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
18
votes
4answers
12k views

How to select cameras for a stereo vision system?

I am in the process of building a stereo vision system to be used on a UGV. The system is for a robot that will be used in a competition wherein the robot is teleoperated to find relatively small ...
17
votes
4answers
8k views

Single camera vision and mapping system

Some time ago I saw a demo of a small 'toy tank' with a single camera mounted on it. This tank was able to drive around the floor and detect objects and then move/steer to avoid them. The interesting ...
13
votes
4answers
7k 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 ...
11
votes
7answers
6k views

Why people use camera instead of laser sensor for robot navigation?

I am working on Robot localization and navigation in urban environments. I want to use Camera. But I am a little bit confused about LRF data or other laser data. Why people want to use camera? why ...
11
votes
4answers
4k views

How to obtain dense point clouds from stereo cameras?

I am trying to use a stereo camera for scene reconstruction, but I can usually only obtain sparse point clouds (i.e. over half the image does not have any proper depth information). I realize that ...
11
votes
1answer
365 views

What is the best way to compute the probabilistic belief of a robot equipped with a vision sensor?

I am trying to implement 'belief space' planning for a robot that has a camera as its main sensor. Similar to SLAM, the robot has a map of 3D points, and it localizes by performing 2D-3D matching with ...
8
votes
2answers
174 views

Floor Segmentation to Determine Navigable Paths

In my application, my robot has the following physical setup: Differential drive mechanics with feedback (wheel encoders) Commercially available webcam mounted with a known transform to the base of ...
8
votes
2answers
93 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 ...
8
votes
1answer
148 views

Public training data for vehicle detectors in computer vision?

This question is to anyone familiar with object (specifically vehicle) detection research. I'm new to computer vision and am confused about training object detection classifiers. Specifically, the ...
6
votes
2answers
174 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 ...
6
votes
3answers
222 views

How can computer vision distinguish one object being contained by another vs being on top of it?

How do we know that an object is contained inside another object or is just lying on top of it? Lets take an example of a cup-plate-spoon. The cup is lying on top of the plate. But the spoon is ...
6
votes
6answers
2k 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 ...
6
votes
3answers
969 views

Visual Odometry options? [closed]

What are the pros/cons of the different visual odometry options? Stereo Camera Optical Flow SLAM other? Criteria: how well it performs vs other odometry options/sensors (lidar, radar) sensor ...
6
votes
2answers
6k 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 ...
6
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 ...
6
votes
1answer
6k views

Are there any advantages to using a LIDAR for SLAM vs a standard RGB camera?

I've been thinking about building a small UAV with an onboard LIDAR, just for fun. I'm interested in SLAM and autonomous flight indoors and thought that I would need a lidar to get a 3D map of the ...
6
votes
1answer
490 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 ...
5
votes
3answers
193 views

F/OSS Optical Object Avoidance

I am beginning work on a larger scale, 250-350 lbs wheeled robot and looking to use both optical and other means of object avoidance. I am concerned with a robot this large causing issues with running ...
5
votes
1answer
85 views

Is it possible to achieve arbitrary precision in camera calibration?

Is it possible to achieve arbitrary precision to the calibration of the extrinsic parameters of a camera or is there a minimum error wich can not be compensated (probably dictated by the camera's ...
5
votes
4answers
340 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 ...
5
votes
1answer
2k views

SLAM: Why use two cameras (stereo) if SLAM can be done using single camera (monocular)?

I am aware that algorithm for monocular SLAM is complex compared to stereo SLAM. But my question is if by any means it is possible to do SLAM using one camera why one should use two cameras to do the ...
5
votes
1answer
170 views

classify if two adjacent surfaces belong to same object

I have a box (cuboid) lying on floor or table. So there are 6 surfaces of the box and 1 surface of the floor. If I take each pair of surface such that the surfaces are "adjacent" to each other, I get ...
5
votes
1answer
3k 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/...
5
votes
2answers
167 views

How to Identify Objects in Space

Using a depth sensing camera like Kinect, I would like to retrieve the position of an predetermined object (e.g. a cup, fork etc so that I would ultimately be able to grab the object). What would be a ...
5
votes
1answer
112 views

Can you find object distance using camera pose

I have bounding boxes detected in RGB images, but no information about the camera's intrinsic properties. Using deep learning (preferably) can I find the distance to the object from the camera in real ...
5
votes
2answers
740 views

Transforming Point Cloud to get Top Down Image [closed]

My task: I have a task where I am asked to track parcels(carton boxes) of different dimensions moving on a conveyor. I am using Asus Xtion pro camera mounted on top of a conveyor in any inclined ...
4
votes
3answers
445 views

What is the best SE3 library for python?

I am currently googling on this topic but I would like to hear your opinion. What is the best self-contained SE3 library that offers interconversion between quaternion, rotation vector, ...
4
votes
2answers
6k views

How can I improve ZED Camera precision? [closed]

I'm using Stereolabs ZED camera for my computer vision project. I did a small research about several sensors on the market and ultimately we decided to go with the ZED Camera. However I'm finding ...
4
votes
2answers
5k views

Difference between 3D Camera(using IR projection) and Stereo Camera?

I am currently busy with a final year project which requires me to track people walking through a doorway. I initially thought this may be possible using a normal camera and using some motion ...
4
votes
1answer
5k 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

Which is the best visual fiducial marker (2D barcode)?

Which is the best visual fiducial marker (2D barcode) for detection and robust and accurate pose estimation? Im not looking for a fiducial marker which can store lot of information. The main goal is ...
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 ...
4
votes
1answer
662 views

How to check lane departure in OpenCV?

I'm using OpenCV 3 in Python 2.7 on a Raspberry Pi 3. My project's aim is to build an autonomous lane departing robot that can detect the two lanes on its sides and continuously correct itself to ...
4
votes
1answer
4k views

Transform Image Using Roll-Pitch-Yaw Angles (image rectification)

UPDATE: This exact problem has been solved in StackOverflow. Please read this post there for further explanation and a working solution. Thanks! I am working on an application where I need to rectify ...
4
votes
2answers
492 views

Is there a way to combine and sync two 2K cameras @ 90fps with ICs

I am searching for a way to minimize the size of a stereo vision module and cannot find any ICs that will combine and sync two MIPI CSI-2 (4 lane) data streams without an FPGA and too much code. ...
4
votes
1answer
3k views

LIDAR solutions [closed]

I am surprised by the price range of Lidar applications considering the simplicity of the design. I try to make a simple project that requires lidar for object recognitions etc. I wouldn't like to use ...
3
votes
4answers
6k views

Using C++ to control a drone

I am relatively new to using drones and was wondering if someone more experienced in the topic could lend a hand. I am familiar with C++ and OpenCV, a facial recognition software that has libraries in ...
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 ...
3
votes
1answer
59 views

Why is a computer vision system similar to the human vision

Does computer vision intentionally mimic the vision of a human or is it just coincidental that a good computer vision system (with convolutional neural networks for example) reassembles some ...
3
votes
2answers
3k 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 ...
3
votes
1answer
330 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 ...
3
votes
5answers
535 views

Using vision for Monte-Carlo localization

From each step of my vision code I am able to get around 400 coordinates of where the robot thinks the walls are I want to integrate this into Monte-Carlo observation step. I'm storing the map of ...
3
votes
2answers
73 views

Question about Lens distortion

Suppose I have a 240x180 camera with the following distortion co-efficients, $$k_1 = -0.138592767408$$ $$k_2=0.0933736664192$$ $$k_3=0.0$$ $$p_1=k_4=-0.000335586987532$$ $$p_2=k_5=0.000173720158228$$ ...
3
votes
1answer
177 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 ...
3
votes
2answers
892 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 ...
3
votes
1answer
514 views

Stereo camera vs. one camera for player detection & ball tracking in basketball scenes?

There are a number of similar questions such as Monocular vs. stereo computer vision robustness for object detection, but none that address my question specifically. My weekend project is to build a ...
3
votes
2answers
164 views

Non-Vision Based Target Tracking

I am building 4-wheeled, knee-high robot with music and speakers on top that will follow a target person as the target moves around. I would like some help with the setup for tracking the target. The ...
3
votes
1answer
275 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
0answers
783 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 ...
2
votes
3answers
1k 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 ...