def __init__(self,vidfile,labelfile,modelFile,labelListFile,exportPath, perClassFrames=40,frameRate=20,context_size=5, banerWidth = 80,scale = 1): # input properties self.vidreader = VideoReader(vidfile); self.labelreader = open(labelfile,'r'); self.N = self.vidreader.frames; self.width,self.height = self.vidreader.width,self.vidreader.height; self.context_size=context_size; self.perClassFrames = perClassFrames; self.labels = load_labels(labelListFile); self.n_outs = len(self.labels); self.flag_colors = []; for index in range(self.n_outs): self.flag_colors.extend([tuple(np.array(cm.jet(index/float(self.n_outs))[:3][::-1])*255)]) self.predictors,self.predictorStartIdx = load_predictors(modelFile); self.input_shape = [self.height,self.width,3] self.batch_size = self.predictors[0].batch_size #write properites self.banerWidth = banerWidth self.vidWriter = VideoWriter(exportPath,self.banerWidth+self.width,self.height,fps=frameRate); self.colors = np.random.randint(256, size=(len(self.labels), 3)) self.scale = scale; #status self.frameIdx = 0; self.tasks = deque(); self.isFinished = False; self.vidWriter.build();
def tracker(inPath,outPath="test_results/tracker.avi"):
#initialization for default value
hog = cv2.HOGDescriptor()
hog.setSVMDetector( cv2.HOGDescriptor_getDefaultPeopleDetector())
vidreader = VideoReader(inPath)
vidwriter = VideoWriter(outPath,vidreader.width,vidreader.height)
vidwriter.build();
frame_idx =0; N = vidreader.frames;
while vidreader.num_remaining_frames() > 0:
frame_idx += 1;
cur_frame = vidreader.read_next();
print 'Perform human tracking.... {0}%\r'.format((frame_idx*100/N)),
if cur_frame is None:
break;
gray_cur_frame = cv2.cvtColor(cur_frame, cv2.COLOR_BGR2GRAY)
found, w = hog.detectMultiScale(gray_cur_frame, winStride=(8,8), padding=(32,32), scale=1.05)
found_filtered = []
#discarding the bounding box on within other
for ri, r in enumerate(found):
for qi, q in enumerate(found):
if ri != qi and inside(r, q):
break
else:
found_filtered.append(r)
draw_detections(cur_frame, found_filtered, 1)
vidwriter.write(cur_frame);
vidreader.close();
vidwriter.close()
cv2.destroyAllWindows()
print "Implemented Human Tracking............. [Done]"
def test_bgsub_mog(inp):
vidreader = VideoReader(inp)
vidwriter = VideoWriter("test_results/bg_sub_mog.avi", vidreader.width,
vidreader.height)
bgsub = get_instance(BGMethods.MOG_SUBSTRACTION)
start = time.time()
process_video(bgsub, vidreader, vidwriter)
time_taken = time.time() - start
print "Tested Background Subtraction (Mixture of Gaussian)... [DONE] in " + str(
time_taken) + " seconds"
def test_bgsub_fd(inp):
vidreader = VideoReader(inp)
vidwriter = VideoWriter("test_results/bg_sub_fd.avi", vidreader.width,
vidreader.height)
bgsub = get_instance(BGMethods.FRAME_DIFFERENCING)
start = time.time()
process_video(bgsub, vidreader, vidwriter, num_blocks=2)
time_taken = time.time() - start
print "Tested Background Subtraction (Frame Differencing)... [DONE] in " + str(
time_taken) + " seconds"
def createVideo(datapath,
group,
outfileName,
shape,
duration=120,
framerate=20,
vidLen=32):
vidOutFileName = outfileName + 'test.avi'
labelOutFileName = outfileName + 'test.txt'
values = []
create_folder_structure_if_not_exists(vidOutFileName)
with open(datapath + os.sep + group + ".txt", 'r') as fp:
for line in fp:
values.extend([line.split()])
numClass = len(values)
numExamples = (duration * framerate) / (vidLen)
randomNumbers = np.random.random_integers(0, numClass - 1, numExamples)
fileWriter = open(labelOutFileName, 'w')
vidWriter = VideoWriter(vidOutFileName, shape[0], shape[1])
vidWriter.build()
for idx, random_idx in enumerate(randomNumbers):
print 'Creating UCF 50 video ... {0}%\r'.format(
(idx * 100 / numExamples)),
classDetails = values[random_idx]
classPath = datapath + os.sep + classDetails[0] + os.sep
classExamples = [
os.path.join(classPath, _file) for _file in os.listdir(classPath)
if os.path.isfile(os.path.join(classPath, _file))
]
chosenExample = classExamples[np.random.randint(len(classExamples))]
#print chosenExample
vidreader = VideoReader(chosenExample, None)
num_frames = vidreader.frames
cnt, frames = vidreader.read(np.random.randint(num_frames - vidLen),
vidLen)
fileWriter.writelines("%d\n" % int(item)
for item in [classDetails[2]] * cnt)
for frame in frames:
vidWriter.write(frame)
vidWriter.close()
fileWriter.close()
type=int)
parser.add_argument("--write_bgsub",
nargs='?',
help="Write bgsub default-0",
default=0,
type=int)
parser.add_argument("--window",
nargs='?',
help="window size default-5",
default=5,
type=int)
parser.add_argument("--overlap",
nargs='?',
help="overlap default-2",
default=2,
type=int)
args = parser.parse_args()
inp = args.input
out = args.output
vidreader = VideoReader(inp)
sal = sal_instance(args.sal, SaliencyProps())
bg = get_instance(args.bg)
smoothner = smooth_instance(feats, args.smoothner)
start = time.time()
process(vidreader, sal, bg, smoothner, args.num_prev_frames,
args.num_blocks, args.write, args.extract, args.write_gray == 1,
args.write_bgsub == 1, args.window, args.overlap, args.rsz_shape)
print "Event Tracker ...", inp, "[DONE] in", (time.time() -
start), "seconds"
