SCRIPTS - added script to look at images offline to improve setttings for alc
This commit is contained in:
leonarski_f committed
1 parent
5f94ccd9d2
commit
206bfcf2db
1 file changed
+804
@@ -0,0 +1,804 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"id": "initial_id",
|
||||
"metadata": {
|
||||
"collapsed": true,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-09T06:54:20.171830792Z",
|
||||
"start_time": "2025-09-03T09:37:36.977231Z"
|
||||
}
|
||||
},
|
||||
"source": [
|
||||
"import cv2\n",
|
||||
"import numpy as np\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns"
|
||||
],
|
||||
"outputs": [],
|
||||
"execution_count": 47
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-03T09:20:49.172543Z",
|
||||
"start_time": "2025-09-03T09:20:49.169238Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": "threshold = 5",
|
||||
"id": "19360e6dda22efb5",
|
||||
"outputs": [],
|
||||
"execution_count": 30
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"jupyter": {
|
||||
"is_executing": true
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"bkg = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/bkg1_50_50.jpg\")\n",
|
||||
"curr_img = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/1002_0_1_50_50_curr_image.tiff\")"
|
||||
],
|
||||
"id": "9fac6cc561e58b70",
|
||||
"outputs": [],
|
||||
"execution_count": null
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-05T11:27:26.501898Z",
|
||||
"start_time": "2025-09-05T11:27:26.496995Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"def flatfield_correction(raw_image, flat_image, dark_image=None):\n",
|
||||
" \"\"\"\n",
|
||||
" Apply flat-field correction to remove uneven illumination\n",
|
||||
"\n",
|
||||
" Args:\n",
|
||||
" raw_image: Your actual image with crystal\n",
|
||||
" flat_image: Image of uniform illumination (no sample)\n",
|
||||
" dark_image: Dark frame (camera with no light), optional\n",
|
||||
" \"\"\"\n",
|
||||
" # Convert to float for calculations\n",
|
||||
" raw = raw_image.astype(np.float32)\n",
|
||||
" flat = flat_image.astype(np.float32)\n",
|
||||
"\n",
|
||||
" if dark_image is not None:\n",
|
||||
" dark = dark_image.astype(np.float32)\n",
|
||||
" # Subtract dark frame from both\n",
|
||||
" raw_corrected = raw - dark\n",
|
||||
" flat_corrected = flat - dark\n",
|
||||
" else:\n",
|
||||
" raw_corrected = raw\n",
|
||||
" flat_corrected = flat\n",
|
||||
"\n",
|
||||
" # Avoid division by zero\n",
|
||||
" flat_corrected[flat_corrected == 0] = 1\n",
|
||||
"\n",
|
||||
" # Apply correction\n",
|
||||
" mean_flat = np.mean(flat_corrected)\n",
|
||||
" corrected = (raw_corrected / flat_corrected) * mean_flat\n",
|
||||
"\n",
|
||||
" # Convert back to original dtype\n",
|
||||
" return np.clip(corrected, 0, 255).astype(raw_image.dtype)"
|
||||
],
|
||||
"id": "114345da7d31b16d",
|
||||
"outputs": [],
|
||||
"execution_count": 139
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-05T11:43:24.969687Z",
|
||||
"start_time": "2025-09-05T11:43:24.954049Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"def create_ring_mask(image, center=None, inner_radius=50, outer_radius=100):\n",
|
||||
" \"\"\"\n",
|
||||
" Create a mask to exclude a ring region\n",
|
||||
"\n",
|
||||
" Args:\n",
|
||||
" image_shape: (height, width) of your image\n",
|
||||
" center: (cx, cy) center of ring, None for image center\n",
|
||||
" inner_radius: Inner radius of ring to mask out\n",
|
||||
" outer_radius: Outer radius of ring to mask out\n",
|
||||
"\n",
|
||||
" Returns:\n",
|
||||
" mask: Binary mask (0 = exclude ring, 255 = use for correction)\n",
|
||||
" \"\"\"\n",
|
||||
"\n",
|
||||
" if len(image.shape) == 3:\n",
|
||||
" h, w, _ = image.shape\n",
|
||||
" else:\n",
|
||||
" h, w = image.shape\n",
|
||||
"\n",
|
||||
"\n",
|
||||
" if center is None:\n",
|
||||
" center = (w // 2, h // 2)\n",
|
||||
"\n",
|
||||
" # Create coordinate arrays\n",
|
||||
" cx, cy = center\n",
|
||||
"\n",
|
||||
" w = int(w)\n",
|
||||
" h = int(h)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
" x = np.arange(w)\n",
|
||||
" y = np.arange(h)\n",
|
||||
" X, Y = np.meshgrid(x, y)\n",
|
||||
"\n",
|
||||
" # Calculate distances from center\n",
|
||||
" distances = np.sqrt((X - cx)**2 + (Y - cy)**2)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
" # Create mask: exclude the ring region\n",
|
||||
" mask = np.ones((h, w), dtype=np.uint8) * 255\n",
|
||||
" ring_region = (distances >= inner_radius) & (distances <= outer_radius)\n",
|
||||
" mask[ring_region] = 0\n",
|
||||
"\n",
|
||||
" return mask\n",
|
||||
"\n",
|
||||
"def flatfield_correction_with_mask(raw_image, flat_image, mask, dark_image=None):\n",
|
||||
" \"\"\"\n",
|
||||
" Apply flat-field correction with mask to exclude certain regions\n",
|
||||
"\n",
|
||||
" Args:\n",
|
||||
" raw_image: Your camera image\n",
|
||||
" flat_image: Flat-field reference\n",
|
||||
" mask: Binary mask (0 = ignore, 255 = use)\n",
|
||||
" dark_image: Dark frame (optional)\n",
|
||||
" \"\"\"\n",
|
||||
" # Convert to float\n",
|
||||
" raw = raw_image.astype(np.float32)\n",
|
||||
" flat = flat_image.astype(np.float32)\n",
|
||||
"\n",
|
||||
" if dark_image is not None:\n",
|
||||
" dark = dark_image.astype(np.float32)\n",
|
||||
" raw_corrected = raw - dark\n",
|
||||
" flat_corrected = flat - dark\n",
|
||||
" else:\n",
|
||||
" raw_corrected = raw\n",
|
||||
" flat_corrected = flat\n",
|
||||
"\n",
|
||||
" # Apply mask to flat field - only use unmasked regions for correction\n",
|
||||
" mask_float = mask.astype(np.float32) / 255.0\n",
|
||||
"\n",
|
||||
" # Calculate mean only from unmasked regions\n",
|
||||
" if len(flat_corrected.shape) == 3:\n",
|
||||
" # Color image\n",
|
||||
" mean_flat = []\n",
|
||||
" for channel in range(flat_corrected.shape[2]):\n",
|
||||
" masked_flat = flat_corrected[:,:,channel] * mask_float\n",
|
||||
" valid_pixels = masked_flat[mask > 0]\n",
|
||||
" mean_flat.append(np.mean(valid_pixels) if len(valid_pixels) > 0 else 1.0)\n",
|
||||
" mean_flat = np.array(mean_flat).reshape(1, 1, -1)\n",
|
||||
" else:\n",
|
||||
" # Grayscale\n",
|
||||
" masked_flat = flat_corrected * mask_float\n",
|
||||
" valid_pixels = masked_flat[mask > 0]\n",
|
||||
" mean_flat = np.mean(valid_pixels) if len(valid_pixels) > 0 else 1.0\n",
|
||||
"\n",
|
||||
" # Avoid division by zero\n",
|
||||
" flat_corrected[flat_corrected <= 0] = 1\n",
|
||||
"\n",
|
||||
" # Apply correction\n",
|
||||
" corrected = (raw_corrected / flat_corrected) * mean_flat\n",
|
||||
"\n",
|
||||
" # In masked regions, keep original values\n",
|
||||
" mask_3d = mask_float\n",
|
||||
" if len(corrected.shape) == 3:\n",
|
||||
" mask_3d = np.stack([mask_float] * corrected.shape[2], axis=2)\n",
|
||||
"\n",
|
||||
" # Blend: use corrected where mask=1, original where mask=0\n",
|
||||
" final_result = corrected * mask_3d + raw_corrected * (1 - mask_3d)\n",
|
||||
"\n",
|
||||
" return np.clip(final_result, 0, 255).astype(np.uint8)\n",
|
||||
"\n",
|
||||
"def create_interactive_ring_mask(image):\n",
|
||||
" \"\"\"\n",
|
||||
" Interactively create a ring mask by clicking on the image\n",
|
||||
" Click center, then inner radius point, then outer radius point\n",
|
||||
" \"\"\"\n",
|
||||
" points = []\n",
|
||||
"\n",
|
||||
" def mouse_callback(event, x, y, flags, param):\n",
|
||||
" if event == cv2.EVENT_LBUTTONDOWN:\n",
|
||||
" points.append((x, y))\n",
|
||||
" cv2.circle(image, (x, y), 3, (0, 255, 0), -1)\n",
|
||||
" cv2.imshow('Select Ring', image)\n",
|
||||
"\n",
|
||||
" if len(points) == 1:\n",
|
||||
" print(\"Click on inner radius of ring\")\n",
|
||||
" elif len(points) == 2:\n",
|
||||
" print(\"Click on outer radius of ring\")\n",
|
||||
"\n",
|
||||
" cv2.imshow('Select Ring', image)\n",
|
||||
" print(\"Click on center of ring\")\n",
|
||||
" cv2.setMouseCallback('Select Ring', mouse_callback)\n",
|
||||
" cv2.waitKey(0)\n",
|
||||
" cv2.destroyAllWindows()\n",
|
||||
"\n",
|
||||
" if len(points) == 3:\n",
|
||||
" center = points[0]\n",
|
||||
" inner_radius = np.sqrt((points[1][0] - center[0])**2 + (points[1][1] - center[1])**2)\n",
|
||||
" outer_radius = np.sqrt((points[2][0] - center[0])**2 + (points[2][1] - center[1])**2)\n",
|
||||
"\n",
|
||||
" mask = create_ring_mask(image.shape, center, inner_radius, outer_radius)\n",
|
||||
" return mask\n",
|
||||
" else:\n",
|
||||
" print(\"Need 3 points!\")\n",
|
||||
" return None\n"
|
||||
],
|
||||
"id": "a1ae8c16d1cb31f7",
|
||||
"outputs": [],
|
||||
"execution_count": 154
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-08T14:23:06.438502Z",
|
||||
"start_time": "2025-09-08T14:23:02.773985Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"min_contour_area = 4\n",
|
||||
"mask = create_ring_mask(curr_img, inner_radius=1000,outer_radius=2000)\n",
|
||||
"diff_image = cv2.absdiff(curr_img, bkg)\n",
|
||||
"diff_image = cv2.cvtColor(diff_image, cv2.COLOR_RGB2GRAY)\n",
|
||||
"thresh_value, binary_image = cv2.threshold(diff_image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)\n",
|
||||
"thresh_value, thresh_normal = cv2.threshold(diff_image, 50, 255, cv2.THRESH_BINARY)\n",
|
||||
"ff = flatfield_correction(curr_img, bkg, dark_image=None)\n",
|
||||
"ff = cv2.cvtColor(ff, cv2.COLOR_RGB2GRAY)\n",
|
||||
"ff_masked = flatfield_correction_with_mask(curr_img, bkg, mask, dark_image=None)\n",
|
||||
"ff_masked = cv2.cvtColor(ff_masked, cv2.COLOR_RGB2GRAY)\n",
|
||||
"thresh_value, thresh_mask = cv2.threshold(ff_masked, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)\n",
|
||||
"kernel = np.ones((3,3), np.uint8)\n",
|
||||
"thresh = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)\n",
|
||||
"thresh = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)\n",
|
||||
"\n",
|
||||
"contours, _ = cv2.findContours(thresh_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n",
|
||||
"valid_contours = [cnt for cnt in contours if cv2.contourArea(cnt) > min_contour_area]\n",
|
||||
"\n",
|
||||
"largest_contour = max(valid_contours, key=cv2.contourArea)\n",
|
||||
"\n",
|
||||
"# Step 6: Find leftmost point\n",
|
||||
"leftmost_point = tuple(largest_contour[largest_contour[:,:,0].argmin()][0])\n",
|
||||
"print(leftmost_point)\n",
|
||||
"\n",
|
||||
"leftmost_point = None\n",
|
||||
"\n",
|
||||
"for contour in contours:\n",
|
||||
" # Loop through each point in the current contour\n",
|
||||
" for point in contour:\n",
|
||||
" x, y = point[0] # Point is a nested array [ [x, y] ]\n",
|
||||
"\n",
|
||||
" # Check if this is the leftmost point\n",
|
||||
" if leftmost_point is None or x < leftmost_point[0]:\n",
|
||||
" leftmost_point = (x, y)\n",
|
||||
" plot_contour = contour\n",
|
||||
"print(leftmost_point)\n",
|
||||
"\n",
|
||||
"c_img = cv2.drawContours(thresh, contours, -1, (0, 255, 0), 1)\n",
|
||||
"plt.subplot(2, 2, 1)\n",
|
||||
"plt.imshow(diff_image)\n",
|
||||
"plt.subplot(2, 2, 2)\n",
|
||||
"plt.imshow(thresh_normal)\n",
|
||||
"#plt.subplot(2, 2, 4)\n",
|
||||
"#plt.imshow(ff_masked)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"result_image = cv2.cvtColor(thresh, cv2.COLOR_GRAY2BGR) if len(thresh.shape) == 2 else thresh.copy()\n",
|
||||
"\n",
|
||||
"# Draw contour\n",
|
||||
"result_image = cv2.drawContours(result_image, [largest_contour], -1, (0, 255, 0), 2)\n",
|
||||
"\n",
|
||||
"# Mark leftmost point\n",
|
||||
"result_image = cv2.circle(result_image, leftmost_point, 100, (0, 0, 255), -1)\n",
|
||||
"result_image = cv2.putText(result_image, f'Leftmost: {leftmost_point}',\n",
|
||||
" (leftmost_point[0] + 10, leftmost_point[1] - 10),\n",
|
||||
" cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)\n",
|
||||
"\n",
|
||||
"print(f'Leftmost point: {leftmost_point}')\n",
|
||||
"\n",
|
||||
"plt.subplot(2, 2, 3)\n",
|
||||
"plt.imshow(binary_image)\n"
|
||||
],
|
||||
"id": "a5363e8d3c71448",
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(np.int32(24), np.int32(979))\n",
|
||||
"(np.int32(24), np.int32(979))\n",
|
||||
"Leftmost point: (np.int32(24), np.int32(979))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<matplotlib.image.AxesImage at 0x7f97e92802c0>"
|
||||
]
|
||||
},
|
||||
"execution_count": 354,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<Figure size 640x480 with 3 Axes>"
|
||||
],
|
||||
"image/png": "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 truncated
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"execution_count": 354
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-08T14:02:01.581369Z",
|
||||
"start_time": "2025-09-08T14:01:56.983788Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"# Load image and convert\n",
|
||||
"img = cv2.imread('/home/leonarski_f/aaredaq/daq/src/aaredaq/991_0_1_50_50_curr_image.tiff', cv2.IMREAD_COLOR)\n",
|
||||
"#img = cv2.imread('/home/leonarski_f/aaredaq/daq/src/aaredaq/0_280_100_50_curr_image_colour.jpg', cv2.IMREAD_COLOR)\n",
|
||||
"\n",
|
||||
"bkg = cv2.imread('/home/leonarski_f/aaredaq/daq/src/aaredaq/bkg1_50_50.jpg')\n",
|
||||
"# Convert to grayscale & enhance\n",
|
||||
"gray_bkg = cv2.cvtColor(bkg, cv2.COLOR_BGR2GRAY)\n",
|
||||
"gray = cv2.subtract(gray, gray_bkg)\n",
|
||||
"gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n",
|
||||
"gray = cv2.GaussianBlur(gray, (5, 5), 0)\n",
|
||||
"gray = cv2.equalizeHist(gray)\n",
|
||||
"\n",
|
||||
"# Mask out camera-case ring\n",
|
||||
"#gray = cv2.subtract(gray, gray_bkg)\n",
|
||||
"mask = np.zeros_like(gray, dtype=np.uint8)\n",
|
||||
"h, w = gray.shape\n",
|
||||
"radius = min(h, w)//2 - 20\n",
|
||||
"center = (w//2, h//2)\n",
|
||||
"\n",
|
||||
"norm=gray\n",
|
||||
"print(radius)\n",
|
||||
"\n",
|
||||
"#norm = flatfield_correction_with_mask(gray, gray_bkg, mask)\n",
|
||||
"\n",
|
||||
"#radius = 500#radius#-factor\n",
|
||||
"print(gray.shape)\n",
|
||||
"# # gray = cv2.bitwise_and(gray, gray, mask=mask)\n",
|
||||
"# # x, y = center[0] - radius, center[1] - radius\n",
|
||||
"# gray_cropped = gray[y:y+2*radius, x:x+2*radius]\n",
|
||||
"# #gray_bkg_cropped = gray[y:y+2*radius, x:x+2*radius]\n",
|
||||
"# #cv2.circle(mask, center, radius, 93, -1)\n",
|
||||
"# print(gray_cropped.shape)\n",
|
||||
"#\n",
|
||||
"# #masked = cv2.bitwise_and(gray, gray, mask=mask)\n",
|
||||
"# #norm = gray_cropped\n",
|
||||
"# masked=gray_cropped\n",
|
||||
"# background= cv2.medianBlur(masked, 51)\n",
|
||||
"#\n",
|
||||
"# norm = cv2.subtract(masked, background)\n",
|
||||
"#norm = cv2.absdiff(masked,gray_bkg)\n",
|
||||
"kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (25,25))\n",
|
||||
"tophat = cv2.morphologyEx(norm, cv2.MORPH_TOPHAT, kernel)\n",
|
||||
"\n",
|
||||
"enhanced = cv2.addWeighted(norm, 0.7, tophat, 0.3, 0)\n",
|
||||
"# Adaptive thresholding\n",
|
||||
"thresh = cv2.adaptiveThreshold(enhanced, 255, cv2.ADAPTIVE_THRESH_MEAN_C,\n",
|
||||
" cv2.THRESH_BINARY_INV, 41, 2)\n",
|
||||
"\n",
|
||||
"# Find contours\n",
|
||||
"contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)\n",
|
||||
"\n",
|
||||
"best_point = None\n",
|
||||
"min_x = w + 1\n",
|
||||
"\n",
|
||||
"print(len(contours))\n",
|
||||
"for cnt in contours:\n",
|
||||
" x,y,wc,hc = cv2.boundingRect(cnt)\n",
|
||||
"\n",
|
||||
" # Skip very large contours (likely mask boundary)\n",
|
||||
" if cv2.contourArea(cnt) > 0.2 * h * w:\n",
|
||||
" print(\"Skipping contour with area\", cv2.contourArea(cnt))\n",
|
||||
" continue\n",
|
||||
"\n",
|
||||
" # Compute distance of contour centroid from image center\n",
|
||||
" M = cv2.moments(cnt)\n",
|
||||
" if M[\"m00\"] != 0:\n",
|
||||
" cx = int(M[\"m10\"]/M[\"m00\"])\n",
|
||||
" cy = int(M[\"m01\"]/M[\"m00\"])\n",
|
||||
" dist = np.sqrt((cx-center[0])**2 + (cy-center[1])**2)\n",
|
||||
" # If centroid is near mask radius, skip (mask edge)\n",
|
||||
" #if abs(dist - radius) < 60:\n",
|
||||
" # print(\"Skipping contour near mask radius\")\n",
|
||||
" # continue\n",
|
||||
"\n",
|
||||
" # Skip vertical pin\n",
|
||||
" if hc > 3*wc:\n",
|
||||
" print(\"Skipping vertical pin\")\n",
|
||||
" continue\n",
|
||||
"\n",
|
||||
" leftmost = tuple(cnt[cnt[:, :, 0].argmin()][0])\n",
|
||||
" if leftmost[0] < min_x:\n",
|
||||
" min_x = leftmost[0]\n",
|
||||
" best_point = leftmost\n",
|
||||
"\n",
|
||||
"# Draw result\n",
|
||||
"if best_point is not None:\n",
|
||||
" print(f\"best_point = {best_point}\")\n",
|
||||
" #cv2.circle(thresh, best_point, 100, (0, 0, 255), -1)\n",
|
||||
" print(radius)\n",
|
||||
" corrected_point = (best_point[0]+factor, best_point[1] +factor)\n",
|
||||
" print(f\"corrected_point {corrected_point}\")\n",
|
||||
" cv2.circle(img, corrected_point, 100, (0, 0, 255), -1)\n",
|
||||
" print(\"Loop tip (leftmost point):\", best_point)\n",
|
||||
"else:\n",
|
||||
" print(\"No suitable contour found\")\n",
|
||||
"\n",
|
||||
"plt.figure(figsize=(10,8))\n",
|
||||
"plt.figure(figsize=(14,10))\n",
|
||||
"plt.subplot(2,4,1); plt.title(\"Original\"); plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))#; plt.axis(\"off\")\n",
|
||||
"plt.subplot(2,4,2); plt.title(\"Cropped\"); plt.imshow(gray_cropped, cmap=\"gray\"); plt.axis(\"off\")\n",
|
||||
"plt.subplot(2,4,3); plt.title(\"Background\"); plt.imshow(norm, cmap=\"gray\"); plt.axis(\"off\")\n",
|
||||
"plt.subplot(2,4,4); plt.title(\"Top-hat\"); plt.imshow(tophat, cmap=\"gray\"); plt.axis(\"off\")\n",
|
||||
"plt.subplot(2,4,5); plt.title(\"Enhanced\"); plt.imshow(enhanced, cmap=\"gray\"); plt.axis(\"off\")\n",
|
||||
"plt.subplot(2,4,6); plt.title(\"Threshold\"); plt.imshow(thresh, cmap=\"gray\")#; plt.axis(\"off\")\n",
|
||||
"plt.subplot(2,4,7); plt.title(\"image with contours\"); #plt.imshow(img)#; plt.axis(\"off\")\n",
|
||||
"contour_vis = cv2.cvtColor(masked, cv2.COLOR_GRAY2BGR)\n",
|
||||
"cv2.drawContours(contour_vis, contours, -1, (0,255,0), 1)\n",
|
||||
"cv2.circle(contour_vis, best_point, 100, (0, 0, 255), -1)\n",
|
||||
"plt.imshow(contour_vis)\n",
|
||||
"plt.show()\n",
|
||||
"\n",
|
||||
"cv2.imwrite('masked.tiff', enhanced)\n",
|
||||
"cv2.imwrite('thresh.tiff', thresh)"
|
||||
],
|
||||
"id": "d98c070865b11f36",
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"1003\n",
|
||||
"(2046, 2046)\n",
|
||||
"10291\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping contour with area 2054203.5\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"Skipping vertical pin\n",
|
||||
"best_point = (np.int32(0), np.int32(1421))\n",
|
||||
"1003\n",
|
||||
"corrected_point (np.int32(250), np.int32(1671))\n",
|
||||
"Loop tip (leftmost point): (np.int32(0), np.int32(1421))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<Figure size 1000x800 with 0 Axes>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<Figure size 1400x1000 with 7 Axes>"
|
||||
],
|
||||
"image/png": "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 truncated
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"True"
|
||||
]
|
||||
},
|
||||
"execution_count": 350,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"execution_count": 350
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-08T11:21:42.726663Z",
|
||||
"start_time": "2025-09-08T11:21:41.711795Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"x#bkg_old = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/alc_test_images/bkg280_020925.jpg\")\n",
|
||||
"#bkg_new = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/alc_test_images/bkg280_03092025.jpg\")\n",
|
||||
"bkg_old = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/bkg280_50_50_old.jpg\")\n",
|
||||
"bkg_new = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/bkg280_50_50.jpg\")\n",
|
||||
"#$bkg_newest = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/bkg280.jpg\")\n",
|
||||
"grey_old = cv2.cvtColor(bkg_old, cv2.COLOR_RGB2GRAY)\n",
|
||||
"grey_new = cv2.cvtColor(bkg_new, cv2.COLOR_RGB2GRAY)\n",
|
||||
"#grey_newest = cv2.cvtColor(bkg_newest, cv2.COLOR_RGB2GRAY)\n",
|
||||
"diff_image = cv2.absdiff(grey_old, grey_new)\n",
|
||||
"_, thresh_diff = cv2.threshold(diff_image, threshold, 255, cv2.THRESH_BINARY)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Simple subtraction (may result in negative values)\n",
|
||||
"diff_simple = cv2.subtract(bkg_new, bkg_old)\n",
|
||||
"\n",
|
||||
"# Weighted difference for motion detection\n",
|
||||
"diff_weighted = cv2.addWeighted(bkg_new, 0.5, bkg_old, -0.5, 128)\n",
|
||||
"\n",
|
||||
"# Using numpy for difference\n",
|
||||
"diff_numpy = np.abs(bkg_new.astype(np.int16) - bkg_old.astype(np.int16)).astype(np.uint8)\n",
|
||||
"\n",
|
||||
"plt.subplot(1,2,1)\n",
|
||||
"plt.imshow(bkg_old)\n",
|
||||
"plt.subplot(1,2,2)\n",
|
||||
"plt.imshow(bkg_new)"
|
||||
],
|
||||
"id": "5c26fa11f85e6483",
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<matplotlib.image.AxesImage at 0x7f97bc9dc7a0>"
|
||||
]
|
||||
},
|
||||
"execution_count": 275,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<Figure size 640x480 with 2 Axes>"
|
||||
],
|
||||
"image/png": "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 truncated
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"execution_count": 275
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-08T08:13:17.148953Z",
|
||||
"start_time": "2025-09-08T08:13:17.046977Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"bkg_old_np = bkg_old.astype(np.float32)\n",
|
||||
"bkg_old_np_normalized = bkg_old.astype(np.float32) / 255.0\n",
|
||||
"bkg_new_np = bkg_old.astype(np.float32)\n",
|
||||
"bkg_new_np_normalized = bkg_old.astype(np.float32) / 255.0\n",
|
||||
"diff_np=bkg_old_np-bkg_new_np\n",
|
||||
"diff_np_normalized=bkg_old_np_normalized-bkg_new_np_normalized"
|
||||
],
|
||||
"id": "95a0ac65d0013e8",
|
||||
"outputs": [],
|
||||
"execution_count": 196
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-08T08:14:30.738697Z",
|
||||
"start_time": "2025-09-08T08:14:30.671257Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"print(\"mean: \", np.mean(grey_old.astype(np.float32)-grey_new.astype(np.float32)))\n",
|
||||
"print(\"std: \", np.std(grey_old.astype(np.float32)-grey_new.astype(np.float32)))\n",
|
||||
"diff_abs = np.abs(grey_old.astype(np.float32)-grey_new.astype(np.float32))\n",
|
||||
"print(np.percentile(diff_abs, 99))"
|
||||
],
|
||||
"id": "83aae96e9df6c807",
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"mean: -6.184164\n",
|
||||
"std: 5.93317\n",
|
||||
"21.0\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"execution_count": 200
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "code",
|
||||
"outputs": [],
|
||||
"execution_count": null,
|
||||
"source": [
|
||||
"threshold_old = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/alc_test_images/bkg280_020925.jpg\")\n",
|
||||
"threshold_new = cv2.imread(\"/home/leonarski_f/aaredaq/daq/src/aaredaq/alc_test_images/bkg280_03092025.jpg\")"
|
||||
],
|
||||
"id": "258a3d679516f15c"
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-05T13:33:03.863166Z",
|
||||
"start_time": "2025-09-05T13:33:03.839938Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"from scipy import ndimage\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"\n",
|
||||
"# Example showing the difference\n",
|
||||
"image = np.random.rand(50, 50) * 100\n",
|
||||
"# Add a bright spot\n",
|
||||
"image[20:30, 35:45] = 200\n",
|
||||
"\n",
|
||||
"# Without thresholding - all pixels contribute\n",
|
||||
"com_no_threshold = ndimage.center_of_mass(image)\n",
|
||||
"print(f\"No threshold COM: ({com_no_threshold[1]:.2f}, {com_no_threshold[0]:.2f})\")\n",
|
||||
"\n",
|
||||
"# With thresholding - only bright pixels contribute\n",
|
||||
"threshold = 150\n",
|
||||
"thresholded = image.copy()\n",
|
||||
"thresholded[thresholded < threshold] = 0\n",
|
||||
"com_with_threshold = ndimage.center_of_mass(thresholded)\n",
|
||||
"print(f\"With threshold COM: ({com_with_threshold[1]:.2f}, {com_with_threshold[0]:.2f})\")\n"
|
||||
],
|
||||
"id": "d70801a606268e76",
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"No threshold COM: (26.11, 24.33)\n",
|
||||
"With threshold COM: (39.50, 24.50)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"execution_count": 189
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-05T13:33:18.254639Z",
|
||||
"start_time": "2025-09-05T13:33:18.248074Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"def center_of_mass_with_threshold(image, threshold):\n",
|
||||
" \"\"\"\n",
|
||||
" Apply threshold before center of mass calculation\n",
|
||||
" \"\"\"\n",
|
||||
" # Create binary mask\n",
|
||||
" binary = (image >= threshold).astype(float)\n",
|
||||
"\n",
|
||||
" # Calculate center of mass on thresholded image\n",
|
||||
" com = ndimage.center_of_mass(binary)\n",
|
||||
"\n",
|
||||
" # Return as (x, y) coordinates\n",
|
||||
" return (com[1], com[0]) if com[0] is not np.nan else None\n"
|
||||
],
|
||||
"id": "1ba37750a7b66b23",
|
||||
"outputs": [],
|
||||
"execution_count": 190
|
||||
},
|
||||
{
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-09-05T13:33:27.236834Z",
|
||||
"start_time": "2025-09-05T13:33:27.231958Z"
|
||||
}
|
||||
},
|
||||
"cell_type": "code",
|
||||
"source": [
|
||||
"def weighted_center_of_mass_threshold(image, threshold):\n",
|
||||
" \"\"\"\n",
|
||||
" Keep original intensities above threshold, zero below\n",
|
||||
" \"\"\"\n",
|
||||
" weighted_image = image.copy()\n",
|
||||
" weighted_image[weighted_image < threshold] = 0\n",
|
||||
"\n",
|
||||
" com = ndimage.center_of_mass(weighted_image)\n",
|
||||
" return (com[1], com[0]) if com[0] is not np.nan else None\n"
|
||||
],
|
||||
"id": "59452341d64bc800",
|
||||
"outputs": [],
|
||||
"execution_count": 191
|
||||
},
|
||||
{
|
||||
"metadata": {},
|
||||
"cell_type": "code",
|
||||
"outputs": [],
|
||||
"execution_count": null,
|
||||
"source": "",
|
||||
"id": "8cf8041e736e5a43"
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 2
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython2",
|
||||
"version": "2.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in new issue
Block a user