arduino_k230 face recognition

k230 and arduino communication

1. Experimental Prerequisites

This tutorial uses Arduino, and the corresponding routine path is [14.export\arduino-K230\8.Arduino_k230_face_recognition].

K230 needs to run the [14.export\CanmvIDE-K230\08.face_recognition.py] program to start the experiment. It is recommended to download it as an offline program. Since the face recognition function requires the registration of face information in advance, please refer to the [7. Face Recognition\7. Register Face Recognition] course first, and then perform this experiment after registering the face.

Items needed:

Windows computer, Arduino, USB to TTL module, K230 visual module (including TF card with image burned in), type-C data cable, connecting cable (Dupont cable)

2. Experimental wiring

3. Main code explanation

​x
void Pto_Data_Parse(uint8_t *data_buf, uint8_t num)
{
    uint8_t pto_head = data_buf[0];
    uint8_t pto_tail = data_buf[num-1];
    if (!(pto_head == PTO_HEAD && pto_tail == PTO_TAIL))
    {
        Serial.print("pto error:pto_head=0x");
    Serial.print(pto_head, HEX);
    Serial.print(" , pto_tail=0x");
    Serial.println(pto_tail, HEX);
        return;
    }
    uint8_t data_index = 1;
    uint8_t field_index[PTO_BUF_LEN_MAX] = {0};
    int i = 0;
    int values[PTO_BUF_LEN_MAX] = {0};
    char msg[PTO_BUF_LEN_MAX] = {0};
    for (i = 1; i < num-1; i++)
    {
        if (data_buf[i] == ',')
        {
            data_buf[i] = 0;
            field_index[data_index] = i;
            data_index++;
        }
    }
    
    for (i = 0; i < data_index; i++)
    {
        if (i == 6)
        {
            memcpy(msg, (char*)data_buf+field_index[i]+1, field_index[i+1]-field_index[i]);
        }
        else
        {
            values[i] = Pto_Char_To_Int((char*)data_buf+field_index[i]+1);
        }
    }
    
    uint8_t pto_len = values[0];
    
    if (pto_len != num)
    {
        Serial.print("pto_len error:");
    Serial.print(pto_len);
    Serial.print(" , data_len:");
    Serial.println(num);
        return;
    }
    uint8_t pto_id = values[1];
    if (pto_id != PTO_FUNC_ID)
    {
        Serial.print("pto_id error:");
    Serial.print(pto_id);
    Serial.print(" , func_id:");
    Serial.println(PTO_FUNC_ID);
        return;
    }
    int x = values[2];
    int y = values[3];
    int w = values[4];
    int h = values[5];
    float score = values[7]/100.0;
    
    Serial.print("face recogition:x:");
    Serial.print(x);
    Serial.print(", y:");
    Serial.print(y);
    Serial.print(", w:");
    Serial.print(w);
    Serial.print(", h:");
    Serial.print(h);
    Serial.print(" msg:'");
    Serial.print(msg);
    Serial.print("', score:");
    Serial.println(score);
    
}
​

The above function is used to parse K230 data. Only when it complies with specific protocols can the corresponding data be parsed.

• x: is the horizontal coordinate of the upper left corner of the recognition box
• y: is the vertical coordinate of the upper left corner of the recognition box
• w: is the width of the recognition box
• h: is the length of the recognition box
• name: is the name of the person being recognized, if it is not registered, it is ‘unknown’
• score: is the score of the person being recognized

4. Experimental Phenomenon

1. After connecting the cables, the k230 visual module runs offline After K230 is connected to Canmv IDE, open the corresponding program, click [Save open script to CanMV board (as main.py)] on the toolbar, and then restart K230.

2. Arduino upload routine code (Note that if the upload fails, disconnect the RXD connection on the Arduino connected to the k230 first, and then plug it back after the upload is successful)

3. The serial port assistant is set to the interface shown in the figure
4. When the K230 camera recognizes a face, the serial port assistant will print out the information transmitted from K230 to arduino.

• x: is the horizontal coordinate of the upper left corner of the recognition box
• y: is the vertical coordinate of the upper left corner of the recognition box
• w: is the width of the recognition box
• h: is the length of the recognition box
• name: is the name of the person being recognized, if it is not registered, it is ‘unknown’
• score: is the score of the person being recognized

As shown in the figure below