Python Opencv实践 - 车辆统计（2）检测线绘制，车辆数量计数和显示
针对我所使用的视频，对上一节的代码进行了修改，增加了更多参数。
Python Opencv实践 - 车辆统计（1）读取视频，移除背景，做预处理_亦枫Leonlew的博客-CSDN博客示例中的图像的腐蚀、膨胀和闭运算等需要根据具体视频进行实验得到最佳效果。https://blog.csdn.net/vivo01/article/details/133756184?spm=1001.2014.3001.5502 主要参数有，检测窗口过滤大小的变量min/max_w/h,检测线的位置和长度(detection_line_x/y/length)，检测线上下偏移量阈值(detection_line_offset)。
由于没有使用深度学习来识别车辆，只是通过传统的计算机视觉方法处理图像后，通过搜索轮廓来实现车辆检测。因此所有参数都是针对我所使用的视频进行了优化，实际运行中，还是会存在无法检测出部分车辆的问题。所有对图像的处理方法和相关参数，需要大家根据自己的视频来进行优化。对于我所使用的视频，我没有直接用MOG2来做背景移除，而是先通过Canny提取边缘后再进行背景移除处理，这一点只是实验出来对我所使用的视频来说效果最好，并非网上所看教程的做法。
import cv2 as cv
import numpy as np
#读取视频文件
videoFile = "../../SampleVideos/TrafficHEB.mp4"
video = cv.VideoCapture(videoFile)
FPS = 15
DELAY = int(1000 / FPS)
kernel = cv.getStructuringElement(cv.MORPH_ELLIPSE, (3,3))
min_w = 82
min_h = 82
max_w = 160
max_h = 160
detection_line_length = 1500
detection_line_x = (1920 - detection_line_length) / 2
detection_line_y = 900
detection_line_offset = 1
cars_detected = 0
#训练MOG2背景移除对象
def trainBgSubtractor(train_video, mog, frameNum):
#train_video = cv.VideoCapture(videoFile)
while True:
ret, frame = train_video.read()
if ret == False:
break
mog.apply(frame, None, 0.01)
frameNum = frameNum - 1
if frameNum <= 0:
break
#train_video.release()
#增加对比度
def imageAdjust(img, clipLimit = 1.5, gridSize = (3,3)):
clahe = cv.createCLAHE(clipLimit, gridSize)
adjusted_img = clahe.apply(img)
return adjusted_img
def filterMask(img, a=None):
kernel = cv.getStructuringElement(cv.MORPH_ELLIPSE, (3, 3))
# Fill any small holes
img = cv.morphologyEx(img, cv.MORPH_CLOSE, kernel)
#img = cv.morphologyEx(img, cv.MORPH_CLOSE, kernel)
# Remove noise
img = cv.morphologyEx(img, cv.MORPH_OPEN, kernel)
# Dilate to merge adjacent blobs
img = cv.dilate(img, kernel, iterations=6)
return img
def rectCenter(x, y, w, h):
return x + w / 2, y + h / 2
#移除背景
#参考资料：https://blog.csdn.net/u014737138/article/details/80389977
#mog = cv.bgsegm.createBackgroundSubtractorMOG()
mog = cv.createBackgroundSubtractorMOG2(history=100, detectShadows=True)
#trainBgSubtractor(video, mog, 100)
while True:
cars_positions = []
ret,frame = video.read()
if ret == False:
break;
#变为灰度图做高斯滤波
frame_gray = cv.cvtColor(frame, cv.COLOR_BGR2GRAY)
frame_gray = cv.Canny(frame_gray, 65, 160)
frame_gray = cv.GaussianBlur(frame_gray, (3,3), 3)
#frame_gray = cv.medianBlur(frame_gray, 3)
frame_gray = imageAdjust(frame_gray, 15, (3,3))
foreground_mask = mog.apply(frame_gray, None, -1)
foreground_mask[foreground_mask < 240] = 0
#foreground_mask = cv.dilate(foreground_mask, kernel, iterations=2)
forground_mask = cv.GaussianBlur(foreground_mask, (3,3), 3)
foreground_mask = filterMask(foreground_mask)
#画出检测线
cv.line(frame,
(int(detection_line_x), int(detection_line_y)),
(int(detection_line_x + detection_line_length),int(detection_line_y)),
(0,50,200))
#查找轮廓
contours,hierarchy = cv.findContours(foreground_mask, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_TC89_L1)
#contours,hierarchy = cv.findContours(foreground_mask, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE)
#绘制轮廓
for contour in contours:
(x,y,w,h) = cv.boundingRect(contour)
#过滤掉小的轮廓框
if w >= min_w and h >= min_h and w <= max_w and h <= max_h:
cv.rectangle(frame, (int(x),int(y)), (int(x + w), int(y + h)), (0,255,0), 2)
#画出车辆中心点
centerX,centerY = rectCenter(x, y, w , h)
cv.circle(frame, (int(centerX), int(centerY)), 4, (0,0,255), -1)
#将车辆加入检测到的车辆列表中
cars_positions.append((centerX, centerY))
#检测车辆中心点是否通过检测线
for (x,y) in cars_positions:
if (y > (detection_line_y - detection_line_offset) and y < (detection_line_y + detection_line_offset) and
x > (detection_line_x) and x < (detection_line_x + detection_line_length)):
cars_detected = cars_detected + 1
print(cars_detected)
#输出文字
cv.putText(frame, 'Vehicle Detected:' + str(cars_detected), (900, 50), cv.FONT_HERSHEY_SIMPLEX, 2, (0,255,0), 5)
cv.imshow("Traffic Original", frame)
cv.imshow("Traffic Processing", foreground_mask)
if cv.waitKey(DELAY) == 27:
break;
video.release()
cv.destroyAllWindows();