I have been working on a school project for the last few months, where I have been automatically generating skeleton files from depthmap files, taken by an XBox Kinect. I would like to compare my accuracy with other algorithms, but I am struggling to find algorithms that don't use a physical Kinect device, and instead just a depthmap file. Does anyone know of a software that does this? Links appreciated!
Not a skeleton, but a bounding box can be generated with this project. I'm still very much open to suggestions.
Related
So I am using Tesseract with C# to read english text and it works like a charm. I use pre-trained data from the tesseract repo:https://github.com/tesseract-ocr/tessdata
So far, so good. However, I fail to understand how to solve the following situation: I have an image with a maximum of three numbers on it:
I also followed this tutorial in order to train my own data but I failed to understand what exactly I am doing mid-way:https://pretius.com/how-to-prepare-training-files-for-tesseract-ocr-and-improve-characters-recognition/
In this tutorial, they used some existing font and train their network accordingly. However, I do not know what this font is. I tried to figure it out myself but was overwhelmed by the huge amount of information about tesseract and actually do not have any idea where to start.
I was wondering if the following would be possible: I have lots of pictures looking like that(in fact, every possible character with every possible color, only difference is that the background is different):
etc...
And with those pictures, I want to train the network, without using any existing font files.
My algorithm right now does not use tesseract, it just screenshots the position of the numbers and I compare pixel-wise. I do not like this appoach though, as the accuracy is something like 60%.
Thanks for your help in advance
I know that tools like this exist but I am yet to find one that does the job in C#. Does a library or open source one exist or at the very least is it possible to make? If it is possible to make can anyone point me in the right direction?
Thanks for the help.
All you need to do is download every separate tile image and stitch them together into a single image.
I'm currently trying to work with a Microsoft Hololens and I want to basically pull some data from a database, copy it into a form that I can use and then, using Unity, visualize it and have that go into the Hololens.
I have pretty limited coding experience and am looking to improve, but any resources and help you can give would be greatly appreciated!
So my basic understanding of how to go about this task is to:
Find the form of the data and put it into a .csv file
Draw data from the .csv file and use it to create a graph in Unity. I don't have a graphing asset to hand so if you can recommend one (free if possible!) let me know.
Using Unity's ability to display to the Hololens to show this as UI element
If this all works I also want to incorporate a system by which the image processing can be used to look at something and therefore generate this graph - I was thinking QR codes or something similar.
Do you guys have any advice, pitfalls and/or resources that could help me?
Thank you!
As said in the comments, the questions is very wide.
But, here you can get some points to start:
You can get the data (or the file) from a WebAPI or any REST service.
You can process as that dataset as you need in Unity.
You can search any graph asset in the Unity Asset Store and send the data to it and display in the hololens.
You can use the ZXing library to read the QR code generated to display the graph as well.
Hope this helps.
I need a c# script for unity that can read the EXIF lat/long data from a photo. i would like to place a posTransform at that location. not sure if this is possible within Unity. i would like to load my images into unity and have a script read the EXIF: 1-GPS lat/long, 2-rotation, 3-timestamp from photographs. i haven't found any info that says this can be done within unity, however, i've read about exiflib github project and other ways outside of unity.
THANKS in advance for help
I maintain a project for extracting metadata from images that will give you what you need.
https://github.com/drewnoakes/metadata-extractor-dotnet
The library supports .NET 3.5 so should work under Unity, though I haven't tested it before.
With it, you would write:
var directories = ImageMetadataReader.ReadMetadata(filePath);
var gpsDirectory = directories.OfType<GpsDirectory>().FirstOrDefault();
if (gpsDirectory != null)
{
var location = gpsDirectory.GetGeoLocation();
Console.WriteLine($"Photo was taken at {location.Latitude},{location.Longitude}");
}
The answer from Drew Noakes doesn't work because it has dependencies on .NET that Unity doesn't support.
In my opinion, the best option right now, after a few days of research, is this project:
https://www.codeproject.com/Articles/5251929/CompactExifLib-Access-to-EXIF-Tags-in-JPEG-TIFF-an
This is a simple one-file project that you can drag in your unity project and that has no external dependencies. And it can read and update EXIF tags for JPG, PNG and TIFF files.
I know I am probably being dense here but I need some help.
I am working on a program that handles mapping of an area, I need to have the map be GEOref'd so I can gather the MGRS coords for any point on the map. I already have a lib I wrote that does this working with images I import one by one using upper left and bottom right coords. I then simply calculate the number of pixels and their offset from the top left and bottom right of the image.
What I am trying to do is create a dragable map like GoogleMaps or any number of other mapping systems.
Here's the kicker. The system is running on a closed network with no access to Google or any other online resource for the maps.
I have 500gb worth of map data that I can work with but the format is something I am not familiar with, a XML file with some georef data, and a truck load of files with .tileset extension.
I assume I need to create some sort of tile stitching routine similar to what you would see in a game engine, but I have no experience with such engines.
Can anyone give me some advice or libs or directions to start researching to parse and use these tileset files and get this function going?