# Revision history [back]

### Good foreground segmentation methods apart from Canny

I have a grey scale image (single channel data) and want to perform something like the Canny edge detection operation on it for foreground segmentation. But, the output has a lot of noise. I also tried bilateral filtering along with it but it didn't help the output.

## Thank you.

Code snippet:

v = np.median(vis)

sigma = 0.33

lower = int(max(0, (1.0 - sigma) * v))

upper = int(min(255, (1.0 + sigma) * v))

edges = cv2.Canny(vis,lower,upper) edges = cv2.Canny(depth_vis,lower,upper)

Below is a sample picture of current Canny detector output. C:\fakepath\canny.png

 2 None berak 32993 ●7 ●81 ●312

### Good foreground segmentation methods apart from Canny

I have a grey scale image (single channel data) and want to perform something like the Canny edge detection operation on it for foreground segmentation. But, the output has a lot of noise. I also tried bilateral filtering along with it but it didn't help the output.

## Thank you.

Code snippet:

v = np.median(vis)

sigma = 0.33

lower = int(max(0, (1.0 - sigma) * v))

upper = int(min(255, (1.0 + sigma) * v))

edges = cv2.Canny(vis,lower,upper) edges = cv2.Canny(depth_vis,lower,upper)

Below is a sample picture of current Canny detector output. C:\fakepath\canny.png

 3 None supra56 943 ●9 ●6

### Good foreground segmentation methods apart from Canny

I have a grey scale image (single channel data) and want to perform something like the Canny edge detection operation on it for foreground segmentation. But, the output has a lot of noise. I also tried bilateral filtering along with it but it didn't help the output.

## Thank you.

Code snippet:

v = np.median(vis)

sigma = 0.33

lower = int(max(0, (1.0 - sigma) * v))

upper = int(min(255, (1.0 + sigma) * v))

edges = cv2.Canny(vis,lower,upper) edges = cv2.Canny(depth_vis,lower,upper)

Below is a sample picture of current Canny detector output.

 4 None supra56 943 ●9 ●6

### Good foreground segmentation methods apart from Canny

I have a grey scale image (single channel data) and want to perform something like the Canny edge detection operation on it for foreground segmentation. But, the output has a lot of noise. I also tried bilateral filtering along with it but it didn't help the output.

## Thank you.

Code snippet:

v = np.median(vis)

sigma = 0.33

lower = int(max(0, (1.0 - sigma) * v))

upper = int(min(255, (1.0 + sigma) * v))

edges = cv2.Canny(vis,lower,upper) edges = cv2.Canny(depth_vis,lower,upper)

Below is a sample picture of current Canny detector output.

 5 None supra56 943 ●9 ●6

### Good foreground segmentation methods apart from Canny

I have a grey scale image (single channel data) and want to perform something like the Canny edge detection operation on it for foreground segmentation. But, the output has a lot of noise. I also tried bilateral filtering along with it but it didn't help the output.

## Thank you.

Code snippet:

 v = np.median(vis)np.median(vis)
sigma = 0.330.33
lower = int(max(0, (1.0 - sigma) * v))v))
upper = int(min(255, (1.0 + sigma) * v))v))
edges = cv2.Canny(vis,lower,upper)
edges = cv2.Canny(depth_vis,lower,upper)cv2.Canny(depth_vis,lower,upper)


Below is a sample picture of current Canny detector output.

 6 retagged sturkmen 6772 ●3 ●48 ●79 https://github.com/stu...

### Good foreground segmentation methods apart from Canny

I have a grey scale image (single channel data) and want to perform something like the Canny edge detection operation on it for foreground segmentation. But, the output has a lot of noise. I also tried bilateral filtering along with it but it didn't help the output.

## Thank you.

Code snippet:

 v = np.median(vis)

sigma = 0.33

lower = int(max(0, (1.0 - sigma) * v))

upper = int(min(255, (1.0 + sigma) * v))

edges = cv2.Canny(vis,lower,upper)
edges = cv2.Canny(depth_vis,lower,upper)


Below is a sample picture of current Canny detector output.