Quantization effect of the parameter space on the performance of hough detector

Hough transform is proposed in literature as an effective technique for target detection in search radars. However, this detector has a disadvantage when the received SNR of radar is low. Although the distribution of noise power in the data space is often uniform and all processing cells of this space approximately receive the same power of noise, after transforming these cells to the Hough parameter space, this distribution will not remain uniform. In other words, noise power in some regions of the parameter space is greater than the others. Therefore, false alarm increases in these regions. Selecting a greater threshold to reduce the number of false detections will result a lower probability of detection in lower SNR cases. In this paper, a new quantization method is used for the parameter space which is based on the Maximum Entropy Quantization. It is verified through simulation results that by using this method, the distribution of noise power in this space will become uniform and the average probability of false alarm will be the same for all parameter cells. Also, the performance of Hough detector with a non-uniform quantized parameter space is compared to uniform quantized one through simulation scenarios and it is shown that an improvement of about 2dB results in the required SNR. A method is also introduced to solve the above mentioned problem of the Hough detector for the cases in which the distribution of noise power in the data space is not known.