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 | 128 +++++++++++++++++++++++++++++-------------
1 files changed, 88 insertions(+), 40 deletions(-)
diff --git a/opencv_dnn.py b/opencv_dnn.py
index 4b2c4e0..744d012 100755
--- a/opencv_dnn.py
+++ b/opencv_dnn.py
@@ -92,7 +92,7 @@
#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=64)
+ set_hash = ih.phash(img_set, hash_size=64)
card_info['card_hash_%d' % hs] = card_hash
card_info['set_hash_%d' % 64] = set_hash
#print('Setting set_hash_%d' % hs)
@@ -263,14 +263,14 @@
# 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]))
+# 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)
@@ -289,8 +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))
+ #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:
@@ -314,21 +314,21 @@
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('Size:', size)
cnts_rect.append(approx)
else:
if i_child != -1:
@@ -415,9 +415,9 @@
det_cards = []
# Detect contours of all cards in the image
cnts = find_card(img_result, size_thresh=size_thresh, debug=debug)
- print('Countours:', len(cnts))
+ #print('Contours:', len(cnts))
for i in range(len(cnts)):
- print('Contour', i)
+ #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])
@@ -436,13 +436,13 @@
'''
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')
- print('img set')
+ #print('img set')
if debug:
cv2.imshow("Set Img#%d" % i, img_set_part)
@@ -460,20 +460,20 @@
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))
+# 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])
+# print('Idx:', ix, 'Name:', cd['name'], 'Set:', cd['set'], 'Diff:', top_matches[ix])
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)
+ #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'])
+ #print('Best Match', 'Name:', best_match['name'], 'Set:', best_match['set'])
min_card = best_match
card_name = min_card['name']
@@ -482,7 +482,7 @@
# 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)
@@ -514,6 +514,7 @@
: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
@@ -535,7 +536,16 @@
try:
while True:
ret, frame = capture.read()
- croped_img = frame[crop_y:-crop_y, crop_x:-crop_x]
+ 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:
@@ -543,6 +553,9 @@
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(fimg, card_pool, hash_size=hash_size, size_thresh=size_thresh,
out_path=None, display=False, debug=debug)
@@ -588,6 +601,7 @@
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():
@@ -608,7 +622,9 @@
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
- for c, card in enumerate(reversed(found_cards[-10:]), 1):
+ 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
@@ -625,19 +641,37 @@
print('Elapsed time: %.2f ms' % elapsed_ms)
if out_path is not None:
vid_writer.write(img_save.astype(np.uint8))
- inp = cv2.waitKey(0)
- if 'q' == chr(inp & 255):
+ 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()
- 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 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')
@@ -673,26 +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, cv2.CAP_V4L)
- 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)
+ 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*500)*(1080-2*200)*0.3))
+ thres = int((1920-2*args.crop_x)*(1080-2*args.crop_y)*(float(args.threshold_percent)/100))
print('Threshold:', thres)
- 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, crop_x=500, crop_y=200, size_thresh=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
@@ -734,6 +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