<html><head></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">Hello Rodrigo, copy-pasting my response from OpenCV user group. <div><br></div><div>I think it is a great initiative and I am looking forward to see such a framework. OpenCV has a lot of infrastructure on object detection that you might want to look at, such as cascade classifier training, several machine learning classifiers and feature extraction methods. I really want to see OpenCV as a library that makes it easy to create an object detection application. OpenCV 2.2 will have some of what you call "install, run, see the graphs coming out" functionality such as a sample running bag-of-words object class detection on PASCAL VOC datasets. This framework can be used for generic object detector training too (PASCAL data structures + OpenCV methods for reading them). </div><div><br></div><div>Having said that, I have to admit that OpenCV does not have a generic framework for training a detector for any type of object. And here is why: the problem is not solved yet. There are a few problems that are solved up to quality accepted by industry, face detection is one of the famous. If you look at the ROC curves from PASCAL VOC papers, a lot of them are far on the research side. OpenCV 2.2 will have two methods for detecting object classes: latent SVM and color descriptors with bag of words. Even if we try now to join them into a single framework, this will be quite hard -- the algorithms are too different. But since this is still a research problem, both approaches might change a lot over a couple of years and this will render our efforts useless. </div><div><br></div><div>So my suggestion is to select the bits and pieces of object detection that are likely to survive and implement a framework for them. I already mentioned VOC datasets -- it is very important to have a data structure definition to work with. Local descriptors will be put in such a framework in OpenCV 2.2, this is a good example of "stable" functionality in my opinion.</div><div><br></div><div>Best Regards, Victor</div><div><br></div><div><div>On Nov 22, 2010, at 12:09 AM, Rodrigo Benenson wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><div class="gmail_quote"><span class="Apple-style-span" style="font-family: arial, sans-serif; white-space: pre-wrap; ">Hello all.</span><br><div><span style="font-family:arial, sans-serif;white-space:pre-wrap"><ul style="padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;margin-top:0px;margin-right:0px;margin-bottom:0px;margin-left:0px">
<br>I'm contacting you because I am considering starting a new open source project to solve a specific problem: training and evaluating objects detection algorithms. <br><br>Hundreds of students have been there before: "I want to create a program that detects objects in images".<br>
They choose a dataset for training (e.g. INRIA pedestrians), a feature descriptor (e.g. HOG), a machine learning method (e.g. linear SVM), and then, they write the code to get it all together.<br><br>In the best case they will take bits and pieces from multiple places and spend a few weeks on the glue code. In the worst case they will spend months reimplementing existing methods.<br>
<br>It is time to stop the madness.<br>Training detectors for objects detection in images is a specific and well defined problem. <br>It is time to share our effort and build a reference open source tool to solve this common problem.<br>
We should have an open source tool that provides all the common bits, the glue and allows us to focus on what we really care: the algorithms.<br><br>In some sense <a href="http://www.google.com/url?sa=D&q=http%3A%2F%2Fopencv.willowgarage.com%2F" style="font-family:arial, sans-serif;color:rgb(0, 62, 168)" target="_blank">OpenCv</a> 2.2 helps a lot to the task, however OpenCv is aimed to be a generic library not a specific application framework. In that sense it will never provide the desired "install, run, see the graphs coming out" experience.<br>
<br>Also <a href="http://www.google.com/url?sa=D&q=http%3A%2F%2FROS.org" style="font-family:arial, sans-serif;color:rgb(0, 62, 168)" target="_blank">ROS.org</a> helps a lot the task, by providing a generic framework to create and exchange software modules, along with standard tools for messages passing, data storage and exploration. However this framework by itself has a non negligible learning curve and it is unfamiliar to anyone outside the robotics community.<br>
<br></ul><ul style="padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;margin-top:0px;margin-right:0px;margin-bottom:0px;margin-left:0px"><br>I currently have my own idea of how things could be. However before creating "yet one more framework" I would like to have <i>your</i> input on the topic.<br>
<br>I have created a short form to collect your opinions. I would be very glad if you could help me go in the right direction by giving your input.<br><br><a href="http://www.google.com/url?sa=D&q=https%3A%2F%2Fspreadsheets.google.com%2Fviewform%3Fformkey%3DdFFzaDlLM1liVGNOS2FENnhrc1VWckE6MQ" style="font-family:arial, sans-serif;color:rgb(0, 62, 168)" target="_blank">https://spreadsheets.google.com/viewform?formkey=dFFzaDlLM1liVGNOS2FENnhrc1VWckE6MQ</a><br>
<br>The form is anonymous and the results are public. <br><br>Based your opinions and ideas I will do my best to move forward an usable open source solution.<br>Further information will be posted at<br><a href="http://www.google.com/url?sa=D&q=https%3A%2F%2Fwave.google.com%2Fwave%2Fwaveref%2Fgooglewave.com%2Fw%2ByH-HOCb6H" style="font-family:arial, sans-serif;color:rgb(0, 62, 168)" target="_blank">https://wave.google.com/wave/waveref/googlewave.com/w+yH-HOCb6H</a> <br>
<br>Best regards,<br><font color="#888888">rodrigo benenson phd.<br></font><br>ps: If you are interested do not hesitate to send me a message. You can contact me via github as "rodrigob".<span></span><span> </span></ul>
</span></div>
</div><br>
_______________________________________________<br>ros-users mailing list<br><a href="mailto:ros-users@code.ros.org">ros-users@code.ros.org</a><br>https://code.ros.org/mailman/listinfo/ros-users<br></blockquote></div><br></body></html>