130 lines
4.3 KiB
Python
130 lines
4.3 KiB
Python
"""
|
|
Person Detection Module using OpenCV HOG (Histogram of Oriented Gradients).
|
|
Uses built-in OpenCV people detector - no external model files required.
|
|
"""
|
|
|
|
import cv2
|
|
import numpy as np
|
|
|
|
|
|
class PersonDetector:
|
|
def __init__(self, model_dir=None, confidence_threshold=0.6):
|
|
"""
|
|
Initialize the person detector with HOG descriptor.
|
|
|
|
Args:
|
|
model_dir: Ignored for HOG (kept for API compatibility)
|
|
confidence_threshold: Threshold for detection weights
|
|
"""
|
|
self.confidence_threshold = confidence_threshold
|
|
|
|
# Initialize HOG descriptor/person detector
|
|
self.hog = cv2.HOGDescriptor()
|
|
self.hog.setSVMDetector(cv2.HOGDescriptor_getDefaultPeopleDetector())
|
|
print("Initialized HOG Person Detector")
|
|
|
|
def detect_people(self, frame):
|
|
"""
|
|
Detect people in a frame using HOG.
|
|
|
|
Args:
|
|
frame: BGR image frame from OpenCV
|
|
|
|
Returns:
|
|
List of tuples (x, y, w, h, confidence) for each detected person
|
|
"""
|
|
# Resize for faster processing (optional, but HOG is computationally expensive)
|
|
# Using a slightly smaller scale can speed things up significantly
|
|
scale = 1.0
|
|
if frame.shape[1] > 640:
|
|
scale = 640 / frame.shape[1]
|
|
frame_small = cv2.resize(frame, None, fx=scale, fy=scale)
|
|
else:
|
|
frame_small = frame
|
|
|
|
# Detect people
|
|
# winStride: step size in x and y
|
|
# padding: padding around the input
|
|
# scale: coefficient of the detection window increase
|
|
(rects, weights) = self.hog.detectMultiScale(
|
|
frame_small,
|
|
winStride=(4, 4),
|
|
padding=(8, 8),
|
|
scale=1.05,
|
|
hitThreshold=0.0 # Default
|
|
)
|
|
|
|
people = []
|
|
|
|
# Convert detected rectangles to our format
|
|
for i, (x, y, w, h) in enumerate(rects):
|
|
confidence = weights[i]
|
|
|
|
# HOG returns confidence scores, usually > 0.
|
|
# We can filter if needed.
|
|
check_conf = float(confidence) if isinstance(confidence, (float, np.float32, np.float64)) else float(confidence[0])
|
|
|
|
if check_conf > self.confidence_threshold:
|
|
# Scale back up if we resized
|
|
if scale != 1.0:
|
|
x = int(x / scale)
|
|
y = int(y / scale)
|
|
w = int(w / scale)
|
|
h = int(h / scale)
|
|
|
|
# Size filtering
|
|
# Ignore detections that are too small (noise) or too large (walls/windows)
|
|
# Assumes 640x480 or similar resolution
|
|
if w < 40 or w > 400 or h < 80 or h > 480:
|
|
continue
|
|
|
|
# Ensure coordinates are within frame bounds (simple clamp)
|
|
x = max(0, x)
|
|
y = max(0, y)
|
|
|
|
people.append((x, y, w, h, check_conf))
|
|
|
|
return people
|
|
|
|
detect_faces = detect_people # Alias for compatibility
|
|
|
|
def draw_people(self, frame, people, color=(0, 255, 0), thickness=2):
|
|
"""
|
|
Draw bounding boxes around detected people.
|
|
"""
|
|
result_frame = frame.copy()
|
|
for (x, y, w, h, confidence) in people:
|
|
cv2.rectangle(result_frame, (x, y), (x + w, y + h), color, thickness)
|
|
|
|
# Draw label
|
|
label = f"Person: {confidence:.2f}"
|
|
|
|
# Get label size
|
|
(label_w, label_h), baseline = cv2.getTextSize(
|
|
label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1
|
|
)
|
|
|
|
# Draw background rectangle for label
|
|
cv2.rectangle(
|
|
result_frame,
|
|
(x, y - label_h - 10),
|
|
(x + label_w, y),
|
|
color,
|
|
-1
|
|
)
|
|
|
|
# Draw text
|
|
cv2.putText(
|
|
result_frame,
|
|
label,
|
|
(x, y - 5),
|
|
cv2.FONT_HERSHEY_SIMPLEX,
|
|
0.5,
|
|
(0, 0, 0),
|
|
1
|
|
)
|
|
|
|
return result_frame
|
|
|
|
draw_faces = draw_people # Alias for compatibility
|