init

find_v2.py

@@ -0,0 +1,130 @@
+import cv2
+import numpy as np
+import joblib
+from skimage.feature import hog
+import imutils
+from imutils.object_detection import non_max_suppression
+from skimage.transform import pyramid_gaussian
+import asyncio
+import concurrent.futures
+
+
+def sliding_window(image, stepSize, windowSize):
+    for y in range(0, image.shape[0] - windowSize[1] + 1, stepSize):
+        for x in range(0, image.shape[1] - windowSize[0] + 1, stepSize):
+            yield (x, y, image[y:y + windowSize[1], x:x + windowSize[0]])
+
+
+# HOG parameters (should match those used during training)
+hog_params = {
+    'orientations': 9,
+    'pixels_per_cell': (8, 8),
+    'cells_per_block': (2, 2),
+    'block_norm': 'L2-Hys'
+}
+
+# Detection parameters
+windowSize = (64, 64)
+hogSize = (128, 128)  # Must match the window size used for training HOG features.
+stepSize = 8  # Step size for sliding window.
+scale_factor = 1.1  # Scaling factor for image pyramid.
+detection_threshold = 0.9  # Minimum probability to consider a detection valid.
+
+# Load the pre-trained model (grid search object containing the best estimator)
+model = joblib.load('svm_natural_images_model.pkl')
+# If the saved object is a GridSearchCV, extract the best estimator.
+if hasattr(model, 'best_estimator_'):
+    model = model.best_estimator_
+
+
+# This initializer will be run in each worker process to set globals.
+def init_worker(_model, _hog_params, _hogSize, _detection_threshold, _windowSize):
+    global model, hog_params, hogSize, detection_threshold, windowSize
+    model = _model
+    hog_params = _hog_params
+    hogSize = _hogSize
+    detection_threshold = _detection_threshold
+    windowSize = _windowSize
+
+
+def process_window(args):
+    # Unpack arguments
+    window, x, y, scale_ratio = args
+    # Ensure proper datatype
+    if window.dtype != np.uint8:
+        window = (window * 255).astype(np.uint8)
+    # Convert to grayscale and resize for HOG extraction
+    gray = cv2.cvtColor(window, cv2.COLOR_BGR2GRAY)
+    gray = cv2.resize(gray, hogSize)
+    # Compute HOG features
+    features = hog(gray, **hog_params)
+    features = features.reshape(1, -1)
+    # Make predictions
+    pred = model.predict(features)
+    prob = model.predict_proba(features)[0]
+    if 'person' in model.classes_:
+        person_index = list(model.classes_).index('person')
+        person_prob = prob[person_index]
+    else:
+        person_prob = 0
+    # Return bounding box if detection meets the criteria
+    if pred[0] == 'person' and person_prob > detection_threshold:
+        startX = int(x * scale_ratio)
+        startY = int(y * scale_ratio)
+        endX = int((x + windowSize[0]) * scale_ratio)
+        endY = int((y + windowSize[1]) * scale_ratio)
+        return (startX, startY, endX, endY)
+    return None
+
+
+async def async_detection(image):
+    detections = []
+    loop = asyncio.get_running_loop()
+    tasks = []
+    # Set up the ProcessPoolExecutor with max 10 processes and initializer
+    with concurrent.futures.ProcessPoolExecutor(
+            max_workers=20,
+            initializer=init_worker,
+            initargs=(model, hog_params, hogSize, detection_threshold, windowSize)
+    ) as executor:
+        for resized in pyramid_gaussian(image, downscale=scale_factor, channel_axis=-1):
+            scale_ratio = image.shape[1] / float(resized.shape[1])
+            for (x, y, window) in sliding_window(resized, stepSize, windowSize):
+                if window.shape[0] != windowSize[1] or window.shape[1] != windowSize[0]:
+                    continue
+                args = (window, x, y, scale_ratio)
+                tasks.append(loop.run_in_executor(executor, process_window, args))
+        results = await asyncio.gather(*tasks)
+    for result in results:
+        if result is not None:
+            detections.append(result)
+    return detections
+
+
+async def main():
+    # Load the test image (update the filename as needed)
+    image = cv2.imread("test.jpg")
+    if image is None:
+        print("Failed to load image!")
+        return
+
+    orig = image.copy()
+    # Run the asynchronous detection
+    detections = await async_detection(image)
+
+    # Apply non-maxima suppression to reduce overlapping boxes
+    if len(detections) > 0:
+        detections = np.array(detections)
+        pick = non_max_suppression(detections, probs=None, overlapThresh=0.3)
+        # Draw the final bounding boxes on the original image.
+        for (xA, yA, xB, yB) in pick:
+            cv2.rectangle(orig, (xA, yA), (xB, yB), (0, 255, 0), 2)
+
+    # Display the detections
+    cv2.imshow("Detections", orig)
+    cv2.waitKey(0)
+    cv2.destroyAllWindows()
+
+
+if __name__ == '__main__':
+    asyncio.run(main())