Hot answers tagged

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 ...
valleymanbs's user avatar
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 (...
HighVoltage's user avatar
  • 1,096
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 ...
koverman47's user avatar
4 votes
Accepted

Visual-Positioning Method

So it sounds like you have an external camera system to track the end effector position and orientation? In that case I would use QR codes or april tags. Stick a couple of these on your end effector, ...
edwinem's user avatar
  • 1,831
4 votes
Accepted

Does a stable library exist for docking robots using images?

There's a lot of solutions out there already for this. I'll start by suggesting AR tags not QR tags. They're better optimized for localizing. The Alvar library is commonly used for tracking AR tags. ...
Tully's user avatar
  • 24.7k
3 votes

what's confidence level? and how can we use it for vehicle detection using OpenCV?

Statistical confidence is most often defined in terms of a score that is the number of standard deviations away from the mean. Now let's say you have a set of states (a state vector) used to define ...
Brian Lynch's user avatar
  • 1,377
3 votes
Accepted

Algorithm for centering an object that is changing speed

It seems that your algorithm that controls the speed of your telescope does not make use of any integral part, thus you've been observing drifts while tracking. Let $e_x$ be the error in the image ...
Ugo Pattacini's user avatar
3 votes

Stereo Camera calibration with different camera types

It looks like what I saw when a colleague of mine was working with fisheye lenses; I found this post after doing an image search for "rectify fisheye image" and following the link from this picture. ...
Chuck's user avatar
  • 16k
3 votes
Accepted

Real-time object classification for an indoor autonomous quad-rotor

tl;dr - SLAM is good enough for your task. The ceiling is the area where your robot will be traveling in. Few things to notice - Ceiling is fixed and not changing. Things on the ceiling are fixed as ...
Tvaṣṭā's user avatar
3 votes

Detecting door blockage using computer vision

In your example image, you show what appears to be a fixed camera feed (for example, a security camera). If it is safe to assume that this is a fixed camera feed, this becomes much easier, since we ...
cst0's user avatar
  • 776
2 votes
Accepted

Stereo Vision Using Compute Module: Pi camera synchronization

You need real camera synchronization which means using cameras that both have external trigger capability (it is like the "remote shutter" on consumer/DSLRs). What you do is feed a common trigger ...
Kozuch's user avatar
  • 633
2 votes

How to check lane departure in OpenCV?

One of the best ways is to use a combination of hough-transform (what you have achieved is nice) and inverse perspective transform (as in http://www.vision.caltech.edu/malaa/publications/aly08realtime....
Prasad Raghavendra's user avatar
2 votes

Image registration with ground plane for surround view

I don't know what the proper way to do this is but I can give you ideas to make it better: define an exact transformation for each camera. You could calibrate each camera using a grid pattern and by ...
Malcolm's user avatar
  • 571
2 votes

Converting Image Coordinates to (x, y) Position for Robotic Arm

A quite simple math is involved in this task, but you need to be aware of the pinhole camera model as well as of the homographic projection. The pinhole camera model gives you the 3D position $(x,y,z)...
Ugo Pattacini's user avatar
2 votes
Accepted

OpenCV get topdown view of planar pattern by using intrinsic and extrinsic from cameraCalibrate

Added OK, guys, simple mistake. I previously used warpPerspective to warp images instead of restoring. Since it works that way, I didn't read the doc thoroughly. It turns out that if it is for ...
ricecakebear's user avatar
2 votes

Trigger two usb cameras at the same time

As you say, you can't trigger them at the exact same time without hardware capable of doing so. Some IMU's supply an external trigger pin, and I see no reason why you couldn't buy cameras that have a ...
sdfgeoff's user avatar
  • 151
2 votes

Trouble aligning/calibrating camera with laser scanner

Within ros there is a lidar_camera_calibration package that should take care of this for you! Their github page has a detailed readme. If you aren't using ros, you can probably take a look at the core ...
Akhil Kurup's user avatar
2 votes

Reflective surface

Reducing reflection on an image is hard, really hard, because you only have the pixels, and they are most likely white. So changing the environment to get good images is the desired solution. Robotiq ...
user_cr's user avatar
  • 21
2 votes
Accepted

Making sense of disparity values after applying `StereoSGBM` from OpenCV

Looking into the documentation of StereoSGBM I found the following explaination link. It says: Some algorithms, like StereoBM or StereoSGBM compute 16-bit fixed ...
vyi's user avatar
  • 205
2 votes

Detecting door blockage using computer vision

You could create a categorical deep learning model by taking images of the door blocked and unblocked. Basically a Hotdog, Not Hotdog model. https://www.datacamp.com/blog/classification-machine-...
Ezward's user avatar
  • 356
2 votes

How to use arbitrary version of OpenCV

In case someone comes up here looking for how to use the source installed OpenCV installation with Python, look for following. When you build the OpenCV installation, make sure to add following ...
Tejal's user avatar
  • 21
2 votes
Accepted

colorize area of point cloud on a 2D image

I managed to achieve better results with cv::dilate. As far as I tested, I haven't lost any perfomance and it is really easy to implement.
renan's user avatar
  • 53
1 vote

Make robot drive as far from obstacles as possible

Some hints: Use Minskowski sums to "grow" the obstacles taking into account the shape/orientation of the robot. Not easy to understand and implement, BUT already implemented in geometrical algorithm ...
nionios's user avatar
  • 311
1 vote

Algorithm for centering an object that is changing speed

The description of the problem fits great to a technique which is called model predictive control. It can solve the problem of tracking an object with a telescope on a mathematical satisfying way. The ...
Manuel Rodriguez's user avatar
1 vote

Algorithm for centering an object that is changing speed

Thanks for the replies. I figured out to make it work. I divided the image into different regions using horizontal lines. Then, I have a timer in C# that every x milliseconds figures out which region ...
mcshaf01's user avatar
1 vote

Image data fusion

What do you mean by data fusion Here's some definitions I can think of: Determine from the features in the scene the positions of the camera Determine from the positions of the camera the geometry ...
Josh Vander Hook's user avatar
1 vote

Fixing robot orientation using AR

I recommend using april tags. They are similar to qr codes but were specifically designed with robotics in mind. There is a library on the april tag website. The library can be used to solve for the ...
holmeski's user avatar
  • 1,853
1 vote
Accepted

How to tringulate many projections of a point to optimal postion?

I will assume, similar to OpenCV, that each camera is a pinhole camera, so you already corrected for things like lens distortion. In this case each visible point in 3D space $(x,y,z)$ gets projected ...
fibonatic's user avatar
  • 941
1 vote

Pictures coordinates to robot coordinates

First note that for px =250 (picture x) you get two different table values tx=0 and tx=2098, then for a difference of 1 unit in px you get a difference of around 2000 in tx (table x). From that it ...
N. Staub's user avatar
  • 1,402
1 vote

Scan an Auditorium, Count People, and Display Open Seats

A Near-IR or IR camera which can rotate and tilt, that is installed over the stage would probably be an acceptable and fairly well performing solution. Installation would be simple: screw on, and ...
Gürkan Çetin's user avatar

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