OpenCV车辆识别

笔者前期对OpenCV进行了一些了解，通过教学视频的学习，大致明白了该库的主要功能。
现将学习后期教学视频中的一组代码记录于此

OpenCV车辆检测项目

• 加载视频
• 通过形态学识别车辆
• 对车辆进行统计
• 显示车辆统计信息

视频加载

import cv2
import numpy as np

cap = cv2.VideoCapture("video.mp4")

while True:
    ret, frame = cap.read()

    if ret == True:
        cv2.imshow("video", frame)

    key = cv2.waitKey(1)
    if key == 27:
        break

cap.release()
cv2.destroyAllWindows()

去背景

• createBackgroundSubtractorMOG(…)
  • history=200

论文：

An improved adaptive background mixture model for real-time tracking with shadow detection

import cv2
import numpy as np

cap = cv2.VideoCapture("video.mp4")

bgsubmog = cv2.bgsegm.createBackgroundSubtractorMOG()

while True:
    ret, frame = cap.read()

    if ret == True:

        # 灰度
        cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        # 去噪（高斯）
        blur = cv2.GaussianBlur(frame, (3, 3), 5)
        # 去背景
        mask = bgsubmog.apply(blur)

        cv2.imshow("video", mask)

    key = cv2.waitKey(1)
    if key == 27:
        break

cap.release()
cv2.destroyAllWindows()

形态学处理

膨胀，腐蚀等，去除噪点，增强图像，方便轮廓提取。

import cv2
import numpy as np

cap = cv2.VideoCapture("video.mp4")

bgsubmog = cv2.bgsegm.createBackgroundSubtractorMOG()

# 形态学kernel
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))

while True:
    ret, frame = cap.read()

    if ret == True:

        # 灰度
        cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        # 去噪（高斯）
        blur = cv2.GaussianBlur(frame, (3, 3), 5)
        # 去背景
        mask = bgsubmog.apply(blur)

        # 腐蚀
        erode = cv2.erode(mask, kernel)

        # 膨胀，还原放大
        dilate = cv2.dilate(erode, kernel, iterations=3)

        # 闭操作，去掉物体内部的小块
        close = cv2.morphologyEx(dilate, cv2.MORPH_CLOSE, kernel)
        close = cv2.morphologyEx(close, cv2.MORPH_CLOSE, kernel)

        cnts, h = cv2.findContours(close, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

        for (i, c) in enumerate(cnts):
            (x, y, w, h) = cv2.boundingRect(c)
            cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 0, 255), 2)

        cv2.imshow("video", frame)

    key = cv2.waitKey(1)
    if key == 27:
        break

cap.release()
cv2.destroyAllWindows()

逻辑处理

• 判断是否为车

  • 通过API获取外轮廓举行
  • 通过宽高进行判断：宽高大于一定值
  • 是车，则绘制矩形边框

• 车辆统计

  • 确定一条检测线并绘制出来
  • 确定检测范围（检测线上下偏移量）
  • 每一帧统计所有确定为车的矩形的中心
  • 遍历中心是否位于检测范围内：是，则统计数量加一
    • 课程中，清空车辆列表的地方感觉不对

import cv2
import numpy as np

min_w = 90
min_h = 90

# 检测线的高度
line_high = 600
# 线的偏移量
offset = 6
# 统计车的数量
carno = 0
# 存放有效车辆的数组
cars = []


def center(x, y, w, h):
    x1 = int(w / 2)
    y1 = int(h / 2)
    cx = x + x1
    cy = y + y1

    return cx, cy


cap = cv2.VideoCapture("video.mp4")

bgsubmog = cv2.bgsegm.createBackgroundSubtractorMOG()

# 形态学kernel
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))

while True:
    ret, frame = cap.read()

    if ret == True:

        # 灰度
        cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        # 去噪（高斯）
        blur = cv2.GaussianBlur(frame, (3, 3), 5)
        # 去背景
        mask = bgsubmog.apply(blur)

        # 腐蚀
        erode = cv2.erode(mask, kernel)

        # 膨胀，还原放大
        dilate = cv2.dilate(erode, kernel, iterations=3)

        # 闭操作，去掉物体内部的小块
        close = cv2.morphologyEx(dilate, cv2.MORPH_CLOSE, kernel)
        close = cv2.morphologyEx(close, cv2.MORPH_CLOSE, kernel)

        cnts, h = cv2.findContours(close, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

        # 绘制检测线
        cv2.line(frame, (10, line_high), (1200, line_high), (0, 0, 255), 3)

        for (i, c) in enumerate(cnts):
            (x, y, w, h) = cv2.boundingRect(c)

            # 对车辆的宽高进行判断
            # 以验证是否是有效的车辆
            isValid = (w >= min_w) and (h >= min_h)
            if not isValid:
                continue

            # 到这里都是有效的车
            cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 0, 255), 2)
            cpoint = center(x, y, w, h)
            cars.append(cpoint)

            for (x, y) in cars:
                if (y > line_high - offset) and (y < line_high + offset):
                    carno += 1
                    cars.remove((x, y))
                    print(carno)

        cv2.imshow("video", frame)

    key = cv2.waitKey(1)
    if key == 27:
        break

cap.release()
cv2.destroyAllWindows()

显示统计信息

• 添加统计信息

...
        cv2.putText(
            frame,
            "Cars Count:" + str(carno),
            (500, 60),
            cv2.FONT_HERSHEY_SIMPLEX,
            2,
            (255, 0, 0),
            5,
        )
        cv2.imshow("video", frame)
...

• 微调
  • 检测范围：调整线的偏移量，防止重复计数或漏记
  • 检测位置：上下移动检测线的位置，防止漏记

补充

机器学习和深度学习存在更好的识别方案，待后期学习。