153 lines
5.5 KiB
Python
153 lines
5.5 KiB
Python
import cv2
|
|
import argparse
|
|
import time
|
|
import os
|
|
import datetime
|
|
|
|
def dir_path(string):
|
|
if os.path.exists(string):
|
|
return string
|
|
else:
|
|
raise NotADirectoryError(string)
|
|
|
|
def init_argparse() -> argparse.ArgumentParser:
|
|
parser = argparse.ArgumentParser(
|
|
prog="FaceDetection",
|
|
usage="%(prog)s [OPTION]",
|
|
description="Run face localization"
|
|
)
|
|
parser.add_argument(
|
|
"-v", "--version", action="version", version=f"{parser.prog} version 1.0.1"
|
|
)
|
|
parser.add_argument(
|
|
"-d", "--dashboard", action='store_true', help="Flag to enable live dashboard with statistics - requires terminal width of 90 columns or greater"
|
|
)
|
|
parser.add_argument(
|
|
"-o", "--output", action='store_true', help="show the resultant directions"
|
|
)
|
|
parser.add_argument(
|
|
"-f", "--file", type=dir_path, nargs="?", help="File to scan instead of using the camera. Useful for generating training data"
|
|
)
|
|
parser.add_argument(
|
|
"-s", "--no-screen", action='store_true', help="Do not show the successful frames"
|
|
)
|
|
parser.add_argument(
|
|
"-t", "--training-data", action='store_true', help="When set, saves successful face-location images and coordinates to use for future training data"
|
|
)
|
|
parser.add_argument(
|
|
'--validate', action="store_true", help="if set, outputs frame_count and box coords for located faces for future validation"
|
|
)
|
|
return parser
|
|
|
|
multiplication_factor = 0.05
|
|
|
|
def get_adjustment_amount(imgSize, currentX, currentY, currentW, currentH):
|
|
|
|
current_top_left = [currentX, currentY]
|
|
current_bottom_right = [currentX + currentW, currentY + currentH]
|
|
|
|
current_top_right = [currentX + currentW, currentY]
|
|
|
|
# find the difference between the left gap and the right gap, divide it by two, and multiply it by the speed scale
|
|
horizontal_adjustment = multiplication_factor * (currentX - (imgSize[0] - current_top_right[0])) / 2
|
|
vertical_adjustment = multiplication_factor * (currentY - (imgSize[0] - current_bottom_right[1])) / 2
|
|
|
|
return [horizontal_adjustment, vertical_adjustment]
|
|
|
|
frames_searched = 1
|
|
faces_found = 0
|
|
start_time = datetime.datetime.now()
|
|
|
|
def draw_dashboard(keep_stat_line = False):
|
|
global frames_searched, faces_found, start_time
|
|
|
|
elapsed_time = datetime.datetime.now() - start_time
|
|
|
|
hours, remainder = divmod(elapsed_time.total_seconds(), 3600)
|
|
minutes, seconds = divmod(remainder, 60)
|
|
|
|
f_found = f"{faces_found} Faces found".ljust(16, ' ')
|
|
f_searched = f"{frames_searched} Frames searched".ljust(21, ' ')
|
|
success_rate = f"{round((faces_found / frames_searched) * 100, 1)}% Success rate".ljust(16, ' ')
|
|
|
|
if keep_stat_line:
|
|
print(f"{f_found} | {f_searched} | {success_rate} | {round(hours)}h {round(minutes)}m {round(seconds)}s elapsed", flush=True)
|
|
else:
|
|
print(f"{f_found} | {f_searched} | {success_rate} | {round(hours)}h {round(minutes)}m {round(seconds)}s elapsed", end="\r", flush=True)
|
|
|
|
|
|
parser = init_argparse()
|
|
args = parser.parse_args()
|
|
|
|
if args.file:
|
|
cap = cv2.VideoCapture(args.file)
|
|
else:
|
|
cap = cv2.VideoCapture(0, cv2.IMREAD_GRAYSCALE) # instead of grayscale you can also use -1, 0, or 1.
|
|
faceCascade = cv2.CascadeClassifier(r"./cascades/cascade_10.xml") # CHECK THIS FIRST TROUBLE SHOOTING
|
|
|
|
datestamp = "{:%Y_%m_%d %H_%M_%S}".format(datetime.datetime.now())
|
|
output_dir = r"./output/" + datestamp + r"/"
|
|
|
|
|
|
if args.training_data:
|
|
if not os.path.exists(output_dir):
|
|
os.makedirs(output_dir)
|
|
with open(output_dir + r"found_faces.csv", 'a') as fd:
|
|
fd.write(f"frame_name, x, y, width, height\n")
|
|
|
|
tmp, frm = cap.read()
|
|
height, width, channels = frm.shape
|
|
if (args.file):
|
|
print(f"Image is {height} tall and {width} wide")
|
|
frame_count = 0
|
|
start_timestamp = time.strftime("%Y%m%d-%H%M%S")
|
|
# print(f"{height*.25}, {width}")
|
|
del tmp, frm
|
|
#Color is 1, grayscale is 0, and the unchanged is -1
|
|
while(True):
|
|
ret, frame = cap.read()
|
|
frames_searched += 1
|
|
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
|
|
|
|
# Detect faces in the image
|
|
faces = faceCascade.detectMultiScale(
|
|
gray,
|
|
scaleFactor=1.2,
|
|
minNeighbors=2,
|
|
# minSize=(70, 90)
|
|
minSize=(200, 200)
|
|
)
|
|
|
|
# Draw a rectangle around the faces
|
|
for (x, y, w, h) in faces:
|
|
if args.training_data:
|
|
frame_name = frames_searched
|
|
with open(output_dir + r"found_faces.csv", 'a') as fd:
|
|
fd.write(f"frame_{frame_name}.jpg, {x}, {y}, {w}, {h}\n")
|
|
cv2.imwrite(output_dir + f"frame_{frame_name}.jpg", frame)
|
|
|
|
if args.validate:
|
|
with open(f"./validation/{start_timestamp}-validation.txt", 'a') as output_validation_file:
|
|
output_validation_file.write(f"{frame_count}, {x}, {y}, {x+w}, {y+h}\n")
|
|
|
|
faces_found += 1
|
|
adjustment_required = get_adjustment_amount([width, height], x, y, w, h)
|
|
cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 255, 255))
|
|
|
|
if args.output:
|
|
print(f"Adjust right: {adjustment_required[0]}".ljust(90, ' '), flush=True)
|
|
print(f"Adjust up : {adjustment_required[1]}", flush=True)
|
|
|
|
if not args.no_screen:
|
|
cv2.imshow('frame', frame)
|
|
|
|
if args.dashboard:
|
|
draw_dashboard()
|
|
|
|
if cv2.waitKey(1) & 0xFF == ord('q'):
|
|
break
|
|
|
|
frame_count += 1
|
|
|
|
draw_dashboard(keep_stat_line=True)
|
|
cap.release()
|