FPGA-Based Robust Ellipse Estimation for Circular Road Sign Detection Samuele Martelli 1 , Roberto Marzotto 2 , Andrea Colombari 2 , Vittorio Murino 1,3 1 Dipartimento di Informatica, University of Verona, 2 eVS embedded Vision Systems S.r.l. 3 IIT Istituto Italiano di Tecnologia, Genova, Italy {samuele.martelli, vittorio.murino}@univr.it, {roberto.marzotto,andrea.colombari}@evsys.net Abstract Estimating parametric curves from images using robust fitting algorithms is a well-known and important computer vision task. We present a complete FPGA design and im- plementation of a fast and robust model fitting algorithm for real-time ellipse detection on video streams. The pro- posed solution relies on a the RANSAC algorithm, modi- fied for FPGA deployment, in combination with an image- preprocessing pipeline in order to perform the intensive pixel-level analysis, reducing each frame to a simple bi- nary image of edges. The design has been developed in a parallel fashion and with specific architectural solutions so as to allow a fast response without degrading the func- tional performances. Experimental results on synthetic and real data show that our implementation, synthesized onto a Xilinx Spartan-3A DSP 3400A device, succesfully runs in real-time with a low resource occupation, while maintain- ing a functionality comparable with the floating-point soft- ware version. 1. Introduction Parametric curve detection and modeling is undoubt- edly one of the fundamental issues in computer vision, which proved to be useful in many real-world applications. Among these, road sign detection constitutes a complex task, recently more and more investigated due to its inclu- sion in Driver Assistance Systems for improved automotive safety. In a typical circular road sign (RS) method, two main issues can be distinguished: the detection, aimed at identi- fying the region of interest (ROI) which may contain a RS; the classification, in which the RS is recognized, assuming that the ROI has been correctly detected [16]. The detec- tion phase is the most important as errors in this stage may severely affect the rest of the processing. This task is also quite difficult since the video sequence is acquired from a moving vehicle, and the images are usually suffering from vibrations, and affected by blurring and non uniform illu- mination. Furthermore, RSs may be partly occluded, dam- aged, or other factors may corrupt the scene making the de- tection more difficult. In addition, the resulting implemen- tation also needs to meet some important requirements like real-time constraints, high reliability and compact size if an embedded platform is employed. While RS classification is often implemented using cor- relation techniques [15], or Artificial Neural Networks (ANNs), RS detection problem has been investigated by many research groups using either colour or shape informa- tion. Most of the leading approaches rely solely on shape analysis are curve fitting methods, like least-square fitting algorithms, Hough Transform (HT) [10], and Random Sam- ple and Consensus (RANSAC) methods [7]. The disadvantages of least square fitting algorithms are well known, being sensitive to the presence of a small number of inaccurately detected edge points solely, due to a moderate noise level. Instead, HT and RANSAC methods became increasingly popular since they can deal with a large set of parametric curves even if data is affected by a large percent- age of outliers. Actually, HT [11, 18] and RANSAC meth- ods [2] are succesfully applied in a wide range of computer vision areas, and have a lot of variants aimed at increasing the efficiency of the basic methods. Basically, HT-based methods transform input data from the image space to a parameter (or accumulator) space, then, by means of a voting mechanism, parametric curves are assigned a score, and the most voted points in the parameter space identify the winner (most probable) curves. In this formulation, it is clear that HT needs a huge amount of memory to store the accumulator space. Specifically in RS detection, several methods have been proposed that try to reduce the computational burden of HT, but embedded implementations still remain demanding in terms of resource allocation. RANSAC-based meth- ods is not suffering from this problem and it is usually preferred because it does not needs to dynamically con- struct accumulators and dynamic memory allocation, which represent a crucial requirement in embedded system design. 1