WO2019228084A1 - 防儿童式智能吹风机 - Google Patents

防儿童式智能吹风机 Download PDF

Info

Publication number
WO2019228084A1
WO2019228084A1 PCT/CN2019/082521 CN2019082521W WO2019228084A1 WO 2019228084 A1 WO2019228084 A1 WO 2019228084A1 CN 2019082521 W CN2019082521 W CN 2019082521W WO 2019228084 A1 WO2019228084 A1 WO 2019228084A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
child
block
processing
hair dryer
Prior art date
Application number
PCT/CN2019/082521
Other languages
English (en)
French (fr)
Inventor
周超强
Original Assignee
Zhou Chaoqiang
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 Zhou Chaoqiang filed Critical Zhou Chaoqiang
Priority to US17/055,858 priority Critical patent/US20210219694A1/en
Publication of WO2019228084A1 publication Critical patent/WO2019228084A1/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
    • 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
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics

Definitions

  • the invention relates to the field of household equipment, in particular to a child-resistant smart hair dryer.
  • the hair dryer is mainly used for drying and shaping the hair, but it can also be used for local drying, heating and physiotherapy in laboratories, physiotherapy rooms, industrial production, art, etc. According to the type of motor used, it can be divided into AC series, AC shaded pole and DC permanent magnet.
  • the advantages of the series-excited hair dryer are large starting torque and high rotation speed, which are suitable for manufacturing high-power hair dryers; the disadvantage is that the noise is large and the commutator has certain interference with telecommunication equipment.
  • Shaded pole hair dryer has the advantages of low noise, long life and no interference to telecommunication equipment; the disadvantages are low speed, poor starting performance and heavy weight.
  • the advantages of permanent magnet hair dryer are light weight, high speed, simple manufacturing process, low cost, and high quality.
  • the present invention provides a child-resistant smart hair dryer, which performs targeted edge deepening of the obtained blocks based on the search results of the blocks with a large content deviation. Processing, thereby improving the efficiency of edge deepening processing; based on the processing of white balance processing equipment and morphological processing equipment, to achieve the orientation and targeted extraction of the foreground image of the image to be processed for the recognition and detection of subsequent images Provide more valuable data to be analyzed; analyze the content of the image when the tailing phenomenon due to jitter is detected, specifically, determine the displacement vector of the image based on the red channel values of each pixel of the image, and use The built-in motor of the hemisphere shooting mechanism performs corresponding displacement correction. On the basis of the above-mentioned high-precision data processing, when the presence of a child is detected, the AC permanent magnet motor of the hair dryer is turned off in time to avoid related accidents.
  • a child-resistant smart hair dryer is provided, and the hair dryer includes:
  • An AC permanent magnet motor is used to drive the fan blade structure of the blower to rotate; the fan blade structure is arranged between the air inlet of the blower and the front mouth of the fan, and is used to suck air from the air inlet during rotation and A centrifugal airflow is formed in the cylinder to be blown out through the front mouth of the duct; a hemispherical shooting mechanism includes a tail-measuring device, an image capturing device, a data analysis device, a DC drive motor, a filter, an optical lens, and an image sensing device.
  • the image sensing device is disposed on the hair dryer and is used to capture an image in front of the hair dryer.
  • the child-resistant smart hair dryer further includes:
  • Tail measurement device connected to the image sensing device, is used to receive the image in front of the fan, and perform image content measurement on the image in front of the fan, to determine whether the tail drag pattern appears in the image in front of the fan, and exists
  • a content trailing signal is issued, otherwise, a normal content signal is issued
  • an image capture device is connected to the trailing measuring device and the image sensing device respectively for receiving the first content trailing
  • the front image of the fan corresponding to the first content drag signal is output as the image to be analyzed, and the front image of the fan closest to the front image of the fan corresponding to the first content drag signal is output as the image to be analyzed. Compare image output.
  • the child-resistant smart hair dryer further includes:
  • a data analysis device connected to the image capture device and configured to receive the image to be analyzed and the image to be compared, and determine a relative value of the image to be analyzed based on an overall comparison between the image to be analyzed and the image to be compared
  • the displacement vector of the image to be compared is output as the current displacement vector.
  • the child-resistant smart hair dryer further includes:
  • a DC driving motor is connected to the filter, the optical lens, the image sensing device, and the data analysis device, respectively, and is used to control the filter, the optical lens, The image sensing devices move together in opposite directions.
  • the child-resistant smart hair dryer further includes:
  • a white balance processing device connected to the hemispherical shooting mechanism and configured to receive an image in front of the hair dryer and perform white balance processing on the image in front of the hair dryer to obtain and output a corresponding white balance image;
  • a morphological processing device Including an expansion processing sub-device and an erosion processing sub-device, the expansion processing sub-device is connected to the white balance processing device, and is configured to receive the white balance image and perform expansion processing on the white balance image to obtain a corresponding Expansion processing image, the corrosion processing sub-device is connected to the expansion processing sub-device, and is configured to receive the expansion processing image and perform corrosion processing on the expansion processing image to obtain a corresponding corrosion processing image;
  • pixel value statistics A device connected to the morphological processing device and configured to receive the corrosion-processed image, obtain each brightness value of each pixel point of the corrosion-processed image, perform a mean square error calculation on each brightness value, and obtain the obtained average The value of the variance is output as reference data; the fragment extraction device is connected to
  • a threshold size a foreground extraction device connected to the noise analysis device and configured to perform background segmentation processing on the segmented fragments based on the determined threshold for each segmented fragment to obtain a corresponding foreground fragment, and Foreground fragments are fitted to obtain a foreground detection image, and the foreground detection image is output; edge enhancement And is connected to the foreground extraction device, and is configured to receive the foreground detection image, and perform edge enhancement processing on the foreground detection image based on a corresponding intensity of the signal-to-noise ratio of the foreground detection image to obtain a corresponding Adaptively enhancing an image and outputting the adaptively enhanced image; a block search device connected to the edge enhancement device, configured to receive the adaptively enhanced image, and perform equalization and block processing on the adaptively enhanced image To obtain each averaged segment, and perform the following operations on each averaged segment: obtain the average value of the brightness value of each pixel point of the averaged segment; the segment search device is further configured to: Each average value of the averaged block
  • the block performs edge deepening processing to obtain corresponding deepened homogenized blocks, and is also used to fit each deepened averaged block and each to-be-filled averaged block to obtain a block-fitted image, and output the Block fitting image; contouring processing device connected to the block deepening device for receiving the block fitting image and performing binarization processing on the block fitting image to obtain and output a corresponding binarized image , Traverse each pixel of the image starting from the upper left corner of the binarized image.
  • the contouring processing device connects all the preliminary contour pixels in the binarized image and performs fitting to obtain multiple fitting closures Curve, modify the initial contour pixels outside the closed closed curve into internal pixels, and use the unmodified initial contour pixels as the final contour pixels; a child recognition device connected to the contouring processing device to use all the final contours
  • the pixels are connected to obtain a plurality of closed areas, and the area of each closed area is determined.
  • a child identification signal is issued; wherein the child identification device is further When there is a closed area with an area equal to the preset child area distribution range, a child unidentified signal is issued; wherein, the AC permanent magnet motor is also connected to the child identification device, and is used for automatically receiving the child identification signal. Turn off, and keep the current operating mode after receiving the child unidentified signal.
  • the filter is disposed in front of the optical lens
  • the image sensing device is disposed in front of the optical lens
  • the child-resistant smart hair dryer in the data analysis device, based on an overall comparison of the image to be analyzed and the image to be compared, determine that the image to be analyzed is relative to the to be compared
  • the displacement vector of the image includes: obtaining each red channel value of each pixel point of the image to be analyzed and each red channel value of the image to be compared, based on each red channel value of each pixel point of the image to be analyzed and the Each red channel value of the images to be compared determines a displacement vector of the image to be analyzed with respect to the image to be compared.
  • FIG. 1 is a schematic structural diagram of a child-resistant smart hair dryer according to an embodiment of the present invention.
  • the hair dryer is a combination of a set of electric heating wires and a small fan with high speed. When energized, the heating wire generates heat, and the wind blown by the fan passes through the heating wire and becomes hot air. If only a small fan rotates, and the heating wire does not heat, then the wind blows out but not the heat.
  • Hair dryers are also dangerous, such as when children are playing with them, or when adults forget to turn off after use and there are children around.
  • the present invention sets up a child-resistant smart hair dryer, which can effectively solve the corresponding technical problems.
  • FIG. 1 is a schematic structural diagram of a child-resistant smart hair dryer according to an embodiment of the present invention.
  • the hair dryer includes a handle 1 and a power connector 2.
  • the hair dryer further includes:
  • AC permanent magnet motor for rotating the blade structure of the blower
  • the air leaf structure is arranged between the air inlet of the hair dryer and the front mouth of the air duct, and is used for sucking in air from the air inlet while rotating, and forming a centrifugal air flow in the air duct to blow out through the front mouth of the air duct;
  • a hemispherical shooting mechanism includes a tail-measuring device, an image capturing device, a data analysis device, a DC drive motor, a filter, an optical lens, and an image sensing device. Take an image in front of the hairdryer.
  • the child-resistant smart hair dryer further includes:
  • Tail measurement device connected to the image sensing device, is used to receive the image in front of the fan, and perform image content measurement on the image in front of the fan, to determine whether the tail drag pattern appears in the image in front of the fan, and exists When dragging the tail pattern, a content tail signal is issued; otherwise, a normal signal is issued;
  • An image capture device which is connected to the tail drag measurement device and the image sensing device, respectively, and is used to forward the fan corresponding to the first tail drag signal when the first tail drag signal is received.
  • the image is output as an image to be analyzed, and the image in front of the air duct closest to the image in front of the air duct corresponding to the first content dragging signal is output as the image to be compared.
  • the child-resistant smart hair dryer further includes:
  • a data analysis device connected to the image capture device and configured to receive the image to be analyzed and the image to be compared, and determine a relative value of the image to be analyzed based on an overall comparison between the image to be analyzed and the image to be compared
  • the displacement vector of the image to be compared is output as the current displacement vector.
  • the child-resistant smart hair dryer further includes:
  • a DC driving motor is connected to the filter, the optical lens, the image sensing device, and the data analysis device, respectively, and is used to control the filter, the optical lens, The image sensing devices move together in opposite directions.
  • the child-resistant smart hair dryer further includes:
  • a white balance processing device connected to the hemispherical shooting mechanism, configured to receive an image in front of the hair dryer, and perform white balance processing on the image in front of the hair dryer to obtain and output a corresponding white balance image;
  • a morphological processing device including an expansion processing sub-device and an erosion processing sub-device, the expansion processing sub-device connected to the white balance processing device, for receiving the white balance image, and performing expansion processing on the white balance image
  • the corrosion processing sub-device is connected to the expansion processing sub-device, and is configured to receive the expansion processing image and perform corrosion processing on the expansion processing image to obtain a corresponding corrosion processing image
  • a pixel value statistics device connected to the morphological processing device and configured to receive the corrosion-processed image, obtain each brightness value of each pixel point of the corrosion-processed image, perform a mean square error calculation on each brightness value, and The obtained mean square error value is output as reference data;
  • a fragment extraction device connected to the pixel value statistics device and configured to receive the corrosion-processed image and the reference data, and uniformly segment the corrosion-processed image based on the reference data to obtain a plurality of segmented fragments, wherein, the larger the reference data is, the larger the number of segmentation fragments obtained by uniformly segmenting the corrosion-processed image;
  • a noise analysis device connected to the fragment extraction device and configured to receive the plurality of segmented fragments, and detect, for each segmented fragment, five types of noise in the top five of the segmented fragments, based on the five types Determining the signal-to-noise ratio of the segmented fragments with amplitudes corresponding to the types of noise, and determining a threshold size for background segmentation of the segmented fragments based on the signal-to-noise ratio of the segmented fragments;
  • a foreground extraction device is connected to the noise analysis device, and is configured to perform background segmentation processing on the segmented fragments based on a determined threshold for each segmented fragment to obtain corresponding foreground fragments, and perform each of the foreground fragments of each segmented fragment. Fitting to obtain a foreground detection image, and outputting the foreground detection image;
  • An edge enhancement device is connected to the foreground extraction device, and is configured to receive the foreground detection image, and perform edge enhancement processing on the foreground detection image based on a corresponding intensity of the signal-to-noise ratio of the foreground detection image to obtain A corresponding adaptively enhanced image, and outputting the adaptively enhanced image;
  • a block search device connected to the edge enhancement device, for receiving the adaptively enhanced image, performing an equalization and block processing on the adaptively enhanced image to obtain each averaged block, and averaged each
  • the segmentation performs the following operations: obtaining an average value of the luminance values of each pixel point of the averaged segmentation; the segmentation search device is further configured to determine the adaptively enhanced image based on each averaged value of each averaged segmentation Image-level brightness average, taking the averaged block whose absolute value of the difference between the average value and the image-level brightness mean exceeds the limit as the target averaged block, and outputting each target averaged block in the adaptively enhanced image
  • a plurality of equalization blocks except for each target equalization block in the adaptive enhanced image are taken as a plurality of equalization blocks to be filled, and the plurality of to-be-filled blocks are output. Homogenization block
  • a block deepening device which is connected to the block search device and is configured to perform edge deepening processing on each target equalization block to obtain a corresponding deepening equalization block, and is also used to separate each deepening equalization block and Fit each homogenized block to be filled to obtain a block-fitted image, and output the block-fitted image;
  • An outline processing device connected to the block deepening device, for receiving a block-fitted image, performing binarization processing on the block-fitted image to obtain and output a corresponding binarized image, and from the binarized image
  • the upper left corner of the image begins to traverse each pixel of the image. For each pixel, if the pixels surrounding more than 5 points are black level pixels or the pixels surrounding more than 5 points are white level pixels, then A pixel is used as an internal pixel, otherwise, the pixel is used as a preliminary contour pixel; the contouring processing device connects all the preliminary contour pixels in the binarized image and performs fitting to obtain multiple fitted closed curves, and closes the fit.
  • the initial contour pixels outside the curve are modified to internal pixels, and the unmodified initial contour pixels are used as the final contour pixels;
  • a child identification device connected to the contouring processing device, configured to connect all final contour pixels to obtain multiple closed areas, determine the area of each closed area, and when there is a closed area with an area equal to a preset child area distribution range When a child identification signal is issued;
  • the child identification device is further configured to send a child unidentified signal when there is no closed area with an area equal to a preset child area distribution range;
  • the AC permanent magnet motor is also connected to the child identification device, and is configured to automatically turn off when the child identification signal is received, and to maintain the current operation mode when the child unidentified signal is received.
  • the filter is disposed in front of the optical lens, and the image sensing device is disposed in front of the optical lens.
  • the data analysis device in the data analysis device, based on an overall comparison of the image to be analyzed and the image to be compared, determining a displacement of the image to be analyzed with respect to the image to be compared
  • the vector includes: acquiring each red channel value of each pixel point of the image to be analyzed and each red channel value of the image to be compared, based on each red channel value of each pixel point of the image to be analyzed and the to be compared Each red channel value of the image determines a displacement vector of the image to be analyzed with respect to the image to be compared.
  • a CPLD chip may be used to implement the child identification device.
  • CPLD has the characteristics of flexible programming, high integration, short design and development cycle, wide application range, advanced development tools, low design and manufacturing costs, low requirements on the designer's hardware experience, no testing of standard products, strong confidentiality, and popular prices. Can realize large-scale circuit design, so it is widely used in product prototype design and product production (generally below 10,000 pieces).
  • CPLD devices can be used in almost all applications of small and medium-sized general-purpose digital integrated circuits. CPLD devices have become an indispensable part of electronic products, and its design and application have become a necessary skill for electronic engineers.
  • CPLD is a type of digital integrated circuit where users construct logic functions according to their needs. The basic design method is to use the integrated development software platform to generate corresponding target files by using schematic diagrams and hardware description languages, and then transfer the code to the target chip through a download cable ("in-system" programming) to realize the designed digital system. .
  • the child-resistant intelligent hair dryer of the present invention in response to the technical problem of low safety level of the hair dryer in the prior art, based on the search result of the block with a large content deviation, the obtained block is subjected to targeted edge deepening processing.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

一种防儿童式智能吹风机，包括：交流永磁电机，用于带动吹风机的风叶结构旋转；风叶结构，设置在吹风机的进风口和风筒前嘴之间，用于在旋转时，从进风口处吸入空气，并在风筒内形成离心气流以通过风筒前嘴吹出；半球拍摄机构，包括拽尾测量设备、图像截取设备、数据分析设备、直流驱动电机、滤光片、光学镜头和图像传感设备，图像传感设备设置在风筒上，用于拍摄风筒前方图像；拽尾测量设备，用于对风筒前方图像执行图像内容测量，以确定风筒前方图像中是否出现拽尾图案，并在存在拽尾图案时，发出内容拽尾信号，否则，发出内容正常信号。该吹风机有效避免了与吹风机相关的儿童事故发生。

Description

防儿童式智能吹风机 技术领域
本发明涉及家用设备领域，尤其涉及一种防儿童式智能吹风机。
背景技术
吹风机主要用于头发的干燥和整形，但也可供实验室、理疗室及工业生产、美工等方面作局部干燥、加热和理疗之用。根据它所使用的电动机类型，可分为交流串激式、交流罩极式和直流永磁式。串激式吹风机的优点是启动转矩大，转速高，适合制造大功率的吹风机；缺点是噪音大，换向器对电信设备有一定的干扰。罩极式吹风机的优点是噪音小，寿命长，对电信设备不会造成干扰；缺点是转速低，启动性能差，重量大。永磁式吹风机的优点是重量轻，转速高，制造工艺简单，造价低，物美价廉。
发明内容
为了解决现有吹风机会引起儿童相关事故的技术问题，本发明提供了一种防儿童式智能吹风机，基于内容偏离度较大的分块的搜索结果，对获取的分块进行针对性的边缘加深处理，从而提升了边缘加深处理的效率；在白平衡处理设备和形态学处理设备的处理的基础上，实现对待处理图像的前景图像的定向、有针对性的提取，为后续图像的识别和检测提供更有价值的待分析数据；在检测到因为抖动而产生的拽尾现象时，对图像内容进行分析，具体地，基于图像的各个像素点的各个红色通道值确定图像的位移矢量，并采用半球拍摄机构的内置电机进行相应的位移矫正，在上述高精度数据处理的基础上，在检测到儿童存在时，及时关闭吹风机的交流永磁电机，从而避免相关事故发生。
根据本发明的一方面，提供了一种防儿童式智能吹风机，所述吹风机包括：
交流永磁电机，用于带动吹风机的风叶结构旋转；风叶结构，设置在吹风机的进风口和风筒前嘴之间，用于在旋转时，从所述进风口处吸入空气，并在风筒内形成离心气流以通过所述风筒前嘴吹出；半球拍摄机构，包括拽尾测量设备、图像截取设备、数据分析设备、直流驱动电机、滤光片、光学镜头和图像传感设备，所述图像传感设备设置在所述风筒上，用于拍摄风筒前方图像。
更具体地，在所述防儿童式智能吹风机中，还包括：
拽尾测量设备，与所述图像传感设备连接，用于接收风筒前方图像，对所述风筒前方图像执行图像内容测量，以确定风筒前方图像中是否出现拽尾图案，并在存在拽尾图案时，发出内容拽尾信号，否则，发出内容正常信号；图像截取设备，分别与所述拽尾测量设备和所述图像传感设备连接，用于在接收到第一个内容拽尾信号时，将所述第一个内容拽尾信号对应的风筒前方图像作为待分析图像输出，将距离所述第一个内容拽尾信号对应的风筒前方图像最近的风筒前方图像作为待比较图像输出。
更具体地，在所述防儿童式智能吹风机中，还包括：
数据分析设备，与所述图像截取设备连接，用于接收所述待分析图像和所述待比较图像，基于所述待分析图像和所述待比较图像的整体比较，确定所述待分析图像相对于所述待比较图像的位移矢量，以作为当前位移矢量输出。
更具体地，在所述防儿童式智能吹风机中，还包括：
直流驱动电机，分别与所述滤光片、所述光学镜头、所述图像传感设备和所述数据分析设备连接，用于基于所述位移矢量控制所述滤光片、所述光学镜头、所述图像传感设备一起进行相反方向的移动。
更具体地，在所述防儿童式智能吹风机中，还包括：
白平衡处理设备，与所述半球拍摄机构连接，用于接收所述风筒前方图像，对所述风筒前方图像执行白平衡处理，以获得并输出对应的白平衡图像；形态学处理设备，包括膨胀处理子设备和腐蚀处理子设备，所述膨胀处理子设备与所述白平衡处理设备连接，用于接收所述白平衡图像，并对所述白平衡图像执行膨胀处理，以获得对应的膨胀处理图像，所述腐蚀处理子设备与所述膨胀处理子设备连接，用于接收所述膨胀处理图像，并 对所述膨胀处理图像执行腐蚀处理，以获得对应的腐蚀处理图像；像素值统计设备，与所述形态学处理设备连接，用于接收所述腐蚀处理图像，获取所述腐蚀处理图像的各个像素点的各个亮度值，对所述各个亮度值执行均方差计算，将获得的均方差的数值作为参考数据输出；碎片提取设备，与所述像素值统计设备连接，用于接收所述腐蚀处理图像和所述参考数据，基于所述参考数据对所述腐蚀处理图像进行均匀式分割，以获得多个分割碎片，其中，所述参考数据越大，对所述腐蚀处理图像进行均匀式分割获得的分割碎片的数量越多；噪声分析设备，与所述碎片提取设备连接，用于接收所述多个分割碎片，针对每一个分割碎片，检测所述分割碎片中幅值排名前五的五种噪声类型，基于所述五种噪声类型分别对应的幅值确定所述分割碎片的信噪比，并基于所述分割碎片的信噪比确定对所述分割碎片进行背景分割的阈值大小；前景提取设备，与所述噪声分析设备连接，用于针对每一个分割碎片，基于确定的阈值对所述分割碎片执行背景分割处理以获得对应的前景碎片，并将各个分割碎片的各个前景碎片进行拟合，以获得前景检测图像，并输出所述前景检测图像；边缘增强设备，与所述前景提取设备连接，用于接收所述前景检测图像，并对所述前景检测图像执行基于所述前景检测图像的信噪比大小的相应强度的边缘增强处理，以获得相应的自适应增强图像，并输出所述自适应增强图像；分块搜索设备，与所述边缘增强设备连接，用于接收所述自适应增强图像，对所述自适应增强图像执行均化分块处理，以获得各个均化分块，对每一个均化分块执行以下操作：获取所述均化分块的各个像素点的亮度值的均值；所述分块搜索设备还用于基于所述各个均化分块的各个均值确定所述自适应增强图像的图像级亮度均值，将均值到所述图像级亮度均值之差的绝对值超限的均化分块作为目标均化分块，并输出所述自适应增强图像中的各个目标均化分块；在所述分块搜索设备中，将所述自适应增强图像中除了各个目标均化分块的多个均化分块作为多个待填充均化分块，并输出所述多个待填充均化分块；分块加深设备，与所述分块搜索设备连接，用于对每一个目标均化分块执行边缘加深处理，以获得对应的加深均化分块，还用于将各个加深均化分块和各个待填充均化分块进行拟合，以获得分块拟合图像，并输出所述分块拟合图像；轮廓化处理设备，与所述分块加深 设备连接，用于接收分块拟合图像，对分块拟合图像执行二值化处理以获得并输出相应的二值化图像，从二值化图像的左上角开始遍历图像的每一个像素，针对每一个像素，如果其周围超过5个点的像素都为黑电平像素或其周围超过5个点的像素都为白电平像素，则将该像素作为内部像素，否则，该像素作为初步轮廓像素；所述轮廓化处理设备将二值化图像中的所有初步轮廓像素连接起来并进行拟合以获得多个拟合封闭曲线，将拟合封闭曲线之外的初步轮廓像素修改为内部像素，将未被修改的初步轮廓像素作为最终轮廓像素；儿童识别设备，与所述轮廓化处理设备连接，用于将所有最终轮廓像素连接起来以获得多个封闭区域，确定每一个封闭区域的面积，当存在面积等于预设儿童面积分布范围的封闭区域时，发出儿童识别信号；其中，所述儿童识别设备还用于当不存在面积等于预设儿童面积分布范围的封闭区域时，发出儿童未识别信号；其中，所述交流永磁电机还与所述儿童识别设备连接，用于在接收到所述儿童识别信号时，自动关闭，以及在接收到所述儿童未识别信号，保持当前的运行模式。
更具体地，在所述防儿童式智能吹风机中：所述滤光片设置在所述光学镜头的前方，所述图像传感设备设置在所述光学镜头的前方。
更具体地，在所述防儿童式智能吹风机中：在所述数据分析设备中，基于所述待分析图像和所述待比较图像的整体比较，确定所述待分析图像相对于所述待比较图像的位移矢量包括：获取所述待分析图像的各个像素点的各个红色通道值以及所述待比较图像的各个红色通道值，基于所述待分析图像的各个像素点的各个红色通道值以及所述待比较图像的各个红色通道值确定所述待分析图像相对于所述待比较图像的位移矢量。
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防儿童式智能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防儿童式智能吹风机的实施方案进行详 细说明。
吹风机是由一组电热丝和一个高转速小风扇组合而成的。通电时，电热丝会产生热量，风扇吹出的风经过电热丝，就变成热风。如果只是小风扇转动，而电热丝不热，那么吹出来的就只是风而不热了。
吹风机也具有一定的危险性，例如在儿童把玩时，或成人使用后忘记关闭而周围有儿童存在时。
为了克服上述不足，本发明搭建了一种防儿童式智能吹风机，能够有效解决相应的技术问题。
图1为根据本发明实施方案示出的防儿童式智能吹风机的结构示意图，所述吹风机包括手柄1和电源连接件2，所述吹风机还包括：
交流永磁电机，用于带动吹风机的风叶结构旋转；
风叶结构，设置在吹风机的进风口和风筒前嘴之间，用于在旋转时，从所述进风口处吸入空气，并在风筒内形成离心气流以通过所述风筒前嘴吹出；
半球拍摄机构，包括拽尾测量设备、图像截取设备、数据分析设备、直流驱动电机、滤光片、光学镜头和图像传感设备，所述图像传感设备设置在所述风筒上，用于拍摄风筒前方图像。
接着，继续对本发明的防儿童式智能吹风机的具体结构进行进一步的说明。
在所述防儿童式智能吹风机中，还包括：
拽尾测量设备，与所述图像传感设备连接，用于接收风筒前方图像，对所述风筒前方图像执行图像内容测量，以确定风筒前方图像中是否出现拽尾图案，并在存在拽尾图案时，发出内容拽尾信号，否则，发出内容正常信号；
图像截取设备，分别与所述拽尾测量设备和所述图像传感设备连接，用于在接收到第一个内容拽尾信号时，将所述第一个内容拽尾信号对应的风筒前方图像作为待分析图像输出，将距离所述第一个内容拽尾信号对应的风筒前方图像最近的风筒前方图像作为待比较图像输出。
在所述防儿童式智能吹风机中，还包括：
数据分析设备，与所述图像截取设备连接，用于接收所述待分析图像 和所述待比较图像，基于所述待分析图像和所述待比较图像的整体比较，确定所述待分析图像相对于所述待比较图像的位移矢量，以作为当前位移矢量输出。
在所述防儿童式智能吹风机中，还包括：
直流驱动电机，分别与所述滤光片、所述光学镜头、所述图像传感设备和所述数据分析设备连接，用于基于所述位移矢量控制所述滤光片、所述光学镜头、所述图像传感设备一起进行相反方向的移动。
在所述防儿童式智能吹风机中，还包括：
白平衡处理设备，与所述半球拍摄机构连接，用于接收所述风筒前方图像，对所述风筒前方图像执行白平衡处理，以获得并输出对应的白平衡图像；
形态学处理设备，包括膨胀处理子设备和腐蚀处理子设备，所述膨胀处理子设备与所述白平衡处理设备连接，用于接收所述白平衡图像，并对所述白平衡图像执行膨胀处理，以获得对应的膨胀处理图像，所述腐蚀处理子设备与所述膨胀处理子设备连接，用于接收所述膨胀处理图像，并对所述膨胀处理图像执行腐蚀处理，以获得对应的腐蚀处理图像；
像素值统计设备，与所述形态学处理设备连接，用于接收所述腐蚀处理图像，获取所述腐蚀处理图像的各个像素点的各个亮度值，对所述各个亮度值执行均方差计算，将获得的均方差的数值作为参考数据输出；
碎片提取设备，与所述像素值统计设备连接，用于接收所述腐蚀处理图像和所述参考数据，基于所述参考数据对所述腐蚀处理图像进行均匀式分割，以获得多个分割碎片，其中，所述参考数据越大，对所述腐蚀处理图像进行均匀式分割获得的分割碎片的数量越多；
噪声分析设备，与所述碎片提取设备连接，用于接收所述多个分割碎片，针对每一个分割碎片，检测所述分割碎片中幅值排名前五的五种噪声类型，基于所述五种噪声类型分别对应的幅值确定所述分割碎片的信噪比，并基于所述分割碎片的信噪比确定对所述分割碎片进行背景分割的阈值大小；
前景提取设备，与所述噪声分析设备连接，用于针对每一个分割碎片，基于确定的阈值对所述分割碎片执行背景分割处理以获得对应的前景碎 片，并将各个分割碎片的各个前景碎片进行拟合，以获得前景检测图像，并输出所述前景检测图像；
边缘增强设备，与所述前景提取设备连接，用于接收所述前景检测图像，并对所述前景检测图像执行基于所述前景检测图像的信噪比大小的相应强度的边缘增强处理，以获得相应的自适应增强图像，并输出所述自适应增强图像；
分块搜索设备，与所述边缘增强设备连接，用于接收所述自适应增强图像，对所述自适应增强图像执行均化分块处理，以获得各个均化分块，对每一个均化分块执行以下操作：获取所述均化分块的各个像素点的亮度值的均值；所述分块搜索设备还用于基于所述各个均化分块的各个均值确定所述自适应增强图像的图像级亮度均值，将均值到所述图像级亮度均值之差的绝对值超限的均化分块作为目标均化分块，并输出所述自适应增强图像中的各个目标均化分块；在所述分块搜索设备中，将所述自适应增强图像中除了各个目标均化分块的多个均化分块作为多个待填充均化分块，并输出所述多个待填充均化分块；
分块加深设备，与所述分块搜索设备连接，用于对每一个目标均化分块执行边缘加深处理，以获得对应的加深均化分块，还用于将各个加深均化分块和各个待填充均化分块进行拟合，以获得分块拟合图像，并输出所述分块拟合图像；
轮廓化处理设备，与所述分块加深设备连接，用于接收分块拟合图像，对分块拟合图像执行二值化处理以获得并输出相应的二值化图像，从二值化图像的左上角开始遍历图像的每一个像素，针对每一个像素，如果其周围超过5个点的像素都为黑电平像素或其周围超过5个点的像素都为白电平像素，则将该像素作为内部像素，否则，该像素作为初步轮廓像素；所述轮廓化处理设备将二值化图像中的所有初步轮廓像素连接起来并进行拟合以获得多个拟合封闭曲线，将拟合封闭曲线之外的初步轮廓像素修改为内部像素，将未被修改的初步轮廓像素作为最终轮廓像素；
儿童识别设备，与所述轮廓化处理设备连接，用于将所有最终轮廓像素连接起来以获得多个封闭区域，确定每一个封闭区域的面积，当存在面积等于预设儿童面积分布范围的封闭区域时，发出儿童识别信号；
其中，所述儿童识别设备还用于当不存在面积等于预设儿童面积分布范围的封闭区域时，发出儿童未识别信号；
其中，所述交流永磁电机还与所述儿童识别设备连接，用于在接收到所述儿童识别信号时，自动关闭，以及在接收到所述儿童未识别信号，保持当前的运行模式。
在所述防儿童式智能吹风机中：所述滤光片设置在所述光学镜头的前方，所述图像传感设备设置在所述光学镜头的前方。
以及在所述防儿童式智能吹风机中：在所述数据分析设备中，基于所述待分析图像和所述待比较图像的整体比较，确定所述待分析图像相对于所述待比较图像的位移矢量包括：获取所述待分析图像的各个像素点的各个红色通道值以及所述待比较图像的各个红色通道值，基于所述待分析图像的各个像素点的各个红色通道值以及所述待比较图像的各个红色通道值确定所述待分析图像相对于所述待比较图像的位移矢量。
另外，可采用CPLD芯片来实现所述儿童识别设备。CPLD具有编程灵活、集成度高、设计开发周期短、适用范围宽、开发工具先进、设计制造成本低、对设计者的硬件经验要求低、标准产品无需测试、保密性强、价格大众化等特点，可实现较大规模的电路设计，因此被广泛应用于产品的原型设计和产品生产(一般在10,000件以下)之中。几乎所有应用中小规模通用数字集成电路的场合均可应用CPLD器件。CPLD器件已成为电子产品不可缺少的组成部分，它的设计和应用成为电子工程师必备的一种技能。CPLD是一种用户根据各自需要而自行构造逻辑功能的数字集成电路。其基本设计方法是借助集成开发软件平台，用原理图、硬件描述语言等方法，生成相应的目标文件，通过下载电缆(“在系统”编程)将代码传送到目标芯片中，实现设计的数字系统。
采用本发明的防儿童式智能吹风机，针对现有技术中吹风机安全等级不高的技术问题，基于内容偏离度较大的分块的搜索结果，对获取的分块进行针对性的边缘加深处理，从而提升了边缘加深处理的效率；在白平衡处理设备和形态学处理设备的处理的基础上，实现对待处理图像的前景图像的定向、有针对性的提取，为后续图像的识别和检测提供更有价值的待分析数据；在检测到因为抖动而产生的拽尾现象时，对图像内容进行分析， 具体地，基于图像的各个像素点的各个红色通道值确定图像的位移矢量，并采用半球拍摄机构的内置电机进行相应的位移矫正，在上述高精度数据处理的基础上，在检测到儿童存在时，及时关闭吹风机的交流永磁电机，避免相关事故发生，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 (7)

  1. 一种防儿童式智能吹风机，其特征在于，所述吹风机包括：
    交流永磁电机，用于带动吹风机的风叶结构旋转；
    风叶结构，设置在吹风机的进风口和风筒前嘴之间，用于在旋转时，从所述进风口处吸入空气，并在风筒内形成离心气流以通过所述风筒前嘴吹出；
    半球拍摄机构，包括拽尾测量设备、图像截取设备、数据分析设备、直流驱动电机、滤光片、光学镜头和图像传感设备，所述图像传感设备设置在所述风筒上，用于拍摄风筒前方图像。
  2. 如权利要求1所述的防儿童式智能吹风机，其特征在于，所述吹风机还包括：
    拽尾测量设备，与所述图像传感设备连接，用于接收风筒前方图像，对所述风筒前方图像执行图像内容测量，以确定风筒前方图像中是否出现拽尾图案，并在存在拽尾图案时，发出内容拽尾信号，否则，发出内容正常信号；
    图像截取设备，分别与所述拽尾测量设备和所述图像传感设备连接，用于在接收到第一个内容拽尾信号时，将所述第一个内容拽尾信号对应的风筒前方图像作为待分析图像输出，将距离所述第一个内容拽尾信号对应的风筒前方图像最近的风筒前方图像作为待比较图像输出。
  3. 如权利要求2所述的防儿童式智能吹风机，其特征在于，所述吹风机还包括：
    数据分析设备，与所述图像截取设备连接，用于接收所述待分析图像和所述待比较图像，基于所述待分析图像和所述待比较图像的整体比较，确定所述待分析图像相对于所述待比较图像的位移矢量，以作为当前位移矢量输出。
  4. 如权利要求3所述的防儿童式智能吹风机，其特征在于，所述吹 风机还包括：
    直流驱动电机，分别与所述滤光片、所述光学镜头、所述图像传感设备和所述数据分析设备连接，用于基于所述位移矢量控制所述滤光片、所述光学镜头、所述图像传感设备一起进行相反方向的移动。
  5. 如权利要求4所述的防儿童式智能吹风机，其特征在于，所述吹风机还包括：
    白平衡处理设备，与所述半球拍摄机构连接，用于接收所述风筒前方图像，对所述风筒前方图像执行白平衡处理，以获得并输出对应的白平衡图像；
    形态学处理设备，包括膨胀处理子设备和腐蚀处理子设备，所述膨胀处理子设备与所述白平衡处理设备连接，用于接收所述白平衡图像，并对所述白平衡图像执行膨胀处理，以获得对应的膨胀处理图像，所述腐蚀处理子设备与所述膨胀处理子设备连接，用于接收所述膨胀处理图像，并对所述膨胀处理图像执行腐蚀处理，以获得对应的腐蚀处理图像；
    像素值统计设备，与所述形态学处理设备连接，用于接收所述腐蚀处理图像，获取所述腐蚀处理图像的各个像素点的各个亮度值，对所述各个亮度值执行均方差计算，将获得的均方差的数值作为参考数据输出；
    碎片提取设备，与所述像素值统计设备连接，用于接收所述腐蚀处理图像和所述参考数据，基于所述参考数据对所述腐蚀处理图像进行均匀式分割，以获得多个分割碎片，其中，所述参考数据越大，对所述腐蚀处理图像进行均匀式分割获得的分割碎片的数量越多；
    噪声分析设备，与所述碎片提取设备连接，用于接收所述多个分割碎片，针对每一个分割碎片，检测所述分割碎片中幅值排名前五的五种噪声类型，基于所述五种噪声类型分别对应的幅值确定所述分割碎片的信噪比，并基于所述分割碎片的信噪比确定对所述分割碎片进行背景分割的阈值大小；
    前景提取设备，与所述噪声分析设备连接，用于针对每一个分割碎片，基于确定的阈值对所述分割碎片执行背景分割处理以获得对应的前景碎片，并将各个分割碎片的各个前景碎片进行拟合，以获得前景检测图像， 并输出所述前景检测图像；
    边缘增强设备，与所述前景提取设备连接，用于接收所述前景检测图像，并对所述前景检测图像执行基于所述前景检测图像的信噪比大小的相应强度的边缘增强处理，以获得相应的自适应增强图像，并输出所述自适应增强图像；
    分块搜索设备，与所述边缘增强设备连接，用于接收所述自适应增强图像，对所述自适应增强图像执行均化分块处理，以获得各个均化分块，对每一个均化分块执行以下操作：获取所述均化分块的各个像素点的亮度值的均值；所述分块搜索设备还用于基于所述各个均化分块的各个均值确定所述自适应增强图像的图像级亮度均值，将均值到所述图像级亮度均值之差的绝对值超限的均化分块作为目标均化分块，并输出所述自适应增强图像中的各个目标均化分块；在所述分块搜索设备中，将所述自适应增强图像中除了各个目标均化分块的多个均化分块作为多个待填充均化分块，并输出所述多个待填充均化分块；
    分块加深设备，与所述分块搜索设备连接，用于对每一个目标均化分块执行边缘加深处理，以获得对应的加深均化分块，还用于将各个加深均化分块和各个待填充均化分块进行拟合，以获得分块拟合图像，并输出所述分块拟合图像；
    轮廓化处理设备，与所述分块加深设备连接，用于接收分块拟合图像，对分块拟合图像执行二值化处理以获得并输出相应的二值化图像，从二值化图像的左上角开始遍历图像的每一个像素，针对每一个像素，如果其周围超过5个点的像素都为黑电平像素或其周围超过5个点的像素都为白电平像素，则将该像素作为内部像素，否则，该像素作为初步轮廓像素；所述轮廓化处理设备将二值化图像中的所有初步轮廓像素连接起来并进行拟合以获得多个拟合封闭曲线，将拟合封闭曲线之外的初步轮廓像素修改为内部像素，将未被修改的初步轮廓像素作为最终轮廓像素；
    儿童识别设备，与所述轮廓化处理设备连接，用于将所有最终轮廓像素连接起来以获得多个封闭区域，确定每一个封闭区域的面积，当存在面积等于预设儿童面积分布范围的封闭区域时，发出儿童识别信号；
    其中，所述儿童识别设备还用于当不存在面积等于预设儿童面积分布 范围的封闭区域时，发出儿童未识别信号；
    其中，所述交流永磁电机还与所述儿童识别设备连接，用于在接收到所述儿童识别信号时，自动关闭，以及在接收到所述儿童未识别信号，保持当前的运行模式。
  6. 如权利要求5所述的防儿童式智能吹风机，其特征在于：
    所述滤光片设置在所述光学镜头的前方，所述图像传感设备设置在所述光学镜头的前方。
  7. 如权利要求6所述的防儿童式智能吹风机，其特征在于：
    在所述数据分析设备中，基于所述待分析图像和所述待比较图像的整体比较，确定所述待分析图像相对于所述待比较图像的位移矢量包括：获取所述待分析图像的各个像素点的各个红色通道值以及所述待比较图像的各个红色通道值，基于所述待分析图像的各个像素点的各个红色通道值以及所述待比较图像的各个红色通道值确定所述待分析图像相对于所述待比较图像的位移矢量。
PCT/CN2019/082521 2018-05-31 2019-04-12 防儿童式智能吹风机 WO2019228084A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/055,858 US20210219694A1 (en) 2018-05-31 2019-04-12 Child-proof smart blow dryer

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810553017.8 2018-05-31
CN201810553017.8A CN109907461A (zh) 2018-05-31 2018-05-31 防儿童式智能吹风机

Publications (1)

Publication Number Publication Date
WO2019228084A1 true WO2019228084A1 (zh) 2019-12-05

Family

ID=66959602

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/082521 WO2019228084A1 (zh) 2018-05-31 2019-04-12 防儿童式智能吹风机

Country Status (3)

Country Link
US (1) US20210219694A1 (zh)
CN (1) CN109907461A (zh)
WO (1) WO2019228084A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110005621B (zh) * 2018-06-13 2020-10-02 宁波瑞卡电器有限公司 离心式防护型吹风机
CN110189340B (zh) * 2019-06-03 2022-01-21 北京达佳互联信息技术有限公司 图像分割方法、装置、电子设备及存储介质
CN111336123A (zh) * 2020-04-03 2020-06-26 广东省无叶科技有限公司 空气放大式吹风机
US11622611B2 (en) * 2020-05-07 2023-04-11 Jacques Depoyian Hair dryer apparatus
CN114235147B (zh) * 2021-12-21 2022-06-21 深圳汝原福永智造科技有限公司 测试装置

Citations (6)

* 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
CN103308517A (zh) * 2013-05-21 2013-09-18 谢绍鹏 中药颜色客观化方法及中药图像获取装置
CN105574866A (zh) * 2015-12-15 2016-05-11 努比亚技术有限公司 一种实现图像处理的方法及装置
CN105590323A (zh) * 2016-02-02 2016-05-18 温州医科大学附属眼视光医院 一种基于眼科裂隙灯照相的滤过泡表面的血管化程度的检测方法
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
CN106845455A (zh) * 2017-03-01 2017-06-13 中国科学院上海高等研究院 基于肤色检测的图像处理方法、系统及服务器

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3832789A (en) * 1972-12-22 1974-09-03 Schick Inc Nestable hair dryer with tensioned positioning
US5101970A (en) * 1990-09-10 1992-04-07 Turner Mike L Personal identification system
US5704135A (en) * 1995-07-10 1998-01-06 Riahi; Sohrab Instant photographic print drying device
US6907678B2 (en) * 1999-11-08 2005-06-21 Hamilton Beach/Proctor-Silex, Inc. Portable electric hair dryer and mount therefor
WO2009076162A2 (en) * 2007-12-05 2009-06-18 Thomas Hanson A hair styling system and apparatus
US8533975B2 (en) * 2010-10-29 2013-09-17 General Electric Company Apparatus and method for refrigeration cycle elevation by modification of cycle start condition
US9970708B2 (en) * 2012-02-01 2018-05-15 Revive Electronics, LLC Methods and apparatuses for drying electronic devices
US11713924B2 (en) * 2012-02-01 2023-08-01 Revive Electronics, LLC Methods and apparatuses for drying electronic devices
EP3568038B1 (en) * 2017-01-12 2023-09-06 Dyson Technology Limited A hand held appliance
CN109907459A (zh) * 2018-05-31 2019-06-21 周超强 多功能手柄式电吹风
CN109919965A (zh) * 2018-06-06 2019-06-21 周超强 风量可调式金属吹风机
US11468490B2 (en) * 2019-01-11 2022-10-11 The Gillette Company Llc Method for providing a customized product recommendation
US10722017B1 (en) * 2020-02-27 2020-07-28 Bonalogic, LLC Smart nozzle for hair dryer
US11553822B2 (en) * 2020-03-19 2023-01-17 Lg Electronics Inc. Drying apparatus and related methods

Patent Citations (6)

* 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
CN103308517A (zh) * 2013-05-21 2013-09-18 谢绍鹏 中药颜色客观化方法及中药图像获取装置
CN105574866A (zh) * 2015-12-15 2016-05-11 努比亚技术有限公司 一种实现图像处理的方法及装置
CN105590323A (zh) * 2016-02-02 2016-05-18 温州医科大学附属眼视光医院 一种基于眼科裂隙灯照相的滤过泡表面的血管化程度的检测方法
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
CN106845455A (zh) * 2017-03-01 2017-06-13 中国科学院上海高等研究院 基于肤色检测的图像处理方法、系统及服务器

Also Published As

Publication number Publication date
CN109907461A (zh) 2019-06-21
US20210219694A1 (en) 2021-07-22

Similar Documents

Publication Publication Date Title
WO2019228084A1 (zh) 防儿童式智能吹风机
WO2021135372A1 (zh) 一种产品缺陷检测方法、装置与系统
CN1932847A (zh) 复杂背景下彩色图像人脸检测的方法
CN107491767B (zh) 端到端的无约束人脸关键点检测方法
Zhou et al. Precise eye localization with improved sdm
WO2019233182A1 (zh) 风量可调式金属吹风机
WO2019233181A1 (zh) 恒温控制型电吹风
CN114067147A (zh) 一种基于局部形状匹配的舰船目标确认方法
Meng et al. Dominant points based hand finger counting for recognition under skin color extraction in hand gesture control system
Yi et al. Long-range hand gesture recognition with joint ssd network
Qazi et al. Automated ball tracking in tennis videos
CN102663713B (zh) 一种基于色彩不变参数的背景减除方法
CN112507767A (zh) 脸部辨识方法及其相关电脑系统
WO2019237819A1 (zh) 基于环境分析的安全型取暖器
WO2022099755A1 (zh) 基于图像识别工作区域的方法、系统及机器人
CN109915887A (zh) 电暖器灭火策略定制机构
CN111192332B (zh) 一种基于烟雾检测的烟机控制方法以及烟机
CN114494712A (zh) 对象提取方法及装置
CN102023163B (zh) 基于dsp的接插件检测系统和检测方法
WO2019242385A1 (zh) 智能化可控型吹风机
WO2019237815A1 (zh) 离心式防护型吹风机
JP7003776B2 (ja) 色決定方法、装置及び電子機器
WO2019228085A1 (zh) 多功能手柄式电吹风
CN113011229A (zh) 基于视觉信息下的选煤厂煤尘爆炸预警方法
CN107918777A (zh) 一种筛除图像不稳定特征点的方法

Legal Events

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

Ref document number: 19811075

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: 19811075

Country of ref document: EP

Kind code of ref document: A1