AprilTags二维码的检测与应用

1 AprilTags介绍

  • AprilTag官网：https://april.eecs.umich.edu/software/apriltag

1、AprilTags类似与二维码QR codes（Quick Response Code；全称为快速响应矩阵图码）

2、AprilTags可以应用于：

  • 相机标定
  • 目标大小估计
  • 测量相机到目标的距离
  • 3D 定位（3D positioning）
  • 机器人
  • SLAM
  • 自主导航（autonomous navigation）

如下图是一个AprilTag Tag36h11的一张图：

我们在相机标定的时候，还会用到很多AprilTags在一起组成的标定板，如下图（图片来源）：

3、AprilTag family默认的是：Tag36h11，在AprilTags中有六个系列families：

  • Tag36h11
  • TagStandard41h12
  • TagStandard52h13
  • TagCircle21h7
  • TagCircle49h12
  • TagCustom48h12

2 使用python库包apriltag对AprilTag进行检测

2.1 python模块apriltag的安装

  • pypi下载安装apriltag库包：https://pypi.org/project/apriltag/

pip install apriltag

2.2 python模块apriltag的测试用例

测试用例（参考）

import apriltag
import cv2
img = cv2.imread('apriltag_foto.jpg'.cv2.IMREAD_GRAYSCALE)
detector = apriltag.Detector()
result = detector.detect(img)

返回结果如下：

[DetectionBase(tag_family='tag36h11', tag_id=2, hamming=0, goodness=0.0, decision_margin=98.58241271972656, homography=array([[ -1.41302664e-01,   1.08428082e+00,   1.67512900e+01],
   [ -8.75899366e-01,   1.50245469e-01,   1.70532040e+00],
   [ -4.89183533e-04,   2.12210247e-03,   6.02052342e-02]]), center=array([ 278.23643912,   28.32511859]), corners=array([[ 269.8939209 ,   41.50381088],
   [ 269.57183838,   11.79248142],
   [ 286.1383667 ,   15.84242821],
   [ 286.18066406,   43.48323059]])),
DetectionBase(tag_family='tag36h11', ... etc

结果中是用collections.OrderedDict存储成字典类型的数据

3 AprilTags二维码检测，以及绘制检测框

1、代码

import cv2
import apriltag


image = cv2.imread('apriltags_36h11.png')

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# 定义AprilTag检测选项，然后检测AprilTags
print(f"[INFO] detection AprilTags ...")
options = apriltag.DetectorOptions(families="tag36h11")
detector = apriltag.Detector(options)
results = detector.detect(gray)
print(results)
print(f"[INFO] {len(results)} total AprilTags detected")

for r in results:
    # extract the bounding box (x, y)-coordinates for the AprilTag
    # and convert each of the (x, y)-coordinate pairs to integers
    (ptA, ptB, ptC, ptD) = r.corners
    ptB = (int(ptB[0]), int(ptB[1]))
    ptC = (int(ptC[0]), int(ptC[1]))
    ptD = (int(ptD[0]), int(ptD[1]))
    ptA = (int(ptA[0]), int(ptA[1]))
    # 绘制检测到的AprilTag的框
    cv2.line(image, ptA, ptB, (0, 255, 0), 2, lineType=cv2.LINE_AA)
    cv2.line(image, ptB, ptC, (0, 255, 0), 2, lineType=cv2.LINE_AA)
    cv2.line(image, ptC, ptD, (0, 255, 0), 2, lineType=cv2.LINE_AA)
    cv2.line(image, ptD, ptA, (0, 255, 0), 2, lineType=cv2.LINE_AA)
    # 绘制 AprilTag 的中心坐标
    (cX, cY) = (int(r.center[0]), int(r.center[1]))
    cv2.circle(image, (cX, cY), 5, (0, 0, 255), -1)
    # draw the tag family on the image
    tagFamily = r.tag_family.decode("utf-8")
    cv2.putText(image, tagFamily, (ptA[0], ptA[1] - 15),
                cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
    print("[INFO] tag family: {}".format(tagFamily))

cv2.imshow("Image", image)
cv2.waitKey(0)

 2、检测结果如下图：

AprilTag标记跟踪

参考

OpenMV是一款具有图像处理功能的单片机摄像头

  • 参考：https://www.pyimagesearch.com/2020/11/02/apriltag-with-python/

  • 参考：https://book.openmv.cc/image/apriltag.html # AprilTag标记跟踪