Shenzhen University

Yongpan Zou

Kaishun Wu

Lu Wang

Jinyong Wu

Jun Xu

Dan Wang

Haibo Lei

Yaqing Wang

Haozhi Dong

Junjun Bao

Hailiang Yang

Disclosed is a few-shot gesture recognition method. The method comprises the following steps: customizing, by a user, gesture categories, and acquiring few samples for each gesture category; inputting the acquired samples into a trained few-shot learning model, extracting a feature vector corresponding to each sample, and synthesizing feature vectors belonging to the same gesture to obtain an average feature vector corresponding to each gesture as a prototype vector; acquiring a corresponding sample for a target gesture implemented by the user, and inputting the sample into the few-shot learning model to obtain a feature vector of the target gesture as a query vector; and calculating similarities between the query vector and prototype vectors of different gestures, and selecting a gesture category corresponding to the prototype vector with the highest similarity as a prediction category of the target gesture.

Few-shot gesture recognition method

A method for user recognition and emotion monitoring based on a smart headset is provided. The smart headset includes an earplug part and a main body, wherein the earplug part is provided with a first microphone and a wearing detection sensor, and a housing of the main body is provided with a signal amplification circuit, a communication module, and a microcontroller. The wearing detection sensor is to detect whether a user wears the smart headset, and the first microphone is to obtain a sound signal in an ear canal. The sound signal is amplified, and then is outputted to the microcontroller. The amplified sound signal is transmitted by the microcontroller to a smart terminal paired with the smart headset to extract a heart sound signal characteristic, and legality of—identity of the user is validated and emotional state of the user is inferred according to the heart sound signal characteristic.

Method for user recognition and emotion monitoring based on smart headset

The invention relates to a limb movement gesture judgment method, which comprises the following steps: a plurality of sensors worn on a moving wrist output induction signals generated by the sensors, and a data packet is formed and sent; the overall state of the multiple induction signals in the received data packet is compared with pre-stored movement type templates, so that the movement type of the moving wrist is determined; standard parameters of the sensor data about the movement type are obtained and separately compared with the multiple received sensor data, whether the movement gesture of the moving limb is normal or not is judged according to the degree of deviation of one or more induction signals from the corresponding standard parameters, and a corresponding prompt message is provided; wherein, the induction signals include a direction acceleration signal, a direction angle acceleration induction signal, and a pressure induction signal. The limb movement gesture judgment method and device have the following beneficial effects of being free of time and place limitations and low in cost.

Limb movement gesture judgment method and device

The present invention provides a screen privacy protection method and system for a mobile terminal device. The screen privacy protection method comprises an environment data acquisition step, a privacy leakage determination step, a determination step and a screen privacy protection step. The present invention has the following advantageous effects: screen privacy can be effectively protected without the addition of hardware, a very good technical effect is achieved, and the screen privacy protection method and system provided by the present invention is worthy of popularization and application.

Screen privacy protection method and system for mobile terminal device

The invention provides a mobile networking method and system for minimizing interference. The mobile networking method comprises the following steps: unmanned aerial vehicles establish connection and communication with ground base stations through a wireless relay method; connection and communication between the unmanned aerial vehicles are established through a wireless self-networking method; multiple unmanned aerial vehicles cooperate to form a cellular network to provide wireless network services for users; the unmanned aerial vehicles receive a received signal strength indicator fed back by an user equipment and measure an angle of arrival of a signal beam from the user equipment; the main lobe of a signal is made to aim at the direction of arrival of service users through a mobile interference alignment method and a beam forming method thus enabling the optimal hovering position of the unmanned aerial vehicle to be obtained.

Mobile networking method and system for minimizing interference

The invention provides an indoor positioning method and system based on a wireless receiver and a camera, belonging to the field of positioning technology. The method in the invention comprises the following steps: a wireless receiver detects a query WIFI signal transmitted by a target device and extracts a MAC address and CSI of the target device from a query WIFI signal; a server captures the MAC address and the CSI of the target device from the wireless receiver, calculates an incident angle of the target device and the wireless receiver and sends a photographing instruction to a camera which photographs an image and uploads the image to the server; the server obtains the distance between the wireless receiver and the target device through the image pixels, and calculates the position information of the target device according to the coordinates of the wireless receiver. The invention realizes the accurate positioning of the target device by using only a wireless receiver and a camera, so that the cost can be controlled and a real-time calculation can be ensured; the combination of the two beneficial effects can help achieve good positioning results.

Growing community of inventors

Guangdong, China

Yongpan Zou