To detect multiple objects of interest, the methods based on Hough transform use non-maxima supression or mode seeking in order to locate and to distinguish peaks in Hough images. Such postprocessing requires tuning of extra parameters and is often fragile, especially when objects of interest tend to be closely located. In the paper, we develop a new probabilistic framework that is in many ways related to Hough transform, sharing its simplicity and wide applicability. At the same time, the framework bypasses the problem of multiple peaks identification in Hough images, and permits detection of multiple objects without invoking nonmaximum suppression heuristics. As a result, the experiments demonstrate a significant improvement in detection accuracy both for the classical task of straight line detection and for a more modern category-level (pedestrian) detection problem.
Iterations of the Hough-like algorithm for multiple object instances detection:
We used image datasets TUD-crossing and TUD-campus containing mostly profile views of pedestrians in relatively crowded locations. The original annotations provided include only the pedestrians occluded by no more than 50%. As we were interested in the performance of the method under significant overlap, we reannotated the data by marking all pedestrians whose head and at least one leg were clearly visible.
By installing, copying, or otherwise using this Software, you agree to be bound by the terms of the Microsoft Research Shared Source License Agreement (non-commercial use only). If you do not agree, do not install copy or use the Software. The Software is protected by copyright and other intellectual property laws and is licensed, not sold.
The software comes “as is”, with no warranties. This means no express, implied or statutory warranty, including without limitation, warranties of merchantability or fitness for a particular purpose, any warranty against interference with your enjoyment of the software or any warranty of title or non-infringement. There is no warranty that this software will fulfill any of your particular purposes or needs. Also, you must pass this disclaimer on whenever you distribute the software or derivative works.
Neither Microsoft nor any contributor to the software will be liable for any damages related to the software or this msr-ssla, including direct, indirect, special, consequential or incidental damages, to the maximum extent the law permits, no matter what legal theory it is based on. Also, you must pass this limitation of liability on whenever you distribute the software or derivative works.
When using this software, please acknowledge the effort that went into development by referencing the corresponding paper. Note that this is not the original software that was used for the paper mentioned below. It is a re-implementation and requires the Open Computer Vision Library.
If you have questions concerning the source code, please contact obarinova [at] graphics [dot] cs [dot] msu [dot] ru (obarinova [at] graphics [dot] cs [dot] msu [dot] ru.)
Download c++ code for pedestrians detection
Download c++ code for lines detection
Slides from CVPR 2010 [zip]
Talk at CVPR 2010 [link]
This project is supported by Microsoft Research programs in Russia. V. Lempitsky is also supported by EU under ERC grant VisRec no. 228180.