From 6943e6eea0eee1ccf3ee9034699b6a94f334b003 Mon Sep 17 00:00:00 2001
From: Constantin Wenger <constantin.wenger@googlemail.com>
Date: Tue, 01 Feb 2022 11:38:21 +0000
Subject: [PATCH] added option to load from streams added option to set crop x and crop y added option to set percentage a card must take up added ability to scroll detected cards list with o and p added ability to remove topmost shown detected card with u
---
opencv_dnn.py | 268 +++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 205 insertions(+), 63 deletions(-)
diff --git a/opencv_dnn.py b/opencv_dnn.py
old mode 100644
new mode 100755
index bf01980..744d012
--- a/opencv_dnn.py
+++ b/opencv_dnn.py
@@ -28,7 +28,7 @@
new_pool = pd.DataFrame(columns=list(card_pool.columns.values))
for hs in hash_size:
new_pool['card_hash_%d' % hs] = np.NaN
- new_pool['set_hash_%d' % hs] = np.NaN
+ new_pool['set_hash_%d' % 64] = np.NaN
#new_pool['art_hash_%d' % hs] = np.NaN
for ind, card_info in card_pool.iterrows():
if ind % 100 == 0:
@@ -49,31 +49,52 @@
for card_name in card_names:
# Fetch the image - name can be found based on the card's information
card_info['name'] = card_name
+ cname = card_name
+ if cname == 'con':
+ cname == 'con__'
img_name = '%s/card_img/png/%s/%s_%s.png' % (Config.data_dir, card_info['set'],
card_info['collector_number'],
- fetch_data.get_valid_filename(card_info['name']))
+ fetch_data.get_valid_filename(cname))
card_img = cv2.imread(img_name)
# If the image doesn't exist, download it from the URL
if card_img is None:
+ set_name = card_info['set']
+ if set_name == 'con':
+ set_name = 'con__'
fetch_data.fetch_card_image(card_info,
- out_dir='%s/card_img/png/%s' % (Config.data_dir, card_info['set']))
+ out_dir='%s/card_img/png/%s' % (Config.data_dir, set_name))
card_img = cv2.imread(img_name)
if card_img is None:
print('WARNING: card %s is not found!' % img_name)
continue
-
- set_img = card_img[575:638, 567:700]
+ """
+ img_cc = cv2.cvtColor(card_img, cv2.COLOR_BGR2GRAY)
+ img_thresh = cv2.adaptiveThreshold(img_cc, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 11, 5)
+ # Dilute the image, then erode them to remove minor noises
+ kernel = np.ones((3, 3), np.uint8)
+ img_dilate = cv2.dilate(img_thresh, kernel, iterations=1)
+ img_erode = cv2.erode(img_dilate, kernel, iterations=1)
+ cnts, hier = cv2.findContours(img_erode, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
+ cnts2 = sorted(cnts, key=cv2.contourArea, reverse=True)
+ cnts2 = cnts2[:10]
+ if True:
+ cv2.drawContours(img_cc, cnts2, -1, (0, 255, 0), 3)
+ #cv2.imshow('Contours', card_img)
+ #cv2.waitKey(10000)
+ """
+ set_img = card_img[595:635, 600:690]
#cv2.imshow(card_info['name'], set_img)
# Compute value of the card's perceptual hash, then store it to the database
#img_art = Image.fromarray(card_img[121:580, 63:685]) # For 745*1040 size card image
img_card = Image.fromarray(card_img)
img_set = Image.fromarray(set_img)
+ #cv2.imshow('Set' + card_names[0], set_img)
for hs in hash_size:
card_hash = ih.phash(img_card, hash_size=hs)
- set_hash = ih.whash(img_set, hash_size=hs)
+ set_hash = ih.phash(img_set, hash_size=64)
card_info['card_hash_%d' % hs] = card_hash
- card_info['set_hash_%d' % hs] = set_hash
+ card_info['set_hash_%d' % 64] = set_hash
#print('Setting set_hash_%d' % hs)
#art_hash = ih.phash(img_art, hash_size=hs)
#card_info['art_hash_%d' % hs] = art_hash
@@ -93,8 +114,10 @@
elif isinstance(hash_size, int):
hash_size = [hash_size]
- num_cores = 15
- num_partitions = 60
+ num_cores = 16
+ num_partitions = round(card_pool.shape[0]/1000)
+ if num_partitions < min(num_cores, card_pool.shape[0]):
+ num_partitions = min(num_cores, card_pool.shape[0])
pool = Pool(num_cores)
df_split = np.array_split(card_pool, num_partitions)
new_pool = pd.concat(pool.map(do_calc, [(split, hash_size) for split in df_split]))
@@ -216,7 +239,7 @@
return corrected
-def find_card(img, thresh_c=5, kernel_size=(3, 3), size_thresh=10000):
+def find_card(img, thresh_c=5, kernel_size=(3, 3), size_thresh=10000, debug=False):
"""
Find contours of all cards in the image
:param img: source image
@@ -229,25 +252,28 @@
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.medianBlur(img_gray, 5)
img_thresh = cv2.adaptiveThreshold(img_blur, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, 11, thresh_c)
- cv2.imshow('Thres', img_thresh)
+ if debug:
+ cv2.imshow('Thres', img_thresh)
# Dilute the image, then erode them to remove minor noises
kernel = np.ones(kernel_size, np.uint8)
img_dilate = cv2.dilate(img_thresh, kernel, iterations=1)
img_erode = cv2.erode(img_dilate, kernel, iterations=1)
- cv2.imshow('Eroded', img_erode)
+ if debug:
+ cv2.imshow('Eroded', img_erode)
# Find the contour
cnts, hier = cv2.findContours(img_erode, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
if len(cnts) == 0:
- #print('no contours')
+# print('no contours')
return []
img_cont = cv2.cvtColor(img_erode, cv2.COLOR_GRAY2BGR)
img_cont_base = img_cont.copy()
cnts2 = sorted(cnts, key=cv2.contourArea, reverse=True)
cnts2 = cnts2[:10]
- for i in range(0, len(cnts2)):
- print(i, len(cnts2[i]))
- cv2.drawContours(img_cont, cnts2, -1, (0, 255, 0), 3)
- cv2.imshow('Contours', img_cont)
+# for i in range(0, len(cnts2)):
+# print(i, len(cnts2[i]))
+ if debug:
+ cv2.drawContours(img_cont, cnts2, -1, (0, 255, 0), 3)
+ cv2.imshow('Contours', img_cont)
# The hierarchy from cv2.findContours() is similar to a tree: each node has an access to the parent, the first child
# their previous and next node
# Using recursive search, find the uppermost contour in the hierarchy that satisfies the condition
@@ -263,6 +289,8 @@
size = cv2.contourArea(cnt)
peri = cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, 0.04 * peri, True)
+ #print('Base Size:', size)
+ #print('Len Approx:', len(approx))
if size >= size_thresh and len(approx) == 4:
# lets see if we got a contour very close in size as child
if i_child != -1:
@@ -277,30 +305,30 @@
# child with biggest area
c_list.sort(key=cv2.contourArea, reverse=True)
c_cnt = c_list[0] # the biggest child
- cv2.drawContours(img_ccont, c_list[:1], -1, (0, 255, 0), 1)
- cv2.imshow('CCont %d' % i_cnt, img_ccont)
+ if debug:
+ cv2.drawContours(img_ccont, c_list[:1], -1, (0, 255, 0), 1)
+ cv2.imshow('CCont', img_ccont)
c_size = cv2.contourArea(c_cnt)
c_approx = cv2.approxPolyDP(c_cnt, 0.04 * peri, True)
if len(c_approx) == 4 and (c_size/size) > 0.85:
rect = cv2.minAreaRect(c_cnt)
box = cv2.boxPoints(rect)
box = np.intp(box)
- print(c_cnt)
- print(box)
+ #print(c_cnt)
+ #print(box)
- print('CSize:', c_size, '%:', c_size/size)
+ #print('CSize:', c_size, '%:', c_size/size)
b2 = []
for x in box:
b2.append([x])
cnts_rect.append(np.array(b2))
-
else:
- print('CF:', (c_size/size))
- print('Size:', size)
+ #print('CF:', (c_size/size))
+ #print('Size:', size)
cnts_rect.append(approx)
else:
- print('CF:', (c_size/size))
- print('Size:', size)
+ #print('CF:', (c_size/size))
+ #print('Size:', size)
cnts_rect.append(approx)
else:
if i_child != -1:
@@ -369,7 +397,7 @@
return img_graph
-def detect_frame(img, card_pool, hash_size=32, size_thresh=100000,
+def detect_frame(img, card_pool, hash_size=32, size_thresh=10000,
out_path=None, display=True, debug=False):
"""
Identify all cards in the input frame, display or save the frame if needed
@@ -386,8 +414,10 @@
img_result = img.copy() # For displaying and saving
det_cards = []
# Detect contours of all cards in the image
- cnts = find_card(img_result, size_thresh=size_thresh)
+ cnts = find_card(img_result, size_thresh=size_thresh, debug=debug)
+ #print('Contours:', len(cnts))
for i in range(len(cnts)):
+ #print('Contour', i)
cnt = cnts[i]
# For the region of the image covered by the contour, transform them into a rectangular image
pts = np.float32([p[0] for p in cnt])
@@ -406,13 +436,15 @@
'''
img_card = Image.fromarray(img_warp.astype('uint8'), 'RGB')
img_card_size = img_warp.shape
- print(img_card_size)
+ #print(img_card_size)
cut = [round(img_card_size[0]*0.57),round(img_card_size[0]*0.615),round(img_card_size[1]*0.81),round(img_card_size[1]*0.940)]
- print(cut)
+ #print(cut)
img_set_part = img_warp[cut[0]:cut[1], cut[2]:cut[3]]
- print(img_set_part.shape)
+ #print(img_set_part.shape)
img_set = Image.fromarray(img_set_part.astype('uint8'), 'RGB')
- cv2.imshow("Set Img#%d" % i, img_set_part)
+ #print('img set')
+ if debug:
+ cv2.imshow("Set Img#%d" % i, img_set_part)
# the stored values of hashes in the dataframe is pre-emptively flattened already to minimize computation time
card_hash = ih.phash(img_card, hash_size=hash_size).hash.flatten()
@@ -422,31 +454,35 @@
hash_diff = min_card['hash_diff']
top_matches = sorted(card_pool['hash_diff'])
- set_img_hash = ih.whash(img_set, hash_size=hash_size).hash.flatten()
- cd_data = pd.DataFrame(columns=list(card_pool.columns.values))
- print(list(card_pool.columns.values))
- candidates = []
- for ix in range(0, 2):
- cdr = card_pool[card_pool['hash_diff'] == top_matches[ix]].iloc[0]
- cd_data.loc[0 if cd_data.empty else cd_data.index.max()+1] = cdr
- cd = cdr
- print('Idx:', ix, 'Name:', cd['name'], 'Set:', cd['set'], 'Diff:', top_matches[ix])
+ card_one = card_pool[card_pool['hash_diff'] == top_matches[0]].iloc[0]
+ card_two = card_pool[card_pool['hash_diff'] == top_matches[1]].iloc[0]
- cd_data['set_hash_diff'] = cd_data['set_hash_%d' % hash_size]
- cd_data['set_hash_diff'] = cd_data['set_hash_diff'].apply(lambda x: np.count_nonzero(x != set_img_hash))
- conf = sorted(cd_data['set_hash_diff'])
- print('Confs:', conf)
- best_match = cd_data[cd_data['set_hash_diff'] == min(cd_data['set_hash_diff'])].iloc[0]
- print('Best Match', 'Name:', best_match['name'], 'Set:', best_match['set'])
+ if card_one['name'] == card_two['name'] and card_one['set'] != card_two['set']:
+ set_img_hash = ih.whash(img_set, hash_size=hash_size).hash.flatten()
+ cd_data = pd.DataFrame(columns=list(card_pool.columns.values))
+# print(list(card_pool.columns.values))
+ candidates = []
+ for ix in range(0, 2):
+ cd = card_pool[card_pool['hash_diff'] == top_matches[ix]].iloc[0]
+ cd_data.loc[0 if cd_data.empty else cd_data.index.max()+1] = cd
+# print('Idx:', ix, 'Name:', cd['name'], 'Set:', cd['set'], 'Diff:', top_matches[ix])
- min_card = best_match
+
+ cd_data['set_hash_diff'] = cd_data['set_hash_%d' % 64]
+ cd_data['set_hash_diff'] = cd_data['set_hash_diff'].apply(lambda x: np.count_nonzero(x != set_img_hash))
+ conf = sorted(cd_data['set_hash_diff'])
+ #print('Confs:', conf)
+ best_match = cd_data[cd_data['set_hash_diff'] == min(cd_data['set_hash_diff'])].iloc[0]
+ #print('Best Match', 'Name:', best_match['name'], 'Set:', best_match['set'])
+
+ min_card = best_match
card_name = min_card['name']
card_set = min_card['set']
det_cards.append((card_name, card_set))
# Render the result, and display them if needed
cv2.drawContours(img_result, [cnt], -1, (0, 255, 0), 2)
- cv2.putText(img_result, card_name, (min(pts[0][0], pts[1][0]), min(pts[0][1], pts[1][1])),
+ cv2.putText(img_result, card_name, (int(min(pts[0][0], pts[1][0])), int(min(pts[0][1], pts[1][1]))),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
if debug:
# cv2.rectangle(img_warp, (22, 47), (294, 249), (0, 255, 0), 2)
@@ -455,15 +491,16 @@
cv2.imshow('card#%d' % i, img_warp)
if display:
cv2.imshow('Result', img_result)
- cv2.waitKey(0)
+ inp = cv2.waitKey(0)
if out_path is not None:
+ print(out_path)
cv2.imwrite(out_path, img_result.astype(np.uint8))
return det_cards, img_result
def detect_video(capture, card_pool, hash_size=32, size_thresh=10000,
- out_path=None, display=True, show_graph=True, debug=False):
+ out_path=None, display=True, show_graph=True, debug=False, crop_x=0, crop_y=0):
"""
Identify all cards in the continuous video stream, display or save the result if needed
:param capture: input video stream
@@ -477,11 +514,13 @@
:return: list of detected card's name/set and resulting image
:return:
"""
+ list_names_from = 0
# Get the dimension of the output video, and set it up
if show_graph:
img_graph = draw_card_graph({}, pd.DataFrame(), -1) # Black image of the graph just to get the dimension
- width = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH)) + img_graph.shape[1]
- height = max(round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)), img_graph.shape[0])
+ width = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH)) - 2*crop_x + img_graph.shape[1]
+ height = max(round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)) - 2*crop_y, img_graph.shape[0])
+ height += 200 # some space to display last detected cards
else:
width = round(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
height = round(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
@@ -490,17 +529,35 @@
max_num_obj = 0
f_len = 10 # number of frames to consider to check for existing cards
exist_cards = {}
+
+ exist_card_single = {}
+ written_out_cards = set()
+ found_cards = []
try:
while True:
ret, frame = capture.read()
+ if not ret:
+ continue
+ y_max_index = -crop_y
+ if crop_y == 0:
+ y_max_index = frame.shape[0]
+ x_max_index = -crop_x
+ if crop_x == 0:
+ x_max_index = frame.shape[1]
+
+ croped_img = frame[crop_y:y_max_index, crop_x:x_max_index]
+ fimg = cv2.flip(croped_img, -1)
start_time = time.time()
if not ret:
# End of video
print("End of video. Press any key to exit")
cv2.waitKey(0)
break
+ if fimg is None:
+ print("flipped image is none")
+ break
# Detect all cards from the current frame
- det_cards, img_result = detect_frame(frame, card_pool, hash_size=hash_size, size_thresh=size_thresh,
+ det_cards, img_result = detect_frame(fimg, card_pool, hash_size=hash_size, size_thresh=size_thresh,
out_path=None, display=False, debug=debug)
if show_graph:
# If the card was already detected in the previous frame, append 1 to the list
@@ -522,18 +579,53 @@
else:
exist_cards[key] = exist_cards[key][1 - f_len:] + [0]
if len(val) == f_len and sum(val) == 0:
- gone.append(key)
+ gone.append(key) # not there anymore
+
+ det_card_map = {}
+ gone_single = []
+ for card_name, card_set in det_cards:
+ skey = '%s (%s)' % (card_name, card_set)
+ det_card_map[skey] = (card_name, card_set)
+
+ for key, val in exist_card_single.items():
+ if key in det_card_map:
+ exist_card_single[key] = exist_card_single[key][1 - f_len:] + [1]
+ else:
+ exist_card_single[key] = exist_card_single[key][1 - f_len:] + [0]
+
+ if len(val) == f_len and sum(val) == 0:
+ gone_single.append(key)
+ if key in written_out_cards:
+ written_out_cards.remove(key)
+ if len(val) == f_len and sum(val) == f_len:
+ if key not in written_out_cards and key in det_card_map:
+ written_out_cards.add(key)
+ found_cards.append(det_card_map[key])
+ list_names_from += 1
+
+ for key in det_card_map:
+ if key not in exist_card_single.keys():
+ exist_card_single[key] = [1]
+ for key in gone_single:
+ exist_card_single.pop(key)
+
+
for key in det_cards_list:
if key not in exist_cards.keys():
exist_cards[key] = [1]
for key in gone:
exist_cards.pop(key)
+
# Draw the graph based on the history of detected cards, then concatenate it with the result image
img_graph = draw_card_graph(exist_cards, card_pool, f_len)
img_save = np.zeros((height, width, 3), dtype=np.uint8)
img_save[0:img_result.shape[0], 0:img_result.shape[1]] = img_result
img_save[0:img_graph.shape[0], img_result.shape[1]:img_result.shape[1] + img_graph.shape[1]] = img_graph
+ start_at = max(0,list_names_from-10)
+ end_at = min(len(found_cards), list_names_from)
+ for c, card in enumerate(reversed(found_cards[start_at:end_at]), 1):
+ cv2.putText(img_save, f'{card[0]} ({card[1].upper()})',(0, height-200+18*c), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
else:
img_save = img_result
@@ -549,13 +641,39 @@
print('Elapsed time: %.2f ms' % elapsed_ms)
if out_path is not None:
vid_writer.write(img_save.astype(np.uint8))
- cv2.waitKey(1)
+ if debug:
+ print("Waiting for keypress to continue")
+ inp = cv2.waitKey(0)
+ else:
+ inp = cv2.waitKey(1)
+ if 'u' == chr(inp & 255):
+ if len(found_cards) > 0:
+ del found_cards[list_names_from-1]
+ list_names_from = min(len(found_cards), max(0, list_names_from))
+
+ #os.sleep(1000)
+ elif 'p' == chr(inp & 255):
+ list_names_from = max(1, list_names_from - 1)
+ elif 'o' == chr(inp & 255):
+ list_names_from = min(len(found_cards),list_names_from + 1)
+ elif 'q' == chr(inp & 255):
+ break
except KeyboardInterrupt:
+ print("KeyboardInterrupt happened")
+ finally:
+ write_found_cards(found_cards)
capture.release()
if out_path is not None:
vid_writer.release()
cv2.destroyAllWindows()
+def write_found_cards(found_cards):
+ with open('detect.txt', 'w') as of:
+ counter = collections.Counter(found_cards)
+ for key in counter:
+ of.write(f'{counter[key]} [{key[1].upper()}] {key[0]}\n')
+
+
def main(args):
# Specify paths for all necessary files
@@ -569,6 +687,8 @@
# Merge database for all cards, then calculate pHash values of each, store them
df_list = []
for set_name in Config.all_set_list:
+ if set_name == 'con':
+ set_name = 'con__'
csv_name = '%s/csv/%s.csv' % (Config.data_dir, set_name)
df = fetch_data.load_all_cards_text(csv_name)
df_list.append(df)
@@ -577,7 +697,7 @@
card_pool.drop('Unnamed: 0', axis=1, inplace=True, errors='ignore')
card_pool = calc_image_hashes(card_pool, save_to=pck_path, hash_size=hash_sizes)
ch_key = 'card_hash_%d' % args.hash_size
- set_key = 'set_hash_%d' % args.hash_size
+ set_key = 'set_hash_%d' % 64
if ch_key not in card_pool.columns:
# we did not generate this hash_size yet
print('We need to add hash_size=%d' % (args.hash_size,))
@@ -587,20 +707,36 @@
# Processing time is almost linear to the size of the database
# Program can be much faster if the search scope for the card can be reduced
- card_pool = card_pool[card_pool['set'].isin(Config.set_2003_list)]
+ #card_pool = card_pool[card_pool['set'].isin(Config.set_2003_list)]
# ImageHash is basically just one numpy.ndarray with (hash_size)^2 number of bits. pre-emptively flattening it
# significantly increases speed for subtracting hashes in the future.
card_pool[ch_key] = card_pool[ch_key].apply(lambda x: x.hash.flatten())
card_pool[set_key] = card_pool[set_key].apply(lambda x: x.hash.flatten())
-
+ print("Hash-Database setup done")
# If the test file isn't given, use webcam to capture video
if args.in_path is None:
- capture = cv2.VideoCapture(0)
- detect_video(capture, card_pool, hash_size=args.hash_size, out_path='%s/result.avi' % args.out_path,
- display=args.display, show_graph=args.show_graph, debug=args.debug)
+ if args.stream_url is None:
+ print("Using webcam")
+ capture = cv2.VideoCapture(0)
+ capture.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter_fourcc(*"MJPG"))
+ capture.set(cv2.CAP_PROP_FRAME_WIDTH, 1920)
+ capture.set(cv2.CAP_PROP_FRAME_HEIGHT, 1080)
+ else:
+ print(f"Using streami {args.stream_url}")
+ capture = cv2.VideoCapture(args.stream_url)
+
+ thres = int((1920-2*args.crop_x)*(1080-2*args.crop_y)*(float(args.threshold_percent)/100))
+ print('Threshold:', thres)
+ if args.out_path is None:
+ out_path = None
+ else:
+ out_path = '%s/result.avi' % args.out_path
+ detect_video(capture, card_pool, hash_size=args.hash_size, out_path=out_path,
+ display=args.display, show_graph=args.show_graph, debug=args.debug, crop_x=args.crop_x, crop_y=args.crop_y, size_thresh=thres)
capture.release()
else:
+ print(f"Using image or video {args.in_path}")
# Save the detection result if args.out_path is provided
if args.out_path is None:
out_path = None
@@ -616,6 +752,8 @@
if test_ext in ['jpg', 'jpeg', 'bmp', 'png', 'tiff']:
# Test file is an image
img = cv2.imread(args.in_path)
+ if img is None:
+ print('Could not read', args.in_path)
detect_frame(img, card_pool, hash_size=args.hash_size, out_path=out_path, display=args.display,
debug=args.debug)
else:
@@ -640,6 +778,10 @@
parser.add_argument('-dbg', '--debug', dest='debug', help='Enable debug mode', action='store_true', default=False)
parser.add_argument('-gph', '--show_graph', dest='show_graph', help='Display the graph for video output',
action='store_true', default=False)
+ parser.add_argument('-s', '--stream', dest='stream_url', type=str)
+ parser.add_argument('-cx', '--crop-x', dest='crop_x', help='crop x amount of pixel on each side in x-axis', type=int, default=0)
+ parser.add_argument('-cy', '--crop-y', dest='crop_y', help='crop x amount of pixel on each side in y-axis', type=int, default=0)
+ parser.add_argument('-tp', '--threshold-percent', dest='threshold_percent', help='percentage amount that the card image needs to take up to be detected',type=int, default=5)
args = parser.parse_args()
if not args.display and args.out_path is None:
# Then why the heck are you running this thing in the first place?
--
Gitblit v1.10.0