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
2
votes
1answer
465 views

How does one calculate distance and angle using a target with known measurements?

The target is in the shape of a U where the horizontal segment is 20 inches, and the two vertical segments are 14 inches. We are using a camera to image the target, and then using vision processing to ...
1
vote
0answers
24 views

Is the distortion introduced by a lens protector significant in practice?

I have a computer-vision application I made to localize a robot in a room; the software has been in use for a while and is working fine. When I calibrated the camera and got the intrinsics and lens ...
3
votes
1answer
122 views

How to estimate the position of multiple static ground targets captured from a down facing camera?

An aerial vehicle captures images of the ground using its down facing camera. From the images, multiple targets are converted from their pixel position to the camera reference frame using the pinhole ...
6
votes
2answers
4k views

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

Consider the system $$ \tag 1 H\delta x=-g $$ where $H$ and $g$ are the Hessian and gradient of some cost function $f$ of the form $f(x)=e(x)^Te(x)$. The function $e(x)=z-\hat{z}(x)$ is an error ...
2
votes
2answers
4k views

Using an RGB + Depth Camera to locate X,Y,Z coordinates of a ball

I've recently been trying to use Gazebo to do some modelling for a couple tasks. I have a robot that's effectively able to locate a ball and get x,y coordinates in terms of pixels using a simple RGB ...
3
votes
3answers
2k views

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

I am working on a project where I want to run some computer vision algorithms (e.g. face recognition) on the live video stream coming from a flying drone. There are many commercial drones out there ...
2
votes
0answers
81 views

choice for camera sensor to be used with LiDAR [closed]

I am doing research on autonomous car and looking for a sensor to be used along with LiDAR laser scanner. Ladybug could be a very good option but the cost!! too expensive. Could you please suggest me ...
3
votes
1answer
334 views

image processing

I am making a Robot goalie, the robot is supposed to detect whether a ball has been thrown in its direction , sense the direction of the ball and then stop it from entering the goal post. A webcam ...
2
votes
1answer
67 views

“Ambiguous up to scale” , Explanation required

I am reading "Computer Vision: Models, Learning, and Inference" in which author writes at several points (like on page 428-429) that although matrix A seems to have 'n' degree of freedom but since it ...
5
votes
1answer
6k views

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

I'm a software developer not experienced in AI or machine learning, but I'm now interested in developing this kind of software. I want to develop software that recognizes some specific objects, ...
4
votes
1answer
1k views

Is it possible to simulate vision (perception) in Gazebo (or other simulators)

Vision is important part of robotics and frequently it is unavoidable component of control loop. E.g. many clothes/garment handling algorithms rely on visual cues in deciding how to proceed. The ...
0
votes
4answers
864 views

What is the cheapest way to detect and identify vehicles entering a gate in real time?

I want to detect and identify each of the vehicles passing through a gate. I have the live video feed of the gate which I initially thought to process and detect the number plates with the help of ...
3
votes
1answer
94 views

3D scanner from Phone Camera

123D software can construct a 3D model from photos taken from your phone. It doesn't process the photos in your phone. Instead, it sends them to the cloud to create 3d model. How can i construct a 3d ...
3
votes
1answer
668 views

Suggestion for a camera [closed]

Are there good low cost cameras that are frequently used in robotics? I am assuming there are cameras that are good fit for robotics ... Works well with OpenCV PC Windows support - USB2/USB3 (GigE, ...
8
votes
2answers
104 views

Conceptual problem regarding electronic shutters

I have been looking at CCD and CMOS sensors and cameras to decide which one to use in the process of automatic control of a printing process. By now I am getting the grips on almost all the essential ...
4
votes
2answers
4k views

Fast C++ library for stereo vision/disparity computation [closed]

I am looking for a library for disparity map / stereo vision computation. These are my requirements: C++ Multi-platform (Linux, Windows, OSX) (preferrable but not mandatory) not CUDA based Suited for ...
7
votes
2answers
7k views

Questions regarding 3D scanning and camera choice [closed]

A few days ago, I just shared my concerns about the price of computer vision hardware on this same exact forum (see What main factors/features explain the high price of most industrial computer vision ...
1
vote
0answers
55 views

Depth of view for a hypercatadioptric camera

I am trying to determine the depth of view for a hypercatadioptric camera (camera lens system and a hyperbolic mirror) based on 1. The following illustration seems pretty clear. For an image point $...
8
votes
3answers
3k views

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

I am a student who is currently working on a computer science project that will require soon computer vision and more specifically stereoscopy (for close depth detection). I am now looking for a great ...
0
votes
2answers
109 views

Dynamically detect changing obstacles

So the idea is that there would be one robot acting as overwatch, which would detect all of the obstacles in an area (which are not necessarily static), and then send the data about the obstacles' ...
5
votes
1answer
4k views

Monocular vs. stereo computer vision robustness for object detection

Are there some genaral rules for the robustness between monocular and stereo vision when considering object detection? I am especially interested in the automotive field - considering distance/...
6
votes
4answers
383 views

How many methods can I use to acquire depth data?

I am a newbie in Robotics. As far as I know, there're generally two ways to acquire depth information of a scene. One is the stereo vision method which applies two cameras. The other is the RGBD ...
3
votes
1answer
516 views

Robot Navigation Feedback using Image Processing

In my project, I've successfully analyzed the arena and have detected the obstacles using an overhead webcam. I also have computed the shortest path. The path data is transmitted to the robot via ...
1
vote
4answers
4k views

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

I am going to start a new project consisting in implementing an autonomous driving RC car. The car as it is now, has a camera installed on each side of the car, i.e. 4 cameras in total. They are ...
6
votes
6answers
3k views

Low power computer for stereo vision

I would like to build a motorized robot with stereo vision that sends visual input to a PC over wifi for processing. A Raspberry Pi would have been perfect for the task if it would be possible to ...
16
votes
4answers
9k views

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

Reading some papers about visual odometry, many use inverse depth. Is it only the mathematical inverse of the depth (meaning 1/d) or does it represent something else. And what are the advantages of ...
4
votes
1answer
298 views

Pose estimation, how to populate set of known edges and points?

I am building an estimator that solves for the camera pose relative to a reference frame which contains a known set of features and edges. Currently, the system works with an unscented kalman filter ...
3
votes
4answers
2k views

Public dataset for monocular visual odometry

I am planning to develop a monocular visual odometry system. Is there any indoor dataset available to the public, along with the ground truth, on which I can test my approach? Note: I am already ...
1
vote
1answer
68 views

Compound vision system or Megapixel camera reduction

Are any commercially available compound vision sensors available? Not a simple 8 sensor system using photo-diodes but a genuine sensor that can provide a >32x32 compound matrix. Would some form of ...
2
votes
2answers
351 views

Robotic cell simulation software, PLC [closed]

I need to simulate robotic cell where cartesian robot trims a PCB arriving on conveyor, picks it up with vacuum cup and and places in another device. After receiving signal from device the robot would ...
2
votes
2answers
703 views

Find Centre Of Circle, when robot can “see” a partial arc

I originally asked this here but I am struggling to take the concepts, particularly "Circumcenter", discussed there and apply it in my context. So here it is in my context... I have a small robot ...
-3
votes
1answer
170 views

I am new in robotics…I want to know about SLAM algorithm…How should I proceed? [closed]

Please give me guidance how should I proceed to know about SLAM algorithm? I am following some youtube videos but those are not so much helpful for me.....
1
vote
3answers
506 views

Real time operating system for robotics vision

I have robot vision system which consists of conveyor with encoder, two cameras (gigabit eth and usb) and simple illuminator. I need to trigger cameras and illuminator when encoder reaches position ...
1
vote
0answers
198 views

How to change the orientation of an object w.r.t a scene?

I am trying to localize an object in a point cloud using ROS, PCL. For that I capture the scene and model using Asus xtion pro sensor. I use RGBDSLAMv2 for capturing the model. Then I use ICP (...
2
votes
2answers
76 views

Image processing in bright lights

We are working on a project which requires us to detect and hit a ball. We are trying to accomplish the task by detecting the position of ball by processing the input from a camera. The problem is ...
1
vote
1answer
689 views

tracking robot in a room

I'm trying to track a simple robot (e.g. arduino, raspberry pi, even toys) in a room using fixed location kinect sensor(s) and cameras at different parts of the room. How might one usually use to do ...
2
votes
2answers
90 views

Detect road surface in a traffic scene point cloud

I want to analyze a traffic scene. My source data is a point cloud like this one (see images at the bottom of that post). I want to be able to detect objects that are on the road (cars, cyclists etc.)....
1
vote
1answer
316 views

kinect - development kit to aid obstacle-avoiding robot?

Some friends and I are interested in working on a robot. I know little to nothing about robotics, but do have a lot of experience with programming. Before we start, I am hoping that I can find some ...
2
votes
0answers
593 views

Correcting GPS track with visual odometry (sensor fusion)

I am trying to build low cost and precise outdoor positioning. I explored NS-RAW with RTKLIB - this would be doable but probably will need either a base station to get the correction data for rover or ...
2
votes
2answers
564 views

image size vs image resolution

I read somewhere that in the case of photoshop for example, the size refers to the number of pixels an image contains, but resolution involves the pixel's size, I don't know whether this definition ...
6
votes
2answers
182 views

computer vision using the FREAK local features descriptor - why overlapping fields?

I am currently studying the FREAK descriptor and I read the article published by its designers. It states that the aim was to mimic the retinal topology, and one of the advantages that could be gained ...
2
votes
1answer
1k views

Machine Vision vs Computer Vision?

I'm trying to understand the core differences between the two topics. Is one simply a newer term? Connotations of automobile vs automation? Something with a screen vs without? I've only ever heard ...
0
votes
2answers
638 views

how to plot a line between two centroids in matlab

I am able to locate centroids of each blocks, but i am unable to join two blocks with a line segment by avoiding the obstacle as shown in the figure. Please need help how do i achieve this using ...
1
vote
1answer
386 views

Are stereo camera calibration data standardized?

Is there a standard format of how stereo calibration data (various matrices, usually saved in XML) are stored? Can I load calibration data generated say from a OpenCV script in C to another OpenCV ...
3
votes
1answer
180 views

Stereo camera baseline not needed for calibration?

I am doing stereo camera calibration as described in this blog post. I wonder I do not need to input camera baseline for the calibration. The fact probably goes back to some very basic mathematics of ...
1
vote
1answer
182 views

Tried Normal Distributions Transform with my own files (in correct PCD format) and it throws errors, why?

http://pointclouds.org/documentation/tutorials/normal_distributions_transform.php#normal-distributions-transform I've used this program with the sample PCD's given and it came out correctly. This was ...
3
votes
2answers
947 views

Connect sensors to beaglebone/arduino in a complex robot

I'm building the biggest robot I've ever done. The hardware I have so far is as follows: HCR-Platform from DFRobot as a base x2 12V 146Rpm DC motor with two phase hall encoder x7 Sharp 2Y0A21 IR ...
6
votes
1answer
590 views

Role of Neuromorphic Computing and Quantum Computing in the field of Robotics and AI

I asked a similar kind of question some time ago (Neuromorphic Engineering and Robotics) Since then, many things have come to the point of revelation. A road-map for neuromorphic computing was ...
0
votes
1answer
100 views

How do I get started in Computer Vision? [closed]

I want to know how to write and run the correct code. I understand that I need to download OpenCV (which I have), but when I try to compile sample code - for example, Blob Detection - it doesn't ...
3
votes
0answers
807 views

Alternatives to Primesense depth cameras? [closed]

I'm looking for low-cost depth cameras (less than 1000 USD) with a range of more than 3 meters. Currently, I have found only SoftKinetic DS-311 that meets these requirements. Here are some other ...