I'm doing some work on pathfinding.
So far I have tested my code on scenes composed of 2D cells.
I've also created a simple 3d scene to test my work on as well.
I'd like to test my work on some 3d scenes .. but it is time consuming to create them.
Does anyone know of any scene datasets that I could use to test my pathfinding algorithms on?
To get a better answer, you really need to specify the dimensionality of the configuration spaces that you want to consider. You aren't going to be tackling protein folding and docking problems (200+ degrees of freedom) with discrete graph searches. Even a relatively small planning problems (in terms of academic problems), of about 6 degrees of freedom can quickly become intractable.
Most of the best examples for planning tend to be published in research papers first, and then make their way into more general use. Some of the best work tends to be published in IEEE journals, or at the Intelligent Robots and Systems (IROS) and International Conference on Robotics and Automation (ICRA) conferences. It may also be worth using the bibliography of a well known reference in the field, such as "Motion Planning" by LaValle as a starting point for further research (available in bibtex here)
Mark Overmars work in the computational geometry and planning communities have made some of the problems considered in his publications very recognizable. It is worth checking if any his current grad students and collaborators have any data sets available at the moment.
If you're happy to still be doing some work in 2d, and to manually convert an image to geometric data, Kris Beevers website has a number of worked examples for a range of planners in 2d work spaces.
The Motion Strategy Library contains a number of classical motion planning problems for use in 2d and 3d workspaces, with varying dimensionality of configuration space depending on the problem. It includes:
L sections into a birdcage
trailers
multiple trailers
mazes
kinematic chains
non-holonomic cars
A more recent implementation of an academic motion planning library is The Open Motion Planning Library developed by the Kavraki lab. Because of licensing, I haven't checked personally, but I assume that they ship some examples and tests with their project.
A number of significantly more complex kinodynamic motion planning examples are now publicly available as part of the OpenRAVE project. Their gallery is eye opening.
when I need big 3D datasets, I usually use attractors or other dynamical series. You simply have to iterate as many time as you want and it will generate a nice set of 3D data.
Try this 'Peter de Jong Attractor':
Xn+1 = sin(a Yn) - cos(b Xn)
Yn+1 = sin(c Xn) - cos(d Yn)
Where (for example): a = 1.4, b = -2.3, c = 2.4, d = -2.1
Related
Working on a small side project related to Computer Vision, mostly to try playing around with OpenCV. It lead me to an interesting question:
Using feature detection to find known objects in an image isn't always easy- objects are hard to find, especially if the features of the target object aren't great.
But if I could choose ahead of time what it is I'm looking for, then in theory I could generate for myself an optimal image for detection. Any quality that makes feature detection hard would be absent, and all the qualities that make it easy would exist.
I suspect this sort of thought went into things like QR codes, but with the limitations that they wanted QR codes to be simple, and small.
So my question for you: How would you generate an optimal image for later recognition by a camera? What if you already know that certain problems like skew, or partial obscuring would occur?
Thanks very much
I think you need something like AR markers.
Take a look at ArToolkit, ArToolkitPlus or Aruco libraries, they have marker generators and detectors.
And papeer about marker generation: http://www.uco.es/investiga/grupos/ava/sites/default/files/GarridoJurado2014.pdf
If you plan to use feature detection, than marker should be specific to used feature detector. Common practice for detector design is good response to "corners" or regions with high x,y gradients. Also you should note the scaling of target.
The simplest detection can be performed with BLOBS. It can be faster and more robust than feature points. For example you can detect circular blobs or rectangular.
Depending on the distance you want to see your markers from and viewing conditions/backgrounds you typically use and camera resolution/noise you should choose different images/targets. Under moderate perspective from a longer distance a color target is pretty unique, see this:
https://surf-it.soe.ucsc.edu/sites/default/files/velado_report.pdf
at close distances various bar/QR codes may be a good choice. Other than that any flat textured object will be easy to track using homography as opposed to 3D objects.
http://docs.opencv.org/trunk/doc/py_tutorials/py_feature2d/py_feature_homography/py_feature_homography.html
Even different views of 3d objects can be quickly learned and tracked by such systems as Predator:
https://www.youtube.com/watch?v=1GhNXHCQGsM
then comes the whole field of hardware, structured light, synchronized markers, etc, etc. Kinect, for example, uses a predefined pattern projected on the surface to do stereo. This means it recognizes and matches million of micro patterns per second creating a depth map from the matched correspondences. Note that one camera sees the pattern and while another device - a projector generates it working as a virtual camera, see
http://article.wn.com/view/2013/11/17/Apple_to_buy_PrimeSense_technology_from_the_360s_Kinect/
The quickest way to demonstrate good tracking of a standard checkerboard pattern is to use pNp function of open cv:
http://www.juergenwiki.de/work/wiki/lib/exe/fetch.php?media=public:cameracalibration_detecting_fieldcorners_of_a_chessboard.gif
this literally can be done by calling just two functions
found = findChessboardCorners(src, chessboardSize, corners, camFlags);
drawChessCornersDots(dst, chessboardSize, corners, found);
To sum up, your question is very broad and there are multiple answers and solutions. Formulate your viewing condition, camera specs, backgrounds, distances, amount of motion and perspective you expect to have indoors vs outdoors, etc. There is no such a thing as a general average case in computer vision!
I was given a project on vehicle type identification with neural network and that is how I came to know the awesomeness of neural technology.
I am a beginner with this field, but I have sufficient materials to learn it. I just want to know some good places to start for this project specifically, as my biggest problem is that I don't have very much time. I would really appreciate any help. Most importantly, I want to learn how to match patterns with images (in my case, vehicles).
I'd also like to know if python is a good language to start this in, as I'm most comfortable with it.
I am having some images of cars as input and I need to classify those cars by there model number.
Eg: Audi A4,Audi A6,Audi A8,etc
You didn't say whether you can use an existing framework or need to implement the solution from scratch, but either way Python is excellent language for coding neural networks.
If you can use a framework, check out Theano, which is written in Python and is the most complete neural network framework available in any language:
http://www.deeplearning.net/software/theano/
If you need to write your implementation from scratch, look at the book 'Machine Learning, An Algorithmic Perspective' by Stephen Marsland. It contains example Python code for implementing a basic multilayered neural network.
As for how to proceed, you'll want to convert your images into 1-D input vectors. Don't worry about losing the 2-D information, the network will learn 'receptive fields' on its own that extract 2-D features. Normalize the pixel intensities to a -1 to 1 range (or better yet, 0 mean with a standard deviation of 1). If the images are already centered and normalized to roughly the same size than a simple feed-forward network should be sufficient. If the cars vary wildly in angle or distance from the camera, you may need to use a convolutional neural network, but that's much more complex to implement (there are examples in the Theano documentation). For a basic feed-forward network try using two hidden layers and anywhere from 0.5 to 1.5 x the number of pixels in each layer.
Break your dataset into separate training, validation, and testing sets (perhaps with a 0.6, 0.2, 0.2 ratio respectively) and make sure each image only appears in one set. Train ONLY on the training set, and don't use any regularization until you're getting close to 100% of the training instances correct. You can use the validation set to monitor progress on instances that you're not training on. Performance should be worse on the validation set than the training set. Stop training when the performance on the validation set stops improving. Once you've accomplished this you can try different regularization constants and choose the one that results in the best validation set performance. The test set will tell you how well your final result is performing (but don't change anything based on test set results, or you risk overfitting to that too!).
If your car images are very complex and varied and you cannot get a basic feed-forward net to perform well, you might consider using 'deep learning'. That is, add more layers and pre-train them using unsupervised training. There's a detailed tutorial on how to do this here (though all the code examples are in MatLab/Octave):
http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
Again, that adds a lot of complexity. Try it with a basic feed-forward NN first.
I'm preparing for a project related to weather visualization. I have some .csv files (100 rows, 120 colums) that contain weather data measured in my country where each cell represents a point with some specific values e.g. temperature or wind speed. Those files may be perceived as sets of points of latitude and longitude that covers my whole country (in fact the values are measured every 5 miles). I'd like to transformed the data and put the values on maps to make some weather visualizations, both 2d and 3d, especially heatmaps or hightmaps. I'm wondering which technology is the best for that. I was thinking of openGL, but all the textures mapping and drawing operations seem a bit difficult to me (but maybe they're not). I'm also considering making Java applets but there are many Java graphics libraries and I don't know wich one is the best for my requirements. Maybe all those things are possible to do in XNA, whcih would be great, because I'm programming mainly in C#. I'd be glad if some more experienced programmers could recommend me an appropriate language and libraries. What would you use to make the work easy and efficient?
OpenGL is just the pencil and paper for program to draw things with. While it certainly is possible to use OpenGL for this, I strongly suggest using an off the shelf visualization tool, like Origin, Matlab Visualization, visualization modules of R, etc.
If you're more looking in the direction of a visualization programming toolkit, have a look at VTK http://www.vtk.org/
But naked OpenGL for that task: Only recommendable if you "speak OpenGL fluently".
As a part of my masters project I proposed to build a virtual trial room application intended for retail clothing stores. Currently its meant to be used directly in store though it may be extended for online stores as well.
This application will show customers how a selected apparel would look on them by showing it on their 3D replica on screen.
It involves 3 steps
Sizing up the customer
Building customer replica 3D humanoid model
Apply simulated cloth on the model
My question is about the feasibility of the project and choice of framework.
Can this be achieved in real time using a normal Desktop computer? If yes what would be appropriate framework ( hardware, software, programming language etc ) for this purpose?
On the work I have done till now, I was planning to achieve above steps in following ways
for step 1 : option a) Two cameras for front and side views or
option b) 1 Kinect or 2 Kinect for complete 3D data
for step 2: either use makehuman (http://www.makehuman.org/) code to build a customised 3D model using above data or build everything from scratch, unsure about the framework.
for step 3: Just need few cloth samples, so thought of building simulated clothes in blender.
Currently I have just the vague idea about different pieces but I am not sure of how to develop complete application.
Theoretically this can be achieved in real time. Many usefull algorithms for video tracking, stereo vision and 3d recostruction are available in OpenCV library. But it's very difficult to build robust solution. For example, you'll probably need to track human body which moves frame to frame and perform pose estimation (OpenCV contains POSIT algorithm), however it's not trivial to eliminate noise in resulting objects coordinates. For inspiration see a nice work on video tracking.
You might want to choose another way, simplify some things, avoid complicated stuff do things less dynamicaly and estimate only clothes size and approximate human location. I this case most likely you will create something usefull and interesting.
I've lost link to one online fiting room where hands and body detection implemented. Using Kinnect solves many problems. But If for some reason you won't use it then AR(augmented reality) helps you (yet another fitting room)
We are developing some stress and strain analysis software at university. Now it's time to move from rectangles and boxes and spheres to some real models. But I still have little idea where to start.
In our software we are going to build mesh and then make calculations, but how do I import solid bodies from CAD/CAE software?
1) How CAD/CAE models are organised? How solid bodies are represented? What are the possibilities of DWG, DXF, IGES, STEP formats? There is e.g. a complete DXF reference, but it's too difficult for me to understand without knowing basic concepts.
2) Are there C++ libraries to import solid bodies from CAD/CAE file formats? Won't it be too difficult to build a complete model to be able to import comprehensive file?
To import solid bodies you first need to export them from the CAD system. Most CAD system datafiles are propriety (unless they've all moved over to XML in the few years I've been out of the industry!). DWG is Autodesk's file format and they don't (well didn't) encourage people to read it directly. They did offer a file reading/writing library if memory serves, but I don't know what the state of that is now. DXF, IGES and STEP are all data transfer formats.
DXF is owned by Autodesk but is published so other companies can use it to read and write models. The DXF reference is complicated, but is just a reference - you need to know the concepts before you can understand what it represents.
Solid models can be represented in a number of ways, either by Constructional Solid Geometry (CSG) where the shape is made up from the addition or subtraction of solid primitives from each other, or by Boundary Representation (B-Rep) where the edges are stored, or by triangulated faces (as used by 3D Studio MAX, WPF and many others) and so on. The particular format will depend on what the modeller is designed to do.
There are libraries and tools for reading the various file formats. I don't know which ones are still active as it's 5+ years since I was heavily involved in 3D graphics. You'd be better off searching for the current crop yourself. I'd recommend starting with Wikipedia - it will have some articles on 3D graphics and there should be plenty of links to further reading and tools/libraries.
Once you have a reader you'll need to convert the data to your internal format - not a trivial task. You might be better off adopting an existing format. One of my jobs was the reading of models from various sources into my company's data structure. My task was greatly helped by the fact that the modellers we supported came with API's that let us read the model meshes directly and from there it was a relatively straightforward (but never easy) task to convert their mesh into ours. There were always edge cases and nuances of the format that caused headaches. These were multiplied several times over if we had to read the file format ourselves - such as for DXF or VRML.
The most common way solid models are represented in current 3D CAD software (CATIA, Pro/Engineer/Solidworks/NX) is through Boundary Representation (B-REP).
However, most of libraries to import such CAD data are proprietary. Some libraries come directly from geometric modelers (such as ACIS with Interop, Parasolid, or Granite), other are from small software companies specialized on the CAD data translation market.
On the open source side, maybe have look at the OpenCascade kernel. This kernel have been open sourced (mostly), and it have some STEP import and meshing functionalities.
Your best bet is to work with an existing open source CAD system, such as BRL-CAD, that includes support for numerous importers and exporters.
Your intuition that learning a given format would be difficult to understand and implement support for is quite true, particularly when dealing with solid geometry formats intended for analysis purposes. Preserving solidity with topological guarantees is important for producing valid analyses, but rarely addressed by simple mesh formats.
In particular for the two prevalent international standards (IGES and STEP), they are excessively complex to support as they can contain the same solid geometry encoded in numerous ways. Consider a simple sphere example. That sphere could be encoded as a simple point and radius (with no explicit surface information, an implicit form common with CSG usage), it could be a polygonal mesh (lossy BREP facets mesh format), it could be a spline surface (BREP NURBS), it could be volumetric (think CT scan data), and more. Focusing on any one of those involves various tradeoffs (simplicity, solidity, analytic guarantees, flexibility, etc).
As mentioned regarding BRL-CAD, it's a large open source solid modeling system that has a lot of functionality in many areas you could leverage, about a dozen libraries of functionality and more than 400 succinct tools (two dozen or so being geometry converters). Even if it doesn't do exactly what you need, you have the source code and can contribute improvements back and collaborate with an existing community to help implement what you need.
Upon re-reading your question, let me completely change my answer. If you all need is meshes, then just use a simple mesh-based format.
OBJ is simple, good, and very standard. Conversion from many CAD formats to OBJ requires a tessellator/mesher, which you don't want to be writing anyway, just get a seat of a CAD package to do the translation. Moi or Rhino are low-cost, and support many formats.
I regularly work with a piece of commercial software for electromagnetic simulations that uses the ACIS modeling kernel and components from Simmetrix. While I can't personally attest to the ease of using those libraries, they do seem to work as advertised and could save you a lot of work. They may not be available on suitable terms for academic use, but they do seem to be designed to do exactly what you want.
As for i know, all of CAD/CAE softwarea support IGES, STEP etc file formats for geometry and ideas, anysis etc for mesh data. Most of time, we find that iges does not contain topological information. But the development of STEP(Standard for the Exchange of Product) started in 1984 as a successor of IGES.The initial plan was that "STEP shall be based on one single, complete, implementation-independent Product Information Model, which shall be the Master Record of the integrated topical and application information models". We have some libraries to read and write these file format. But as i wrote code to read and write geometries as well as mesh, reading or writing these file formats is not difficult, but alot boring.