17
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 generated data to be processed is enormous. You have to transfer and process data faster which comes out again as rising cost. Finally cameras usually have a ...
16
Features like the sun and clouds and other things that are very far off would have a distance estimate of inf. This can cause a lot of problems. To get around it, the inverse of the distance is estimated. All of the infs become zeros which tend to cause fewer problems.
11
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 that, filtering approaches such as the extended Kalman filter (EKF) make an assumption that the error associated with features is Gaussian.
In a visual ...
7
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 depth based on camera-like projective sensors (eyes). Many make use of binocular disparity -- the fact that the distance between the same scene point in two ...
7
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
Newer versions of aruco is GPL licensed, hence opencv is stuck on an old implementation of aruco when it was still BSD.
More susceptible to rotational ambiguity at ...
6
As a neuroscientist/engineer who teaches vision in a physiology course for engineers, but who hasn't read any of the FREAK docs, I'd point people to the works of David Marr, or maybe Kuffler. I found a nice review at Introduction to visual computation and
the primate visual system - 11MB PDF.
Retinal receptive fields (or more properly, ganglion cell ...
6
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 ship the device "calibrated" then no one knows what happened after the camera was calibrated in factory and before you got it (mechanical shock, temperature swings)...
6
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 between your map and the world is not even constant over time so that if you come back to your starting point, it's going to be difficult to match the beginning and ...
6
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 decomposition and it's quite good if you don't go too far (2 or 3 meters for a 20cm marker). There is the C implementation made by the authors at University of ...
6
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 available from PyPy, with classes and functions. This is a Python port of my Robotics/Spatial Math Toolbox for MATLAB
Sophus C++/Eigen with Python wrappers
5
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-depth-perception-with-raspberry-pi/
Even then, you will have to write optimized GPU Code in assembler to get anything near acceptable performance if you try to do ...
5
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 available from the library website.
Depends, especially on how you are going to combine scans into a full 3D pointclound (if you need 360 degree views.) ...
5
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 over the last decade is how you deal with shadows, light changes, and foliage moving.
There are tons of resources on this topic, but here is a good one I ...
5
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 algorithm to solve this problem:
Raspberry Pi Ball tracking
Using OpenCV on the Beagleboard to track an Aibo pink ball
OpenCV Tutorial C++ - Color Detection & ...
5
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 density $p(x, y)$ over two variables $x$ and $y$, and we would like to marginalize out or "eliminate a variable", lets say $y$ in this case:
\begin{...
5
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 cases it would be more suitable to choose a lidar instead of a camera and vice-versa.
A LIDAR doesn't require light to perceive the environment whereas a camera ...
5
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.
Neural networks were originally designed based on what was known of neurons at the time, for example the activation functions are loosely based on how signals in ...
5
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
Interesting question! Thanks for introducing me to FREAK!
The paper just says that overlapping fields "increases redundancy", my interpretation is that like most detectors, FREAK is essentially scrolling a detection window over the image. If you arbitrarily break the image into non-overlapping windows then there's a good chance you'll break a useful image ...
4
These are two different things which share a lot in common.
Simply spoken the CV's task is to perform automatic image processing and then display it to humans.
The MV has to do similar things but you do not get an image as result, you get data.
For example: "There are 6 apples in this image" or "The image shows that the product has a malfunction"
Sources:
...
4
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.2008.2003276
4
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 cameras. I've bought it and its price is reasonable. At that time, the price was roughly 272 CAD. Of course, the price is now more expensive than before but I ...
4
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, a single bundle adjustment (BA) iteration is performed in a manner similar to what I initially described in the question.
The reason the marginal / schur ...
4
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 independently positition many unique barcode-like fiducial markers, sometimes called fiducial targets, frame markers, augmented reality marker, etc.,
such as ...
4
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 low->high range goes from $0.5^\circ$ -> $0.025^\circ$)
Lower power usage
Passive sensor (doesn't require 'clean' signal of a laser)
4
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 towards hardware.
Cost differences between using an embedded GPU vs. the cloud?
Depends on your volume. The cloud is not necessarily cheaper than hardware in ...
4
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 attempt to explain why it is used.
Lets first setup how the optimization problem looks for your two different possibilities with just 2 cameras. So we are only ...
4
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 Novel Objects using Vision
Direct Perception and Action Decision for Unknown Object Grasping
Realtime plane detection for projection Augmented Reality in an ...
3
"All I need to do".... Famous last words. This is a very complicated project to attempt for multiple reasons. I'll try to break down these challenges. For documentation, the datasheet has all the information that you need, but there is probably not any code available that is ready to use. Sparkfun has recently introduced a 'degree of difficulty' rating for ...
3
Wow, walls, mazes, casting rays. Does anyone have Wolfenstein/Doom deja vu?
Back in the day, these games had to solve similar problems, calculating the intersection between lines (of fire or movement) and the walls of the map. For Wolfenstein, it was fairly easy because the map was arranged in a grid, and they used Ray Casting.
For Doom, it was a little ...
Only top voted, non community-wiki answers of a minimum length are eligible