亮度较大(大于30％)时，可以进行多次调节。当手部执行张开或者闭合动作时，灯的亮度可以随着手部张开/闭合的动作逐渐变化，也可以在手部张开/闭合的动作执行完毕后，直接调整亮度至最后的结果。The brightness adjustment module 14 generates a control instruction for adjusting the brightness of the incoming lamp according to the variation of the degree of hand opening. The brightness of the lamp decreases as the opening of the portion increases. After the brightness of the lamp is adjusted to the maximum value, the hand continues to open, and the brightness of the lamp does not increase; after the brightness of the lamp is adjusted to the minimum brightness, the hand continues to close, and the brightness does not decrease. There are two ways to realize the above control command: 1. Each degree of opening of the hand from fully closed (clenching a fist) to fully open (finger straightening) is respectively related to the light from the minimum brightness (such as the light is turned off) to the maximum brightness ( For example, each brightness of light saturation) corresponds one to one, and the preferred degree of opening in this process is proportional to the brightness of the light; 2. Each opening of the hand from fully open to fully closed to fully closed The changes in the degree of opening correspond to each change from zero change in brightness to the minimum change in brightness, that is, the minimum change of the hand from open to fully closed, such as -30% (the brightness is reduced by 30%), The maximum change from fully closed to fully opened hands (brightness increases by 30%), for example, if a hand is fully closed to 50% opened, the brightness will increase by 15%. When it is large (greater than 30%), multiple adjustments can be made. When the hand opens or closes, the brightness of the light can gradually change with the hand opening/closing action, or the brightness can be adjusted directly to the final result after the hand opening/closing action is completed.
本灯效控制系统还具有颜色调整模块，用于在开合程度的变化速度大于预设值时，生成切换灯的颜色的控制指令。也即在上述和的变化速度大于预设值时，灯效控制装置21响应该控制指令，将灯的颜色由当前颜色切换为另一颜色，此处颜色是指单一的颜色，也可以是多种颜色组合而成的颜色。The lighting effect control system also has a color adjustment module, which is used to generate a control instruction for switching the color of the lights when the change speed of the opening and closing degree is greater than a preset value. That is to say, when the speed of change of the above-mentioned sum is greater than the preset value, the lighting effect control device 21 responds to the control command and switches the color of the lamp from the current color to another color. The color here refers to a single color, or it can be multiple colors. A combination of colors.
人完成一次手部的开合大概需要几百毫秒，取一段时间间隔为Δt(Δt<100ms)定为单位时间，求得Δt之前的手部的图像的面积(即求出的和，下同)为St，当前手部的图像的面积为St+Δt，利用公式得出手部的图像的面积的变化速度：It takes about a few hundred milliseconds for a person to open and close a hand. Take a period of time as Δt (Δt<100ms) as the unit time, and obtain the area of the hand image before Δt (that is, the obtained sum, the same below ) is S t , the area of the current hand image is S t+Δt , and the change speed of the area of the hand image is obtained by using the formula:
如此可得到Δt内的手部的图像的面积的变化速度υs。进一步判断υs是正值还是负值，如果υs是正值，表示手部的动作状态为张开状态，如果υs为负值表示手部的动作状态为状态。In this way, the rate of change ν s of the area of the image of the hand within Δt can be obtained. Further judge whether υ s is a positive value or a negative value. If υ s is positive, it means that the action state of the hand is an open state, and if υ s is a negative value, it means that the action state of the hand is a state.
图2是本发明的基于手势识别的灯效控制方法一优选实施例的流程图。在本实施例中，该灯效控制方法包含下述步骤：FIG. 2 is a flow chart of a preferred embodiment of the lighting effect control method based on gesture recognition in the present invention. In this embodiment, the lighting effect control method includes the following steps:
S1、获取图像拍摄模块所拍摄的包含操作者的手部的图像。在本实施例中，图像为摄像头所拍摄，拍摄的图像为彩色图像。S1. Obtain an image including the operator's hand captured by the image capturing module. In this embodiment, the image is captured by a camera, and the captured image is a color image.
S2、提取出所述图像中手部的图像。本实施例中，步骤S2具体包括：S2. Extract the image of the hand in the image. In this embodiment, step S2 specifically includes:
首先，将RGB图像进行灰度化处理，经处理后的每一个像素的像素值为：First, grayscale the RGB image, and the pixel value of each pixel after processing is:
Gray＝R*0.299+G*0.587+B*0.114Gray＝R*0.299+G*0.587+B*0.114
其中，Gray为灰度化处理后形成的灰度图的像素值，R、G、B分别为灰度化处理之前的彩图中红、绿、蓝所对应的像素值。Among them, Gray is the pixel value of the grayscale image formed after the grayscale processing, and R, G, and B are the pixel values corresponding to red, green, and blue in the color image before the grayscale processing, respectively.
其次，根据下述公式，计算出灰度化处理后图像中每一个像素的灰度值的类间方差，得出使得类间方差最大的灰度值 Secondly, according to the following formula, calculate the inter-class variance of the gray value of each pixel in the image after grayscale processing, and obtain the gray value that maximizes the inter-class variance
g＝ω1×ω2×(μ1-μ2)2，g＝ω 1 ×ω 2 ×(μ 1 -μ 2 ) 2 ,
式中，g为类间方差，ω1为灰度化处理后图像中灰度值大于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ1灰度化处理后图像中灰度值大于当前选定的灰度值的像素的平均灰度值，ω2为灰度化处理后图像中灰度值小于当前选定的灰度值的像素点数占整幅图像的像素点数的比例，μ2灰度化处理后图像中灰度值小于当前选定的灰度值的像素的平均灰度值；In the formula, g is the variance between classes, ω 1 is the ratio of the number of pixels whose gray value is greater than the currently selected gray value in the image to the number of pixels in the entire image after gray scale processing, μ 1 after gray scale processing The average gray value of the pixels whose gray value is greater than the currently selected gray value in the image, ω2 is the number of pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing, accounting for the entire image The ratio of the number of pixels, μ 2 the average gray value of the pixels whose gray value is smaller than the currently selected gray value in the image after grayscale processing;
然后，以得出的使得类间方差最大的灰度值作为分割阈值，将灰度化处理后的图像进行二值化处理，然后进行膨胀操作和腐蚀操作滤除背景，得出手部的图像。在本实施例中，灰度值小于的像素被二值化为“0”，否则被二值化为“1”，所有二值化为“1”的像素组成本发明的手部的图像，而二值化为“0”的像素组成本发明的手背所处的背景的图像。Then, using the obtained gray value that maximizes the variance between classes as the segmentation threshold, the gray-scaled image is binarized, and then dilated and eroded to filter out the background to obtain the image of the hand. In this embodiment, the gray value is less than The pixel is binarized to "0", otherwise it is binarized to "1", all the pixels binarized to "1" form the image of the hand of the present invention, and the pixels binarized to "0" An image of the background on which the back of the hand sits that make up the invention.
S3、根据提取出的手部的图像，识别出手部的张开程度。为了减少被发明中的面积的计算误差，在二值化处理后，还可以采用膨胀操作和腐蚀操作，滤除背景中的噪声，即滤除二值化为“0”的像素所包围的少量的“1”。然后对二值化处理后的图像进行求和，等效于对手部的图像的区域进行求和来表示，将所有的“1”相加起来得出和，和的大小代表手部的张开程度，和的变化速度也能反映手部的张开程度的变化速度，和变化越快，张开程度的变化越大，和变化越慢，张开程度的变化越小。S3. Recognize the degree of opening of the hand according to the extracted image of the hand. In order to reduce the calculation error of the area being invented, after the binarization process, expansion operation and erosion operation can also be used to filter out the noise in the background, that is, to filter out a small amount of pixels surrounded by binarized to "0" 1". Then sum the binarized images, which is equivalent to summing the area of the hand image, adding all "1" to get the sum, and the size of the sum represents the opening of the hand The change speed of the degree and can also reflect the change speed of the degree of opening of the hand. The faster the change of and is, the greater the change of the degree of opening is, and the slower the change of and is, the smaller the change of the degree of opening is.
S4、根据手部张开程度的变化生成用于调整来灯的亮度的控制指令，控制指令作用于灯时满足：当手部张开程度增大时，灯的亮度增大，当手部的张开程度增小时，灯的亮度减小。实现上述控制指令的方式有两种：1、手部从完全闭合(握拳)到完全张开(手指伸直)的每一个张开程度分别与灯从最小亮度(如灯关闭)到最大亮度(如灯光饱和)的每一个亮度一一对应，优选的这个过程中的张开程度与灯的亮度成正比例；2、手部由完全张开到完全闭合至由完全闭合到完全张开每一个张开程度的变化分别与亮度零变化量到亮度最小变化量的每一个变化量一一对应，即手部从张开到完全闭合对应最小变化量，如-30％(亮度减小30％)，手部完全闭合到完全张开对应最大变化量(亮度增加30％)，如某次手部有手部完全闭合到张开50％，则亮度变大15％，当需要多次调整的亮度较大(大于30％)时，可以进行多次调节。S4. Generate a control command for adjusting the brightness of the incoming light according to the change of the hand opening degree. As the degree of opening increases, the brightness of the lamp decreases. There are two ways to realize the above control command: 1. Each degree of opening of the hand from fully closed (clenching a fist) to fully open (finger straightening) is respectively related to the light from the minimum brightness (such as the light is turned off) to the maximum brightness ( For example, each brightness of light saturation) corresponds one to one, and the preferred degree of opening in this process is proportional to the brightness of the light; 2. Each opening of the hand from fully open to fully closed to fully closed The changes in the degree of opening correspond to each change from zero change in brightness to the minimum change in brightness, that is, the minimum change of the hand from open to fully closed, such as -30% (the brightness is reduced by 30%), The maximum change from fully closed to fully opened hands (brightness increases by 30%), for example, if a hand is fully closed to 50% opened, the brightness will increase by 15%. When it is large (greater than 30%), multiple adjustments can be made.
本灯效控制方法还具有颜色调整步骤：在开合程度的变化速度大于预设值时，生成切换灯的颜色的控制指令。也即在上述和的变化速度大于预设值时，灯效控制装置21响应该控制指令，将灯的颜色由当前颜色切换为另一颜色，此处颜色是指单一的颜色，也可以是多种颜色组合而成的颜色。The lighting effect control method also has a color adjustment step: when the change speed of the opening and closing degree is greater than a preset value, a control instruction for switching the color of the lamp is generated. That is to say, when the speed of change of the above-mentioned sum is greater than the preset value, the lighting effect control device 21 responds to the control command and switches the color of the lamp from the current color to another color. The color here refers to a single color, or it can be multiple colors. A combination of colors.
人完成一次手部的开合大概需要几百毫秒，取一段时间间隔为Δt(Δt<100ms)定为单位时间，求得Δt之前的手部的图像的面积(即求出的和，下同)为St，当前手部的图像的面积为St+Δt，利用公式得出手部的图像的面积的变化速度：It takes about a few hundred milliseconds for a person to open and close a hand. Take a period of time as Δt (Δt<100ms) as the unit time, and obtain the area of the hand image before Δt (that is, the obtained sum, the same below ) is S t , the area of the current hand image is S t+Δt , and the change speed of the area of the hand image is obtained by using the formula:
如此可得到Δt内的手部的图像的面积的变化速度υs。进一步判断υs是正值还是负值，如果υs是正值，表示手部的动作状态为张开状态，如果υs为负值表示手部的动作状态为状态。In this way, the rate of change ν s of the area of the image of the hand within Δt can be obtained. Further judge whether υ s is a positive value or a negative value. If υ s is positive, it means that the action state of the hand is an open state, and if υ s is a negative value, it means that the action state of the hand is a state.
上面结合附图对本发明的实施例进行了描述，但是本发明并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本发明的启示下，在不脱离本发明宗旨和权利要求所保护的范围情况下，还可做出很多形式，这些均属于本发明的保护之内。Embodiments of the present invention have been described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementations, and the above-mentioned specific implementations are only illustrative, rather than restrictive, and those of ordinary skill in the art will Under the enlightenment of the present invention, many forms can also be made without departing from the gist of the present invention and the protection scope of the claims, and these all belong to the protection of the present invention.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710577064.1A CN107371307B (en) | 2017-07-14 | 2017-07-14 | A kind of lamp effect control method and system based on gesture identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710577064.1A CN107371307B (en) | 2017-07-14 | 2017-07-14 | A kind of lamp effect control method and system based on gesture identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107371307A CN107371307A (en) | 2017-11-21 |
| CN107371307B true CN107371307B (en) | 2018-06-05 |
Family
ID=60307408
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710577064.1A Active CN107371307B (en) | 2017-07-14 | 2017-07-14 | A kind of lamp effect control method and system based on gesture identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107371307B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110636676A (en) * | 2018-06-22 | 2019-12-31 | 欧阳院红 | Stage lighting control system |
| CN111107701B (en) * | 2018-10-25 | 2022-02-01 | 松下电气机器（北京）有限公司 | Lamp controller and lighting system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143195A (en) * | 2014-07-04 | 2014-11-12 | 华南理工大学 | A Correction Method for Tracking Offset Caused by Hand Shape Change During Gesture Tracking |
| CN106227350A (en) * | 2016-07-28 | 2016-12-14 | 青岛海信电器股份有限公司 | Method and the smart machine that operation controls is carried out based on gesture |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201032087A (en) * | 2009-02-19 | 2010-09-01 | Asustek Comp Inc | Command control system and method thereof |
| JP2013069224A (en) * | 2011-09-26 | 2013-04-18 | Sony Corp | Motion recognition apparatus, motion recognition method, operation apparatus, electronic apparatus, and program |
| CN105357842B (en) * | 2015-12-11 | 2018-10-02 | 北京毫米科技有限公司 | Master control intelligent lamp |
-
2017
- 2017-07-14 CN CN201710577064.1A patent/CN107371307B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104143195A (en) * | 2014-07-04 | 2014-11-12 | 华南理工大学 | A Correction Method for Tracking Offset Caused by Hand Shape Change During Gesture Tracking |
| CN106227350A (en) * | 2016-07-28 | 2016-12-14 | 青岛海信电器股份有限公司 | Method and the smart machine that operation controls is carried out based on gesture |
Non-Patent Citations (1)
| Title |
|---|
| 灰度图像二值化算法研究;孙少林，马志强，汤伟;《价值工程》;20100531;第1-2页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107371307A (en) | 2017-11-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nikam et al. | Sign language recognition using image based hand gesture recognition techniques | |
| CN107660039B (en) | A kind of lamp control system of identification dynamic gesture | |
| CN108449531B (en) | Suspended touch camera module, electronic equipment and touch method | |
| CN102799263B (en) | A kind of gesture recognition method and gesture recognition control system | |
| CN103455790B (en) | A kind of skin identification method based on complexion model | |
| CN109271875B (en) | A fatigue detection method based on key point information of eyebrows and eyes | |
| CN108604046B (en) | Photographic support device and working method thereof | |
| WO2002092180A3 (en) | Device and method for digitizing an object | |
| CN103220421A (en) | Method and device for using mobile terminal to carry out self photographing | |
| CN106503707B (en) | Licence plate recognition method and device under a kind of infrared lighting condition | |
| CN104065862A (en) | Information processing method and electronic device | |
| CN107371307B (en) | A kind of lamp effect control method and system based on gesture identification | |
| CN101516002A (en) | Camera and method for adjusting flash | |
| CN109451233A (en) | A kind of device acquiring fine definition face-image | |
| KR101674099B1 (en) | Apparatus for generating image for face authentication and method thereof | |
| CN109996379B (en) | Light control method and device | |
| KR101783999B1 (en) | Gesture recognition using chroma-keying | |
| CN103558225A (en) | Method for testing complementary metal oxide semiconductor (CMOS) image chip | |
| CN105516577B (en) | Camera shooting control method and system | |
| CN107357421A (en) | A kind of PPT control method for playing back and system based on gesture identification | |
| CN100484203C (en) | Same vision field multi-spectral video stream acquiring device and method | |
| CN108391356A (en) | A kind of Intelligent House Light control system | |
| CN118107605A (en) | Vehicle control method and system based on steering wheel gesture interaction | |
| CN108429886A (en) | A camera method and terminal | |
| CN206835226U (en) | It is a kind of that there is the anti-camera taken on the sly |
Legal Events
| 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 |