diff --git a/.github/workflows/format.yml b/.github/workflows/format.yml
index d72cdf4..c0bedf3 100644
--- a/.github/workflows/format.yml
+++ b/.github/workflows/format.yml
@@ -6,9 +6,9 @@ name: Ultralytics Actions
on:
push:
- branches: [main,master]
+ branches: [main]
pull_request:
- branches: [main,master]
+ branches: [main]
jobs:
format:
diff --git a/README.md b/README.md
index a10cb1f..0933fb0 100644
--- a/README.md
+++ b/README.md
@@ -57,7 +57,7 @@ The repository contains various methods for vehicle speed estimation. If you're
-
+
# 📚 Citation
diff --git a/utils/NLS.py b/utils/NLS.py
index 6bb85ef..b0dbafc 100644
--- a/utils/NLS.py
+++ b/utils/NLS.py
@@ -202,7 +202,7 @@ def fcnNLS_batch(K, P, pw, cw): # solves for pxyz, cxyz[1:], crpy[1:]
z[nanz] = 0
crpy = np.zeros((nc, 3))
x = np.concatenate((pw, cw[1:], crpy)).ravel() # [tp_pos, cam_pos, cam_rpy, K3]
- range_cal = norm(cw[1])
+ norm(cw[1])
def fzKautograd_batch(x, K, nc, nt): # for autograd
pw = x[: nt * 3].reshape(nt, 3)
@@ -247,7 +247,7 @@ def fzKautograd_batch(x, K, nc, nt): # for autograd
pw = x[:j].reshape(nt, 3)
cw = x[j : j + nc * 3].reshape(nc, 3) # cam pos
cw = np.concatenate((np.zeros((1, 3)), cw), 0)
- ca = x[j + nc * 3 : j + nc * 3 * 2].reshape(nc, 3) # cam rpy
+ x[j + nc * 3 : j + nc * 3 * 2].reshape(nc, 3) # cam rpy
return cw, pw
@@ -325,5 +325,5 @@ def fzKautograd_batch(x, K, nc, nt): # for autograd
pw = x[:j].reshape(nt, 3)
cw = sc2cc(sc) @ C # cam pos
cw = np.concatenate((np.zeros((1, 3)), cw), 0)
- ca = x[j : j + 3] # cam rpy
+ x[j : j + 3] # cam rpy
return cw, pw
diff --git a/vidExample.py b/vidExample.py
index 4ba3217..cbd1418 100644
--- a/vidExample.py
+++ b/vidExample.py
@@ -151,7 +151,6 @@ def vidExamplefcn():
P[0:2, vg, i] = p.T # xy
P[2:4, vp, i] = p_.T # xy_proj
P[4, vg, i] = i
- im0 = im
msvFrame = 5
if i == msvFrame:
@@ -168,7 +167,7 @@ def vidExamplefcn():
# imrgb = cv2.cvtColor(imbgr,cv2.COLOR_BGR2RGB)
# plots.imshow(cv2.cvtColor(imrgb,cv2.COLOR_BGR2HSV_FULL)[:,:,0])
im_gaussian = cv2.GaussianBlur(im, (3, 3), 0)
- im_canny = cv2.Canny(im_gaussian, 100, 200)
+ cv2.Canny(im_gaussian, 100, 200)
# plots.imshow(cv2.GaussianBlur(im_canny, (9, 9), 0))
if isVideo: