I have to start work on application for analysis of satellite imagery to identify some man made structure. I would like to use C or Java for this.
For satellite I am planning to use Google Maps data.
I have three questions here:
What is best source for GIS data besides Google Maps/earth.
Best language to write such an application considering i will have to use third-party APIs
Is there a open image processing engine available which identifies man made structures?
Thats a lot of questions but I hope the smarter guys here can help me here.
Overly processed imagery such as Google or Bing maps is a horrible source of imagery for performing feature extraction or feature recognition. Usually, you want the most unprocessed, raw form possible with camera models... of course, if you don't have access to this sort of data, then you have to work with what you have.
A more important consideration of Google Maps/Earth imagery is that you may run afoul of their License Agreement. I suggest you check it before you decide on their data as your imagery source. In particular, if you bypass their API's, you've violated their license agreement.
As far as libraries and langauges, there are dozens of machine vision libraries available. I can't recommend one over the other as I've only been a down-stream consumer of their results. My understanding of the problem is that the biggest concern is how you build the "models" to compare against... i.e. how do you give the system an "example" of what you're looking for.
Once you've found a library, then you can make a decision on the language. Generally, a high-level language like Python or Matlab is used for this kind of prototyping. Once a method has been found, then conversion to a "higher performance" language is done--if necessary.
Personally, I'd probably use Python because (1) it's freely available, (2) has a significant community in the scientific and research worlds, and (3) can interop with a wide variety of languages and platforms.
Specifically, check out Glovis: http://glovis.usgs.gov/
You can browse the earth, and download maps from several different satellites and sensors. Even though you have to go through a bogus "ordering" process, the imagery is free.
You may find the USGS (United States Geological Survey) website helpful. They provide both GIS information and a wide range of data sets.
I agree with James Schek. Google gives you RGB images - not the most helpful fot your task. Most imagery will have a couple of additional channels that may be better suited for you. Different channels show different features, water, urban areas, types of foliage etc. For example an infra-red channel could be used to pick out buildings in a cool climate. If you contact several data provider they may be able to recommend the best channels to use in their data.
Ariel imagery can be huge, numerous terrabytes for a detailed world database. Carefully consider how much information you need to process. If you are only doing a few square miles performance is not an issue. If you are processing thousands of square miles, performance becomes an issue. Processing millions, performance is mission critical and must be considered from day one.
Knowing the number of channels you need to process, your performance requirements and the file format of your data, look around for libraries that fulfil all your requirements. Many of them are written in C/C++ so using a language that interops with them both could be helpful
Take a look at this demo:
Finding Vegetation in a Multispectral Image
, part of the Image Processing Toolbox in MATLAB. It is related to your problem of analysing satellite images to find specific patterns.
I believe it's an excellent example of the sort of things you can achieve easily with MATLAB using very little code.
Related
I've been doing some research on the feasibility of building a mobile/web app that allows users to say a phrase and detects the accent of the user (Boston, New York, Canadian, etc.). There will be about 5 to 10 predefined phrases that a user can say. I'm familiar with some of the Speech to Text API's that are available (Nuance, Bing, Google, etc.) but none seem to offer this additional functionality. The closest examples that I've found are Google Now or Microsoft's Speaker Recognition API:
http://www.androidauthority.com/google-now-accents-515684/
https://www.microsoft.com/cognitive-services/en-us/speaker-recognition-api
Because there are going to be 5-10 predefined phrases I'm thinking of using a machine learning software like Tensorflow or Wekinator. I'd have initial audio created in each accent to use as the initial data. Before I dig deeper into this path I just wanted to get some feedback on this approach or if there are better approaches out there. Let me know if I need to clarify anything.
There is no public API for such a rare task.
Accent detection as language detection is commonly implemented with i-vectors. Tutorial is here. Implementation is available in Kaldi.
You need significant amount of data to train the system even if your sentences are fixed. It might be easier to collect accented speech without focusing on the specific sentences you have.
End-to-end tensorflow implementation is also possible but would probably require too much data since you need to separate speaker-instrinic things from accent-instrinic things (basically perform the factorization like i-vector is doing). You can find descriptions of similar works like this and this one.
You could use(this is just an idea, you will need to experiment a lot) a neural network with as many outputs as possible accents you have with a softmax output layer and cross entropy cost function
The problem statement is kind of vague but i am looking for directions because of privacy policy i can't share exact details. so please help out.
We have a problem at hand where we need to increase the efficiency of equipment or in other words decide on which values across multiple parameters should the machines operate to produce optimal outputs.
My query is whether it is possible to come up with such numbers using Linear Regression or Multinomial Logistic Regression algorithms, if no then can you please specify which algorithms will be more suitable. Also can you please point me to some active research done on this kind of problem that is available in public domain.
Does the type of problem i am asking suggestions for comes in the area of Machine Learning ?
Lots of unknowns here but I’ll make some assumptions.
What you are attempting to do could probably be achieved with multiple linear regression. I have zero familiarity with the Amazon service (I didn’t even know it existed until you brought this up, it’s not available in Europe). However, a read of the documentation suggests that the Amazon service would be capable of doing this for you. The problem you will perhaps have is that it’s geared to people unfamiliar with this field and a lot of its functionality might be removed or clumped together to prevent confusion. I am under the impression that you have turned to this service because you too are somewhat unfamiliar with this field.
Something that may suit your needs better is Response Surface Methodology (RSM), which I have applied to industrial optimisation problems that I think are similar to what you suggest. RSM works best if you can obtain your data through an experimental design such as a Central Composite Design or Box-Behnken design. I suggest you spend some time Googling these terms to get your head around them, I don’t think it’s an unmanageable burden to learn how to apply these with no prior experience in this area. Because your question is vague, only you can determine if this really is suitable. If you already have the data in an unstructured format, you can still generate an RSM but it is less robust. There are plenty of open-access articles using these techniques but Science Direct is conveniently down at the moment!
Minitab is a software package that will do all the regression and RSM for you. Its strength is that it has a robust GUI and partially reflects Excel so it is far less daunting to get into than something like R. It also has plenty of guides online. They offer a 30 day free trial so it might be worth doing some background reading, collecting the tutorials you need and develop a plan of action before downloading the trial.
Hope that is some help.
I'm looking an algorithm that analyzes a portrait-photo of a person and outputs a descriptive text like "young man, rather long nose, green eyes".
It doesn't matter if the output is very precise or not; it is for an art installation. But it should be possible to do it automatic.
I found this one: https://code.google.com/p/deep-learning-faces/, but it is impossible for me to fulfill the hardware and software requirements (NVIDIA Fermi GPUs & matlab)
Do you know of anything more accessible?
There are a few free face analyser APIs that are fairly easy to use:
Rekognition, by Orbeus
MP Face Analyzer SDK (evaluation) by MotionPortrait
Faceplusplus (linked above)
You might have to take measurements of an "average face" to make interpretations like "long nose". ToonifyMe is an app that caricatures faces using this approach.
Some of these API's can actually work on a Pi. Recognition does the analysis in the cloud, so that should be doable.
This is one of the hardest problems in computer vision. I'd recommend you watch the ted talk by Fei-Fei Li to get an understanding of it:
https://www.ted.com/talks/fei_fei_li_how_we_re_teaching_computers_to_understand_pictures
In short: If you want to use any of the state-of-the-art methods you will need a lot of processing power. A lot more than just a single high-end graphics card, I'm talking about super computing here.
And unless you're really lucky and find a research group that has released their implementation, this also requires a huge amount of engineering.
I found this online service that describes faces: http://www.faceplusplus.com/
It has a very well documented API and seems to be free of charge. Or at least I didn't find any information about pricing.
I'd like to programatically do some signal processing on a live sound feed.
Specifically I'd like to be able to isolate certain bands of frequencies and play around with phase shifting.
I've not worked in this area before from a purely software perspective and a quick google search turned up very little useful information.
Does anyone know of any good information resources for this topic area?
Matlab is a good starting point. It has the necessary toolboxes and functions that will allow you to capture audio signals, run different kind of filters over them and write them to wav files. The UI is easy to navigate through and it's simple enough to generate plots and visualize results.
http://www.mathworks.com/products/signal/
If, however, you're looking to develop real-world applications, then Python can come in handy. They have toolkits like SciPy, Numpy, Audiolab that offer the same functions as Matlab does.
http://www.scipy.org
Link
http://scikits.appspot.com/audiolab
In a nutshell, Matlab is good for testing ideas and prototyping, Python is good for testing as well as real-world application development. And Python is free. Matlab might cost you if you're not a student anymore.
http://www.dspguide.com/
This is a super excellent reference on digital signal processing techniques in general. It's not a programming guide, per se, but covers the techniques and the theory clearly and simply, and provides pseudocode and examples so that you can implement in the language of your choice. You'll be hard up to find a more complete reference, and you can download it for free online!
I'm new to image processing and I want to do a project in object detection. So help me by suggesting a step-by-step procedure to this project. Thanx.
Object detection is a very complex problem that includes some real hardcore math and long tuning of parameters to the computation methods involved. Your best bet is to use some freely available library for that - Google will help.
There are lot of algorithms about the theme and no one is the best of all. It's usually a mixture of them what makes the best solution to the solution.
For example, for object movement detection you could look at frame differencing and misture of gaussians.
Also, it's very dependent of your application, the environment (i.e. noise, signal quality), the processing capacity you may have available, the allowable error margin...
Besides, for it to work, most of time it's first necessary to do some kind of image processing to the input data like median filter, sobel filter, contrast enhancement and a large so on.
I think you should start reading all you can: books, google and, very important, a lot of papers about the subjects (there are many free in internet) you are interested in.
And first of all, i think it's fundamental (at least it has been for me) having a good library for testing. The one i have used/use is OpenCV. It's very complete, implement many of the actual more advanced algorithms, is very active, has a big community and it's free.
Open Computer Vision Library (OpenCV)
Have luck ;)
Take a look at AForge.NET. It's nowhere near Project Natal's levels of accuracy or usefulness, but it does give you the tools to learn the algorithms easily. It's an image processing and AI library and there are several tutorials on colored object tracking and motion detection.
Another one to look at is OpenCV from Intel. I believe it's a bit more advanced, but it's written in C.
Take a look at this. It might get you started in this complex field. The algorithm pages that it links to are interesting reading.
http://sun-valley.stanford.edu/projects/helicopters/final.html
This lecture by Jeff Hawkins, will give you an idea about the state of the art in this super-difficult field.
Seems that video disappeared... but this vid should cover similar ground.