I am not understanding the reason for this error 'cameraMatrix' is an invalid keyword argument for detectMarkers()

Question

Full error is:

OpenCV(4.7.0) :-1: error: (-5:Bad argument) in function 'detectMarkers'
> Overload resolution failed:
>  - 'cameraMatrix' is an invalid keyword argument for detectMarkers()

My camera calibration code works fine (to my understanding) i have input my values however when i run the code i am still getting cameraMatrix errors. Please help me understand why i would be getting this error.

import numpy as np
import cv2
import sys
import time


ARUCO_DICT = {
    "DICT_4X4_50": cv2.aruco.DICT_4X4_50,
    "DICT_4X4_100": cv2.aruco.DICT_4X4_100,
    "DICT_4X4_250": cv2.aruco.DICT_4X4_250,
    "DICT_4X4_1000": cv2.aruco.DICT_4X4_1000,
    "DICT_5X5_50": cv2.aruco.DICT_5X5_50,
    "DICT_5X5_100": cv2.aruco.DICT_5X5_100,
    "DICT_5X5_250": cv2.aruco.DICT_5X5_250,
    "DICT_5X5_1000": cv2.aruco.DICT_5X5_1000,
    "DICT_6X6_50": cv2.aruco.DICT_6X6_50,
    "DICT_6X6_100": cv2.aruco.DICT_6X6_100,
    "DICT_6X6_250": cv2.aruco.DICT_6X6_250,
    "DICT_6X6_1000": cv2.aruco.DICT_6X6_1000,
    "DICT_7X7_50": cv2.aruco.DICT_7X7_50,
    "DICT_7X7_100": cv2.aruco.DICT_7X7_100,
    "DICT_7X7_250": cv2.aruco.DICT_7X7_250,
    "DICT_7X7_1000": cv2.aruco.DICT_7X7_1000,
    "DICT_ARUCO_ORIGINAL": cv2.aruco.DICT_ARUCO_ORIGINAL,
    "DICT_APRILTAG_16h5": cv2.aruco.DICT_APRILTAG_16h5,
    "DICT_APRILTAG_25h9": cv2.aruco.DICT_APRILTAG_25h9,
    "DICT_APRILTAG_36h10": cv2.aruco.DICT_APRILTAG_36h10,
    "DICT_APRILTAG_36h11": cv2.aruco.DICT_APRILTAG_36h11
}

def aruco_display(corners, ids, rejected, image):
    
    if len(corners) > 0:
        
        ids = ids.flatten()
        
        for (markerCorner, markerID) in zip(corners, ids):
            
            corners = markerCorner.reshape((4, 2))
            (topLeft, topRight, bottomRight, bottomLeft) = corners
            
            topRight = (int(topRight[0]), int(topRight[1]))
            bottomRight = (int(bottomRight[0]), int(bottomRight[1]))
            bottomLeft = (int(bottomLeft[0]), int(bottomLeft[1]))
            topLeft = (int(topLeft[0]), int(topLeft[1]))

            cv2.line(image, topLeft, topRight, (0, 255, 0), 2)
            cv2.line(image, topRight, bottomRight, (0, 255, 0), 2)
            cv2.line(image, bottomRight, bottomLeft, (0, 255, 0), 2)
            cv2.line(image, bottomLeft, topLeft, (0, 255, 0), 2)
            
            cX = int((topLeft[0] + bottomRight[0]) / 2.0)
            cY = int((topLeft[1] + bottomRight[1]) / 2.0)
            cv2.circle(image, (cX, cY), 4, (0, 0, 255), -1)
            
            cv2.putText(image, str(markerID),(topLeft[0], topLeft[1] - 10), cv2.FONT_HERSHEY_SIMPLEX,
                0.5, (0, 255, 0), 2)
            print("[Inference] ArUco marker ID: {}".format(markerID))
            
    return image


def pose_estimation(frame, aruco_dict_type, matrix_coefficients, distortion_coefficients):

    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    cv2.aruco_dict = cv2.aruco.getPredefinedDictionary(aruco_dict_type)
    parameters = cv2.aruco.DetectorParameters()

    corners, ids, rejected_img_points = cv2.aruco.detectMarkers(gray, cv2.aruco_dict,parameters=parameters,
        cameraMatrix=matrix_coefficients,
        distCoeff=distortion_coefficients)

    if len(corners) > 0:
        for i in range(0, len(ids)):
           
            rvec, tvec, markerPoints = cv2.aruco.estimatePoseSingleMarkers(corners[i], 0.02, matrix_coefficients,
                                                                       distortion_coefficients)
            
            cv2.aruco.drawDetectedMarkers(frame, corners) 

            cv2.aruco.drawAxis(frame, matrix_coefficients, distortion_coefficients, rvec, tvec, 0.01)  

    return frame


aruco_type = "DICT_4X4_50"

arucoDict = cv2.aruco.getPredefinedDictionary(ARUCO_DICT[aruco_type])

arucoParams = cv2.aruco.DetectorParameters()

intrinsic_camera = np.array(((981.69820777, 0, 637.86160616),(0,983.8672381, 364.31555519),(0,0,1)))
distortion = np.array((0.0366562741,-0.153342145,-0.000307462615,-0.000078917106,0.215865749))

cap = cv2.VideoCapture(0)

cap.set(cv2.CAP_PROP_FRAME_WIDTH, 1280)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 720)

while cap.isOpened():
    
    ret, img = cap.read()

    output = pose_estimation(img, ARUCO_DICT[aruco_type], intrinsic_camera, distortion)

    cv2.imshow('Estimated Pose', output)

    key = cv2.waitKey(1) & 0xFF
    if key == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

I just want to understand why this error is popping up so i can move on :D

welcome. please take the [tour]. – Christoph Rackwitz Feb 03 '23 at 11:54 — Christoph Rackwitz, Feb 03 '23 at 11:54

score 0 · Answer 1 · answered Feb 02 '23 at 12:32

0

OpenCV's aruco API changed in the past year or so, after v4.5.5.

Some APIs that should not deal with intrinsics did previously accept intrinsics parameters. Not any longer.

Detection (detectMarkers()) is a purely 2D operation that should never deal with intrinsics. It returns screen-space 2D coordinates for the corners of each marker.

Pose estimation (estimatePoseSingleMarkers()) should take intrinsics.

It was always an error to pass intrinsics to both APIs at the same time.

answered Feb 02 '23 at 12:32

Christoph Rackwitz

11,317
4
27
36

mmm to my understand I am using detectMarkers() to read in the 2d image then which we made corners = to. Then we push it through to the next if statement where we estimate the 3d image. If i use estimatePoseSingleMarker() in replacement for detectMarkers() i received: > - estimatePoseSingleMarkers() missing required argument 'distCoeffs' (pos 4) – NiccyT Feb 02 '23 at 21:46
I got it working!! I believe.. haven't tested it for accuracy i removed the intrinsic values from the detectMarker portion of the code and now works. – NiccyT Feb 02 '23 at 22:43

I am not understanding the reason for this error 'cameraMatrix' is an invalid keyword argument for detectMarkers()

1 Answers1