Opencv 摄像机姿态估计给出错误结果
我试图根据两幅不同图像中的匹配点来估计相机的相对运动。很像这里描述的: 但估计的平移和旋转没有意义 我使用合成输入来确保所有的点都是有效的和完美的定位 在立方体中均匀分布10 x 10 x 10点。 (立方体以蓝色正面、红色背面、浅色顶部和深色底部绘制) 摄影机位于立方体前面,指向正面 摄影机位于立方体左侧,指向左侧面 我绘制了两个投影图。您可以轻松地从视觉上验证摄影机已平移90度,并在两个投影之间的x-z平面上沿对角线移动 在代码中,旋转(以度为单位)表示为(0,-90,0) 平移为(0.7071,0,0.7071),相机移动距离正好为1 然后我在2d点集上进行FindSentialMat()和recoverPose(),以获得平移和旋转估计 我希望看到与生成图像相同的平移和旋转,但估计完全错误:Opencv 摄像机姿态估计给出错误结果,opencv,3d-reconstruction,opencv-python,Opencv,3d Reconstruction,Opencv Python,我试图根据两幅不同图像中的匹配点来估计相机的相对运动。很像这里描述的: 但估计的平移和旋转没有意义 我使用合成输入来确保所有的点都是有效的和完美的定位 在立方体中均匀分布10 x 10 x 10点。 (立方体以蓝色正面、红色背面、浅色顶部和深色底部绘制) 摄影机位于立方体前面,指向正面 摄影机位于立方体左侧,指向左侧面 我绘制了两个投影图。您可以轻松地从视觉上验证摄影机已平移90度,并在两个投影之间的x-z平面上沿对角线移动 在代码中,旋转(以度为单位)表示为(0,-90,0) 平移为(0
rotation estimate: (-74.86565284711004, -48.52201867665918, 121.26023708879158)
translation estimate: [[0.96576997]
[0.17203598]
[0.19414426]]
如何恢复实际的(0,-90,0),(0.7071,0,07071)转换
显示两个立方体图像并打印估算值的完整代码:
import cv2
import numpy as np
import math
def cameraMatrix(f, w, h):
return np.array([
[f, 0, w/2],
[0, f, h/2],
[0, 0, 1]])
n = 10
f = 300
w = 640
h = 480
K = cameraMatrix(f, w, h)
def cube(x=0, y=0, z=0, radius=1):
c = np.zeros((n * n * n, 3), dtype=np.float32)
for i in range(0, n):
for j in range(0, n):
for k in range(0, n):
index = i + j * n + k * n * n
c[index] = [i, j, k]
c = 2 * c / (n - 1) - 1
c *= radius
c += [x, y, z]
return c
def project3dTo2dArray(points3d, K, rotation, translation):
imagePoints, _ = cv2.projectPoints(points3d,
rotation,
translation,
K,
np.array([]))
p2d = imagePoints.reshape((imagePoints.shape[0],2))
return p2d
def estimate_pose(projectionA, projectionB):
E, _ = cv2.findEssentialMat(projectionA, projectionB, focal = f)
_, r, t, _ = cv2.recoverPose(E, projectionA, projectionB)
angles, _, _, _, _, _ = cv2.RQDecomp3x3(r)
print('rotation estimate:', angles)
print('translation estimate:', t)
def main():
c = cube(0, 0, math.sqrt(.5), 0.1)
rotation = np.array([[0], [0], [0]], dtype=np.float32)
translation = np.array([[0], [0], [0]], dtype=np.float32)
zeroProjection = project3dTo2dArray(c, K, rotation, translation)
displayCube(w, h, zeroProjection)
rotation = np.array([[0], [-90], [0]], dtype=np.float32)
translation = np.array([[math.sqrt(.5)], [0], [math.sqrt(.5)]], dtype=np.float32)
print('applying rotation: ', rotation)
print('applying translation: ', translation)
rotate90projection = project3dTo2dArray(c, K, rotation * math.pi / 180, translation)
displayCube(w, h, rotate90projection)
estimate_pose(zeroProjection, rotate90projection)
def displayCube(w, h, points):
img = np.zeros((h, w, 3), dtype=np.uint8)
plotCube(img, points)
cv2.imshow('img', img)
k = cv2.waitKey(0) & 0xff
if k == ord('q'):
exit(0)
def plotCube(img, points):
# Red back face
cv2.line(img, tuple(points[n*n*(n-1)]), tuple(points[n*n*(n-1)+n-1]), (0, 0, 255), 2)
cv2.line(img, tuple(points[n*n*(n-1)+n*(n-1)]), tuple(points[n*n*(n-1)+n*(n-1)+n-1]), (0, 0, 128), 2)
cv2.line(img, tuple(points[n*n*(n-1)]), tuple(points[n*n*(n-1)+n*(n-1)]), (0, 0, 200), 2)
cv2.line(img, tuple(points[n*n*(n-1)+n-1]), tuple(points[n*n*(n-1)+n*(n-1)+n-1]), (0, 0, 200), 2)
# gray connectors
cv2.line(img, tuple(points[0]), tuple(points[n*n*(n-1)]), (150, 150, 150), 2)
cv2.line(img, tuple(points[n-1]), tuple(points[n*n*(n-1)+n-1]), (150, 150, 150), 2)
cv2.line(img, tuple(points[n*(n-1)]), tuple(points[n*n*(n-1)+n*(n-1)]), (100, 100, 100), 2)
cv2.line(img, tuple(points[n*(n-1)+n-1]), tuple(points[n*n*(n-1)+n*(n-1)+n-1]), (100, 100, 100), 2)
# Blue front face
cv2.line(img, tuple(points[0]), tuple(points[n-1]), (255, 0, 0), 2)
cv2.line(img, tuple(points[n*(n-1)]), tuple(points[n*(n-1)+n-1]), (128, 0, 0), 2)
cv2.line(img, tuple(points[0]), tuple(points[n*(n-1)]), (200, 0, 0), 2)
cv2.line(img, tuple(points[n-1]), tuple(points[n*(n-1)+n-1]), (200, 0, 0), 2)
main()
结果是我的代码中有一些小错误(比如错误的主点)。 下面的工作代码显示了3个图像 首先是一个立方体显示在摄像机前面。 第二个是相同的立方体,但投影不同。摄像机已移动1个单元,并绕所有3个轴旋转。 摄像机的平移和旋转由两个投影估计。 第三个显示使用旋转和平移估计投影的立方体 因为第二个和第三个图像是相似的,所以代码可以工作
import cv2
import numpy as np
import math
def cameraMatrix(f, w, h):
return np.array([
[f, 0, w/2],
[0, f, h/2],
[0, 0, 1]])
n = 10
f = 300
w = 640
h = 480
K = cameraMatrix(f, w, h)
def cube(x=0, y=0, z=0, radius=1):
c = np.zeros((n * n * n, 3), dtype=np.float32)
for i in range(0, n):
for j in range(0, n):
for k in range(0, n):
index = i + j * n + k * n * n
c[index] = [i, j, k]
c = 2 * c / (n - 1) - 1
c *= radius
c += [x, y, z]
return c
def project3dTo2dArray(points3d, K, rotation, translation):
imagePoints, _ = cv2.projectPoints(points3d,
rotation,
translation,
K,
np.array([]))
p2d = imagePoints.reshape((imagePoints.shape[0],2))
return p2d
def estimate_pose(projectionA, projectionB):
principal_point = (w/2,h/2)
E, m = cv2.findEssentialMat(projectionA, projectionB, focal = f, pp = principal_point, method=cv2.RANSAC, threshold=1, prob=0.999)
_, r, t, _ = cv2.recoverPose(E, projectionA, projectionB, focal = f, pp = principal_point, mask = m)
angles, _, _, _, _, _ = cv2.RQDecomp3x3(r)
return angles, t
def main():
c = cube(0, 0, math.sqrt(.5), 0.1)
rotation = np.array([[0], [0], [0]], dtype=np.float32)
translation = np.array([[0], [0], [0]], dtype=np.float32)
zeroProjection = project3dTo2dArray(c, K, rotation, translation)
displayCube(w, h, zeroProjection)
rotation = np.array([[10], [-30], [5]], dtype=np.float32)
translation = np.array([[math.sqrt(.7)], [0], [math.sqrt(.3)]], dtype=np.float32)
print('applying rotation: ', rotation)
print('applying translation: ', translation)
movedprojection = project3dTo2dArray(c, K, rotation * math.pi / 180, translation)
displayCube(w, h, movedprojection)
estRot, estTra= estimate_pose(zeroProjection, movedprojection)
print('rotation estimate:', estRot)
print('translation estimate:', estTra)
rotation = np.array([[estRot[0]], [estRot[1]], [estRot[2]]], dtype=np.float32)
translation = np.array([[estTra[0]], [estTra[1]], [estTra[2]]], dtype=np.float32)
estimateProjection = project3dTo2dArray(c, K, rotation * math.pi / 180, translation)
displayCube(w, h, estimateProjection)
def displayCube(w, h, points):
img = np.zeros((h, w, 3), dtype=np.uint8)
plotCube(img, points)
cv2.imshow('img', img)
k = cv2.waitKey(0) & 0xff
if k == ord('q'):
exit(0)
def plotCube(img, points):
# Red back face
cv2.line(img, tuple(points[n*n*(n-1)]), tuple(points[n*n*(n-1)+n-1]), (0, 0, 255), 2)
cv2.line(img, tuple(points[n*n*(n-1)+n*(n-1)]), tuple(points[n*n*(n-1)+n*(n-1)+n-1]), (0, 0, 128), 2)
cv2.line(img, tuple(points[n*n*(n-1)]), tuple(points[n*n*(n-1)+n*(n-1)]), (0, 0, 200), 2)
cv2.line(img, tuple(points[n*n*(n-1)+n-1]), tuple(points[n*n*(n-1)+n*(n-1)+n-1]), (0, 0, 200), 2)
# gray connectors
cv2.line(img, tuple(points[0]), tuple(points[n*n*(n-1)]), (150, 150, 150), 2)
cv2.line(img, tuple(points[n-1]), tuple(points[n*n*(n-1)+n-1]), (150, 150, 150), 2)
cv2.line(img, tuple(points[n*(n-1)]), tuple(points[n*n*(n-1)+n*(n-1)]), (100, 100, 100), 2)
cv2.line(img, tuple(points[n*(n-1)+n-1]), tuple(points[n*n*(n-1)+n*(n-1)+n-1]), (100, 100, 100), 2)
# Blue front face
cv2.line(img, tuple(points[0]), tuple(points[n-1]), (255, 0, 0), 2)
cv2.line(img, tuple(points[n*(n-1)]), tuple(points[n*(n-1)+n-1]), (128, 0, 0), 2)
cv2.line(img, tuple(points[0]), tuple(points[n*(n-1)]), (200, 0, 0), 2)
cv2.line(img, tuple(points[n-1]), tuple(points[n*(n-1)+n-1]), (200, 0, 0), 2)
main()
您是否验证了结果是错误的,而不是根据我在链接问题中的回答对值的解释?8分可能不够。更新代码使用1000点。还更新了代码以使用平移距离=1,因为recoverPose()仅提供平移方向单位向量。(距离未知)这是我要恢复的信息:平移=(0.7071,0,0.7071),旋转=(0,-90,0)