Questions tagged [computer-vision]

The goal of computer vision is an automatic extraction of information out of images. It includes methods for acquiring, processing, analyzing, and understanding images and high-dimensional data from the real world in order to produce numerical or symbolic information, e.g., in the forms of decisions. The image data can take many forms, such as video sequences, views from multiple cameras, or multi-dimensional data from a medical scanner.

Filter by
Sorted by
Tagged with
1
vote
1answer
29 views

Depth camera pixel values to 3D coordinates

I have a robotic arm 6-DOF and an Intel RealSense depth camera. I want to go from pixel values to 3D world coordinates, is it possible with eye-in-hand calibration? If yes can you guide me on how to ...
0
votes
0answers
18 views

Semantic Segmentation vs Optical Flow Object Detection

Can anybody compare semantic segmentation against optical flow for pixel-level clustering and object detection?
0
votes
0answers
22 views

RGBD Camera Compatibility with ROS

I am looking for a good RGBD Camera that I want to use with ROS. Is there a way to know if a camera will work with ROS? Or is it that every camera is compatible with the usb_cam node? I want to send ...
0
votes
0answers
12 views

Understanding how the Kinect v1 works with Structured Light to compute disparity

I am reading this description here concerning calibration of the Kinect v1. I am trying to get an understanding of how it all works. From what I understand, the kinect has an near-infrared projector ...
0
votes
0answers
19 views

Unseen object segmentation problem

I have the following task: to select all the individual items in the RGB image into separate segments, and among these items there may be items that have not been used before. I have attached an ...
0
votes
3answers
90 views

ROS Webcam Stream Really Slow

I am trying to stream the images from my camera to a VM via ROS. Here is my setup: Raspberry Pi 3B+ with Picamera v2. It is running ROS Noetic with cv_camera_node ...
1
vote
1answer
30 views

Visual Odometry terminology: Scale, Relative scale, absolute scale

I'm watching a MOOC about Machine Vision for Robotics, but I really do not know the meaning of some vocabulary of this domain. For example, What does the professor mean when he says this: However, we ...
0
votes
0answers
27 views

Is Image Based Visual Servoing a non-linear controller?

Is Image Based Visual Servoing a non-linear controller? I think it is as the Image Jacobian has square terms of u & v (image-plane coords). Where $p_u, p_v$ are the width & height of each ...
1
vote
2answers
41 views

Is two cameras equivalent to Stereo camera setup?

I have two webcams, which are mounted close together. I plan to use them to find out the true depth of certain pixels of images. Suppose I use a standard multi camera calibration setup and find out ...
0
votes
0answers
87 views

ImportError: /opt/ros/kinetic/lib/python2.7/dist-packages/cv2.so: undefined symbol: PyCObject_Type

So I followed this guide to install opencv on Ubuntu 16.04 LTS https://www.pyimagesearch.com/2016/10/24/ubuntu-16-04-how-to-install-opencv/. When I try running a python script that imports cv2 I get ...
1
vote
0answers
20 views

Is there any RAPID instruction to save image as variable in YuMi integrated vision without using RobotStudio?

I want to perceive the images from the cameras embedded in YuMi IRB 14000 arms and store them as videos, in Ubuntu without using ABB RobotStudio. is there any way to do that? if yes how can I do that ...
1
vote
2answers
72 views

What are the purpose of pre-trained weights for YOLO object detector?

Dear Research Community, I am new to object detection research and currently working on a project which will detect people using YOLO from a top-down camera image. While looking through tutorials for ...
1
vote
1answer
156 views

Is easier to detect a large or a small marker? (Aruco / Apriltags)

I need to detect Aruco/Apriltags markers and perform pose estimation, but I've no particular constraint on their physical size. I'm not talking about the number of square (e.g. 4x4, 6x6, etc.), but of ...
0
votes
0answers
12 views

Lane Keeping Assistance Systems (LKAS) but with only one reference line

I am aware of the conventional Lane Keeping Assistance Systems (LKAS) approaches like sliding windows-based and CNN-based The end result of either of them is 2 lines of reference and the steering ...
0
votes
0answers
16 views

How can we estimate reliable angular motion from a monocular camera?

While I am working on a project, a question comes to my mind; how can we estimate reliable angular motion from a monocular camera, just for a typical indoor environment within a few seconds? So to ...
2
votes
0answers
21 views

Choosing cameras for stereo vision system?

I'm in the process of building a stereo vision system with YOLO detection. The system have to detect airplanes in far distance and also measure the depth from the airplane to the camera. I think ...
1
vote
2answers
29 views

How well does object detection transfer from simulation to reality? [closed]

I'm looking to learn more about this sim-to-real gap. I'm new to the concept and am trying to understand what to look for. Most notably i'm curious about how well an object detection algorithm trained ...
0
votes
2answers
66 views

Trajectory planning in unstructured environments

How is trajectory planning normally carried out in off-road/unstructured environments? In particular I'm interested in how stereo vision can be used to plot trajectories over obstacles - for example, ...
0
votes
0answers
26 views

How can I calibrate 3 cameras and track the object using only synchronized cameras feeds from all the cameras?

I have camera feed (in the form of RGB images) from 3 cameras with partially overlapping Field-of-view i.e. for the time stamp 0 to 100, I have total 300 frames or say synchronized 100 RGB frames for ...
1
vote
0answers
20 views

Size of smallest feature from pixel depth resolution

How do I get the size in mm of the smallest feature a depth camera can detect? Known variables are: distance from the target (for instance 1 meter), depth resolution in pixels (for instance 1280 x 720)...
0
votes
1answer
101 views

How can I calibrate 3 cameras without knowing global pose of the object & camera locations? How can I find the pose of each camera wrt the first one?

I have camera feed (in the form of RGB images) from 3 cameras with partially overlapping Field-of-view i.e. for the time stamp 0 to 100, I have total 300 frames or say synchronized 100 RGB frames for ...
1
vote
2answers
144 views

Triangulation: Ceres solver minimizes only the last residual block

I have been attempting to estimate a bunch of 3d coordinates viewed via a multi-view setup with known poses, I have the code running, but the output of ceres seems baffling. There are 7 image frames/...
0
votes
0answers
14 views

Drone based CV via base station - power requirments

Currently computer vision based inference is impractical on a drone given the significant power draw. Is connecting a drone to a base station which does CV a viable solution to this issue? Has it been ...
1
vote
1answer
71 views

How is the depth estimation done in DTAM / LSD-SLAM (direct VSLAM)?

I know that DTAM and LSD-SLAM both employ the photometric error between two keyframes to estimate the image depth. But I don't know what the photometric error describes precisely. In the DTAM paper, I ...
0
votes
0answers
70 views

ModuleNotFoundError: No module named 'second.core.non_max_suppression.nms'

I am using Anaconda base environment for second.pytorch of ubuntu 16.04 after executing the following: nvidia-docker run -it --rm -v /media/yy/960evo/datasets/:/root/data -v $HOME/pretrained_models:/...
0
votes
0answers
27 views

Are there some papers or books that compactly elaborate the essential part of the multiple view geometry?

I am a novice to visual SLAM and computer vision. Recently I've read a paper "A micro Lie theory for state estimation in robotics" dedicated to introducing the essential part that necessary to ...
0
votes
0answers
22 views

get position of objects using ir

I originally wanted to make a shoddy vr system with two IMU's in two seperate right and left controllers, which their values could be sent over wifi to the game service unity so I can plot their ...
0
votes
0answers
30 views

Serial communication of IMU and Encoder arduino code

Pls, I need people to help me look at where I am getting it wrong. I test this code on Arduino ide and got the result I wanted but sending it to Matlab through serial communication, I obtained a ...
0
votes
1answer
50 views

Computing Essential Matrix from Fundamental Matrix

I have calibrated my cameras using OpenCV. I used cv.stereoCalibrate to get the E, and F matrices. I wanted to do a sanity check to see if the E matrix obtained is ...
1
vote
1answer
41 views

Automatic License Plate Recognition System in Highway

We are working on a computer vision project where an automated robotic system will be deployed on a 3-lane highway. We are using a bosch IP camera (I don't remember the model exactly, but it cost ...
0
votes
0answers
18 views

Bundle Adjustment for Monocular SLAM

I am confused with how monocular BA works in visual-based SLAM. Is there any tutorials I can do in openCV to provide me some visualization aid? Thank You.
0
votes
0answers
77 views

How is a point triangulated with SVD with 2 correspondences?

According to these slides, if you have 2 correspondences for one 3D point, is is possible to build a system of linear equations (slide 27): AX = 0 And solve for <...
2
votes
1answer
40 views

Sensors to detect targets in low visibility environment

I want to know what type of sensor hardware I need to allow detection of moving targets (20mm - 200mm size range) in heavily murky water, where visibility range of typical camera can be limited to 0.5 ...
0
votes
2answers
103 views

Guidance on SBC for Visual-Based SLAM [closed]

Intro: I am a student that just started a project regarding prototyping a mobile robot that involve Indoor SLAM implementation. I am very new to the field of computer vision, SLAM and SBC (single ...
1
vote
0answers
37 views

How does inverse compositional Lucas–Kanade algorithm work?

I am trying to understand the Lucas–Kanade algorithm since I am reading a paper in which is applied the inverse compositional Lucas–Kanade algorithm, but in order to understand the latter I have to ...
1
vote
1answer
44 views

Dual constraint non-linear optimization for SLAM

I am trying to achieve a nonlinear optimization for SLAM on a function that contains two different constraints, like this : $$ T_{opt} = \underset{T}{\arg\min} \sum_i(\left\lVert T.X_i - x_i \right\...
0
votes
1answer
37 views

Good Software Projects for Aspiring Engineers [closed]

With the pandemic going on, our school has decided to officially shutdown all sponsored club meetings. Now that we are all digital, our robotics club was looking for projects that students can do at ...
1
vote
0answers
40 views

Intel Realsense Cameras for Object Avoidance and SLAM to go to destination

My goal is to make a UAV which can search an area while avoiding obstacles. I figured I would navigate using the SLAM and Intel Realsense D435i (a stereoscopic camera with an IMU built in), but all of ...
0
votes
0answers
29 views

Intel RealSense Depth Camera D435i Wide Imager questions?

I have just ordered my d435i and while it was not intended to do NDVI I read the data sheet and noticed it had seperate image sensors, it is possible to read the IR image from either left, right or ...
0
votes
0answers
19 views

Single Camera + Laser Projector Triangulation

I want to combine a laser line projector (projects a laser plane) and a single web camera to determine the X, Y, Z position of the laser point. I am slightly confused as to how to use the fact that we ...
0
votes
1answer
26 views

Tracking 3D motion using a stereo camera

Assuming you have a fixed stereo camera, looking at a rigid object, what are the techniques used to track the object? My google searches lead me to optical flow and similar algorithms, but I believe ...
1
vote
0answers
38 views

Interpreting results from Camera Calibration?

I used OpenCV's findChessboardCorners on a few checkerboard images (40~) and about 27 seemed to find the corners accurately. How does one proceed from here? Do I calculate the reprojection error over ...
3
votes
1answer
4k views

AprilTag vs Aruco markers [closed]

AprilTag and Aruco are both popular methods for vision-based fiducial marker pose estimation. What are the pros and cons of each fiducial marker pose estimation systems?
2
votes
2answers
119 views

How to handle landmarks in Bundle Adjustment?

At the moment I try to understand Bundle Adjustment on a level to be able to implement it on my own. The major point I'm still confused at is the management of the landmarks. So, let's think of a few ...
0
votes
1answer
39 views

Camera mounted on robotic arm - XYZ mapping

I have a 5 axis robotic arm that has a depth camera mounted near the toolhead on the left side. I have object detection software running on the camera and can find the XYZ of any object in mm that ...
2
votes
0answers
23 views

Disparity error in active light stereo systems?

Based on this relationship, if we have to estimate the 'disparity error' of a stereo system which uses active light on the scene - can we estimate the disparity error to be very small? According to ...
2
votes
1answer
29 views

Active Light Stereopsis: 1 Camera + Projector Vs. 2 Camera + Projector

What is the difference between using 1 Camera and a Projector and using 2 Cameras and a Projector for creating structure from motion? Is it that if we use only 1 camera and a projector then we will ...
2
votes
1answer
34 views

Facial Detection combined with Path Planning using Kinect Sensor

I am planning to use a Kinect Sensor on a mobile robot for path planning based on facial detection. Assuming I am able to detect the faces of 5 individuals in a room (both the environment and the ...
2
votes
1answer
120 views

Fusing Multiple Lidars Into 1 Point Cloud

I have a car with 8 lidars, each with a field of view of 60 degrees. My car looks like this How can I merge all the lidar readings into 1 point cloud?
4
votes
1answer
69 views

Performing Image alignment using pyramid levels with semi dense depth

To gain some confidence, I want to implement the camera tracking (optimization problem) discussed in Semi Dense Visual Odometry for a monocular cameraJ Engel, J Strum, D Cremers $$E(\xi) = \underset{i}...

1
2 3 4 5