Papers by Keyword: Randomized Hough Transform

Abstract: This paper makes some improvements on Roberts representation for straight line in space and proposes a coarse-to-fine three-dimensional (3D) Randomized Hough Transform (RHT) for the detection of dim targets. Using range, bearing and elevation information of the received echoes, 3D RHT can detect constant velocity target in space. In addition, this paper applies a coarse-to-fine strategy to the 3D RHT, which aims to solve both the computational and memory complexity problems. The validity of the coarse-to-fine 3D RHT is verified by simulations. In comparison with the 2D case, which only uses the range-bearing information, the coarse-to-fine 3D RHT has a better practical value in dim target detection.

Abstract: Lane detection is the key technology of the intelligent vehicle based on machine vision. In order to improve the detection of real-time, a lane detection and prediction algorithm based on Randomized Hough Transform is developed in this paper. The algorithm includes lane detection algorithm and prediction algorithm. First of all at identification stages, scan the pretreated image in order to search lanes candidate points, and combine with the lanes angle range of constraints, fit the candidate boundary points by Randomized Hough Transform for the improvement of real-time and robustness. The driveway line prediction algorithm is also proposed. With the dynamic searching window, weights of prediction are adaptive and they can make the line prediction more accurate. Test results show that algorithm has good real-time and robust performance.

Abstract: This paper presents a track-before-detect (TBD) algorithm for detection of unknown quantity of targets with parabolic tracks. First, eliminate large number of clutters orderly by expanded trellis and the method of mean power. And then get candidate parabolas by Randomized Hough Transform (RHT). The true tracks of the targets are extracted successfully by a strategy of outliers eliminating at last. Experimental results indicate that the proposed algorithm is capable of detecting multiple targets without the assumptions of an upper bound to the number of targets.