Fast Hough transform: A hierarchical approach
Computer Vision, Graphics, and Image Processing
Computer Vision, Graphics, and Image Processing
A new curve detection method: randomized Hough transform (RHT)
Pattern Recognition Letters
Perception sensor for a mobile robot
Real-Time Imaging - Special issue on special-purpose architectures for real-time imaging, part 2
A real-time image segmentation on a massively parallel architecture
Real-Time Imaging
Implementation of low level image processing algorithms on a reconfigurable perception system
CAMP '95 Proceedings of the Computer Architectures for Machine Perception
A New Multilevel Line-Based Stereo Vision Algorithm Based on Fuzzy Techniques
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
On using the CAM concept for parametric curve extraction
IEEE Transactions on Image Processing
Hi-index | 0.00 |
The aim of this paper is to present a parallel hardware architecture well dedicated for complex two-dimensional (2D) and three-dimensional (3D) video processing. It is composed of a mixture of Digital Signal Processing (DSP) and Field Programmable Gate Array (FPGA) technologies and uses the Content Addressable Memory (CAM) as a main processing unit. Some applications ranging from accurate 2D segment extraction to 3D segment reconstruction have been successfully implemented. Their common characteristic is to use the Hough Transform (HT) as the basic concept, augmented with some modifications in order to make them well adapted to the hardware, and in addition to resolve some of their classical problems. This may include quantization errors, huge memory-processing requirements of the parameter space, and occlusion. Experimental results indicate that a small amount of hardware, mounted on a PC board, can deliver real-time performance and high accuracy. This is an improvement over previous systems, where execution time of the second-order using a greater amount of hardware has been proposed.