HandTrackingModule.py

import cv2
import mediapipe as mp
import time
import math
import itertools
import numpy as np
import copy
from collections import deque
import tensorflow as tf


def pre_process_point_history(image, point_history):
    image_width, image_height = image.shape[1], image.shape[0]

    temp_point_history = copy.deepcopy(point_history)

    # 相対座標に変換
    base_x, base_y = 0, 0
    for index, point in enumerate(temp_point_history):
        if index == 0:
            base_x, base_y = point[0], point[1]

        temp_point_history[index][0] = (temp_point_history[index][0] -
                                        base_x) / image_width
        temp_point_history[index][1] = (temp_point_history[index][1] -
                                        base_y) / image_height

    # 1次元リストに変換
    temp_point_history = list(itertools.chain.from_iterable(temp_point_history))

    del temp_point_history[0:2]

    return temp_point_history


class handDetector():
    def __init__(self, mode=False, maxHands=2, detectionCon=0.5, trackCon=0.5):
        self.mode = mode
        self.maxHands = maxHands
        self.detectionCon = detectionCon
        self.trackCon = trackCon
        
        # ジェスチャー認識用モデルロード
        tflite_save_path = './ML/gesture_classifier.tflite'
        self.interpreter = tf.lite.Interpreter(model_path=tflite_save_path)
        self.interpreter.allocate_tensors()
        self.input_details = self.interpreter.get_input_details()
        self.output_details = self.interpreter.get_output_details()

        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(self.mode, self.maxHands, model_complexity=0, min_detection_confidence=0.5, min_tracking_confidence=0.5)
        self.mpDraw = mp.solutions.drawing_utils
        self.tipIds = [4, 8, 12, 16, 20]
        self.history_length = 16
        self.point_history = deque(maxlen=self.history_length)
        self.gesture_label = ['Heart', 'Triangle']

    def findHands(self, img, draw=True):
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        self.results = self.hands.process(imgRGB)
        # print(results.multi_hand_landmarks)

        if self.results.multi_hand_landmarks:
            for handLms in self.results.multi_hand_landmarks:
                if draw:
                    self.mpDraw.draw_landmarks(img, handLms, self.mpHands.HAND_CONNECTIONS)
        return img

    def findPosition(self, img, handNo=0, draw=True, gesture=False):
        xList = []
        yList = []
        bbox = []
        self.lmList = []
        gesture_id = -1
        if self.results.multi_hand_landmarks:
            myHand = self.results.multi_hand_landmarks[handNo]
            for id, lm in enumerate(myHand.landmark):
                # print(id, lm)
                h, w, c = img.shape
                cx, cy = int(lm.x * w), int(lm.y * h)
                xList.append(cx)
                yList.append(cy)
                # print(id, cx, cy)
                self.lmList.append([id, cx, cy])
                if id == 8:
                    self.point_history.append([cx, cy])
                if draw:
                    cv2.circle(img, (cx, cy), 5, (255, 0, 255), cv2.FILLED)

            xmin, xmax = min(xList), max(xList)
            ymin, ymax = min(yList), max(yList)
            bbox = xmin, ymin, xmax, ymax
            

            if gesture:
                if len(self.point_history) == self.history_length:
                    temp_point_history = pre_process_point_history(img, self.point_history)

                    self.interpreter.set_tensor(
                        self.input_details[0]['index'],
                        np.array([temp_point_history]).astype(np.float32))
                    self.interpreter.invoke()
                    tflite_results = self.interpreter.get_tensor(self.output_details[0]['index'])

                    gesture_id = np.argmax(np.squeeze(tflite_results))
                    cv2.putText(img, self.gesture_label[gesture_id], (500, 450), cv2.FONT_HERSHEY_SIMPLEX, 1, (99, 71, 255), 2, cv2.LINE_AA)
            else:
                cv2.putText(img, "OFF", (500, 450), cv2.FONT_HERSHEY_SIMPLEX, 1, (99, 71, 255), 2, cv2.LINE_AA)

            if draw:
                cv2.rectangle(img, (xmin - 20, ymin - 20), (xmax + 20, ymax + 20), (0, 255, 0), 2)
        return self.lmList, self.point_history, bbox, gesture_id

    def fingersUp(self):
        fingers = []
        # Thumb
        if self.lmList[self.tipIds[0]][1] > self.lmList[self.tipIds[0]-1][1]:
            fingers.append(1)
        else:
            fingers.append(0)

        # Fingers
        for id in range(1, 5):

            if self.lmList[self.tipIds[id]][2] < self.lmList[self.tipIds[id] - 2][2]:
                fingers.append(1)
            else:
                fingers.append(0)

        # totalFingers = fingers.count(1)

        return fingers

    def findDistance(self, p1, p2, img, draw=True, r=15, t=3):
        x1, y1 = self.lmList[p1][1:]
        x2, y2 = self.lmList[p2][1:]
        cx, cy = (x1 + x2) // 2, (y1 + y2) // 2

        if draw:
            cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), t)
            cv2.circle(img, (x1, y1), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (x2, y2), r, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (cx, cy), r, (0, 0, 255), cv2.FILLED)
        length = math.hypot(x2 - x1, y2 - y1)

        return length, img, [x1, y1, x2, y2, cx, cy]


def main():
    pTime = 0
    cTime = 0
    cap = cv2.VideoCapture(1)
    detector = handDetector()
    while True:
        success, img = cap.read()
        img = detector.findHands(img)
        lmList, bbox = detector.findPosition(img)
        if len(lmList) != 0:
            print(lmList[4])

        cTime = time.time()
        fps = 1 / (cTime - pTime)
        pTime = cTime

        cv2.putText(img, str(int(fps)), (10, 70), cv2.FONT_HERSHEY_PLAIN, 3,
                    (255, 0, 255), 3)

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


if __name__ == "__main__":
    main()