WO2019242385A1 - 智能化可控型吹风机 - Google Patents

智能化可控型吹风机 Download PDF

Info

Publication number
WO2019242385A1
WO2019242385A1 PCT/CN2019/082513 CN2019082513W WO2019242385A1 WO 2019242385 A1 WO2019242385 A1 WO 2019242385A1 CN 2019082513 W CN2019082513 W CN 2019082513W WO 2019242385 A1 WO2019242385 A1 WO 2019242385A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
hair dryer
pixel
pixel point
noise
Prior art date
Application number
PCT/CN2019/082513
Other languages
English (en)
French (fr)
Inventor
周超强
Original Assignee
周超强
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 周超强 filed Critical 周超强
Publication of WO2019242385A1 publication Critical patent/WO2019242385A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A45—HAND OR TRAVELLING ARTICLES
    • A45D—HAIRDRESSING OR SHAVING EQUIPMENT; EQUIPMENT FOR COSMETICS OR COSMETIC TREATMENTS, e.g. FOR MANICURING OR PEDICURING
    • A45D20/00—Hair drying devices; Accessories therefor
    • A45D20/04—Hot-air producers
    • A45D20/08—Hot-air producers heated electrically
    • A45D20/10—Hand-held drying devices, e.g. air douches
    • A—HUMAN NECESSITIES
    • A45—HAND OR TRAVELLING ARTICLES
    • A45D—HAIRDRESSING OR SHAVING EQUIPMENT; EQUIPMENT FOR COSMETICS OR COSMETIC TREATMENTS, e.g. FOR MANICURING OR PEDICURING
    • A45D20/00—Hair drying devices; Accessories therefor
    • A45D20/04—Hot-air producers
    • A45D20/08—Hot-air producers heated electrically
    • A45D20/10—Hand-held drying devices, e.g. air douches
    • A45D20/12—Details thereof or accessories therefor, e.g. nozzles, stands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • 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
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person

Definitions

  • the invention relates to the field of hair dryers, in particular to an intelligent and controllable hair dryer.
  • a set of constant temperature automatic electric control elements are connected in series to the heating element of the hair dryer. It can automatically switch on the circuit when the wind turbine is in normal operation and automatically cut off the circuit when it encounters special conditions (such as overheating of the heating element).
  • thermoplastic engineering materials mainly polycarbonate, modified polybenzene, modified polypropylene, etc.
  • the present invention provides an intelligent and controllable hair dryer, which connects the heating wire body and the curve matching device, and is used to interrupt the power line connection with the hair dryer when a signal is not present in the human body.
  • the standard identification area identification mechanism and the adaptive mode-based image enhancement mechanism are used to effectively improve the efficiency and effect of image processing.
  • the image is processed with high-precision image simplification to obtain the image to be analyzed for subsequent image recognition and image detection.
  • the real-time correction device is used to perform vector correction on the gun camera based on the direction vector of the gun camera. It is to measure the direction vector of the gun camera using a pixel-level high-precision content analysis mechanism.
  • an intelligent and controllable hair dryer includes:
  • a heating bracket is provided at the air nozzle position of the hair dryer, the heating bracket is used to overlap the heating wire body; the heating wire body is connected to the power line of the hair dryer for heating when the power line is in an energized state; a gun camera is provided At the blower nozzle position, it is used to take an image of the scene where the blower nozzle is located to output continuous multiple frames of the nozzle image on the time axis; the contrast enhancement device is connected to the gun camera and is used to receive the current A mouthpiece scene image at time, performing contrast enhancement processing on the mouthpiece scene image to obtain a contrast enhancement image, and outputting the contrast enhancement image; a first noise processing device connected to the contrast enhancement device for receiving The contrast-enhanced image, performing noise type analysis on the contrast-enhanced image to obtain various types of noise in the contrast-enhanced image and a maximum amplitude corresponding to each type of noise; a second noise processing device, and the A first noise processing device is connected to receive various noises in the contrast enhanced image Type and the maximum ampli
  • the standard deviation of the degree value is detected to obtain the respective standard deviations corresponding to the respective regions;
  • the region processing device is connected to the gray value analysis device, and is configured to receive the respective standard deviations of the respective regions, and calculate the standard deviations of the respective regions.
  • Mean value the area where the distance from the standard deviation to the mean value exceeds the limit is used as the recognition area, and image enhancement processing based on its signal-to-noise ratio is performed on each recognition area to obtain the corresponding enhanced area
  • the area processing device is further configured to: Delete each recognition area from the non-linear filtering image and fill in each enhancement area accordingly to obtain a corresponding area processing image;
  • a gradient analysis device is connected to the area processing device and is used to receive the area processing image, and Perform grayscale processing on the area processed image to obtain a corresponding grayscale image, and determine the grayscale For each gradient of the pixel value of each pixel in the image to the pixel values of surrounding pixels, when each gradient is greater than or equal to a preset gradient threshold, the
  • the pixel When each gradient is less than the preset gradient threshold, The pixel is judged to be a non-edge pixel; a curve matching device is connected to the gradient analysis device and is used to connect all edge pixels to obtain several closed curves, which are respectively segmented from the grayscale image based on the several closed curves. For the corresponding patterns, when there is a pattern that exceeds the preset standard image of the human body, a human presence signal is issued, otherwise, a human non-existence signal is issued; wherein the heating wire body also matches the curve matching device A connection for interrupting the power line connection with the hair dryer when the signal of the absence of the human body is received.
  • the intelligent controllable hair dryer further includes:
  • a shake sensing device is provided on the gun camera and is used to detect the current position of the gun camera and determine a difference between the current position and a preset fixed position, where the difference includes a horizontal change amount and A vertical change amount, and when the horizontal change amount changes between positive and negative values, or when the vertical change amount changes between positive and negative values, a first sensing signal is issued, otherwise, a second Induction signal.
  • the intelligent controllable hair dryer further includes:
  • a first pixel processing device connected to the gun camera, and configured to receive two frames of images obtained in sequence from the gun camera as a current image and a subsequent image, and obtain each pixel of the current image
  • the pixel value of the point and the pixel value of each pixel point of the subsequent image are acquired, and the jitter detection mode is entered when the first sensing signal is received, and the jitter detection is exited when the second sensing signal is received.
  • the first pixel point processing device performs the following processing in the shake detection mode: acquiring each pixel point from the current image as each reference pixel point based on an Archimedes curve, and each reference pixel point is The coordinates in the current image are used as the corresponding reference coordinates.
  • the subsequent image is searched from the subsequent image for a pixel point whose pixel value near the reference coordinate is equal to the reference pixel point pixel value.
  • acquiring each pixel point from the current image as each reference pixel point based on the Archimedes curve includes: taking the lower right corner pixel point of the current image as An Archimedes curve is drawn in the current image at the starting position, and each pixel point that the Archimedes curve passes along the line is used as each reference pixel point.
  • the intelligent controllable hair dryer further includes:
  • the second pixel processing device is connected to the first pixel processing device and is configured to obtain multiple reference pixels and multiple target pixels corresponding to the multiple reference pixels, respectively, and determine each reference coordinate to its corresponding Horizontal displacement of target coordinates, average the horizontal displacement of each reference coordinate to obtain the horizontal movement of the image, determine the vertical displacement of each reference coordinate to its corresponding target coordinate, and average the vertical displacement of each reference coordinate to obtain The amount of vertical movement of the image, determining the amount of time movement based on the timestamp of the current image and the timestamp of the subsequent time, and calculating the amount of movement based on the amount of time movement, the amount of horizontal movement of the image, and the amount of vertical movement of the image Direction vector of gun camera.
  • the intelligent controllable hair dryer further includes:
  • a real-time correction device connected to the gun camera and the second pixel processing device, respectively, for receiving a direction vector of the gun camera, and based on the direction vector of the gun camera, to the gun camera Perform vector correction.
  • performing standard deviation detection of gray values on each region of the non-linear filtered image includes: for each region , Extracting the gray value of each pixel point of the area, and calculating the standard deviation of the area based on the gray value of each pixel point of the area.
  • the weight analysis device further stores the type weight comparison table in advance, and the type weight comparison table stores the influence of each noise type on the binarization threshold The weight is also used to store the initialization binarization threshold in advance.
  • FIG. 1 is a schematic structural diagram of an intelligent and controllable hair dryer according to an embodiment of the present invention.
  • centrifugal blowers and axial blowers.
  • the centrifugal type relies on the motor to drive the wind blades to rotate, so that the air entering the blower gets inertial centrifugal force and continuously exhausts the air.
  • Its disadvantage is that the exhausted wind does not all flow through the motor, and the motor heats up higher; the advantage is that the noise is lower.
  • the axial-flow motor drives the blades to rotate, pushing the air entering the blower to flow axially, and continuously exhausting air. Its advantage is that all the exhausted wind flows through the motor, the motor has good cooling conditions, and the insulation is not easy to age; its disadvantage is that the noise is relatively large.
  • metal type hair dryers and plastic type hair dryers.
  • Metal hair dryers are rugged and can withstand higher temperatures.
  • Plastic hair dryers are lightweight and have good insulation properties, but they are easy to age and have poor high temperature resistance.
  • the present invention sets up an intelligent and controllable hair dryer, thereby solving the corresponding technical problems.
  • FIG. 1 is a schematic structural diagram of an intelligent and controllable hair dryer according to an embodiment of the present invention.
  • the hair dryer includes a housing 1, a handle rear end 2, an integrated circuit board 3, and a button assembly 4.
  • the hair dryer further includes:
  • a heating bracket is arranged at the air nozzle position of the hair dryer, and the heating bracket is used for overlapping the heating wire body;
  • the heating wire body is connected to the power line of the hair dryer, and is configured to generate heat when the power line is in an energized state;
  • a gun camera is set at the position of the blower of the hair dryer, and is used for image capturing of the scene where the blower of the hair dryer is located, so as to output continuous multiple frames of blower scene images on the time axis;
  • a contrast enhancement device which is connected to the gun camera and is configured to receive a tuyere scene image at the current time, perform contrast enhancement processing on the tuyere scene image to obtain a contrast-enhanced image, and output the contrast-enhanced image;
  • a first noise processing device connected to the contrast enhancement device and configured to receive the contrast enhanced image and perform noise type analysis on the contrast enhanced image to obtain various types of noise and each of the types in the contrast enhanced image The maximum amplitude corresponding to the noise type;
  • a second noise processing device connected to the first noise processing device, and configured to receive various types of noise in the contrast-enhanced image and a maximum amplitude corresponding to each type of noise, based on the maximum amplitude from large to small Sort the various noise types in the order of, and output the three noise types in the first three of the serial number as the three types of noise to be processed;
  • a weight analysis device connected to the second noise processing device and configured to receive the three types of noise to be processed, and determine three impact weights corresponding to the three types of noise to be processed based on the type weight comparison table, And using the three influence weights to perform sequential correction processing on the initialization binarization threshold to obtain a correction threshold after the correction processing is completed, and output the correction threshold;
  • An image simplification device connected to the weight analysis device, for receiving the modified threshold, performing a binarization process on the contrast-enhanced image using the modified threshold to obtain an image to be analyzed, and outputting the image to be analyzed Analyze the image;
  • a non-linear filtering device connected to the image simplification device and configured to receive the image to be analyzed and perform a non-linear filtering image on the image to be analyzed to obtain and output a corresponding non-linear filtering image;
  • a gray value analysis device connected to the non-linear filtering device and configured to receive the non-linear filtering image, and perform standard deviation detection of the gray value on each region of the non-linear filtering image to obtain each region respectively The corresponding standard deviations;
  • An area processing device connected to the gray value analysis device and configured to receive each standard deviation of each area, calculate an average value of each standard deviation of each area, and use the area where the distance between the standard deviation and the average value exceeds a limit as an identification area Performing image enhancement processing based on its signal-to-noise ratio on each recognition area to obtain a corresponding enhanced area, and the area processing device is further configured to delete each recognition area from the non-linear filtering image and fill in the corresponding areas accordingly.
  • Each enhancement region to obtain a corresponding region processing image;
  • a gradient analysis device which is connected to the area processing device and is used to receive the area processed image, perform grayscale processing on the area processed image to obtain a corresponding grayscale image, and determine a pixel of each pixel in the grayscale image Each gradient from the value to the pixel value of the surrounding pixels. When each gradient is greater than or equal to a preset gradient threshold, the pixel is judged as an edge pixel. When each gradient is less than the preset gradient threshold, the pixel is judged as a non-edge. Pixels
  • a curve matching device is connected to the gradient analysis device and is used to connect all edge pixels to obtain several closed curves. Based on the several closed curves, a plurality of corresponding patterns are respectively segmented from the grayscale image.
  • a pattern exceeding the limit of the standard human body image is preset, a human body presence signal is issued; otherwise, a human body absence signal is issued;
  • the heating wire body is also connected to the curve matching device, and is used for interrupting the connection with the power line of the hair dryer when the signal of the absence of the human body is received.
  • the intelligent and controllable hair dryer further includes:
  • a shake sensing device is provided on the gun camera and is used to detect the current position of the gun camera and determine a difference between the current position and a preset fixed position, where the difference includes a horizontal change amount and A vertical change amount, and when the horizontal change amount changes between positive and negative values, or when the vertical change amount changes between positive and negative values, a first sensing signal is issued, otherwise, a second Induction signal.
  • the intelligent and controllable hair dryer further includes:
  • a first pixel processing device connected to the gun camera, and configured to receive two frames of images obtained in sequence from the gun camera as a current image and a subsequent image, and obtain each pixel of the current image
  • the pixel value of the point and the pixel value of each pixel point of the subsequent image are acquired, and the jitter detection mode is entered when the first sensing signal is received, and the jitter detection is exited when the second sensing signal is received.
  • the first pixel point processing device performs the following processing in the shake detection mode: acquiring each pixel point from the current image as each reference pixel point based on an Archimedes curve, and each reference pixel point is The coordinates in the current image are used as the corresponding reference coordinates.
  • the subsequent image is searched from the subsequent image for a pixel point whose pixel value near the reference coordinate is equal to the reference pixel point pixel value.
  • acquiring each pixel point from the current image as each reference pixel point based on the Archimedes curve includes: taking the lower right corner pixel point of the current image as An Archimedes curve is drawn in the current image at the starting position, and each pixel point that the Archimedes curve passes along the line is used as each reference pixel point.
  • the intelligent and controllable hair dryer further includes:
  • the second pixel processing device is connected to the first pixel processing device and is configured to obtain multiple reference pixels and multiple target pixels corresponding to the multiple reference pixels, respectively, and determine each reference coordinate to its corresponding Horizontal displacement of target coordinates, average the horizontal displacement of each reference coordinate to obtain the horizontal movement of the image, determine the vertical displacement of each reference coordinate to its corresponding target coordinate, and average the vertical displacement of each reference coordinate to obtain The amount of vertical movement of the image, determining the amount of time movement based on the timestamp of the current image and the timestamp of the subsequent time, and calculating the amount of movement based on the amount of time movement, the amount of horizontal movement of the image, and the amount of vertical movement of the image Direction vector of gun camera.
  • the intelligent and controllable hair dryer further includes:
  • a real-time correction device connected to the gun camera and the second pixel processing device, respectively, for receiving a direction vector of the gun camera, and based on the direction vector of the gun camera, to the gun camera Perform vector correction.
  • performing standard deviation detection of gray values on each region of the nonlinear filtered image includes: for each region, extracting the The gray value of each pixel point of the area is calculated based on the gray value of each pixel point of the area.
  • the weight analysis device further stores the type weight comparison table in advance, and the type weight comparison table stores an influence weight of each noise type on the binarization threshold, and Used to store the initialization binarization threshold in advance.
  • the gun camera includes a CMOS sensor and a data output interface.
  • the CMOS sensor is used to sense continuous multiple frames of wind nozzle scene images on the time axis.
  • the data output interface is connected to the CMOS sensor and is used to output time. Continuous multi-frame mouthpiece scene images on the axis.
  • the heating wire body is connected with the curve matching device, and is used for interrupting the connection with the hair dryer when no signal is present in the human body
  • the power line is connected to reduce the unnecessary loss of the blower and improve the safety of the scene.
  • the standard deviation area identification mechanism and the adaptive mode-based image enhancement mechanism are used to effectively improve the efficiency and effect of image processing.
  • Contrast-enhanced images are subjected to high-precision image simplification processing to obtain images to be analyzed for subsequent image recognition and image detection; real-time correction equipment is used to vectorize the gun camera based on the direction vector of the gun camera For correction, the key is to use the pixel-level high-precision content analysis mechanism to measure the direction vector of the gun camera, thereby solving the above technical problems.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Image Processing (AREA)

Abstract

一种智能化可控型吹风机，包括：发热支架，设置在吹风机的风嘴位置，发热支架用于搭接发热丝体；发热丝体，与吹风机的电力线连接，用于在电力线处于通电状态时发热；枪式摄像机，设置在吹风机的风嘴位置，用于对吹风机的风嘴所在场景进行图像拍摄，以输出时间轴上连续的多帧风嘴场景图像；对比度增强设备，与枪式摄像机连接，用于接收当前时刻的风嘴场景图像，对风嘴场景图像执行对比度增强处理，以获得对比度增强图像，并输出对比度增强图像，该吹风机能够提高吹风机的智能化水准。

Description

智能化可控型吹风机 技术领域
本发明涉及吹风机领域，尤其涉及一种智能化可控型吹风机。
背景技术
在吹风机的发热元件上，都串联了一组恒温自动电控元件，它可以在风筒正常工作情况下，自动接通电路，遇到特殊情况(如电热元件过热等现象)时自动切断电路。在风筒外壳材料的选择上，也由过去选用金属(如铜或冷轧铁板)材料，改为选用热塑性工程材料(主要有聚碳酸脂、改性聚苯、改性聚丙烯等)制成。
发明内容
为了解决当前吹风机无端损耗的技术问题，本发明提供了一种智能化可控型吹风机，将发热丝体与曲线匹配设备连接，用于在接收到人体不存在信号时，中断与吹风机的电力线连接，从而减少吹风机不必要损耗的同时，提高现场的安全性，其中，采用标准差的区域辨识机制以及采用基于自适应模式的图像增强机制，有效提升了图像处理的效率和效果；对对比度增强后的图像进行高精度的图像简化处理，以获得待分析图像，便于后续的图像识别和图像检测；采用实时校正设备以基于所述枪式摄像机的方向矢量对所述枪式摄像机进行矢量校正，关键的是，采用像素级的高精度内容分析机制实现对所述枪式摄像机的方向矢量的测量。
根据本发明的一方面，提供了一种智能化可控型吹风机，所述吹风机包括：
发热支架，设置在吹风机的风嘴位置，所述发热支架用于搭接发热丝体；发热丝体，与吹风机的电力线连接，用于在所述电力线处于通电状态时发热；枪式摄像机，设置在吹风机的风嘴位置，用于对吹风机的风嘴所 在场景进行图像拍摄，以输出时间轴上连续的多帧风嘴场景图像；对比度增强设备，与所述枪式摄像机连接，用于接收当前时刻的风嘴场景图像，对所述风嘴场景图像执行对比度增强处理，以获得对比度增强图像，并输出所述对比度增强图像；第一噪声处理设备，与所述对比度增强设备连接，用于接收所述对比度增强图像，对所述对比度增强图像进行噪声类型分析，以获得所述对比度增强图像中各种噪声类型以及每一种噪声类型对应的最大幅值；第二噪声处理设备，与所述第一噪声处理设备连接，用于接收所述对比度增强图像中各种噪声类型以及每一种噪声类型对应的最大幅值，基于最大幅值的从大到小的顺序对所述各种噪声类型进行排序，将序号前三的三种噪声类型作为三种待处理噪声类型输出；权重分析设备，与所述第二噪声处理设备连接，用于接收所述三种待处理噪声类型，基于所述类型权重对照表确定所述三种待处理噪声类型分别对应的三个影响权重，并采用所述三个影响权重对所述初始化二值化阈值进行按顺序的修正处理，以获得修正处理完毕后的修正化阈值，并输出所述修正化阈值；图像简化设备，与所述权重分析设备连接，用于接收所述修正化阈值，采用所述修正化阈值对所述对比度增强图像执行二值化处理，以获得待分析图像，并输出所述待分析图像；非线性滤波设备，与所述图像简化设备连接，用于接收所述待分析图像，对所述待分析图像执行非线性滤波图像，以获得并输出对应的非线性滤波图像；灰度值分析设备，与所述非线性滤波设备连接，用于接收所述非线性滤波图像，对所述非线性滤波图像的各个区域分别执行灰度值的标准差检测，以获得各个区域分别对应的各个标准差；区域处理设备，与所述灰度值分析设备连接，用于接收各个区域的各个标准差，计算各个区域的各个标准差的均值，将标准差到所述均值的距离超过限量的区域作为识别区域，对每一个识别区域执行基于其信噪比的图像增强处理，以获得对应的增强区域，所述区域处理设备还用于将所述非线性滤波图像中删除各个识别区域，并相应地补入各个增强区域，以获得对应的区域处理图像；梯度分析设备，与所述区域处理设备连接，用于接收区域处理图像，对区域处理图像执行灰度化处理以获得相应的灰度化图像，判断所述灰度化图像中每一个像素的像素值到周围像素的像素值的各个梯度，当各个梯度中存在大于等于预设梯度阈值时，将该像素判断 为边缘像素，当各个梯度都小于预设梯度阈值时，将该像素判断为非边缘像素；曲线匹配设备，与所述梯度分析设备连接，用于将所有边缘像素进行连接以获得若干个封闭曲线，基于若干个封闭曲线分别从灰度化图像处分割出对应的若干个图案，当存在与预设人体标准图像的匹配度超限的图案时，发出人体存在信号，否则，发出人体不存在信号；其中，所述发热丝体还与所述曲线匹配设备连接，用于在接收到所述人体不存在信号时，中断与吹风机的电力线连接。
更具体地，在所述智能化可控型吹风机中，还包括：
抖动感应设备，设置在枪式摄像机上，用于检测所述枪式摄像机的当前位置，并确定所述当前位置与预设固定位置之间的差值，所述差值包括水平方向变化量和垂直方向变化量，并在所述水平方向变化量在正值负值之间变化时或所述垂直方向变化量在正值负值之间变化时，发出第一感应信号，否则，发出第二感应信号。
更具体地，在所述智能化可控型吹风机中，还包括：
第一像素点处理设备，与所述枪式摄像机连接，用于接收从所述枪式摄像机中获取前后顺序的两帧图像以分别作为当前图像和后续图像，并获取所述当前图像的各个像素点的像素值以及获取所述后续图像的各个像素点的像素值，在接收到所述第一感应信号时，进入抖动检测模式，在接收到所述第二感应信号时，退出所述抖动检测模式；所述第一像素点处理设备在所述抖动检测模式中执行以下处理：基于阿基米德曲线从所述当前图像中获取各个像素点以作为各个参考像素点，每一个参考像素点在所述当前图像中的坐标作为对应的参考坐标，对于每一个参考像素点，基于其像素值从所述后续图像中搜索所述参考坐标附近的像素值等于所述参考像素点像素值的像素点以作为所述参考像素点对应的目标像素点，将所述目标像素点在所述后续图像中的坐标作为对应的目标坐标；在所述第一像素点处理设备中，基于阿基米德曲线从所述当前图像中获取各个像素点以作为各个参考像素点包括：以所述当前图像右下角像素点为起始位置在所述当前图像中画出阿基米德曲线，并将阿基米德曲线沿线经过的各个像素点作为各个参考像素点。
更具体地，在所述智能化可控型吹风机中，还包括：
第二像素点处理设备，与所述第一像素点处理设备连接，用于获取多个参考像素点和多个参考像素点分别对应的多个目标像素点，确定每一个参考坐标到其对应的目标坐标的水平位移，对各个参考坐标的各个水平位移求均值以获得图像水平移动量，确定每一个参考坐标到其对应的目标坐标的垂直位移，对各个参考坐标的各个垂直位移求均值以获得图像垂直移动量，基于所述当前图像的时间戳和所述后续时间的时间戳确定时间移动量，以及基于所述时间移动量、所述图像水平移动量和所述图像垂直移动量计算所述枪式摄像机的方向矢量。
更具体地，在所述智能化可控型吹风机中，还包括：
实时校正设备，分别与所述枪式摄像机和所述第二像素点处理设备连接，用于接收所述枪式摄像机的方向矢量，并基于所述枪式摄像机的方向矢量对所述枪式摄像机进行矢量校正。
更具体地，在所述智能化可控型吹风机中：在所述灰度值分析设备中，对所述非线性滤波图像的各个区域分别执行灰度值的标准差检测包括：对于每一个区域，提取所述区域的各个像素点的灰度值，基于所述区域的各个像素点的灰度值计算所述区域的标准差。
更具体地，在所述智能化可控型吹风机中在所述区域处理设备中，识别区域的信噪比越小，对其执行的图像增强处理的幅度越大。
更具体地，在所述智能化可控型吹风机中：所述权重分析设备还预先存储所述类型权重对照表，所述类型权重对照表保存了每一个种噪声类型对二值化阈值的影响权重，还用于预先存储初始化二值化阈值。
附图说明
以下将结合附图对本发明的实施方案进行描述，其中：
图1为根据本发明实施方案示出的智能化可控型吹风机的结构示意图。
具体实施方式
下面将参照附图对本发明的智能化可控型吹风机的实施方案进行详细说明。
按送风方式来分，有离心式吹风机和轴流式吹风机。离心式靠电动机带动风叶旋转，使进入吹风机的空气获得惯性离心力，不断向外排风。它的缺点是排出的风没有全部流经电动机，电动机升温较高；优点是噪音较低。
轴流式电动机带动风叶旋转，推动进入吹风机的空气作轴向流动，不断地向外排风。它地优点是排出的风全部流经电动机，电动机冷却条件好，绝缘不容易老化；它的缺点是噪音较大。
按外壳所用材料来分，有金属型吹风机和塑料型吹风机。金属型吹风机坚固耐用，可以承受较高的温度。塑料型吹风机重量轻，绝缘性能好，但是容易老化，而且耐高温性能差。
为了克服上述不足，本发明搭建了一种智能化可控型吹风机，从而解决了相应的技术问题。
图1为根据本发明实施方案示出的智能化可控型吹风机的结构示意图，所述吹风机包括壳体1、手柄后端2、集成电路板3和按钮组件4，所述吹风机还包括：
发热支架，设置在吹风机的风嘴位置，所述发热支架用于搭接发热丝体；
发热丝体，与吹风机的电力线连接，用于在所述电力线处于通电状态时发热；
枪式摄像机，设置在吹风机的风嘴位置，用于对吹风机的风嘴所在场景进行图像拍摄，以输出时间轴上连续的多帧风嘴场景图像；
对比度增强设备，与所述枪式摄像机连接，用于接收当前时刻的风嘴场景图像，对所述风嘴场景图像执行对比度增强处理，以获得对比度增强图像，并输出所述对比度增强图像；
第一噪声处理设备，与所述对比度增强设备连接，用于接收所述对比度增强图像，对所述对比度增强图像进行噪声类型分析，以获得所述对比度增强图像中各种噪声类型以及每一种噪声类型对应的最大幅值；
第二噪声处理设备，与所述第一噪声处理设备连接，用于接收所述对比度增强图像中各种噪声类型以及每一种噪声类型对应的最大幅值，基于最大幅值的从大到小的顺序对所述各种噪声类型进行排序，将序号前三的 三种噪声类型作为三种待处理噪声类型输出；
权重分析设备，与所述第二噪声处理设备连接，用于接收所述三种待处理噪声类型，基于所述类型权重对照表确定所述三种待处理噪声类型分别对应的三个影响权重，并采用所述三个影响权重对所述初始化二值化阈值进行按顺序的修正处理，以获得修正处理完毕后的修正化阈值，并输出所述修正化阈值；
图像简化设备，与所述权重分析设备连接，用于接收所述修正化阈值，采用所述修正化阈值对所述对比度增强图像执行二值化处理，以获得待分析图像，并输出所述待分析图像；
非线性滤波设备，与所述图像简化设备连接，用于接收所述待分析图像，对所述待分析图像执行非线性滤波图像，以获得并输出对应的非线性滤波图像；
灰度值分析设备，与所述非线性滤波设备连接，用于接收所述非线性滤波图像，对所述非线性滤波图像的各个区域分别执行灰度值的标准差检测，以获得各个区域分别对应的各个标准差；
区域处理设备，与所述灰度值分析设备连接，用于接收各个区域的各个标准差，计算各个区域的各个标准差的均值，将标准差到所述均值的距离超过限量的区域作为识别区域，对每一个识别区域执行基于其信噪比的图像增强处理，以获得对应的增强区域，所述区域处理设备还用于将所述非线性滤波图像中删除各个识别区域，并相应地补入各个增强区域，以获得对应的区域处理图像；
梯度分析设备，与所述区域处理设备连接，用于接收区域处理图像，对区域处理图像执行灰度化处理以获得相应的灰度化图像，判断所述灰度化图像中每一个像素的像素值到周围像素的像素值的各个梯度，当各个梯度中存在大于等于预设梯度阈值时，将该像素判断为边缘像素，当各个梯度都小于预设梯度阈值时，将该像素判断为非边缘像素；
曲线匹配设备，与所述梯度分析设备连接，用于将所有边缘像素进行连接以获得若干个封闭曲线，基于若干个封闭曲线分别从灰度化图像处分割出对应的若干个图案，当存在与预设人体标准图像的匹配度超限的图案时，发出人体存在信号，否则，发出人体不存在信号；
其中，所述发热丝体还与所述曲线匹配设备连接，用于在接收到所述人体不存在信号时，中断与吹风机的电力线连接。
接着，继续对本发明的智能化可控型吹风机的具体结构进行进一步的说明。
在所述智能化可控型吹风机中，还包括：
抖动感应设备，设置在枪式摄像机上，用于检测所述枪式摄像机的当前位置，并确定所述当前位置与预设固定位置之间的差值，所述差值包括水平方向变化量和垂直方向变化量，并在所述水平方向变化量在正值负值之间变化时或所述垂直方向变化量在正值负值之间变化时，发出第一感应信号，否则，发出第二感应信号。
在所述智能化可控型吹风机中，还包括：
第一像素点处理设备，与所述枪式摄像机连接，用于接收从所述枪式摄像机中获取前后顺序的两帧图像以分别作为当前图像和后续图像，并获取所述当前图像的各个像素点的像素值以及获取所述后续图像的各个像素点的像素值，在接收到所述第一感应信号时，进入抖动检测模式，在接收到所述第二感应信号时，退出所述抖动检测模式；所述第一像素点处理设备在所述抖动检测模式中执行以下处理：基于阿基米德曲线从所述当前图像中获取各个像素点以作为各个参考像素点，每一个参考像素点在所述当前图像中的坐标作为对应的参考坐标，对于每一个参考像素点，基于其像素值从所述后续图像中搜索所述参考坐标附近的像素值等于所述参考像素点像素值的像素点以作为所述参考像素点对应的目标像素点，将所述目标像素点在所述后续图像中的坐标作为对应的目标坐标；在所述第一像素点处理设备中，基于阿基米德曲线从所述当前图像中获取各个像素点以作为各个参考像素点包括：以所述当前图像右下角像素点为起始位置在所述当前图像中画出阿基米德曲线，并将阿基米德曲线沿线经过的各个像素点作为各个参考像素点。
在所述智能化可控型吹风机中，还包括：
第二像素点处理设备，与所述第一像素点处理设备连接，用于获取多个参考像素点和多个参考像素点分别对应的多个目标像素点，确定每一个参考坐标到其对应的目标坐标的水平位移，对各个参考坐标的各个水平位 移求均值以获得图像水平移动量，确定每一个参考坐标到其对应的目标坐标的垂直位移，对各个参考坐标的各个垂直位移求均值以获得图像垂直移动量，基于所述当前图像的时间戳和所述后续时间的时间戳确定时间移动量，以及基于所述时间移动量、所述图像水平移动量和所述图像垂直移动量计算所述枪式摄像机的方向矢量。
在所述智能化可控型吹风机中，还包括：
实时校正设备，分别与所述枪式摄像机和所述第二像素点处理设备连接，用于接收所述枪式摄像机的方向矢量，并基于所述枪式摄像机的方向矢量对所述枪式摄像机进行矢量校正。
在所述智能化可控型吹风机中：在所述灰度值分析设备中，对所述非线性滤波图像的各个区域分别执行灰度值的标准差检测包括：对于每一个区域，提取所述区域的各个像素点的灰度值，基于所述区域的各个像素点的灰度值计算所述区域的标准差。
在所述智能化可控型吹风机中：在所述区域处理设备中，识别区域的信噪比越小，对其执行的图像增强处理的幅度越大。
以及在所述智能化可控型吹风机中：所述权重分析设备还预先存储所述类型权重对照表，所述类型权重对照表保存了每一个种噪声类型对二值化阈值的影响权重，还用于预先存储初始化二值化阈值。
另外，所述枪式摄像机包括CMOS传感器和数据输出接口，所述CMOS传感器用于感应时间轴上连续的多帧风嘴场景图像，所述数据输出接口与所述CMOS传感器连接，用于输出时间轴上连续的多帧风嘴场景图像。
采用本发明的智能化可控型吹风机，针对现有技术中吹风机自适应控制能力差的技术问题，将发热丝体与曲线匹配设备连接，用于在接收到人体不存在信号时，中断与吹风机的电力线连接，从而减少吹风机不必要损耗的同时，提高现场的安全性，其中，采用标准差的区域辨识机制以及采用基于自适应模式的图像增强机制，有效提升了图像处理的效率和效果；对对比度增强后的图像进行高精度的图像简化处理，以获得待分析图像，便于后续的图像识别和图像检测；采用实时校正设备以基于所述枪式摄像机的方向矢量对所述枪式摄像机进行矢量校正，关键的是，采用像素级的 高精度内容分析机制实现对所述枪式摄像机的方向矢量的测量，从而解决了上述技术问题。
可以理解的是，虽然本发明已以较佳实施例披露如上，然而上述实施例并非用以限定本发明。对于任何熟悉本领域的技术人员而言，在不脱离本发明技术方案范围情况下，都可利用上述揭示的技术内容对本发明技术方案做出许多可能的变动和修饰，或修改为等同变化的等效实施例。因此，凡是未脱离本发明技术方案的内容，依据本发明的技术实质对以上实施例所做的任何简单修改、等同变化及修饰，均仍属于本发明技术方案保护的范围内。

Claims (8)

  1. 一种智能化可控型吹风机，其特征在于，所述吹风机包括：
    发热支架，设置在吹风机的风嘴位置，所述发热支架用于搭接发热丝体；
    发热丝体，与吹风机的电力线连接，用于在所述电力线处于通电状态时发热；
    枪式摄像机，设置在吹风机的风嘴位置，用于对吹风机的风嘴所在场景进行图像拍摄，以输出时间轴上连续的多帧风嘴场景图像；
    对比度增强设备，与所述枪式摄像机连接，用于接收当前时刻的风嘴场景图像，对所述风嘴场景图像执行对比度增强处理，以获得对比度增强图像，并输出所述对比度增强图像；
    第一噪声处理设备，与所述对比度增强设备连接，用于接收所述对比度增强图像，对所述对比度增强图像进行噪声类型分析，以获得所述对比度增强图像中各种噪声类型以及每一种噪声类型对应的最大幅值；
    第二噪声处理设备，与所述第一噪声处理设备连接，用于接收所述对比度增强图像中各种噪声类型以及每一种噪声类型对应的最大幅值，基于最大幅值的从大到小的顺序对所述各种噪声类型进行排序，将序号前三的三种噪声类型作为三种待处理噪声类型输出；
    权重分析设备，与所述第二噪声处理设备连接，用于接收所述三种待处理噪声类型，基于所述类型权重对照表确定所述三种待处理噪声类型分别对应的三个影响权重，并采用所述三个影响权重对所述初始化二值化阈值进行按顺序的修正处理，以获得修正处理完毕后的修正化阈值，并输出所述修正化阈值；
    图像简化设备，与所述权重分析设备连接，用于接收所述修正化阈值，采用所述修正化阈值对所述对比度增强图像执行二值化处理，以获得待分析图像，并输出所述待分析图像；
    非线性滤波设备，与所述图像简化设备连接，用于接收所述待分析图像，对所述待分析图像执行非线性滤波图像，以获得并输出对应的非线性滤波图像；
    灰度值分析设备，与所述非线性滤波设备连接，用于接收所述非线性滤波图像，对所述非线性滤波图像的各个区域分别执行灰度值的标准差检测，以获得各个区域分别对应的各个标准差；
    区域处理设备，与所述灰度值分析设备连接，用于接收各个区域的各个标准差，计算各个区域的各个标准差的均值，将标准差到所述均值的距离超过限量的区域作为识别区域，对每一个识别区域执行基于其信噪比的图像增强处理，以获得对应的增强区域，所述区域处理设备还用于将所述非线性滤波图像中删除各个识别区域，并相应地补入各个增强区域，以获得对应的区域处理图像；
    梯度分析设备，与所述区域处理设备连接，用于接收区域处理图像，对区域处理图像执行灰度化处理以获得相应的灰度化图像，判断所述灰度化图像中每一个像素的像素值到周围像素的像素值的各个梯度，当各个梯度中存在大于等于预设梯度阈值时，将该像素判断为边缘像素，当各个梯度都小于预设梯度阈值时，将该像素判断为非边缘像素；
    曲线匹配设备，与所述梯度分析设备连接，用于将所有边缘像素进行连接以获得若干个封闭曲线，基于若干个封闭曲线分别从灰度化图像处分割出对应的若干个图案，当存在与预设人体标准图像的匹配度超限的图案时，发出人体存在信号，否则，发出人体不存在信号；
    其中，所述发热丝体还与所述曲线匹配设备连接，用于在接收到所述人体不存在信号时，中断与吹风机的电力线连接。
  2. 如权利要求1所述的智能化可控型吹风机，其特征在于，所述吹风机还包括：
    抖动感应设备，设置在枪式摄像机上，用于检测所述枪式摄像机的当前位置，并确定所述当前位置与预设固定位置之间的差值，所述差值包括水平方向变化量和垂直方向变化量，并在所述水平方向变化量在正值负值之间变化时或所述垂直方向变化量在正值负值之间变化时，发出第一感应信号，否则，发出第二感应信号。
  3. 如权利要求2所述的智能化可控型吹风机，其特征在于，所述吹 风机还包括：
    第一像素点处理设备，与所述枪式摄像机连接，用于接收从所述枪式摄像机中获取前后顺序的两帧图像以分别作为当前图像和后续图像，并获取所述当前图像的各个像素点的像素值以及获取所述后续图像的各个像素点的像素值，在接收到所述第一感应信号时，进入抖动检测模式，在接收到所述第二感应信号时，退出所述抖动检测模式；所述第一像素点处理设备在所述抖动检测模式中执行以下处理：基于阿基米德曲线从所述当前图像中获取各个像素点以作为各个参考像素点，每一个参考像素点在所述当前图像中的坐标作为对应的参考坐标，对于每一个参考像素点，基于其像素值从所述后续图像中搜索所述参考坐标附近的像素值等于所述参考像素点像素值的像素点以作为所述参考像素点对应的目标像素点，将所述目标像素点在所述后续图像中的坐标作为对应的目标坐标；在所述第一像素点处理设备中，基于阿基米德曲线从所述当前图像中获取各个像素点以作为各个参考像素点包括：以所述当前图像右下角像素点为起始位置在所述当前图像中画出阿基米德曲线，并将阿基米德曲线沿线经过的各个像素点作为各个参考像素点。
  4. 如权利要求3所述的智能化可控型吹风机，其特征在于，所述吹风机还包括：
    第二像素点处理设备，与所述第一像素点处理设备连接，用于获取多个参考像素点和多个参考像素点分别对应的多个目标像素点，确定每一个参考坐标到其对应的目标坐标的水平位移，对各个参考坐标的各个水平位移求均值以获得图像水平移动量，确定每一个参考坐标到其对应的目标坐标的垂直位移，对各个参考坐标的各个垂直位移求均值以获得图像垂直移动量，基于所述当前图像的时间戳和所述后续时间的时间戳确定时间移动量，以及基于所述时间移动量、所述图像水平移动量和所述图像垂直移动量计算所述枪式摄像机的方向矢量。
  5. 如权利要求4所述的智能化可控型吹风机，其特征在于，所述吹风机还包括：
    实时校正设备，分别与所述枪式摄像机和所述第二像素点处理设备连接，用于接收所述枪式摄像机的方向矢量，并基于所述枪式摄像机的方向矢量对所述枪式摄像机进行矢量校正。
  6. 如权利要求5所述的智能化可控型吹风机，其特征在于：
    在所述灰度值分析设备中，对所述非线性滤波图像的各个区域分别执行灰度值的标准差检测包括：对于每一个区域，提取所述区域的各个像素点的灰度值，基于所述区域的各个像素点的灰度值计算所述区域的标准差。
  7. 如权利要求6所述的智能化可控型吹风机，其特征在于：
    在所述区域处理设备中，识别区域的信噪比越小，对其执行的图像增强处理的幅度越大。
  8. 如权利要求7所述的智能化可控型吹风机，其特征在于：
    所述权重分析设备还预先存储所述类型权重对照表，所述类型权重对照表保存了每一个种噪声类型对二值化阈值的影响权重，还用于预先存储初始化二值化阈值。
PCT/CN2019/082513 2018-06-19 2019-04-12 智能化可控型吹风机 WO2019242385A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810631776.1A CN110169641A (zh) 2018-06-19 2018-06-19 智能化可控型吹风机
CN201810631776.1 2018-06-19

Publications (1)

Publication Number Publication Date
WO2019242385A1 true WO2019242385A1 (zh) 2019-12-26

Family

ID=67689260

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/082513 WO2019242385A1 (zh) 2018-06-19 2019-04-12 智能化可控型吹风机

Country Status (2)

Country Link
CN (1) CN110169641A (zh)
WO (1) WO2019242385A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111775829B (zh) * 2019-10-29 2021-04-27 江门市悦隆电子科技有限公司 智能化显示屏驱动平台、方法及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5940980A (en) * 1997-06-02 1999-08-24 Lee; Anessa E. Hands-free hair dryer
CN105303615A (zh) * 2015-11-06 2016-02-03 中国民航大学 一种图像二维拼接与三维表面重建的组合方法
CN105831950A (zh) * 2016-05-11 2016-08-10 京东方科技集团股份有限公司 一种电吹风控制装置、电吹风组件及电吹风控制方法
CN107276770A (zh) * 2017-08-09 2017-10-20 无锡北斗星通信息科技有限公司 一种无线路由自动关闭方法
CN207428677U (zh) * 2017-05-12 2018-06-01 东莞力禾电器有限公司 一种吹风机的消音进风结构

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5940980A (en) * 1997-06-02 1999-08-24 Lee; Anessa E. Hands-free hair dryer
CN105303615A (zh) * 2015-11-06 2016-02-03 中国民航大学 一种图像二维拼接与三维表面重建的组合方法
CN105831950A (zh) * 2016-05-11 2016-08-10 京东方科技集团股份有限公司 一种电吹风控制装置、电吹风组件及电吹风控制方法
CN207428677U (zh) * 2017-05-12 2018-06-01 东莞力禾电器有限公司 一种吹风机的消音进风结构
CN107276770A (zh) * 2017-08-09 2017-10-20 无锡北斗星通信息科技有限公司 一种无线路由自动关闭方法

Also Published As

Publication number Publication date
CN110169641A (zh) 2019-08-27

Similar Documents

Publication Publication Date Title
US11450146B2 (en) Gesture recognition method, apparatus, and device
CN106164980B (zh) 信息处理装置以及信息处理方法
US9165194B2 (en) Heuristic-based approach for automatic payment gesture classification and detection
WO2015058381A1 (zh) 从连拍图像中选择图像的方法和终端
CN105701476A (zh) 一种基于机器视觉的生产线产品自动化识别系统及方法
WO2019228084A1 (zh) 防儿童式智能吹风机
KR102006763B1 (ko) Cctv 영상을 이용한 도로 혼잡도 분석 방법 및 시스템
WO2019242385A1 (zh) 智能化可控型吹风机
US10965885B2 (en) Clothes and accessories fitting method, display system and computer-readable recording medium thereof
CN107067417A (zh) Lk光流法和三帧差法结合的运动目标检测方法
CN110363789B (zh) 一种面向实际工程应用的长期视觉跟踪方法
CN104346778B (zh) 图像的边缘增强方法和装置以及数码摄像设备
AU2018201707A1 (en) Video analysis method and system for detecting material on conveyor belt
Jeong et al. Probabilistic method to determine human subjects for low-resolution thermal imaging sensor
TWI749714B (zh) 瑕疵檢測方法、瑕疵分類方法及其系統
JP5679760B2 (ja) 侵入物体検出装置
CN106807651A (zh) 一种基于温度与面积建模的煤矸分拣方法及其装置
CN107008662A (zh) 一种基于温度与面积建模的煤矸分拣方法及其装置
Verstockt et al. Wavelet-based multi-modal fire detection
KR20140042551A (ko) 영상기반 사람 검출을 위한 특징 추출 방법 및 장치
Leng et al. An improved pedestrians detection algorithm using HOG and ViBe
WO2019237816A1 (zh) 基于选择按钮的屏蔽式电吹风
Li et al. Autonomous flame detection in video based on saliency analysis and optical flow
CN107335563A (zh) 一种喷水控制方法
Sharma et al. Efficient object detection with its enhancement

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: 19823113

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: 19823113

Country of ref document: EP

Kind code of ref document: A1