Search found 18 matches

by Uio96
04 Mar 2020, 20:36
Forum: Bug reports
Topic: Potential memory leak problem with the vision sensor
Replies: 1
Views: 1029

Potential memory leak problem with the vision sensor

Hi there, I am using VREP v3.6.2 to generate a bunch of images. It was fine at first but after thousands of rounds, the memory it consumed became so big. Then eventually, the system crashed. I am currently using python API like vrep.simxGetVisionSensorImage to obtain the raw image. I guess the probl...
by Uio96
01 Feb 2020, 22:16
Forum: General questions
Topic: Coordinate transformation from camera frame to world frame
Replies: 1
Views: 289

Re: Coordinate transformation from camera frame to world frame

I just double-checked my code. The problem is with my point cloud input. The other stuff is good. Thanks anyway.
by Uio96
01 Feb 2020, 20:07
Forum: General questions
Topic: Coordinate transformation from camera frame to world frame
Replies: 1
Views: 289

Coordinate transformation from camera frame to world frame

Hi there, I'm trying to transform coordinates from camera frame to world frame. I first use the Lua script to get the transformation matrix between the camera and the world origin, e.g. Trans=sim.getObjectMatrix(cameraHandle,-1). Then I transform the point cloud obtained by the vision sensor in Matl...
by Uio96
28 Nov 2019, 22:34
Forum: General questions
Topic: Mismatch of RGB image and depth image
Replies: 4
Views: 408

Re: Mismatch of RGB image and depth image

Got you. Thank you so much. I figured out another way to solve my problem indirectly.
by Uio96
21 Nov 2019, 17:32
Forum: General questions
Topic: Mismatch of RGB image and depth image
Replies: 4
Views: 408

Re: Mismatch of RGB image and depth image

Thanks for the reply. In fact, I do not use the Lua script but use the python remote API instead. I do not think it will make a difference if the depth and RGB images are acquired at the same time.

I used function like:
vrep.simxGetVisionSensorImage
vrep.simxGetVisionSensorDepthBuffer
by Uio96
20 Nov 2019, 17:16
Forum: General questions
Topic: Mismatch of RGB image and depth image
Replies: 4
Views: 408

Mismatch of RGB image and depth image

Hi there, Recently, I met a wired problem of mismatch of RGB image and depth image. E.g. I first run my simulation and then when my objects have not FULLY stopped there, I just pause the simulation (to save time). I find that in some cases, a mismatch of RGB image and depth image will occur. I guess...
by Uio96
13 Nov 2019, 20:36
Forum: General questions
Topic: How to map from 3D coordinates to 2D coordinates in image
Replies: 1
Views: 286

Re: How to map from 3D coordinates to 2D coordinates in image

I finally solve the problem. It was my mistake. Previously, I set up camera's intrinsics matrix but did not update the vision sensor.
by Uio96
13 Nov 2019, 04:34
Forum: General questions
Topic: How to map from 3D coordinates to 2D coordinates in image
Replies: 1
Views: 286

How to map from 3D coordinates to 2D coordinates in image

Hi there, After I get the 3D coordinates of the object in the vision sensor frame, I want to extract their corresponding 2D coordinates in the output image. I try to use some codes like cam_intrinsics = np.hstack((self.cam_intrinsics, np.zeros((self.cam_intrinsics.shape[0], 1), dtype=self.cam_intrin...
by Uio96
13 Nov 2019, 04:15
Forum: General questions
Topic: How to get the coordinates in the camera frame?
Replies: 2
Views: 356

Re: How to get the coordinates in the camera frame?

Hi there, I think I find another way to deal with it. Just use simGetObjectMatrix api to get the transformation matrix. I guess the previous problem is that I was not sure how to calculate the transformation matrix using pos and euler information. The exact relationship in vrep still remains ambiguo...
by Uio96
12 Nov 2019, 18:22
Forum: General questions
Topic: How to get the coordinates in the camera frame?
Replies: 2
Views: 356

How to get the coordinates in the camera frame?

Hi there, I'm trying to transform the coordinates from a local frame to the camera frame. It's a simple task and I just followed steps in like http://www.cs.cmu.edu/~16385/s17/Slides/11.1_Camera_matrix.pdf like X_c = R(X_l - C) X_c represents coordinates in the camera frame, R represents rotation ma...