57results about How to "No invasion of privacy" patented technology

The invention discloses an indoor falling detection method, which comprises the following steps that: obtaining the temperature image of the induction area of a thermopile sensor, wherein the temperature image comprises the temperature value of each pixel in the induction area; according to the temperature image, obtaining a foreground image, and calculating the connected domain of the foregroundimage; judging whether the number of pixels in the connected domain is greater than a first preset value or not; if the number of pixels in the connected domain is greater than the first preset value,judging that the foreground image is the image of a human body target, and judging whether both a line number and a row number occupied by the image in the temperature image do not meet a preset ruleor not; if the both the line number and the row number occupied by the image in the temperature image do not meet the preset rule, judging that the human body target is under a lying / crouching gesture, and judging whether the position of the human body target is a preset position or not; and if the position of the human body target is not the preset position, judging that the human body target falls down. By use of the method, the accuracy of indoor falling detection is improved, and meanwhile, the indoor falling detection method is free from wearing, does not violate privacy and is not affected by ambient light. The invention also discloses an indoor falling detection system which has the above beneficial effects.

The invention relates to the technical field of commodity self-service, and particularly relates to a store commodity self-service shopping guide device based on big data. The store commodity self-service shopping guide device comprises a shell, wherein the interior of the shell is divided into an upper chamber and a lower chamber by a horizontally disposed partition plate; a bearing is mounted inthe middle of the bottom surface of the upper chamber; a square sliding rod is vertically mounted in a bearing pedestal; the top end of the sliding rod is vertically inserted into a sliding pipe, andthe cross section of the sliding pipe is square; the top end of the sliding pipe is vertically mounted on the bottom surface of a shopping guide terminal; hydraulic rods are symmetrically mounted onthe two sides of the bottom surface of the interior of the upper chamber; the hydraulic rods are symmetrically arranged, and the top ends of the hydraulic rods are connected to the bottom surface of the shopping guide terminal through a guide structure; the bottom end of the sliding rod extends vertically into the lower chamber; and a speed reducer is mounted in the middle of the bottom surface ofthe lower chamber. The height of the shopping guide terminal is adjusted through the hydraulic rods, and the height of a user is matched during use; and a guide wheel and an annular guide groove arematched with each other, so that the lifting of the shopping guide terminal is not influenced, and the rotation of the shopping guide terminal is not affected.

The invention discloses a flexible intelligent sitting posture monitoring system based on hip pressure. The system comprises a piezoresistive film sensor, an interface adapter plate, a data acquisition plate and a data processing device, and the piezoresistive film sensor comprises a plurality of force sensitive point units and is used for sensing sitting posture pressure of a user; the data acquisition board acquires pressure distribution data sensed by the piezoresistive film sensor through the interface adapter board and transmits the pressure distribution data to the data processing equipment; and the data processing equipment processes the received pressure distribution data, and identifies the sitting posture category of the user by using a trained deep learning model. The sitting posture recognition device has the advantages of being accurate in sitting posture recognition, small in size, high in portability, convenient to use, low in cost and not limited by territory environments.

The invention provides a prison cell monitoring device, system and method. The prison cell monitoring device includes: one or more nanogenerators and a central processing circuit; the signal output end of the nanogenerator is connected to the central processing circuit; when the nanogenerator is subjected to instantaneous pressure, the signal output terminal outputs the first electrical signal to the central Processing circuit, when the nanogenerator is subjected to variable pressure, the signal output terminal outputs a second electrical signal to the central processing circuit, and when the variable pressure received by the nanogenerator disappears, the signal output terminal outputs a third electrical signal to the central processing circuit , the central processing circuit sends out an alarm signal according to whether the first electrical signal, the second electrical signal and / or the third electrical signal is received. The present invention utilizes the characteristics of the forward and reverse voltages output by the nanometer generator to timely alarm and remind the abnormality of the criminal on the bed, so as to prevent problems before they happen and achieve the purpose of monitoring the criminals.

The present invention relates to a multi-target breathing and heart rate monitoring method and system based on millimeter-wave radar. The millimeter-wave radar module performs non-contact heart rate and respiration rate detection, which avoids cumbersome contact monitoring procedures and does not offend the detected ones. user's privacy. Compared with the non-contact detection technology in the prior art, the present invention improves the detection accuracy and greatly enhances the reliability of the measurement. The present invention monitors and analyzes the breathing and heart rate data of the monitoring object in real time through the vital signs monitoring platform, which can prevent the monitoring object from sudden unexpected diseases, or provide timely alarms in the event of an emergency; medical staff can timely monitor the vital signs through the vital signs monitoring platform Master the vital signs data of the monitoring object, timely evaluate the physical condition of the monitoring object and give professional opinions and suggestions; the family members of the monitoring object can obtain the health report of the monitoring object through the vital signs monitoring platform, and follow the professional guidance. Nursing the monitoring objects.

The invention discloses a non-contact user identity authentication method based on RFID and a convolutional neural network, and the method comprises the steps: simulating the unlocking of a sudoku of a mobile phone, deploying an RFID tag matrix, collecting the phase information during the movement of a hand, and achieving the identity authentication of a user through the convolutional neural network. The method comprises the following implementation steps of: 1, acquiring phase information of an action for identity authentication; 2, preprocessing the acquired phase information; 3, extracting starting point information of each action sample from the preprocessed phase information; 4, making the obtained phase information into a data set, and training the data by adopting a deep learning convolutional neural network to obtain a convolutional neural network model for authentication; 5, identifying the action of the user by using the trained model when the identity of the user is authenticated; and 6, obtaining an authentication result, and judging whether authentication succeeds or not. According to the invention, the invention employs the CNN-based convolutional neural network to extract the features in the phase, carries out the motion recognition, carries out the identity authentication, and is better in accuracy, safety and robustness.

The invention discloses a face generation privacy protection method based on hierarchical k anonymous identity replacement, which comprises the following steps: firstly, preprocessing a face image data set, then constructing a hierarchical k anonymous generative adversarial network structure, and constructing a hierarchical k anonymous objective function; constructing a face replacement generative adversarial network structure, and constructing a target function of face replacement; and finally training and testing by using a public data set to obtain a trained hierarchical k anonymous generative adversarial network and a face replacement generative adversarial network. The replaced target face is also generated through the network, so that privacy of others cannot be invaded, and compared with a conventional mosaic shielding method, the method is more effective and more friendly visually. Experimental results obviously prove the high efficiency and practicability of the method, and the privacy protection of the figure image is more efficient and beautiful.

There is provided an image display system for displaying a state of an examinee in a visible state. The examinee carries a mobile terminal (10). The mobile terminal includes a biological sensor (11) for measuring biological information on the examinee and an environment information sensor (12) for measuring environment information surrounding the examinee. The information measured is transmitted to an image display device (20) connected by a network (100). The image display device (20) has a CPU (29) for judging the state of the examinee from the biological information and the environment information, generating an image expressing the state of the examinee, and displaying it on a display section (23).

The invention discloses a method for automatically recognizing calligraphy gestures based on Wi-Fi signals. The method uses Wi-Fi signals to obtain calligraphy character gesture data, sequentially performs feature extraction and stroke segmentation on the data, and uses learning algorithms to reconstruct data. A method of comparison against a standard database to identify a certain written font. The method of the present invention utilizes existing commercial equipment, does not need to modify hardware, and does not require additional deployment of equipment for users, and wireless signals are easy to obtain, and ordinary smart mobile devices can be used to turn on hotspots to transmit wireless signals; The local area network analyzes the CSI value of the physical layer in a non-intrusive and device-independent manner, without changing the wireless signal communication protocol, and has broad application prospects.

The invention relates to a sleep monitoring method based on internet of things, the method comprises the steps of detecting whether or not the custodian has entered the monitoring area; detecting whether or not the custodian is lying in bed, gathering information of gravity acceleration and parameters of physiological characteristics; sending the information of gravity acceleration and the parameters of physiological characteristics to an external intelligent terminal; judging whether or not the custodian is in a motionless state using the intelligent terminal, according to the received information of gravity acceleration; judging whether or not the custodian is in a sleeping state using the intelligent terminal, according to the parameters of physiological characteristics; gathering the nightmare sounds or the state information of somniloquy and information of sleeping environment parameters; attaching time information on the information of gravity acceleration, the parameters of physiological characteristics, the nightmare sounds or the state information of somniloquy and the information of sleeping environment parameters using the intelligent terminal, and sending the information to a background server. The method can capture the sleeping quality and the physiological characteristics of the custodian in time without violating the privacy space of the custodian.

The invention discloses a photographing device detection method. The method comprises the following steps: performing data capture in a WiFi sniffing mode to obtain data; analyzing the obtained data according to a preset suspected standard to obtain suspected data of a shooting device; analyzing the suspected data of the shooting device according to a preset confirmation condition to determine whether the suspected data meets the confirmation condition or not; if the confirmation condition is met, determining that the suspected data of the shooting device meeting the confirmation condition isdata corresponding to the shooting device. The wireless shooting device in the current environment can be accurately found out in a mode of preliminarily screening suspected data and then further confirming the suspected data.

The invention relates to a personnel-monitoring system and a method. The personnel-monitoring system and the method record shifting signals of the objects at pre-calculated positions in a monitoring region within pre-set time and calculate personnel dynamic habits in the monitoring region. A habitual nature pattern or a non habitual nature pattern is automatically chosen to judge any shifting behaviors of objects in the monitoring system by being coordinated with the in-and-out conditions of the personnel. If abnormal conditions happen, regulators are informed in real time, so that the threat of the health or life security of the personnel in the monitoring region can be prevented through lower labor, equipment cost, relatively positive and reliable means.

The invention discloses a service identification method applicable to a broadband access network. Multiple data frames of different servers of the broadband access network are screened, so that data frames corresponding to TCP and UDP protocols are obtained; service flow division of the data frames is carried out according to quintuple data; service flow flow-pool groups are established; various service flow flow-pool groups each comprise an uplink service flow flow-pool and a downlink service flow flow-pool; for each service flow flow-pool, a service type label is added; then, an integrated convolutional neural network is constructed; the integrated convolutional neural network comprises an uplink one-dimensional convolutional neural network, a downlink one-dimensional convolutional neural network, an interactive one-dimensional convolutional neural network and an arbitrament module; the three one-dimensional convolutional neural networks are respectively trained by adopting the service flow flow-pool groups; when the broadband access network is practically operated, the captured data frames are standardized into service flow data packets; and the service flow data packets are input into the convolutional neural networks, so that a service identification result is obtained. According to the service identification method applicable to the broadband access network disclosed by the invention, due to introduction of a convolutional neural network algorithm in deep learning, fine-grained and high-precision service identification can be realized.