Spaces:
Build error
Build error
File size: 3,775 Bytes
39dc633 e876d5a 39dc633 8eff39a 39dc633 e876d5a 8eff39a 39dc633 8eff39a 39dc633 8eff39a e876d5a 8eff39a e876d5a 8eff39a e876d5a 8eff39a e876d5a 8eff39a e876d5a 8eff39a e876d5a 8eff39a e876d5a 8eff39a 39dc633 e876d5a 8eff39a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 | import cv2
import mediapipe as mp
import numpy as np
import gradio as gr
import tempfile
# Path to hand landmark model file (make sure it's in your repo!)
MODEL_PATH = "hand_landmarker.task"
# MediaPipe setup
BaseOptions = mp.tasks.BaseOptions
HandLandmarker = mp.tasks.vision.HandLandmarker
HandLandmarkerOptions = mp.tasks.vision.HandLandmarkerOptions
VisionRunningMode = mp.tasks.vision.RunningMode
mp_image = mp.Image
mp_format = mp.ImageFormat
# Define hand connections and colors for visualization
HAND_CONNECTIONS = [
(0, 1), (1, 2), (2, 3), (3, 4),
(0, 5), (5, 6), (6, 7), (7, 8),
(0, 9), (9,10), (10,11), (11,12),
(0,13), (13,14), (14,15), (15,16),
(0,17), (17,18), (18,19), (19,20)
]
FINGER_COLORS = {
'thumb': (245, 245, 245),
'index': (128, 0, 128),
'middle': (0, 255, 0),
'ring': (0, 165, 255),
'pinky': (255, 0, 0),
'palm': (100, 100, 100)
}
def get_finger_color(start_idx):
if start_idx in range(0, 5):
return FINGER_COLORS['thumb']
elif start_idx in range(5, 9):
return FINGER_COLORS['index']
elif start_idx in range(9, 13):
return FINGER_COLORS['middle']
elif start_idx in range(13, 17):
return FINGER_COLORS['ring']
elif start_idx in range(17, 21):
return FINGER_COLORS['pinky']
else:
return FINGER_COLORS['palm']
def process_video(video_file):
# Gradio may send a dict or path string depending on how input is passed
if isinstance(video_file, dict):
video_path = video_file["name"]
else:
video_path = video_file
cap = cv2.VideoCapture(video_path)
if not cap.isOpened():
raise ValueError("Could not open video.")
fps = cap.get(cv2.CAP_PROP_FPS) or 24
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
# Prepare output video path
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
tmp_out = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
out_path = tmp_out.name
out = cv2.VideoWriter(out_path, fourcc, fps, (w, h))
# Load hand detection model
options = HandLandmarkerOptions(
base_options=BaseOptions(model_asset_path=MODEL_PATH),
running_mode=VisionRunningMode.IMAGE,
num_hands=2,
min_hand_detection_confidence=0.5,
min_hand_presence_confidence=0.5,
min_tracking_confidence=0.5
)
with HandLandmarker.create_from_options(options) as landmarker:
while cap.isOpened():
ret, frame = cap.read()
if not ret:
break
rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
results = landmarker.detect(mp_img)
if results.hand_landmarks:
for hand_landmarks in results.hand_landmarks:
points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
for start, end in HAND_CONNECTIONS:
color = get_finger_color(start)
cv2.line(frame, points[start], points[end], color, 2)
for x, y in points:
cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
out.write(frame)
cap.release()
out.release()
return out_path
# Gradio app interface
demo = gr.Interface(
fn=process_video,
inputs=gr.Video(label="Upload Video or Record via Webcam"),
outputs=gr.Video(label="Hand Landmark Annotated Video"),
title="🖐️ Hand Detection using MediaPipe",
description="Upload a video or record from webcam. The system will detect hands and annotate keypoints using MediaPipe HandLandmarker."
)
if __name__ == "__main__":
demo.launch()
|