HandDetector.py

import cv2
import mediapipe as mp
import time
import logging

logger = logging.getLogger(__name__)


class HandDetector:
    def __init__(
        self,
        static_image_mode=False,
        max_num_hands=2,
        min_detection_confidence=0.5,
        min_tracking_confidence=0.5,
    ):
        self.static_image_mode = static_image_mode
        self.max_num_hands = max_num_hands
        self.min_detection_confidence = min_detection_confidence
        self.min_tracking_confidence = min_tracking_confidence

        self.mp_hands = mp.solutions.hands
        self.mp_draw = mp.solutions.drawing_utils
        self.hands = self.mp_hands.Hands(
            self.static_image_mode, self.max_num_hands, self.min_detection_confidence, self.min_tracking_confidence
        )

    def find_hands(self, img, draw=True):
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        results = self.hands.process(imgRGB)

        if results.multi_hand_landmarks:
            for hand in results.multi_hand_landmarks:

                if draw:
                    self.mp_draw.draw_landmarks(img, hand, self.mp_hands.HAND_CONNECTIONS)

        return img

    def find_position(self, img, hand_num=0, draw=True):
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        results = self.hands.process(imgRGB)
        lm_list = []

        if results.multi_hand_landmarks:
            my_hand = results.multi_hand_landmarks[hand_num]
            for _id, lm in enumerate(my_hand.landmark):
                h, w, c = img.shape
                cx, cy = int(lm.x * w), int(lm.y * h)
                lm_list.append([_id, cx, cy])
                if draw:
                    cv2.circle(img, (cx, cy), 10, (255, 0, 255), cv2.FILLED)

        return lm_list


def main():
    cap = cv2.VideoCapture(0)

    pTime = 0
    cTime = 0

    detector = HandDetector()

    while True:
        success, img = cap.read()

        img = detector.find_hands(img)
        # lm_list_hand_0 = detector.find_position(img, hand_num=0)

        cTime = time.time()
        fps = 1 / (cTime - pTime)
        pTime = cTime
        cv2.putText(
            img,
            str(int(fps)),
            (10, 70),
            cv2.FONT_HERSHEY_PLAIN,
            3,
            (255, 255, 255),
            3,
        )

        cv2.imshow("Image", img)
        cv2.waitKey(1)


if __name__ == "__main__":
    main()