CN104914991A - Wearable intelligent bracelet gesture recognition method and device - Google Patents

Abstract

The invention relates to a wearable intelligent bracelet gesture recognition device. A control method includes the steps that a gesture instruction sending module sends a gesture needing judging to a microprocessor; the microprocessor drives a position sensor to collect data through a DMP library and judges whether the gesture needs recognizing according to the collected data. The wearable intelligent bracelet gesture recognition device comprises the position sensor, the micro processor and the gesture instruction sending module, wherein the position sensor is an MP9150 module, the microprocessor is an STM32F103 single-chip microcomputer, the gesture instruction sending module comprises a mobile phone app for sending instructions, and instructions are transmitted through a Bluetooth module. When in work, the gesture instruction sending module sends a gesture needing judging to the microprocessor, and the microprocessor drives the position sensor to collect data through the DMP library and judges whether the gesture needs recognizing according to the collected data. The wearable intelligent bracelet gesture recognition device is simple, saves cost and is high in gesture recognition rate.

Description

Wearable smart bracelet gesture recognition method and device thereof

technical field

The invention belongs to the technical field of smart wearable bracelets, and in particular relates to a gesture recognition method and a device thereof for a wearable smart bracelet.

Background technique

Due to the many movements of the human hand, the gestures are complex, and different movements sometimes overlap, making gesture recognition one of the difficult problems in current research. At present, there are many methods of gesture recognition. For example, the Myo bracelet uses bioelectricity to judge gestures by detecting the potential of muscles. Another example is the gesture judgment method described in the patent No. CN 103885645, which uses an image sensing device to recognize gestures. These recognition methods are relatively complicated, and the accuracy of gesture recognition is not high. If various gestures are recognized at the same time during gesture recognition, the interference between different gestures is very large, resulting in a low recognition rate.

At present, there are also some methods for recognizing gestures with MPU6050 (such as patent No. CN 103593055), but only MPU6050 is used to collect raw data, and Kalman filter algorithm is mostly used when data is processed, and this algorithm has great influence on the performance of microprocessor. Very demanding, demanding speed. In many cases, two microprocessors must be used to realize gesture recognition, one for data processing and one for gesture recognition, which greatly increases the cost of gesture recognition and the complexity of hardware circuits.

Contents of the invention

In order to solve the above problems, the present invention provides a gesture recognition method and device thereof for a wearable smart bracelet.

A wearable smart bracelet gesture recognition device, including a position sensor, a microprocessor, and a gesture command sending module; the position sensor is an MP9150 module, and the MPU9150 module integrates a three-axis gyroscope, a three-axis accelerometer, and a three-axis Magnetometer, an expandable digital motion processor DMP and an I2C interface; The microprocessor is STM32F103, and the MPU9150 module is electrically connected with the microprocessor through the I2C interface; the gesture instruction sending module includes a mobile phone APP, which is electrically connected to the microprocessor through a Bluetooth module; the Bluetooth module shown is CC2540, which is electrically connected to the microprocessor through a serial port.

The above-mentioned wearable smart bracelet gesture recognition method sends the gesture that needs to be judged to the microprocessor through the gesture instruction sending module, and the microprocessor drives the position sensor to collect data through the DMP library and the microprocessor judges whether it needs to be recognized through the collected data. gesture.

Preferably, the gesture recognition method includes the following steps:

a STM32 initialization;

b MPU9150 initialization;

c STM32 writes the DMP library to the MPU9150;

d STM32 reads the acceleration, angular velocity, and quaternion to obtain the Euler angle;

e judge whether the gesture instruction sending module sends an instruction, if so, then proceed to the next step, if not, then return to the previous step;

f calls the corresponding gesture function to judge gesture recognition;

g Whether the gesture read is consistent with the gesture to be recognized, if so, proceed to the next step, if not, return to the previous step;

h STM32 sends corresponding information to the gesture command sending module to prompt that the gesture recognition is correct.

Preferably, the micro-opening of the MPU9150 internal DMP includes the following steps:

a sensor setting;

b Whether the sensor setting is successful, if so, proceed to the next step, if not, the program enters an endless loop;

c Fifo setting and judging whether it is successful, if so, proceed to the next step, if not, the program enters an infinite loop;

d DMP sampling rate setting;

e Whether the sampling rate setting is successful, if so, proceed to the next step, if not, the program enters an endless loop;

f Turn on the DMP function;

g whether the DMP function is opened successfully, if so, proceed to the next step, if not, the program enters an infinite loop;

h initial direction setting deviation;

i Whether the initialization direction setting deviation is successful, if so, proceed to the next step, if not, the program enters an endless loop;

j DMP enabled;

k Whether the DMP enable is successful, if so, proceed to the next step, if not, the program enters an infinite loop;

l Fifo speed setting;

m Whether the Fifo speed setting is successful, if so, proceed to the next step, if not, the program enters an infinite loop;

n DMP self-test;

o Whether the DMP self-test is successful, if so, go to the next step, if not, the program enters an endless loop;

p Enable DMP successfully.

Preferably, the process of judging whether it is a gesture that needs to be recognized includes the following steps:

a read MPU9150 data;

b Whether the initial position of the MPU9150 is within the range of the set initial position, if yes, proceed to the next step, if not, return to the previous step;

c Write down the Euler angle, acceleration and angular velocity of the current position;

d Delay for a short period of time;

e read the MPU9150 data again;

f Compare the data collected twice to judge whether the gesture is correct, if so, proceed to the next step, if not, return to step a;

g Gesture recognition ends.

The wearable smart bracelet gesture recognition method and its device provided by the present invention, the data collected by driving the MPU9150 through the DMP library is already processed data, and the acceleration, angular velocity, and Euler angle can be directly obtained, and no complicated Karl The Mann filter algorithm reduces the burden on the microprocessor, no longer needs to use two microprocessors, and reduces the cost. Pre-writing the actions that need to be judged in the microprocessor can reduce the complexity of gesture recognition and improve the gesture recognition rate.

Description of drawings

The accompanying drawings described here are used to provide a further understanding of the present invention, constitute a part of the application, and do not constitute an improper limitation of the present invention. In the accompanying drawings:

Fig. 1 is the system schematic diagram of the embodiment of the present invention;

Fig. 2 is the overall working flowchart of gesture recognition method;

Figure 3 is a flowchart of opening the internal DMP of the MPU9150;

Fig. 4 is a flowchart of gesture recognition.

Detailed ways

The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, where the schematic embodiments and descriptions of the present invention are used to explain the present invention, but not to limit the present invention.

As shown in Figure 1, a wearable smart bracelet gesture recognition device includes a position sensor, a microprocessor and a gesture command sending module; the position sensor is an MP9150 module, and the MPU9150 module integrates a three-axis gyroscope, three Axis accelerometer, three-axis magnetometer, an expandable digital motion processor DMP and an I2C interface; the microprocessor is STM32F103, and the MPU9150 module is electrically connected to the microprocessor through the I2C interface; the gesture The instruction sending module includes a mobile phone APP, which is electrically connected to the microprocessor through a bluetooth module; the bluetooth module shown is CC2540, which is electrically connected to the microprocessor through a serial port.

The above-mentioned wearable smart bracelet gesture recognition method sends the gesture that needs to be judged to the microprocessor through the gesture instruction sending module, and the microprocessor drives the position sensor to collect data through the DMP library and the microprocessor judges whether it needs to be recognized through the collected data. gesture.

Wherein, as shown in Figure 2, the gesture recognition method includes the following steps:

a STM32 initialization;

b MPU9150 initialization;

c STM32 writes the DMP library to the MPU9150;

d STM32 reads the acceleration, angular velocity, and quaternion to obtain the Euler angle;

e judge whether the gesture instruction sending module sends an instruction, if so, then proceed to the next step, if not, then return to the previous step;

f calls the corresponding gesture function to judge gesture recognition;

g Whether the gesture read is consistent with the gesture to be recognized, if so, proceed to the next step, if not, return to the previous step;

h STM32 sends corresponding information to the gesture command sending module to prompt that the gesture recognition is correct.

Wherein, as shown in Figure 3, the described opening MPU9150 internal DMP includes the following steps:

a sensor setting;

b Whether the sensor setting is successful, if so, proceed to the next step, if not, the program enters an endless loop;

c Fifo setting and judging whether it is successful, if so, proceed to the next step, if not, the program enters an infinite loop;

d DMP sampling rate setting;

e Whether the sampling rate setting is successful, if so, proceed to the next step, if not, the program enters an endless loop;

f Turn on the DMP function;

g Whether the DMP function is enabled successfully, if so, proceed to the next step, if not, the program enters an infinite loop;

h initial direction setting deviation;

i Whether the initialization direction setting deviation is successful, if so, proceed to the next step, if not, the program enters an endless loop;

j DMP enabled;

k Whether the DMP enable is successful, if so, proceed to the next step, if not, the program enters an infinite loop;

l Fifo speed setting;

m Whether the Fifo speed setting is successful, if so, proceed to the next step, if not, the program enters an infinite loop;

n DMP self-test;

o Whether the DMP self-test is successful, if so, proceed to the next step, if not, the program enters an endless loop;

p Enable DMP successfully.

Wherein, as shown in Figure 4, the process of determining whether it is a gesture that needs to be recognized includes the following steps:

a read MPU9150 data;

b Whether the initial position of the MPU9150 is within the range of the set initial position, if yes, proceed to the next step, if not, return to the previous step;

c Write down the Euler angle, acceleration and angular velocity of the current position;

d Delay for a short period of time;

e read the MPU9150 data again;

f Compare the data collected twice to judge whether the gesture is correct, if so, proceed to the next step, if not, return to step a;

g Gesture recognition ends.

The technical solutions provided by the embodiments of the present invention have been introduced in detail above, and the principles and implementation modes of the embodiments of the present invention have been explained by using specific examples in this paper. The descriptions of the above embodiments are only applicable to help understand the embodiments of the present invention At the same time, for those of ordinary skill in the art, according to the embodiment of the present invention, there will be changes in the specific implementation and application scope. In summary, the content of this specification should not be construed as limiting the present invention.

Claims (5)

1. A wearable smart bracelet gesture recognition device, characterized in that: Including position sensor, microprocessor and gesture instruction sending module; The position sensor is an MP9150 module, and the MPU9150 module integrates a three-axis gyroscope, a three-axis accelerometer, a three-axis magnetometer, an expandable digital motion processor DMP and an I2C interface; The microprocessor is STM32F103, and the MPU9150 module is electrically connected with the microprocessor through an I2C interface; The gesture command sending module is electrically connected to the microprocessor through a bluetooth module; The bluetooth module is CC2540, which is electrically connected with the microprocessor through a serial port. 2. A wearable intelligent wristband gesture recognition method is characterized in that comprising the following steps: The gesture command sending module sends the gesture that needs to be judged to the microprocessor, and the microprocessor drives the position sensor to collect data through the DMP library, and the microprocessor judges whether it is a gesture that needs to be recognized through the collected data. 3. The wearable smart bracelet gesture recognition method as claimed in claim 2, wherein the gesture recognition method comprises the following steps: a STM32 initialization; b MPU9150 initialization; c STM32 writes the DMP library to the MPU9150; d STM32 reads the acceleration, angular velocity, and quaternion to obtain the Euler angle; e judge whether the gesture instruction sending module sends an instruction, if so, proceed to the next step, if not, return to the previous step; f Call the corresponding gesture function to judge gesture recognition; g Whether the gesture read is consistent with the gesture to be recognized, if so, proceed to the next step, if not, return to the previous step; h STM32 sends corresponding information to the gesture command sending module to prompt that the gesture recognition is correct. 4. The wearable smart bracelet gesture recognition method according to claim 2, wherein said opening the MPU9150 internal DMP comprises the following steps: a sensor setting; b Whether the sensor setting is successful, if so, go to the next step, if not, the program enters an endless loop; c Fifo setting and judging whether it is successful, if so, proceed to the next step, if not, the program enters an infinite loop; d DMP sampling rate setting; e Whether the sampling rate setting is successful, if so, proceed to the next step, if not, the program enters an infinite loop; f Turn on the DMP function; g Whether the DMP function is enabled successfully, if so, proceed to the next step, if not, the program enters an infinite loop; h initial direction setting deviation; i Whether the initialization direction setting deviation is successful, if so, proceed to the next step, if not, the program enters an infinite loop; j DMP enabled; k Whether the DMP enable is successful, if so, proceed to the next step, if not, the program enters an infinite loop; l Fifo speed setting; m Whether the Fifo speed setting is successful, if so, proceed to the next step, if not, the program enters an infinite loop; n DMP self-test; o Whether the DMP self-test is successful, if so, go to the next step, if not, the program enters an endless loop; p Open DMP successfully. 5. The wearable smart bracelet gesture recognition method according to claim 2, wherein the process of judging whether it is a gesture that needs to be recognized comprises the following steps: a Read MPU9150 data; b Whether the initial position of the MPU9150 is within the range of the set initial position, if yes, proceed to the next step, if not, return to the previous step; c Write down the Euler angle, acceleration and angular velocity of the current position; d Delay for a short period of time; e read the MPU9150 data again; f Compare the data collected twice to judge whether the gesture is correct, if yes, proceed to the next step, if not, return to step a; g Gesture recognition ends.