首先效果图:
语言:python + OpenCV
简单的背景减差算法实现移动物体检测。
学习目标:
1. 理解背景减差算法
2. OpenCV图像滤波
3. 通过连通区域检测目标
前景 = 当前帧 - 背景
但在某些情况下,我们不能得到静态帧,因为光可以改变,或者一些物体会被某人移动,或者总是存在运动,等等。在这种情况下,我们保存了一些帧,并试图找出其中大多数像素是相同的,然后这个像素变为背景的一部分。一般来说,我们如何得到这个背景,以及我们用来选择更合适的滤波器。
在这个例子中,我们使用MOG(混合高斯)进行背景减差,效果:
可以看出一些噪声,和阴影,我们使用标准的滤波器去移除他们。
import os
import logging
import logging.handlers
import random
import numpy as np
import skvideo.io
import cv2
import matplotlib.pyplot as plt
import utils
# without this some strange errors happen
cv2.ocl.setUseOpenCL(False)
random.seed(123)
# ============================================================================
IMAGE_DIR = "./out"
VIDEO_SOURCE = "input.mp4"
SHAPE = (720, 1280) # HxW
# ============================================================================
def train_bg_subtractor(inst, cap, num=500):
'''
BG substractor need process some amount of frames to start giving result
'''
print ('Training BG Subtractor...')
i = 0
for frame in cap:
inst.apply(frame, None, 0.001)
i += 1
if i >= num:
return cap
def main():
log = logging.getLogger("main")
# creting MOG bg subtractor with 500 frames in cache
# and shadow detction
bg_subtractor = cv2.createBackgroundSubtractorMOG2(
history=500, detectShadows=True)
# Set up image source
# You can use also CV2, for some reason it not working for me
cap = skvideo.io.vreader(VIDEO_SOURCE)
# skipping 500 frames to train bg subtractor
train_bg_subtractor(bg_subtractor, cap, num=500)
frame_number = -1
for frame in cap:
if not frame.any():
log.error("Frame capture failed, stopping...")
break
frame_number += 1
utils.save_frame(frame, "./out/frame_%04d.png" % frame_number)
fg_mask = bg_subtractor.apply(frame, None, 0.001)
utils.save_frame(frame, "./out/fg_mask_%04d.png" % frame_number)
# ============================================================================
if __name__ == "__main__":
log = utils.init_logging()
if not os.path.exists(IMAGE_DIR):
log.debug("Creating image directory `%s`...", IMAGE_DIR)
os.makedirs(IMAGE_DIR)
main()
滤波
对于这个例子,我们用到了下列滤波器:
阈值、膨胀、腐蚀、开运算、闭运算
现在我们将使用它们来消除前景掩码上的一些噪声。
首先,我们将使用闭运算来消除区域的空隙,然后开运算以移除1到2个PX点,然后在膨胀处理使目标更大。
def filter_mask(img):
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2, 2))
# Fill any small holes
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
# Remove noise
opening = cv2.morphologyEx(closing, cv2.MORPH_OPEN, kernel)
# Dilate to merge adjacent blobs
dilation = cv2.dilate(opening, kernel, iterations=2)
# threshold
th = dilation[dilation < 240] = 0
return th
前景如下:
通过检测连通区域进行目标检测
我们使用cv2.findContours函数实现;
cv2.CV_RETR_EXTERNAL — get only outer contours.
cv2.CV_CHAIN_APPROX_TC89_L1 - use Teh-Chin chain approximation algorithm (faster)
def get_centroid(x, y, w, h):
x1 = int(w / 2)
y1 = int(h / 2)
cx = x + x1
cy = y + y1
return (cx, cy)
def detect_vehicles(fg_mask, min_contour_width=35, min_contour_height=35):
matches = []
# finding external contours
im, contours, hierarchy = cv2.findContours(
fg_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_TC89_L1)
# filtering by with, height
for (i, contour) in enumerate(contours):
(x, y, w, h) = cv2.boundingRect(contour)
contour_valid = (w >= min_contour_width) and (
h >= min_contour_height)
if not contour_valid:
continue
# getting center of the bounding box
centroid = get_centroid(x, y, w, h)
matches.append(((x, y, w, h), centroid))
return matches
我们通过高度、宽度和添加质心来添加一些过滤
封装,算法实现一般流程:
class PipelineRunner(object):
'''
Very simple pipline.
Just run passed processors in order with passing context from one to
another.
You can also set log level for processors.
'''
def __init__(self, pipeline=None, log_level=logging.DEBUG):
self.pipeline = pipeline or []
self.context = {}
self.log = logging.getLogger(self.__class__.__name__)
self.log.setLevel(log_level)
self.log_level = log_level
self.set_log_level()
def set_context(self, data):
self.context = data
def add(self, processor):
if not isinstance(processor, PipelineProcessor):
raise Exception(
'Processor should be an isinstance of PipelineProcessor.')
processor.log.setLevel(self.log_level)
self.pipeline.append(processor)
def remove(self, name):
for i, p in enumerate(self.pipeline):
if p.__class__.__name__ == name:
del self.pipeline[i]
return True
return False
def set_log_level(self):
for p in self.pipeline:
p.log.setLevel(self.log_level)
def run(self):
for p in self.pipeline:
self.context = p(self.context)
self.log.debug("Frame #%d processed.", self.context['frame_number'])
return self.context
class PipelineProcessor(object):
'''
Base class for processors.
'''
def __init__(self):
self.log = logging.getLogger(self.__class__.__name__)
作为输入构造函数将采取将按顺序运行的处理器列表。每个处理器都是这项工作的一部分。让我们创建轮廓检测处理器。
class ContourDetection(PipelineProcessor):
'''
Detecting moving objects.
Purpose of this processor is to subtrac background, get moving objects
and detect them with a cv2.findContours method, and then filter off-by
width and height.
bg_subtractor - background subtractor isinstance.
min_contour_width - min bounding rectangle width.
min_contour_height - min bounding rectangle height.
save_image - if True will save detected objects mask to file.
image_dir - where to save images(must exist).
'''
def __init__(self, bg_subtractor, min_contour_width=35, min_contour_height=35, save_image=False, image_dir='images'):
super(ContourDetection, self).__init__()
self.bg_subtractor = bg_subtractor
self.min_contour_width = min_contour_width
self.min_contour_height = min_contour_height
self.save_image = save_image
self.image_dir = image_dir
def filter_mask(self, img, a=None):
'''
This filters are hand-picked just based on visual tests
'''
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2, 2))
# Fill any small holes
closing = cv2.morphologyEx(img, cv2.MORPH_CLOSE, kernel)
# Remove noise
opening = cv2.morphologyEx(closing, cv2.MORPH_OPEN, kernel)
# Dilate to merge adjacent blobs
dilation = cv2.dilate(opening, kernel, iterations=2)
return dilation
def detect_vehicles(self, fg_mask, context):
matches = []
# finding external contours
im2, contours, hierarchy = cv2.findContours(
fg_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_TC89_L1)
for (i, contour) in enumerate(contours):
(x, y, w, h) = cv2.boundingRect(contour)
contour_valid = (w >= self.min_contour_width) and (
h >= self.min_contour_height)
if not contour_valid:
continue
centroid = utils.get_centroid(x, y, w, h)
matches.append(((x, y, w, h), centroid))
return matches
def __call__(self, context):
frame = context['frame'].copy()
frame_number = context['frame_number']
fg_mask = self.bg_subtractor.apply(frame, None, 0.001)
# just thresholding values
fg_mask[fg_mask < 240] = 0
fg_mask = self.filter_mask(fg_mask, frame_number)
if self.save_image:
utils.save_frame(fg_mask, self.image_dir +
"/mask_%04d.png" % frame_number, flip=False)
context['objects'] = self.detect_vehicles(fg_mask, context)
context['fg_mask'] = fg_mask
return contex
所以只需将BG减法、滤波和检测部分合并在一起即可。
现在让我们创建一个处理器,它将链接到不同帧上的检测对象,并创建路径,也将计算到达出口区域的车辆。
'''
Counting vehicles that entered in exit zone.
Purpose of this class based on detected object and local cache create
objects pathes and count that entered in exit zone defined by exit masks.
exit_masks - list of the exit masks.
path_size - max number of points in a path.
max_dst - max distance between two points.
'''
def __init__(self, exit_masks=[], path_size=10, max_dst=30, x_weight=1.0, y_weight=1.0):
super(VehicleCounter, self).__init__()
self.exit_masks = exit_masks
self.vehicle_count = 0
self.path_size = path_size
self.pathes = []
self.max_dst = max_dst
self.x_weight = x_weight
self.y_weight = y_weight
def check_exit(self, point):
for exit_mask in self.exit_masks:
try:
if exit_mask[point[1]][point[0]] == 255:
return True
except:
return True
return False
def __call__(self, context):
objects = context['objects']
context['exit_masks'] = self.exit_masks
context['pathes'] = self.pathes
context['vehicle_count'] = self.vehicle_count
if not objects:
return context
points = np.array(objects)[:, 0:2]
points = points.tolist()
# add new points if pathes is empty
if not self.pathes:
for match in points:
self.pathes.append([match])
else:
# link new points with old pathes based on minimum distance between
# points
new_pathes = []
for path in self.pathes:
_min = 999999
_match = None
for p in points:
if len(path) == 1:
# distance from last point to current
d = utils.distance(p[0], path[-1][0])
else:
# based on 2 prev points predict next point and calculate
# distance from predicted next point to current
xn = 2 * path[-1][0][0] - path[-2][0][0]
yn = 2 * path[-1][0][1] - path[-2][0][1]
d = utils.distance(
p[0], (xn, yn),
x_weight=self.x_weight,
y_weight=self.y_weight
)
if d < _min:
_min = d
_match = p
if _match and _min <= self.max_dst:
points.remove(_match)
path.append(_match)
new_pathes.append(path)
# do not drop path if current frame has no matches
if _match is None:
new_pathes.append(path)
self.pathes = new_pathes
# add new pathes
if len(points):
for p in points:
# do not add points that already should be counted
if self.check_exit(p[1]):
continue
self.pathes.append([p])
# save only last N points in path
for i, _ in enumerate(self.pathes):
self.pathes[i] = self.pathes[i][self.path_size * -1:]
# count vehicles and drop counted pathes:
new_pathes = []
for i, path in enumerate(self.pathes):
d = path[-2:]
if (
# need at list two points to count
len(d) >= 2 and
# prev point not in exit zone
not self.check_exit(d[0][1]) and
# current point in exit zone
self.check_exit(d[1][1]) and
# path len is bigger then min
self.path_size <= len(path)
):
self.vehicle_count += 1
else:
# prevent linking with path that already in exit zone
add = True
for p in path:
if self.check_exit(p[1]):
add = False
break
if add:
new_pathes.append(path)
self.pathes = new_pathes
context['pathes'] = self.pathes
context['objects'] = objects
context['vehicle_count'] = self.vehicle_count
self.log.debug('#VEHICLES FOUND: %s' % self.vehicle_count)
return context