Abdul-UOiT
commented
4 years ago 1- If you are using single RGB image, then the only info. you can get is 2D. Unless, you use post-processing method that takes advantage from the 2D data and retrieves the 3D data which includes the depth axis (the distance bet. camera frame and object frame). This method requires 3d-pre-defined info. of the target object.
2- another suggestion, you can use stereo camera (depth image), this one gives you depth information directly. It called vision sensor in v-rep.
When using the video detection software to teach the system to grab the objects in the bin, how will it know how far down to travel to pick up the objects?