Код: Выделить всё
import cv2
import mediapipe as mp
import time
cap = cv2.VideoCapture(1)
BaseOptions = mp.tasks.BaseOptions
GestureRecognizer = mp.tasks.vision.GestureRecognizer
GestureRecognizerOptions = mp.tasks.vision.GestureRecognizerOptions
GestureRecognizerResult = mp.tasks.vision.GestureRecognizerResult
VisionRunningMode = mp.tasks.vision.RunningMode
# Callback function to print gesture recognition results
def print_result(result: GestureRecognizerResult, output_image: mp.Image, timestamp_ms: int):
if result.gestures:
# Get the category name of the recognized gesture
category_name = result.gestures[0][0].category_name
# print(category_name)
print(result)
else:
print("No gestures recognized")
# Initialize MediaPipe drawing utils and hands module
mp_drawing = mp.solutions.drawing_utils
mp_hands = mp.solutions.hands
# Configure options for the gesture recognizer
options = GestureRecognizerOptions(
base_options=BaseOptions(model_asset_path='C:\\Users\\golut\\OneDrive\\Documents\\Projects\\Virtual Mouse\\models\\gesture_recognizer.task'),
running_mode=VisionRunningMode.LIVE_STREAM,
result_callback=print_result
)
# Create a gesture recognizer instance
with GestureRecognizer.create_from_options(options) as recognizer:
print('Gesture recognizer created')
while True:
success, img = cap.read()
if not success:
print("Ignoring empty camera frame.")
continue
# Convert BGR image to RGB for MediaPipe processing
rgb_img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# Detect hand landmarks using MediaPipe Hands
with mp_hands.Hands(max_num_hands=2, min_detection_confidence=0.5) as hands:
results = hands.process(rgb_img)
if results.multi_hand_landmarks:
for hand_landmarks in results.multi_hand_landmarks:
# Draw hand landmarks on the image with specified color and thickness
mp_drawing.draw_landmarks(
img, hand_landmarks, mp_hands.HAND_CONNECTIONS,
mp_drawing.DrawingSpec(color=(0, 255, 0), thickness=2, circle_radius=2),
mp_drawing.DrawingSpec(color=(0, 0, 255), thickness=2, circle_radius=2)
)
# Prepare image for gesture recognition
mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=rgb_img)
current_time_ms = int(time.time() * 1000)
# Perform gesture recognition on the processed image
detected_gestures = recognizer.recognize_async(mp_image, current_time_ms)
img = cv2.flip(img, 1) # Flips the image horizontally
cv2.imshow("Imshow", img)
if cv2.waitKey(10) == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
Проблема в том, что распознаватель жестов выдает только один вывод: левая или правая рука, в зависимости от того, какая рука была обнаружена первой, а последняя игнорируется. В приведенном примере MediaPipe обе руки, показанные камере с разными жестами, распознаются независимо. Ссылка на демо-версию медиапайпа
Код: Выделить всё
GestureRecognizerResult(gestures=[[Category(index=-1, score=0.7995390892028809,
display_name='', category_name='Open_Palm')]], handedness=[[Category(index=0, score=0.9178019165992737, display_name='Right', category_name='Right')]],
hand_landmarks=[[NormalizedLandmark(x=0.23192565143108368, y=0.8508237600326538, z=3.7175095712882467e-07, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.2964465022087097, y=0.807819128036499, z=-0.02174699306488037, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.3386477530002594, y=0.7381684184074402, z=-0.026875635609030724, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.3652242422103882, y=0.6717657446861267, z=-0.03148443624377251, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.39171433448791504, y=0.627888560295105, z=-0.03597773239016533, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.30005523562431335, y=0.6441321969032288, z=-0.002747688442468643, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.3194928765296936, y=0.5634738802909851, z=-0.015889683738350868, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.3276906907558441, y=0.5102080702781677, z=-0.0299211535602808, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.33434727787971497, y=0.46343517303466797, z=-0.04088740795850754, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.2615800201892853, y=0.6335919499397278, z=-0.002842121757566929, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.26276978850364685, y=0.5426733493804932, z=-0.014345655217766762, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.2621628940105438, y=0.48378312587738037, z=-0.028536789119243622, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.26235222816467285, y=0.43310630321502686, z=-0.03940063342452049, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.22592493891716003, y=0.6417601108551025, z=-0.006861940026283264, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.2230750024318695, y=0.5614591240882874, z=-0.01952073909342289, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.22449643909931183, y=0.5094373822212219, z=-0.029860520735383034, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.229284405708313, y=0.46403464674949646, z=-0.03746004030108452, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.19173786044120789, y=0.663299024105072, z=-0.0136506836861372, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.18222525715827942, y=0.604834794998169, z=-0.025881653651595116, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.18415895104408264, y=0.5673394799232483, z=-0.03144041821360588, visibility=0.0, presence=0.0),
NormalizedLandmark(x=0.19118154048919678, y=0.5324922800064087, z=-0.034897807985544205, visibility=0.0, presence=0.0)]],
hand_world_landmarks=[[Landmark(x=-0.012245522812008858, y=0.09203963726758957, z=-0.0038926522247493267, visibility=0.0, presence=0.0),
Landmark(x=0.021369636058807373, y=0.06962162256240845, z=-0.009559692814946175, visibility=0.0, presence=0.0),
Landmark(x=0.042654991149902344, y=0.04227661341428757, z=-0.012077674269676208, visibility=0.0, presence=0.0),
Landmark(x=0.0617685541510582, y=0.014768477529287338, z=-0.011491118930280209, visibility=0.0, presence=0.0),
Landmark(x=0.07398916780948639, y=-0.012367911636829376, z=-0.0075836945325136185, visibility=0.0, presence=0.0),
Landmark(x=0.025482138618826866, y=-0.0010876771993935108, z=0.006445789244025946, visibility=0.0, presence=0.0),
Landmark(x=0.03543740138411522, y=-0.02912675403058529, z=-0.00173004565294832, visibility=0.0, presence=0.0),
Landmark(x=0.040552493184804916, y=-0.0489623099565506, z=-0.007902431301772594, visibility=0.0, presence=0.0),
Landmark(x=0.04358145594596863, y=-0.06487865746021271, z=-0.0319957509636879, visibility=0.0, presence=0.0),
Landmark(x=0.0016808465588837862, y=-0.004498452879488468, z=0.006683729123324156, visibility=0.0, presence=0.0),
Landmark(x=0.004972374066710472, y=-0.04138147830963135, z=-0.003927251789718866, visibility=0.0, presence=0.0),
Landmark(x=0.00558849610388279, y=-0.06327502429485321, z=-0.020593348890542984, visibility=0.0, presence=0.0),
Landmark(x=0.0066368915140628815, y=-0.08291880786418915, z=-0.039193443953990936, visibility=0.0, presence=0.0),
Landmark(x=-0.018360454589128494, y=-0.0009643810335546732, z=-0.0038148483727127314, visibility=0.0, presence=0.0),
Landmark(x=-0.015782665461301804, y=-0.03162727132439613, z=-0.013909644447267056, visibility=0.0, presence=0.0),
Landmark(x=-0.013191262260079384, y=-0.05145301669836044, z=-0.028273196890950203, visibility=0.0, presence=0.0),
Landmark(x=-0.009723789989948273, y=-0.0685187503695488, z=-0.04024944826960564, visibility=0.0, presence=0.0),
Landmark(x=-0.035820234566926956, y=0.011946788057684898, z=-0.0120608601719141, visibility=0.0, presence=0.0),
Landmark(x=-0.03725161403417587, y=-0.009996423497796059, z=-0.017715157940983772, visibility=0.0, presence=0.0),
Landmark(x=-0.036166295409202576, y=-0.028470497578382492, z=-0.026987750083208084, visibility=0.0, presence=0.0),
Landmark(x=-0.030654065310955048, y=-0.03972318768501282, z=-0.03699912130832672, visibility=0.0, presence=0.0)]])
Подробнее здесь: https://stackoverflow.com/questions/785 ... -object-ha
