17 votes

Why do people use camera instead of laser sensor for robot navigation?

A 3D laser range finder or LIDAR such as the one on the Google Car is far more expensive than a camera. The other reason is that while in case of a LIDAR the distance of every pixel is available, the ...
11 votes

What is inverse depth (in odometry) and why would I use it?

The inverse depth parameterisation represents a landmark's distance, d, from the camera exactly as it says, as proportional to 1/d within the estimation algorithm. The rational behind the approach is ...
  • 111
10 votes
Accepted

AprilTag vs Aruco markers

Aruco (as implemented in OpenCV) pros Easy to set up (with readily available aruco marker generator, opencv & ros implementation, etc.) fewer false detection (with default parameters) cons ...
  • 273
7 votes

What is the best SE3 library for python?

Writing your own package is always the best way to learn. If you want to try something premade here are a few packages to choose from: Spatial Math Toolbox for Python Python3+numpy+scipy, also ...
  • 1,652
7 votes
Accepted

Why do robots need rangefinders while animals don't?

Animals and robots both need to understand something about the 3D structure of the world in order to thrive. Because it's so important, animals have evolved a huge number of strategies to estimate ...
  • 1,652
6 votes

How can I improve ZED Camera precision?

I don't know what you mean by "precision" and how do you measure it. The sensing accuracy will probably go back to the camera calibration precision and the stereo matching algorithm used. If they ...
  • 633
6 votes

SLAM: Why use two cameras (stereo) if SLAM can be done using single camera (monocular)?

The most important point is the scale. If you do monocular SLAM, your map will only be accurate up to scale so that you e.g. cannot compute the length of the travelled path in meters. The scale ...
  • 1,345
6 votes

Which is the best visual fiducial marker (2D barcode)?

AprilTag is the state-of-the-art solution for pose estimation. The library itself already has pre-built functions to compute the marker position, given its size. The pose is estimated by homography ...
5 votes
Accepted

Questions regarding 3D scanning and camera choice

My favorite is the Learning OpenCV book. It has a fantastic stereo / 3D section that introduces concepts from the ground up. If you're at a university, you might be able to find the digital version ...
  • 176
5 votes
Accepted

Low power computer for stereo vision

You probably are asking too much of inexpensive components. The raspberry Pi does not have 2 camera connections, but its brother, the Pi Compute board does. http://makezine.com/2014/11/03/stereo-...
  • 2,013
5 votes
Accepted

How can I recognize animals in a video stream or static images with openCV or other library/software?

Given that you are doing a more "constrained" goal, with a "mostly" static background, I would recommend simply doing a "background image subtraction" method. The "hard part" which has come a long way ...
5 votes

image processing

Ball detection using vision is not extremely difficult, especially if the ball is easy to recognize. There are a lot of tutorials and blogs which give a detailed explanation on how to implement an ...
  • 260
5 votes

SLAM : Why is marginalization the same as schur's complement?

The following are mostly based on "Factor Graphs for Robot Perception" by Frank Dellaert and Michael Kaess, with additional notes: As a reminder, marginalization is about having a joint ...
5 votes
Accepted

Are there any advantages to using a LIDAR for SLAM vs a standard RGB camera?

My question: are there cases where you'd still need a LIDAR or can this expensive sensor be replaced with a standard camera? ... A each one of them has its advantages/disadvantages. Thus in some ...
  • 319
5 votes

Why is a computer vision system similar to the human vision

I would argue that the similarities are largely superficial. More "classical" machine vision approaches focused on finding features a human can identify such as lines, texture and blobs of color. ...
  • 415
5 votes
Accepted

What is the best SE3 library for python?

ROS's tf.transformations.py has self-contained code for doing these functions and can be used without installing ros. In fact, the python code only depends on numpy! transformations.py
4 votes

What is inverse depth (in odometry) and why would I use it?

Davison's paper introducing the method is easy enough to understand: Inverse Depth Parametrization for Monocular SLAM by Javier Civera, Andrew J. Davison, and J. M. Martınez Montiel DOI: 10.1109/TRO....
4 votes
Accepted

Real-time video processing on video feed from a drone's camera

This AR.Drone provides SDK, therefore, you can access the images on real-time. It is fully compatible with Linux. They have examples also for smartphones. I believe android and iPhone. It has two ...
  • 2,429
4 votes
Accepted

SLAM : Why is marginalization the same as schur's complement?

See the walk-through The Schur complement helps with the closed form derivation but isn't necessary. It's just a nice convenient property of Gaussians and the covariance matrices. In these papers,...
4 votes

What the name of this kind of computer vision?

In general, markers used to measure position visually are called fiducial markers. Some applications have a single type of fiducial (a solid circle or a cross) repeated many times. Some applications ...
  • 4,425
4 votes

Why do people use camera instead of laser sensor for robot navigation?

In addition to those points in Bence's answer, cameras can: Calculate many complex features that result in very robust matching between frames, and object recognition High angular resolution (typical ...
  • 882
4 votes
Accepted

Smart camera image processing on embedded GPU vs. in the cloud

Performance differences between using an embedded GPU vs. the cloud? For your context (to my mind, gesture recognition would ideally be realtime), the latency of going over the cloud would push me ...
4 votes
Accepted

Determine the relative camera pose given two RGB camera frames in openCV-python

If you understand how relative pose estimation works in theory, it should be quite trivial to translate it into OpenCV code. First, you can pick any feature detection/description approach you like (...
  • 1,101
4 votes
Accepted

Why do we need a marginalization in Bundle Adjustment?

I am still not entirely sure what you are asking, but I believe this may answer your question. Also note I myself don't fully understand all the details behind the marginalization trick, but I will ...
  • 1,661
4 votes
Accepted

Robotic Hand Grasp Planning - How do I find the initial contact point for each finger when grasping an object?

This is an excellent question that is currently being explored directly by field experts. Here are some of the latest publications that consider the problem you are encountering: Robotic Grasping of ...
3 votes
Accepted

Fast C++ library for stereo vision/disparity computation

I'll try to answer this question on my own, but feel free to add more information on that. We tried OpenCV's standard disparity function, but it fell short mainly because of item #4. Further, it is ...
  • 131
3 votes

Public dataset for monocular visual odometry

http://vision.in.tum.de/data/datasets/rgbd-dataset This is a set of recordings for the Kinect and Asus Xtion pro, which are all indoors (in offices and a hangar). It comes with precise ground truth ...
  • 176
3 votes

Public dataset for monocular visual odometry

This is another more recent one, based on the paper A Photometrically Calibrated Benchmark For Monocular Visual Odometry by Engel et al: http://vision.in.tum.de/data/datasets/mono-dataset This gives ...
3 votes
Accepted

Computer vision with single camera vs. distance sensors for obstacle detection

Honestly, I don't think you should use the cameras just because you have them. The ultrasonic sensor is a way simpler and more effective solution. There are ways to tell depth with one camera, but ...
3 votes

What main factors/features explain the high price of most industrial computer vision hardware?

So the Kinect uses a set of IR points to determine depth, not true stereoscopy. the DUO M and the Bumbee both use two cameras to achieve this, I am not familiar enough with them to give a good ...
  • 1,909

Only top scored, non community-wiki answers of a minimum length are eligible