I want to create a application which converts 2d-images/video into a 3d model. While researching on it i found out similar application like Trnio, Scann3D, Qlone,and few others(Though few of them provide poor output 3D model). I also find out about a technology launched by the microsoft research called mobileFusion which showed the same vision i was hoping for my application but these apps were non like that.
Creating a 3D modelling app is complex task, and achieving it to a high standard requires a lot of studying. To point you in the right direction, you most likely want to perform something called Structure-from-Motion(SfM) or Simultaneous Localization and Mapping (SLAM).
If you want to program this yourself OpenCV is a good place to start if you know C++ or Python. A typical pipeline involves; feature extraction and matching, camera pose estimation, triangulation and then optimised using a bundle adjustment. All pipelines for SfM and SLAM follow these general steps (with exceptions of course). All of these steps are possible is OpenCV although Googles Ceres Solver is an excellent open-source bundle adjustment. SfM generally goes onto dense matching which is where you get very dense point clouds which are good for creating meshes. A free open-source pipeline for this is OpenSfM. Another good source for tools is OpenMVG which has all of the tools you need to make a full pipeline.
SLAM is similar to SfM, however, has more of a focus on real-time application and less on absolute accuracy. Applications for this is more centred around robotics where a robot wants to know where it is relative to its environment, but it not so concerned on absolute accuracy. The top SLAM algorithms are ORB-SLAM and LSD-SLAM. Both are open-source and free for you to implement into your own software.
So really it depends what you want... SfM for high accuracy, SLAM for real-time. If you want a good 3D model I would recommend using existing algorithms as they are very good.
The best commercial software in my opinion... Agisoft Photoscan. If you can make anything half as good as this i'd be very impressed. To answer your question what resources will you require. In my opinion, python/c++ skills, the ability to google well and a spare time to read up on photogrammetry and SfM properly.
Related
I have a task: to determine the sound source location.
I had some experience working with tensorflow, creating predictions on some simple features and datasets. I assume that for this task, there would be necessary to analyze the sound frequences and probably other related data on training and then prediction steps. The sound goes from the headset, so human ear is able to detect the direction.
1) Did somebody already perform that? (unfortunately couldn't find any similar project)
2) What kind of caveats could I meet while trying to achieve that?
3) Am I able to do that using this technology approach? Are there any other sound processing frameworks / technologies / open source projects that could help me ?
I am asking that here, since my research on google, github, stackoverflow didn't show me any relevant results on that specific topic, so any help is highly appreciated!
This is typically done with more traditional DSP with multiple sensors. You might want to look into time difference of arrival(TDOA) and direction of arrival(DOA). Algorithms such as GCC-PHAT and MUSIC will be helpful.
Issues that you might encounter are: DOA accuracy is function of the direct to reverberant ratio of the source, i.e. the more reverberant the environment the harder it is to determine the source location.
Also you might want to consider the number of location dimensions you want to resolve. A point in 3D space is much more difficult than a direction relative to the sensors
Using ML as an approach to this is not entirely without merit but you will have to consider what it is you would be learning, i.e. you probably don't want to learn the test rooms reverberant properties but instead the sensors spatial properties.
I have been playing around with building some deep learning models in Python and now I have a couple of outcomes I would like to be able to show friends and family.
Unfortunately(?), most of my friends and family aren't really up to the task of installing any of the advanced frameworks that are more or less necessary to have when creating these networks, so I can't just send them my scripts in the present state and hope to have them run.
But then again, I have already created the nets, and just using the finished product is considerably less demanding than making it. We don't need advanced graph compilers or GPU compute powers for the show and tell. We just need the ability to make a few matrix multiplications.
"Just" being a weasel word, regrettably. What I would like to do is convert the the whole model (connectivity,functions and parameters) to a model expressed in e.g. regular Numpy (which, though not part of standard library, is both much easier to install and easier to bundle reliably with a script)
I fail to find any ready solutions to do this. (I find it difficult to pick specific keywords on it for a search engine). But it seems to me that I can't be the first guy who wants to use a ready-made deep learning model on a lower-spec machine operated by people who aren't necessarily inclined to spend months learning how to set the parameters in an artificial neural network.
Are there established ways of transferring a model from e.g. Theano to Numpy?
I'm not necessarily requesting those specific libraries. The main point is I want to go from a GPU-capable framework in the creation phase to one that is trivial to install or bundle in the usage phase, to alleviate or eliminate the threshold the dependencies create for users without extensive technical experience.
An interesting option for you would be to deploy your project to heroku, like explained on this page:
https://github.com/sugyan/tensorflow-mnist
I am currently working on a (school-)project involving a robot having to navigate a corn field.
We need to make the complete software in NI Labview.
Because of the tasks the robot has to be able to perform the robot has to know it's position.
As sensors we have a 6-DOF IMU, some unrealiable wheel encoders and a 2D laser scanner (SICK TIM351).
Until now I am unable to figure out any algorithms or tutorials, and thus really stuck on this problem.
I am wondering if anyone ever attempted in making SLAM work in labview, and if so are there any examples or explanations to do this?
Or is there perhaps a toolkit for LabVIEW that contains this function/algorithm?
Kind regards,
Jesse Bax
3rd year mechatronic student
As Slavo mentioned, there's the LabVIEW Robotics module that contains algorithms like A* for pathfinding. But there's not very much there that can help you solve the SLAM problem, that I am aware of. The SLAM problem consist of the following parts: Landmark extraction, data association, state estimation and updating of state.
For landmark extraction, you have to pick one or multiple features that you want the robot to recognize. This can for example be a corner or a line(wall in 3D). You can for example use clustering, split and merge or the RANSAC algorithm. I believe your laser scanner extract and store the points in a list sorted by angle, this makes the Split and Merge algorithm very feasible. Although RANSAC is the most accurate of them, but also has a higher complexity. I recommend starting with some optimal data points for testing the line extraction. You can for example put your laser scanner in a small room with straight walls and perform one scan and save it to an array or a file. Make sure the contour is a bit more complex than just four walls. And remove noise either before or after measurement.
I haven't read up on good methods for data association, but you could for example just consider a landmark new if it is a certain distance away from any existing landmarks or update an old landmark if not.
State estimation and updating of state can be achieved with the complementary filter or the Extended Kalman Filter (EKF). EKF is the de facto for nonlinear state estimation [1] and tend to work very well in practice. The theory behind EKF is quite though, but it should be a tad easier to implement. I would recommend using the MathScript module if you are going to program EKF. The point of these two filters are to estimate the position of the robot from the wheel encoders and landmarks extracted from the laser scanner.
As the SLAM problem is a big task, I would recommend program it in multiple smaller SubVI's. So that you can properly test your parts without too much added complexity.
There's also a lot of good papers on SLAM.
http://www.cs.berkeley.edu/~pabbeel/cs287-fa09/readings/Durrant-Whyte_Bailey_SLAM-tutorial-I.pdf
http://ocw.mit.edu/courses/aeronautics-and-astronautics/16-412j-cognitive-robotics-spring-2005/projects/1aslam_blas_repo.pdf
The book "Probabalistic Robotics".
https://wiki.csem.flinders.edu.au/pub/CSEMThesisProjects/ProjectSmit0949/Thesis.pdf
LabVIEW provides LabVIEW Robotics module. There are also plenty of templates for robotics module. Firstly you can check the Starter Kit 2.0 template Which will provide you simple working self driving robot project. You can base on such template and develop your own application from working model, not from scratch.
I'm currently using a Processing Kinect library which supplies a depth map. I was wondering how I could take that and use it to create a 2D skeleton, if possible. Not looking for any code here, just a general process I could use to achieve those results.
Also, given that we've seen this in several of the Kinect games so far, would it be difficult to have multiple skeletons running at once?
Disclaimer: the reason why you still didn't get an answer for this question is probably because that's a current research problem. So I can't give you a direct answer but will try to help with some information and useful resources for this topic.
There are mainly 2 different approaches to create a skeleton from a depth map. The first one is to use machine learning, the second is purely algorithmic.
For the machine learning one, you'd need many samples of people doing a predetermined move, and use those samples to train your favorite learning algorithm. That's the approach that was taken and implemented by Microsoft in the XBox (source), it works really well BUT you need millions of samples to make it reliable... quite a drawback.
The "algorithmic" approach (understand without using a training set) can be done in many different ways and is a research problem. It's often based on modeling the possible body postures and trying to match that with the depth image received. That's the approach that was chosen by PrimeSense (the guys behind the kinect depth camera technology) for their skeleton tracking tool NITE.
The OpenKinect community maintains a wiki where they list some interesting research material about this topic. You might also be interested in this thread on the OpenNI mailing list.
If you're looking for an implementation of a skeleton tracking tool, PrimeSense released NITE (closed source), the one they made: it's part of the OpenNI framework. That's what's used in most of the videos you might have seen that involve skeleton tracking. I think it's able to handle up to 2 skeletons at the same time, but that requires confirmation.
The best solution is to use FAAST (http://projects.ict.usc.edu/mxr/faast/) which requires OpenNI. I have struggled to get OpenNI to work on my computer. I have not seen an approach yet using Code Laboratories' CL NUI.
An algorithmic approach is http://code.google.com/p/skeletonization/ but you may have a problem because your depthmap only represents surfaces and no closed objects.
Closed. This question is off-topic. It is not currently accepting answers.
Want to improve this question? Update the question so it's on-topic for Stack Overflow.
Closed 10 years ago.
Improve this question
I'm a beginner in game development and game programming. I have experience in computer graphics - mainly OpenGL
In those days Finally, I have some spare time to polish my game coding skills.
But when coming to program a simple 3d game, I couldn't find any good resource for free textures and models for 3d graphics (for 2d game for example, I found many resources for sprite sheets and so on).
Is there any good resource you're familiar with for 3d game textures/models?
This is not a programming queston.
As far as I know, good, free and high-quality modeling resources does not exist (from "good", "free" and "high-quality", select two).
There are multiple free model repositories, but quality of content is generally poor, and there are few places where you can buy models.
There are free textures in multiple places (like this one), and they are easier to find than good free models.
Also, most of free content frequently includes some kind of catch - "non-commercial use only", "creative commons share alike"(i.e. if you make derivative, it should use same license), or it is under GPL.
Anyway, if you're okay with "Creative Commons share alike" and GPL, then you can probably use content from some of opensource games (OpenArena ), and get quite a lot of textures from wikipedia or wikimedia commons, flickr, and you can google for "free textures". You should be careful about using content from opensource games - some opensource projects (like war$ow and sauerbraten) use closed-source/restricted licenses for game content (i.e. you're free to reuse modify engine, but you cannot modify game content and you cannot use it with modified engine. Reasons are pretty obvious).
Anyway, it depends on what kind of model you want. It is pretty easy to find "easy" stuff like boxes, barrels, etc, because everyone can do that. When it comes to guns and vehicles, there will be a trouble - quality will drop, and number of good models will decrease. And if you want a fully rigged animated character with multiple animation, normally you can forget about it - such content is almost impossible to find. But you can probably use mods for Q3 and Q2 if you want characters (you can forget about physics in this case, though)
I'd recommend to forget about "free stuff", and try to make content yourself or hire someone to do that.
If you decide to make content yourself, then you'll need digital photo camera and (optionally) graphic tablet. You can make mediocre textures from photos (digital camera is cheap) using gimp, gimp-resynthesizer plugin, gimp-texturisze plugin, high-pass filters, etc. You can also make normal maps using blender or gimp, and there are even tutorials about extracting them from photos (you still will need to process them by hand). Modeling and animation can be done in blender (after 1 or two weeks of training) using reference photos. Low poly modeling is pretty quick (20 minutes to make a low-poly low-quality gun, hour or two to make simple character), but texture and animation will take more (setting up animation for character can take a few hours for amateur, making one animation for character will take at least several hours as well, making texture unwrap - hour, painting texture - up to few days, depending on quality you want, available reference material, availability of graphic tablet, etc). It is possible to cut corners a bit - for example, for making animations, you can film motion using photo camera(or video camera), and then use it for rotoscoping. Also, you'll need to find some kind of model format blender can export to, or you'll have to write an export plugin in python.
The Blender foundation has a large model repository which may be of use.
There are some free models at Turbosquid that I use sometimes for my XNA games.
But of course, the best stuff is not free.
My experience is that there is very little in the way of quality 3d models with animation and full rigging freely available. There a few companies like this who sell suitable models cheaply and I guess most hobbyists could afford one or two models from them fairly easily which would probably be sufficient for learning. (I have no connection to them but I did buy one model pack from them which I quite liked)
It would be nice if there were a few more generally freely available 3d animated models around though. I even think it might be in the interests of some of the companies that make them to give a few away. If I'd been able to get further in my hobby projects I might have spent £100-200 in total on some nice model packs to make my project better, but due to the lack of any real 3d animated models I ended up losing interest in all my 3d projects before I got to the point of thinking maybe I'd spend a little money on this hobby. I wonder if the availability of a few more free quality models would actually significantly increase the size of the market for those companies as more people got their projects to the point where they were willing to spend a little money on it.
Some company should make a nice model pack with a few static models and a couple of fully rigged and animated humans and "monsters" and say that if the community donates £10000 they'll release them for free use. I suspect there are enough people out there who would like a few quality models they might reach this target in the same way that Blender was originally sold to the public.
I know that it's been a long time since this question was asked, but I ran into same problem when programming in XNA and I found a good solution. As long as you don't need rigged / animated models, Google Warehouse is the best place to search. As far as I know, each model submitted to Google Warehouse is available on Creative Commons license. You just need to:
Download and install Google Sketchup (Sketchup download)
Browse to find a model (Google Warehouse) - there's a 3D preview for each one!
Get a plugin to export Sketchup models to .X - I recommend the '3D RAD' plugin (3D RAD download)
If your model does not look good after the export, try to separate it into several less complex ones.
you are looking for open game art ...
http://thefree3dmodels.com/ has a multitude of free 3D models. I've used a few of these for animation purpose, maybe it'll help you too.