I want to use tango for mechanical design. I would like to put scanned files on Autocad. Scanning existing pipes and steel structures. Is it possible with tango? For example with Zenfone AR?
Where can I find scanned stock samples to try with Autocad?
There are a handful of Tango applications on the Play Store that reconstruct 3D worlds on a scan. Google has written Constructor Developer Tool. The share feature inside Constructor creates a .zip file with a model and texture in .obj and .png formats.
I hope this helps!
Related
I have a web application where user uploads the images of their locations. I want to write a program to detect the type of location and list of objects from the image. I write a program in C# using alturos YOLO to detect objects in the image. The result is fine for me but the problem is i want to detect the place type from the image. Like, if you upload some image that has snow then it should detect the "Snow" keyword. If you upload the "Lake" image then it should show keywords like "Lake, water, river etc". I am a web developer and never done any Machine Learning or image processing thing. But i am keen to learn this. Is there any way to do this or anyone can tell me the right path to do this.
I found this "https://www.clarifai.com/" but i want to write my own code because i have large number of images.
All in all, I'm pretty sure that there's no single correct answer to this. You could implement image recognition in a hundred different equally correct ways using different tools. So here's my opinionated perspective. Anyone and everyone is free to agree/disagree with what I'm saying.
I've worked a bit with Open CV (Python) in the past. There are a great number of libraries available based on it, so you can probably find a working base to build off of. I think that it should be capable of doing the task you specify, although I'm not quite sure how it would be done.
The other framework for machine learning and object recognition that I have seen is Apple's Create ML/ Core ML system (Swift or Objective-C). My experience with that one is as limited as cloning a git repo and poking around inside, but it looks pretty powerful.
We have an existing three.js application and are experimenting with adding support for cad designs. Previously we managed these with some custom rendering of geojson data that we created from DXF files, but now we're looking to use Autodesk Forge to allow support for more data types and pre-process the data before rendering.
As a preface, we cannot simply just use the Forge viewer threejs version as this would involve us rewriting our entire application to be built as extensions on top of the Forge viewer.
So the plan is, for 3D files, I'm looking at downloading the obj/mtl files from the Forge api and loading those directly in vanilla three.js using their OBJLoader2 example. Based off my initial testing, this appears to work and renders to my liking. I can control how the meshes are created and ensure it is optimized to work within my application.
The problem comes when I'm trying to load 2D files as the forge api only lets me download f2d files which as far as I know, I have no way of loading these using vanilla three.js. Any ideas? Is there another format 2D designs will export as that I might be able to load independently?
At the moment I don't know of a simple pipeline to load 2D in plain Three.js. By 2d I am guessing that you mean dwg/dxf, if not the case be more explicit... Forge Model Derivatives REST API doesn't provide another export format from dwg than svf (f2d).
You could convert a 2d dwg into a 3d one by adding a 3d solid to it for example, but then I don't know what the obj export would be, probably not really interesting but you may want to give it a try.
Another option would be to use the Design Automation API with AutoCAD, you could upload a dwg and run some custom dll that would convert the drawing into your custom format that you can then load in your viewer, this will require AutoCAD ObjectARX or .Net API expertise and depending on the complexity of the drawings you plan to handle, may be a fair piece of work.
Finally you may want to consider using the Forge Viewer, even if that means rewriting parts of your app, the viewer is based on Three.js so you may be able to migrate some of your features rather easily, all the UI is just html/css and you can integrate any UI JavaScript framework on top of it. This may end up being a more powerful and flexible solution in the long term than a convoluted pipeline of translations between formats... By exporting 3d to obj you are also loosing all metadata embedded in a CAD file, this may or may not be an issue to you.
I hope that helps
As it is shown in Project Tango GTC Video, some local features are extracted and tracked for motion estimation that is then fused with accelerometer data.
Since any developer may need to track features to develop his/her apps, I was wondering if there would be a way to get those features through APIs.
Although it is possible to extract some point and retrieve their flow using estimated 6DOF pose returned by the APIs, it adds extra overhead. Another issue with this approach is that the pure visual flow (including outliers) is not achievable and is influenced by IMU data.
So my question is that if these features are tracked using hardware-accelerated algorithms, how can we get them using APIs without having to implement it and do a redundant task.
Any answer and suggestion would be appreciated.
It is straightforward to compile OpenCV for the Tango with nVidia's TADP package. Use 3.0r4. You may need to merge some OpenCV-4-Android bits but it's easy, and the ES examples will fail on the device but don't sweat it.
Google released the "Project Tango ADF Inspector" on play store - I haven't actually had any time to play with it, but its the first thing to offer any look inside that data - I think Google considers this data sensitive and is cautious in this area, with good reason - If you look for the starred "important" note on this page you should get a feel for the sensitivity of that issue.
We are using WEBGL to render OBJ models . What is the best approach to protect these assets.
or at least make it difficult for someone to pull out the obj mesh . source.
There has been few threads discussing this issue but most of them confined to rudimentary ways like disabling right click on browser etc.
Any suggestions please
The "best" approach is to write your own file format. The user aiming to read your files will then have to find the loading code in your minified code.
What's the best approach on any other platform? I can stick the CD or DVD from any console game in my PC and read the files directly off the disc. I can look at any files installed on my PC games. I can back up the apps on my iOS or Android devices and read those files on my PC. What do you expect to be different in WebGL?
I am working on project and my task is to export house plan from AutoCAD to some format that is most adaptable for SCADA. Any suggestion will help me. Thanks!
As you didn't specify which HMI/SCADA package, you'll get a general answer. Since ALL packages are basically a GUI, a bitmap (.bmp) graphic will be fine for most, if not all.
One thing I do know for sure, Rockwell's FactoryTalk View will allow you to import a .dxf file, but I think this is the only package that will let you do this. WinCC and InTouch certainly don't have this kind of support.
For the sake of compatibility, an image file would be best.
I'm one of developers of open source Scada-LTS.
We can add functionality of loading svg or 3dx background on view (HMI) in Scada-LTS.
Your dfx file can be converted into svg or x3d format.
For example you may use:
http://kabeja.sourceforge.net to svg convertion.
https://www.blender.org to x3d convertion.
Schneider ClearSCADA is capable of importing dxf files into HMI screens with some limitations
I do a lot of SCADA work and to honest I have yet to come across a package that has a anything but garbage for a graphics editor. The one exception is Wonderware's archestra ide...but for a home project you won't be using that!
I would recommend creating an image for a background (png, jpg, etc) and then laying your animated graphics and data on top of that. My tools of choice are Sketchup for CAD tasks, Inkscape for vector graphic tasks, and Blender for 3d rendering. Then I take the assets created in those tools and bring them into whatever SCADA package I'm working with.