An intelligent control system applied to villas

Abstract

The present invention discloses an intelligent control system for a villa, comprising a camera module, a recognition module, and an intelligent control module. The camera module is used to capture facial images of residents entering the villa; the recognition module is used to identify the resident corresponding to the facial image; and the intelligent control module is used to control household appliances based on the identified resident. The present invention determines the identity of the resident entering the villa using the facial image and then controls the intelligent household appliances based on the resident's pre-set policies. This significantly improves the level of intelligent control over the villa's household appliances and increases the efficiency of control over the villa's intelligent household appliances, eliminating the need for residents to adjust numerous household appliances one by one.

Description

Technical Field

[0001] The present invention relates to the field of control, and in particular to an intelligent control system applied to a villa. Background Art

[0002] Since villas have a large space area, there are correspondingly more home appliances. In the existing technology, when the home appliances in the villa need to be controlled, the home appliances are generally adjusted one by one manually after the villa residents return to the villa. This method is not only cumbersome, but also cannot be adaptively adjusted to the home appliances according to the different returning residents, and the degree of intelligence is relatively low. Summary of the Invention

[0003] The purpose of the present invention is to disclose an intelligent control system applied to a villa, so as to solve the problem of how to intelligently control household appliances in the villa.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] An intelligent control system applied to a villa, comprising a shooting module, a recognition module and an intelligent control module;

[0006] The shooting module is used to obtain facial images of residents entering the villa;

[0007] The recognition module is used to identify the resident corresponding to the facial image;

[0008] The intelligent control module is used to control home appliances based on the identified residents.

[0009] Preferably, the shooting module includes a detection unit and a shooting unit;

[0010] The detection unit is used to detect whether there are residents entering the shooting area in the villa;

[0011] The shooting unit is used to obtain a facial image of a resident when a resident enters a shooting area in the villa.

[0012] Preferably, the monitoring unit includes a human proximity sensor, which is arranged in the shooting area and is used to detect whether there is a resident entering the shooting area.

[0013] Preferably, the shooting unit includes a camera subunit and a control subunit;

[0014] The camera subunit is used to obtain facial images of residents;

[0015] The control subunit is used to determine whether the facial image can be sent to the recognition module, and if so, send the facial image to the recognition module;

[0016] If not, the camera subunit is controlled to obtain the facial image of the resident again.

[0017] Preferably, the recognition module includes a feature matching unit and a feature storage unit;

[0018] The feature storage unit is used to store feature data of the facial image of the resident taken in advance;

[0019] The feature matching unit is used to match the feature data of the facial image sent by the shooting module with each feature data stored in the feature storage unit to determine the resident corresponding to the facial image.

[0020] Preferably, the feature matching unit includes a feature extraction subunit and a matching subunit;

[0021] The feature extraction subunit is used to obtain feature data of the facial image sent by the shooting module;

[0022] The matching subunit is used to match the feature data of the facial image sent by the shooting module with each feature data stored in the feature storage unit to determine the resident corresponding to the facial image.

[0023] Preferably, the intelligent control module includes a customization unit, a control strategy storage unit and a control unit;

[0024] Custom units are used for residents to set control strategies;

[0025] The control strategy storage unit is used to store the control strategy and the residents corresponding to the control strategy;

[0026] The control unit is used to obtain the corresponding control strategy from the control strategy storage unit according to the resident identified by the identification module, and control the home appliances based on the control strategy.

[0027] Preferably, the control strategy includes the name and control parameters of the home appliance.

[0028] The present invention can achieve the following effects:

[0029] The present invention determines the identity of the resident entering the villa through facial images, and then controls the smart home devices based on the strategy pre-set by the resident, which greatly improves the level of intelligent control of the home appliances in the villa and improves the efficiency of controlling the smart home appliances in the villa. The resident does not need to adjust numerous home appliances one by one every time. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0031] Figure 1 This is a diagram showing an embodiment of an intelligent control system applied to a villa according to the present invention.

[0032] Figure 2 This is a diagram of an embodiment of the present invention for obtaining feature data of a facial image sent by a shooting module. DETAILED DESCRIPTION

[0033] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0034] like Figure 1 In one embodiment shown, the present invention provides an intelligent control system for a villa, comprising a shooting module, a recognition module and an intelligent control module;

[0035] The shooting module is used to obtain facial images of residents entering the villa;

[0036] The recognition module is used to identify the resident corresponding to the facial image;

[0037] The intelligent control module is used to control home appliances based on the identified residents.

[0038] Preferably, the shooting module includes a detection unit and a shooting unit;

[0039] The detection unit is used to detect whether there are residents entering the shooting area in the villa;

[0040] The shooting unit is used to obtain a facial image of a resident when a resident enters a shooting area in the villa.

[0041] Specifically, the shooting area may be a designated space area near the gate of the villa.

[0042] Specifically, household appliances include lights, curtains, air conditioners, aromatherapy machines, humidifiers, etc.

[0043] Preferably, the monitoring unit includes a human proximity sensor, which is arranged in the shooting area and is used to detect whether there is a resident entering the shooting area.

[0044] In addition to human proximity sensors, it can also be an infrared detection sensor, an infrared ranging sensor, or other device that can detect the entry of a person.

[0045] Preferably, the shooting unit includes a camera subunit and a control subunit;

[0046] The camera subunit is used to obtain facial images of residents;

[0047] The control subunit is used to determine whether the facial image can be sent to the recognition module, and if so, send the facial image to the recognition module;

[0048] If not, the camera subunit is controlled to obtain the facial image of the resident again.

[0049] In the above embodiment, the facial image obtained by the camera subunit is not directly transmitted to the recognition module, but is judged by the control subunit before deciding whether to transmit it to the recognition module. This setting can improve the quality of the facial image transmitted to the recognition module.

[0050] Preferably, the determining whether the facial image can be sent to the recognition module includes:

[0051] The following formula is used to obtain the judgment factor of the facial image:

[0052]

[0053] Among them, judgf represents the judgment factor, w1, w2, and w3 represent weights, fcset represents the set of all sub-images after the face image is divided into nfcset sub-images of the same area, and avel i represents the median value of the brightness component of all pixels in sub-image i, stdavel represents the set median value variance contrast value, N1 represents the number of foreground pixels in the face image, N2 represents the number of background pixels in the face image, frtd represents the mean of the gradient values of all foreground pixels in the face image, bktd represents the mean of the gradient values of all background pixels in the face image; std represents the set mean contrast value of the gradient values;

[0054] If the judgment factor is greater than the set factor threshold, it is determined that the facial image can be sent to the recognition module;

[0055] If the judgment factor is less than or equal to the set factor threshold, it is determined that the facial image cannot be sent to the recognition module.

[0056] The calculation and judgment process primarily considers the number of pixels, the variance of the median values of the sub-image brightness components, and the mean gradient values. The larger the ratio between N1 and N2, the smaller the variance of the median values of the sub-image brightness components, and the greater the difference in the mean gradient values between foreground and background pixels, the larger the judgment factor, indicating more effective information in the facial image, a more uniform brightness distribution, and a greater difference between the background and foreground, indicating higher quality. By considering these multiple factors, the probability of selecting high-quality facial images can be increased.

[0057] Preferably, the recognition module includes a feature matching unit and a feature storage unit;

[0058] The feature storage unit is used to store feature data of the facial image of the resident taken in advance;

[0059] The feature matching unit is used to match the feature data of the facial image sent by the shooting module with each feature data stored in the feature storage unit to determine the resident corresponding to the facial image.

[0060] Specifically, during the matching process, the similarity between the two matching parties is mainly calculated. When the similarity meets the requirements, it means that the matching is successful.

[0061] Preferably, the feature matching unit includes a feature extraction subunit and a matching subunit;

[0062] The feature extraction subunit is used to obtain feature data of the facial image sent by the shooting module;

[0063] The matching subunit is used to match the feature data of the facial image sent by the shooting module with each feature data stored in the feature storage unit to determine the resident corresponding to the facial image.

[0064] Preferably, if Figure 2 As shown, the step of obtaining the feature data of the facial image sent by the shooting module includes:

[0065] Use an image segmentation algorithm to perform image segmentation processing on the facial image to obtain a set U of foreground pixels;

[0066] Perform dilation and erosion operations on the foreground image composed of pixels in set U to obtain a filled image.

[0067] Get the brightness component image L corresponding to the filled image in the Lab color space;

[0068] Perform edge recognition processing on L to obtain a set S of edge pixels contained in L;

[0069] Perform edge enhancement on the filled image based on the set S to obtain the enhanced image inhcImg;

[0070] Perform adaptive filtering on the filled image to obtain a filtered image K;

[0071] Fuse inhcImg and K to obtain the fused image M;

[0072] Perform image segmentation processing on the fused image M to obtain the target image P;

[0073] Get the feature data in the target image P.

[0074] In the prior art, grayscale conversion, noise reduction and other operations are generally performed before the image is segmented. However, this also results in a large number of pixels in the background area being involved in the calculation during the previous processing, which will undoubtedly affect the efficiency of obtaining feature data, thereby affecting the timeliness of the present invention's adjustment of home appliances.

[0075] Therefore, the present invention first performs image segmentation, then performs dilation and erosion operations to remove holes and obtain a rough foreground area. Then, after performing operations such as enhancement and filtering on the foreground area, the image is segmented again to obtain the accurate foreground area, i.e., the target image. This approach ensures the effectiveness of image preprocessing while taking into account computational efficiency.

[0076] In the process of image enhancement, the present invention first obtains edge pixel points in L, and then performs edge enhancement processing in the filled image, which can map the edge information in L to the enhanced image, thereby highlighting the edge information of the image and improving the accuracy of feature data acquisition.

[0077] At the same time, the present invention also fuses inhcImg and K to further enhance the edge features in the fused image M.

[0078] Preferably, the step of performing image segmentation processing on the facial image using an image segmentation algorithm to obtain a set U of foreground pixels includes:

[0079] The OTSU algorithm is used to segment the facial image and obtain a set U of foreground pixels.

[0080] Preferably, performing edge enhancement processing on the filled image based on the set S to obtain the enhanced image inhcImg includes:

[0081] Get the set S' of pixels corresponding to the pixels in the set S in the filled image.

[0082] Use the following formula to perform edge enhancement on the pixels in the set S':

[0083] inhcImg(pixs)=[Φ×tsImg(pixs)+(1-Φ)×L(pixs)]×Θ

[0084] Among them, inhcImg(pixs) represents the pixel value of pixs in inhcImg after edge enhancement processing is performed on the pixel point pixs in the set S', Φ represents the scale parameter, tsImg(pixs) represents the pixel value of the pixel point pixs in the filling image tsImg, L(pixs) represents the pixel value of the corresponding pixel point of pixs in the brightness component image L, and Θ represents the set enhancement coefficient.

[0085] Specifically, when performing edge enhancement processing, in addition to considering the pixel values in inhcImg, the pixel values in the brightness component image L are also considered, and edge enhancement is achieved through weighted summation of the two pixel values.

[0086] Preferably, the step of performing adaptive filtering on the filled image to obtain the filtered image K comprises:

[0087] Store the pixel points in the filled image except the set S' into the set T;

[0088] In the filled image, the pixel points in the set T are filtered to obtain a filtered image K.

[0089] In the above embodiment, the present invention performs filtering processing on non-edge pixels in the fill image, which can avoid reducing the difference between edge pixels and surrounding pixels after filtering the edge pixels, thereby better retaining edge information while achieving filtering.

[0090] Preferably, for pixel point t in set T, filtering is performed in the following manner:

[0091] Use the Gaussian filter algorithm to filter the pixel point t to obtain the pixel point t';

[0092] Determine whether the pixel t' meets the filtering requirements. If not, use the following formula to filter the pixel t':

[0093]

[0094] Where K(t') represents the pixel value of pixel t' in the filtered image K, blk(t') represents the set of pixels in the W×W neighborhood of pixel t', tsImg(v) represents the pixel value of pixel v in the filled image tsImg,

[0095] Z1(v) represents the pixel value weight, Z2(v) represents the similarity weight, tsImg(t') represents the pixel value of pixel t' in the filled image tsImg, Γ represents the first control parameter, shc(t',v) represents the Euclidean distance between pixel v and pixel t', and λ represents the second control parameter.

[0096] During filtering, the present invention first performs filtering using a Gaussian filter, which has a relatively high computational efficiency. If the filtering result does not meet the requirements, a secondary filtering process is performed using an algorithm that is more accurate but takes longer than Gaussian filtering. This effectively achieves a good balance between filtering efficiency and filtering accuracy. The influence of surrounding pixels is taken into account, and a comprehensive consideration of both pixel values and similarity is made to improve the accuracy of the filtering results.

[0097] Preferably, determining whether the pixel point t' meets the filtering requirements includes:

[0098] Calculate the variance of the gradient value between pixel t' and the pixel in blk(t'). If the variance is greater than the set variance threshold, it means that pixel t' does not meet the filtering requirements. If the variance is less than the set variance threshold, it means that pixel t' meets the filtering requirements.

[0099] Preferably, performing image segmentation processing on the fused image M to obtain the target image P includes:

[0100] The fusion image M is segmented using an image segmentation algorithm based on a genetic algorithm to obtain the target image P.

[0101] Preferably, the intelligent control module includes a customization unit, a control strategy storage unit and a control unit;

[0102] Custom units are used for residents to set control strategies;

[0103] The control strategy storage unit is used to store the control strategy and the residents corresponding to the control strategy;

[0104] The control unit is used to obtain the corresponding control strategy from the control strategy storage unit according to the resident identified by the identification module, and control the home appliances based on the control strategy.

[0105] Specifically, control strategies include individual strategies and multi-person strategies;

[0106] The personal strategy means that when there is only one resident entering the villa, the home appliances in the villa will be controlled according to the control strategy set by the resident. The multi-person strategy means that if the number of residents is greater than or equal to 2, the home appliances in the villa will be controlled according to the corresponding multi-person strategy.

[0107] For example, when the residents entering include both older residents and young users, since the elderly are not suitable for air conditioning that is too cold, the control unit will adjust the air conditioning temperature according to the corresponding temperature in the multi-person strategy.

[0108] Preferably, the control strategy includes the name and control parameters of the home appliance.

[0109] For example, the name of the home device is living room air conditioner, and the control parameter is 26 degrees Celsius.

[0110] The present invention can achieve the following effects:

[0111] The present invention determines the identity of the resident entering the villa through facial images, and then controls the smart home devices based on the strategy pre-set by the resident, which greatly improves the level of intelligent control of the home appliances in the villa and improves the efficiency of controlling the smart home appliances in the villa. The resident does not need to adjust numerous home appliances one by one every time.

[0112] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0113] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent control system applied to a villa, characterized in that: Including shooting module, recognition module and intelligent control module; The shooting module is used to obtain facial images of residents entering the villa; The recognition module is used to identify the resident corresponding to the facial image; The intelligent control module is used to control home devices based on the identified residents; The shooting module includes a detection unit and a shooting unit; The detection unit is used to detect whether there are residents entering the shooting area in the villa; The shooting unit is used to obtain a facial image of a resident when a resident enters the shooting area in the villa; The shooting unit includes a camera subunit and a control subunit; The camera subunit is used to obtain facial images of residents; The control subunit is used to determine whether the facial image can be sent to the recognition module, and if so, send the facial image to the recognition module; If not, the camera subunit is controlled to obtain the resident's facial image again; The determining whether the facial image can be sent to the recognition module includes: The following formula is used to obtain the judgment factor of the facial image: Among them, judgf represents the judgment factor, w1, w2, and w3 represent weights, fcset represents the set of all sub-images after the face image is divided into nfcset sub-images of the same area, and avel i represents the median value of the brightness component of all pixels in sub-image i, stdavel represents the set median value variance contrast value, N1 represents the number of foreground pixels in the face image, N2 represents the number of background pixels in the face image, frtd represents the mean of the gradient values of all foreground pixels in the face image, bktd represents the mean of the gradient values of all background pixels in the face image; std represents the set mean contrast value of the gradient values; If the judgment factor is greater than the set factor threshold, it is determined that the facial image can be sent to the recognition module; If the judgment factor is less than or equal to the set factor threshold, it is determined that the facial image cannot be sent to the recognition module.

2. The intelligent control system for villas according to claim 1, characterized in that: The detection unit includes a human proximity sensor, which is arranged in the shooting area and is used to detect whether there is a resident entering the shooting area.

3. The intelligent control system for villas according to claim 1, characterized in that: The recognition module includes a feature matching unit and a feature storage unit; The feature storage unit is used to store feature data of the facial image of the resident taken in advance; The feature matching unit is used to match the feature data of the facial image sent by the shooting module with each feature data stored in the feature storage unit to determine the resident corresponding to the facial image.

4. The intelligent control system for villas according to claim 3, characterized in that: The feature matching unit includes a feature extraction subunit and a matching subunit; The feature extraction subunit is used to obtain feature data of the facial image sent by the shooting module; The matching subunit is used to match the feature data of the facial image sent by the shooting module with each feature data stored in the feature storage unit to determine the resident corresponding to the facial image.

5. The intelligent control system for villas according to claim 1, characterized in that: The intelligent control module includes a customization unit, a control strategy storage unit and a control unit; Custom units are used for residents to set control strategies; The control strategy storage unit is used to store the control strategy and the residents corresponding to the control strategy; The control unit is used to obtain the corresponding control strategy from the control strategy storage unit according to the resident identified by the identification module, and control the home appliances based on the control strategy.

6. The intelligent control system for villas according to claim 5, characterized in that: The control strategy includes the name and control parameters of the home appliance.

Images