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.
246
questions
0
votes
0
answers
9
views
How to scale projection matrix?
I was going through the camera calibration lecture by professor Shree Nayar.
At 4:49, he is :
Scaling the projection matrix implies simultaneously scalign the world and the camera, which does not ...
- 111
0
votes
0
answers
14
views
Bridging connection between HoloLens2 and a computer running on ROS2 Foxy
I wanted to consider using HoloLens2 for my project using ROS2. But before buying one, I was hoping to ask around if someone already tried using ROS2 FastDDS to make Hololens2 communicate with a ...
0
votes
0
answers
9
views
Selecting frames from video for surface extraction using feature matching
I have a video of an object sitting on an ArUco board. I am currently using ArUco markers to estimate camera transformation and knowing camera intrinsics assessing F.
I use BRISK and FLANN to match ...
- 101
0
votes
1
answer
57
views
Calibration of camera using ROS, without camera info
As part of a college project, I need to communicate with a TM5-700 robotic arm developed by Omron, and implement, for now, a pick and place pipeline. For that, I am required to access the camera ...
1
vote
3
answers
158
views
Installing Ros2 on the Jetson Xavier Nano
My team and I are trying to install Ros2 on the Jetson Xavier Nano so or robot can have computer vision, but the Jetson runs an old version of Ros. How can newer versions of ROS be used on the Jetson ...
- 11
0
votes
1
answer
31
views
Calculate target orientation
I have the following setup:
I want to move the "Drill" frame to "Target1" with the opposite Z axis direction. I have calculated translation between "Target1" and "...
0
votes
0
answers
42
views
How to get an axis in camera coordinate system pybullet?
I am using pybullet to render a robot simulation. This robot have 2 joints and hence, 2 corresponding axes of rotation. I know that when I use getJointInfo on this ...
- 101
0
votes
0
answers
43
views
Gazebo Garden : Green line in camera image with OGRE 1 render engine but not with OGRE 2
While loading the same map in gazebo garden with ogre 1 or ogre 2, the map looks the same in the GUI, but a green line appears in the camera image when using ogre1 (no distortion or noise applied, ...
- 1
1
vote
0
answers
46
views
World to pixel transformation in Pyrender
I'm trying to transform a point in a 3D world rendered with pyrender to pixel coordinates. The world to camera frame transformation seems to work, however the camera to pixel frame transformation is ...
- 11
1
vote
2
answers
60
views
Detecting door blockage using computer vision
I want to detect door blockage on a camera. Basically if the exit door is blocked by an object, it detects it as an anomaly. How can we do it? Is it possible to do it using OpenCV?
Remember, it doesn’...
- 111
1
vote
1
answer
66
views
Move gantry system to detected position in image plane
I have the following simplified gantry system (cartesian robot) that can move in the x axis direction:
My goal is to position the red pointer on top of the target (i.e., I want the real world x-...
0
votes
0
answers
42
views
Python How to fuse road segmentation data from an image to AOA data(distance, angle)
I have road segmentation data which is highlighted by the semi-transparent blue color.
It is an Numpy matrix with 0 means not road, 1 represents road.
I also have AOA data which tells the distance and ...
- 101
0
votes
0
answers
29
views
Making an automated chessboard
I want to create an automated chessboard. At the moment, I'm making the project and deciding what technology to use to detect which piece is at what position and how to move them. I'm not so skilled ...
- 1
0
votes
0
answers
32
views
Plane-plus-parallax equation
Given a stereo rig, the following equation establishes a relation between the image $\mathbf{m}$ of point $M$ in the left camera and the image $\mathbf{m}'$ of the the same point in the right camera. $...
- 101
0
votes
0
answers
25
views
Mono Slam scale tracking
How is the scale tracked in monoecular slam algorithms between image pairs?
It appears the 5point algorithm is used to initially compute the first two cameras poses but after that you want to maintain ...
- 337
3
votes
1
answer
60
views
How is the Homography formula derived?
In the Wikipedia article about Homography, the projective transformation between picture A to picture B is defined as:
$H_{ab} = R - \frac{t n^T}{d}$
However, the formula lacks the derivation. How is ...
0
votes
0
answers
57
views
Stereo Bundle Adjustment
When doing stereo based visual odometry and bundle adjustment how does the stereo constraint get factored into the photometric error?
Do you use the fact the second cameras location is known wrt the ...
- 337
0
votes
1
answer
64
views
Question about bundle adjustment
When doing bundle adjustment do landmarks gets optimized as stand alone variables or are they viewed as a function of the robots first position when they are detected?
- 337
0
votes
1
answer
125
views
Why would you use direct SLAM over feature-based?
I am curious, why would you ever choose direct slam(photometric consistency, etc) over feature based slam? Particularly for dynamic scenes?
It seems you're always better off aligning fewer points ...
- 337
0
votes
1
answer
35
views
Stabilising 3d cameras for mapping outdoors - mechanical or programmatic
I am preparing to mount Intel Realsense and Zed and Oak-d cameras onto a 4 wheel mobility scooter to do mapping of my local area.
I'm not looking for recommendations but rather an understanding of ...
- 130
0
votes
0
answers
225
views
IMU to Camera transformation
Suppose you are implementing SLAM or VIO system, you have your camera C and IMU and a coordinate transformation between them (R, T).
How do convert IMU measurements to camera accelerations and ...
- 337
1
vote
1
answer
92
views
Calculating the depth in a general stereo vision system
When calculating the depth of a pixel using two cameras, most of the literature I have read describes stereo vision with the cameras having parallel optical axis as shown in the picture below. Because ...
- 113
2
votes
1
answer
205
views
Pipeline for dense reconstruction using pose estimation from orb-slam and stereo camera
I am trying to perform dense reconstruction using a sequence of images from a calibrated stereo camera. I have been using orb-slam3 to give me the camera's pose estimation. I am also generating the ...
- 23
0
votes
1
answer
203
views
How to perform time-offset calibration use GTSAM in Camera-IMU system?
Assume we have camera poses data and IMU data(which include gyr and acc data) with different timestamps, now I want to estimate this value, I known that this can be done in many ways(EKF,MSCKF), but I ...
- 1
0
votes
1
answer
68
views
Camera Calibration Matrix accuracy
When we do camera calibration, we have to find calibration matrix $M$, which is found by first finding extrinsic matrix and then intrinsic matrix. To validate the accuracy of calibration matrix, we ...
- 105
0
votes
1
answer
85
views
6D pose estimation of a known 3D CAD object [closed]
I'm looking for a codebase for 6DOF pose estimation of a known 3D CAD object with RGB or RGBD. It must be:
-Usable commercially (licensed under BSD, MIT, BOOST, etc.), not GPL.
-Easy to setup and use (...
- 248
0
votes
1
answer
74
views
2
votes
0
answers
58
views
Monocular SLAM position estimation
I have been reading about mono SLAM and I have a couple questions which are not so clear:
When doing pose estimation, I have seen people both reference homography transformation and also reference 5\...
- 337
0
votes
0
answers
38
views
How to find fundamental matrix based on other fundamental matrix and camera movement?
I am trying to speed up some multi-camera system that relies on calculation of fundamental matrices between each camera pair.
Please notice the following is pseudocode. ...
- 101
0
votes
1
answer
74
views
Center line steering with differential drive
I’ve got 2 motors that drives my unit and I can easily steer it manually by simply adding more speed to one wheel vs the other.
Now I’m automating the rover using image processing to follow a driveway....
- 23
0
votes
1
answer
68
views
How does baseline work with forward motion in Monocular Visual Odometry
In my computer vision class we are studying visual odometry. In this we calculate the Fundamental matrix using 2 frames from forward motion using the concept of stereo-vision. But in stereo vision the ...
- 1
1
vote
2
answers
575
views
roslaunch exit code 2 error
I am implementing a simple roslaunch file but I am getting an exit code 2 status I have pasted the exact log below any idea what would cause this and how I can rectify it.
...
- 21
0
votes
1
answer
119
views
Mobile robotic arm camera position
I'm working on my graduation project which is a mobile robotic arm that performs pick and place tasks.
I wanted to know the possible ways to mount the camera where i can reach the desired destination ...
- 1
0
votes
1
answer
28
views
Explanation of the epipolar constraint in stereo imaging
I am watching this video, in which the epipolar constraint is defined as
$x_l \cdot (x_l \times t)=0$
It means that the vector $x_l$ that passes through the observed point and the left camera origin ...
- 101
0
votes
1
answer
23
views
What are the usual results for pedestrian posture detection?
When talking about lane detection in a road, usually robotic computer vision system give lines in an image.
For detecting obstacles, those system give Bounding Boxes.
My question is, for pedestrian (...
- 103
3
votes
1
answer
233
views
Unstable principal point estimation in zoom camera calibration
I have a camera with a 1/2.9" image sensor from FLIR and a 12-50mm motorized zoom lens from Theia. Because the lens is a motorized zoom lens, I tried to calibrate the camera for different zoom ...
- 31
0
votes
2
answers
749
views
Number of pixels required to identify something
When using an RGB camera, what is the minimum number of pixels of an object that you need to identify something (theoretical or rule of thumb)?
The image would be taken out in the wild with a complex ...
1
vote
1
answer
42
views
Can you plug a CMOS camera (like the iPhone 8 back camera) into an mPCIe in a laptop?
I read that 12 megapixel iPhone cameras don’t record video in 12 megapixels because the processors are not able to keep up. It seems though, that if I could plug the CMOS sensor to the CPU of a laptop,...
- 113
1
vote
0
answers
150
views
Cheap global shutter cameras with external synchronization
Please recommend cameras for multi-camera setup satisfying the following conditions:
Relatively cheap (up to 100$ per camera).
Global shutter.
No filters on lenses or pixels.
Resolution of 1 MP or ...
- 111
1
vote
1
answer
48
views
Autonomous harvesting robots. What are model possible components and interactions for the entire system? [closed]
I found a video which talk about best autonomous robots that use IA technology to harvest crops. The video is very interesting because, the “ecosystem” of each robot varies a lot from company to ...
- 11
2
votes
1
answer
203
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
3
answers
926
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
...
2
votes
1
answer
614
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 ...
- 189
1
vote
2
answers
465
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 ...
- 113
1
vote
0
answers
67
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 ...
- 142
1
vote
2
answers
3k
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
1
answer
1k
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 ...
- 248
2
votes
0
answers
49
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
2
answers
86
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 ...
- 31
0
votes
2
answers
85
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, ...
- 337