在背景几乎相似的图像中检测目标

Question

我必须检测笼子里的老鼠，输入的图像如下所示：

目前，我正在使用视频流中的cv.createBackgroundSubtractorMOG2()来查找包含老鼠的区域，然后使用Canny Edge detector来提取老鼠的轮廓。然而，这并不能很好地工作。老鼠移动得越多越好，但我猜可能有更好的方法来检测老鼠。

有没有人对如何检测老鼠有不同的想法？

提前感谢

Answer 1

在减去背景之后，你可以使用一个阈值来去除噪声。尝试保存减去的图像并查看其外观。下面是我用来调整过滤器参数的脚本(使用减去的图像运行它)：

import cv2
import numpy as np

screenshot_path = 'screenshot.bmp'

def nothing(x):
    pass


# Creating a window for later use
cv2.namedWindow('mask', cv2.WINDOW_NORMAL)
cv2.namedWindow('trackbar', cv2.WINDOW_NORMAL)

# Starting with 100's to prevent error while masking
h, s, v = 100, 100, 100

# Creating track bar

cv2.createTrackbar('h', 'trackbar', 0, 180, nothing)
cv2.createTrackbar('s', 'trackbar', 0, 255, nothing)
cv2.createTrackbar('v', 'trackbar', 164, 255, nothing)
cv2.createTrackbar('h2', 'trackbar', 120, 180, nothing)
cv2.createTrackbar('s2', 'trackbar', 12, 255, nothing)
cv2.createTrackbar('v2', 'trackbar', 253, 255, nothing)
frame = cv2.imread(screenshot_path)

# converting to HSV
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

while (1):
    # get info from track bar and appy to result
    h = cv2.getTrackbarPos('h', 'trackbar')
    s = cv2.getTrackbarPos('s', 'trackbar')
    v = cv2.getTrackbarPos('v', 'trackbar')
    h2 = cv2.getTrackbarPos('h2', 'trackbar')
    s2 = cv2.getTrackbarPos('s2', 'trackbar')
    v2 = cv2.getTrackbarPos('v2', 'trackbar')

    # Normal masking algorithm
    lower = np.array([h, s, v])
    upper = np.array([h2, s2, v2])

    mask = cv2.inRange(hsv, lower, upper)

    result = cv2.bitwise_and(frame,frame,mask = mask)

    cv2.imshow('result', result)
    print(h, s, v, h2, s2, v2)
    k = cv2.waitKey(5) & 0xFF
    if k == 27:
        break

cv2.destroyAllWindows()

如果这不起作用，我将使用像CSRT这样的对象跟踪器API

# python opencv_object_tracking.py
# python opencv_object_tracking.py --video dashcam_boston.mp4 --tracker csrt

# import the necessary packages
from imutils.video import VideoStream
from imutils.video import FPS
import argparse
import imutils
import time
import cv2

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video", type=str,
    help="path to input video file")
ap.add_argument("-t", "--tracker", type=str, default="kcf",
    help="OpenCV object tracker type")
args = vars(ap.parse_args())

# extract the OpenCV version info
(major, minor) = cv2.__version__.split(".")[:2]

# if we are using OpenCV 3.2 OR BEFORE, we can use a special factory
# function to create our object tracker
if int(major) == 3 and int(minor) < 3:
    tracker = cv2.Tracker_create(args["tracker"].upper())

# otherwise, for OpenCV 3.3 OR NEWER, we need to explicity call the
# approrpiate object tracker constructor:
else:
    # initialize a dictionary that maps strings to their corresponding
    # OpenCV object tracker implementations
    OPENCV_OBJECT_TRACKERS = {
        "csrt": cv2.TrackerCSRT_create,
        "kcf": cv2.TrackerKCF_create,
        "boosting": cv2.TrackerBoosting_create,
        "mil": cv2.TrackerMIL_create,
        "tld": cv2.TrackerTLD_create,
        "medianflow": cv2.TrackerMedianFlow_create,
        "mosse": cv2.TrackerMOSSE_create
    }

    # grab the appropriate object tracker using our dictionary of
    # OpenCV object tracker objects
    tracker = OPENCV_OBJECT_TRACKERS[args["tracker"]]()

# initialize the bounding box coordinates of the object we are going
# to track
initBB = None

# if a video path was not supplied, grab the reference to the web cam
if not args.get("video", False):
    print("[INFO] starting video stream...")
    vs = VideoStream(src=0).start()
    time.sleep(1.0)

# otherwise, grab a reference to the video file
else:
    vs = cv2.VideoCapture(args["video"])

# initialize the FPS throughput estimator
fps = None

# loop over frames from the video stream
while True:
    # grab the current frame, then handle if we are using a
    # VideoStream or VideoCapture object
    frame = vs.read()
    frame = frame[1] if args.get("video", False) else frame

    # check to see if we have reached the end of the stream
    if frame is None:
        break

    # resize the frame (so we can process it faster) and grab the
    # frame dimensions
    frame = imutils.resize(frame, width=500)
    (H, W) = frame.shape[:2]

    # check to see if we are currently tracking an object
    if initBB is not None:
        # grab the new bounding box coordinates of the object
        (success, box) = tracker.update(frame)

        # check to see if the tracking was a success
        if success:
            (x, y, w, h) = [int(v) for v in box]
            cv2.rectangle(frame, (x, y), (x + w, y + h),
                (0, 255, 0), 2)

        # update the FPS counter
        fps.update()
        fps.stop()

        # initialize the set of information we'll be displaying on
        # the frame
        info = [
            ("Tracker", args["tracker"]),
            ("Success", "Yes" if success else "No"),
            ("FPS", "{:.2f}".format(fps.fps())),
        ]

        # loop over the info tuples and draw them on our frame
        for (i, (k, v)) in enumerate(info):
            text = "{}: {}".format(k, v)
            cv2.putText(frame, text, (10, H - ((i * 20) + 20)),
                cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)

    # show the output frame
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    # if the 's' key is selected, we are going to "select" a bounding
    # box to track
    if key == ord("s"):
        # select the bounding box of the object we want to track (make
        # sure you press ENTER or SPACE after selecting the ROI)
        initBB = cv2.selectROI("Frame", frame, fromCenter=False,
            showCrosshair=True)

        # start OpenCV object tracker using the supplied bounding box
        # coordinates, then start the FPS throughput estimator as well
        tracker.init(frame, initBB)
        fps = FPS().start()

    # if the `q` key was pressed, break from the loop
    elif key == ord("q"):
        break

# if we are using a webcam, release the pointer
if not args.get("video", False):
    vs.stop()

# otherwise, release the file pointer
else:
    vs.release()

# close all windows
cv2.destroyAllWindows()