chore: backup before migration to new repo
This commit is contained in:
Warren
@@ -1,8 +1,8 @@
|
||||
#!/opt/homebrew/bin/python3.11
|
||||
"""
|
||||
Face Processor - Face Detection
|
||||
Uses OpenCV Haar Cascade (local, no extra download needed)
|
||||
Alternative: MediaPipe (requires model download)
|
||||
Face Processor - Face Detection & Demographics
|
||||
Uses InsightFace for detection, age, and gender analysis.
|
||||
Falls back to OpenCV Haar Cascade if InsightFace fails.
|
||||
"""
|
||||
|
||||
import sys
|
||||
@@ -15,7 +15,7 @@ from redis_publisher import RedisPublisher
|
||||
|
||||
|
||||
def process_face(video_path: str, output_path: str, uuid: str = ""):
|
||||
"""Process video for face detection"""
|
||||
"""Process video for face detection and demographics analysis"""
|
||||
|
||||
publisher = RedisPublisher(uuid) if uuid else None
|
||||
if publisher:
|
||||
@@ -23,56 +23,82 @@ def process_face(video_path: str, output_path: str, uuid: str = ""):
|
||||
|
||||
try:
|
||||
import cv2
|
||||
except ImportError:
|
||||
import numpy as np
|
||||
import insightface
|
||||
except ImportError as e:
|
||||
error_msg = f"Missing dependency: {e.name}"
|
||||
if publisher:
|
||||
publisher.error("face", "opencv-python not installed")
|
||||
publisher.error("face", error_msg)
|
||||
result = {"frame_count": 0, "fps": 0.0, "frames": []}
|
||||
if publisher:
|
||||
publisher.complete("face", "0 frames")
|
||||
with open(output_path, "w") as f:
|
||||
json.dump(result, f, indent=2)
|
||||
return result
|
||||
|
||||
if publisher:
|
||||
publisher.info("face", "FACE_LOADING_CASCADE")
|
||||
|
||||
# Try to use OpenCV's built-in Haar Cascade
|
||||
# This is included with OpenCV
|
||||
face_cascade = cv2.CascadeClassifier(
|
||||
cv2.data.haarcascades + "haarcascade_frontalface_default.xml"
|
||||
)
|
||||
|
||||
if face_cascade.empty():
|
||||
# 1. Initialize InsightFace
|
||||
use_insightface = False
|
||||
app = None
|
||||
try:
|
||||
if publisher:
|
||||
publisher.error("face", "Could not load Haar Cascade")
|
||||
result = {"frame_count": 0, "fps": 0.0, "frames": []}
|
||||
publisher.info("face", "LOADING_INSIGHTFACE")
|
||||
# 'buffalo_l' is a robust model. det_size can be adjusted.
|
||||
app = insightface.app.FaceAnalysis(
|
||||
name="buffalo_l", providers=["CPUExecutionProvider"]
|
||||
)
|
||||
app.prepare(ctx_id=0, det_size=(320, 320))
|
||||
use_insightface = True
|
||||
if publisher:
|
||||
publisher.complete("face", "0 frames")
|
||||
with open(output_path, "w") as f:
|
||||
json.dump(result, f, indent=2)
|
||||
return result
|
||||
publisher.info("face", "INSIGHTFACE_LOADED")
|
||||
except Exception as e:
|
||||
print(f"[WARNING] InsightFace failed to load: {e}")
|
||||
use_insightface = False
|
||||
|
||||
# 2. Fallback to Haar Cascade
|
||||
face_cascade = None
|
||||
if not use_insightface:
|
||||
if publisher:
|
||||
publisher.info("face", "LOADING_HAAR_CASCADE")
|
||||
face_cascade = cv2.CascadeClassifier(
|
||||
cv2.data.haarcascades + "haarcascade_frontalface_default.xml"
|
||||
)
|
||||
if face_cascade.empty():
|
||||
if publisher:
|
||||
publisher.error("face", "Could not load Haar Cascade")
|
||||
result = {"frame_count": 0, "fps": 0.0, "frames": []}
|
||||
with open(output_path, "w") as f:
|
||||
json.dump(result, f, indent=2)
|
||||
return result
|
||||
if publisher:
|
||||
publisher.info("face", "HAAR_CASCADE_LOADED")
|
||||
|
||||
if publisher:
|
||||
publisher.info("face", "FACE_CASCADE_LOADED")
|
||||
publisher.info("face", "PROCESSING_VIDEO")
|
||||
|
||||
# Get video info
|
||||
cap = cv2.VideoCapture(video_path)
|
||||
if not cap.isOpened():
|
||||
if publisher:
|
||||
publisher.error("face", "Could not open video")
|
||||
result = {"frame_count": 0, "fps": 0.0, "frames": []}
|
||||
with open(output_path, "w") as f:
|
||||
json.dump(result, f, indent=2)
|
||||
return result
|
||||
|
||||
fps = cap.get(cv2.CAP_PROP_FPS)
|
||||
total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
||||
cap.release()
|
||||
|
||||
# Optimization: Process every N frames to speed up analysis
|
||||
# Since we just need attributes for the person identity, we don't need every single frame.
|
||||
sample_interval = 30
|
||||
if total_frames > 0:
|
||||
estimated_samples = total_frames // sample_interval
|
||||
else:
|
||||
estimated_samples = 0
|
||||
|
||||
frame_count = 0
|
||||
processed_count = 0
|
||||
frames_data = []
|
||||
|
||||
if publisher:
|
||||
publisher.info("face", f"fps={fps}, frames={total_frames}")
|
||||
publisher.progress("face", 0, total_frames, "Starting")
|
||||
|
||||
# Process every N frames to speed up
|
||||
sample_interval = 30 # Process every 30 frames
|
||||
|
||||
frames = []
|
||||
frame_count = 0
|
||||
processed = 0
|
||||
|
||||
cap = cv2.VideoCapture(video_path)
|
||||
publisher.progress("face", 0, estimated_samples, "Starting")
|
||||
|
||||
while True:
|
||||
ret, frame = cap.read()
|
||||
@@ -81,62 +107,92 @@ def process_face(video_path: str, output_path: str, uuid: str = ""):
|
||||
|
||||
frame_count += 1
|
||||
|
||||
# Sample frames
|
||||
# Sampling
|
||||
if frame_count % sample_interval != 0:
|
||||
continue
|
||||
|
||||
processed += 1
|
||||
processed_count += 1
|
||||
timestamp = (frame_count - 1) / fps if fps > 0 else 0
|
||||
|
||||
# Convert to grayscale
|
||||
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
|
||||
|
||||
# Detect faces
|
||||
try:
|
||||
faces = face_cascade.detectMultiScale(
|
||||
gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30)
|
||||
)
|
||||
except Exception as e:
|
||||
if publisher:
|
||||
publisher.error("face", f"Frame {frame_count}: {e}")
|
||||
faces = []
|
||||
|
||||
face_list = []
|
||||
for x, y, w, h in faces:
|
||||
face_list.append(
|
||||
{
|
||||
"face_id": None,
|
||||
"x": int(x),
|
||||
"y": int(y),
|
||||
"width": int(w),
|
||||
"height": int(h),
|
||||
"confidence": 0.8, # Haar cascade doesn't provide confidence
|
||||
}
|
||||
)
|
||||
|
||||
# Only add frames with faces
|
||||
try:
|
||||
if use_insightface and app:
|
||||
# InsightFace Detection & Analysis
|
||||
faces = app.get(frame)
|
||||
for face in faces:
|
||||
bbox = face.bbox.astype(int)
|
||||
bx, by, bw, bh = (
|
||||
bbox[0],
|
||||
bbox[1],
|
||||
bbox[2] - bbox[0],
|
||||
bbox[3] - bbox[1],
|
||||
)
|
||||
|
||||
# Extract Attributes
|
||||
age = int(face.age) if hasattr(face, "age") else None
|
||||
gender_val = face.gender if hasattr(face, "gender") else None
|
||||
gender = (
|
||||
"female"
|
||||
if gender_val == 0
|
||||
else ("male" if gender_val == 1 else None)
|
||||
)
|
||||
|
||||
face_list.append(
|
||||
{
|
||||
"x": int(bx),
|
||||
"y": int(by),
|
||||
"width": int(bw),
|
||||
"height": int(bh),
|
||||
"confidence": float(face.det_score)
|
||||
if hasattr(face, "det_score")
|
||||
else 0.9,
|
||||
"attributes": {"age": age, "gender": gender},
|
||||
}
|
||||
)
|
||||
else:
|
||||
# Haar Cascade Fallback (No Age/Gender)
|
||||
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
|
||||
faces = face_cascade.detectMultiScale(
|
||||
gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30)
|
||||
)
|
||||
for x, y, w, h in faces:
|
||||
face_list.append(
|
||||
{
|
||||
"x": int(x),
|
||||
"y": int(y),
|
||||
"width": int(w),
|
||||
"height": int(h),
|
||||
"confidence": 0.8,
|
||||
"attributes": {"age": None, "gender": None},
|
||||
}
|
||||
)
|
||||
except Exception as e:
|
||||
print(f"[ERROR] Frame processing error: {e}")
|
||||
|
||||
if face_list:
|
||||
frames.append(
|
||||
frames_data.append(
|
||||
{
|
||||
"frame": frame_count - 1,
|
||||
"timestamp": round(timestamp, 3),
|
||||
"faces": face_list,
|
||||
}
|
||||
)
|
||||
|
||||
if publisher:
|
||||
publisher.progress(
|
||||
"face",
|
||||
processed,
|
||||
total_frames // sample_interval,
|
||||
processed_count,
|
||||
estimated_samples,
|
||||
f"Frame {frame_count}",
|
||||
)
|
||||
|
||||
cap.release()
|
||||
|
||||
result = {"frame_count": total_frames, "fps": fps, "frames": frames}
|
||||
result = {"frame_count": total_frames, "fps": fps, "frames": frames_data}
|
||||
|
||||
if publisher:
|
||||
publisher.complete("face", f"{len(frames)} frames with faces")
|
||||
publisher.complete("face", f"{len(frames_data)} frames processed")
|
||||
|
||||
with open(output_path, "w") as f:
|
||||
json.dump(result, f, indent=2)
|
||||
@@ -145,7 +201,7 @@ def process_face(video_path: str, output_path: str, uuid: str = ""):
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Face Detection")
|
||||
parser = argparse.ArgumentParser(description="Face Detection & Demographics")
|
||||
parser.add_argument("video_path", help="Path to video file")
|
||||
parser.add_argument("output_path", help="Output JSON path")
|
||||
parser.add_argument("--uuid", "-u", help="UUID for Redis progress", default="")
|
||||
|
||||
Reference in New Issue
Block a user