• An iterative decoding scheme on random burst error correction with Reed-Solomon codes

      Gao, Xin; Univ Arizona, Dept Elect & Comp Engn (INDERSCIENCE ENTERPRISES LTD, 2018)
      We investigate the decoding scheme of conventional Reed-Solomon (R-S) codes, and propose a systematic model to achieve better decoding results on random burst error corrections. We follow the iterative decoding procedure and verify this decoding model by implementing a typical R-S (15, 9) code, then present complexity analysis of this decoding model on the improvements for burst error correction. Simulations on several examples of R-S codes display the validity of this decoding scheme.
    • A thresholding scheme of eliminating false detections on vehicles in wide-area aerial imagery

      Gao, Xin; Univ Arizona, Dept Elect & Comp Engn (INDERSCIENCE ENTERPRISES LTD, 2018)
      Post-processings are usually necessary to reduce false detections on vehicles in wide-area aerial imagery. In order to improve the performance of vehicle detection, we propose a two-stage scheme, which consists of a thresholding method by constructing a pixel-weight based thresholding policy to classify pixels in the greyscale feature map of an automatic detection algorithm followed by morphological filtering. We use two aerial videos for performance evaluation, and compare the automatic detection results with the ground-truth objects. We compute average F-score and percentage of wrong classifications towards six detection algorithms before and after applying the proposed scheme. We measure the variation of overlap ratios from detections to objects, and establish sensitivity analysis to evaluate the performance of proposed scheme by combining it on each of two representative algorithms. Simulation results verify both validity and efficiency of the proposed thresholding scheme, also display the difference of detection performance between datasets and among algorithms.
    • Vehicle detection in wide-area aerial imagery: cross-association of detection schemes with post-processings

      Gao, Xin; Univ Arizona, Dept Elect & Comp Engn (INDERSCIENCE ENTERPRISES LTD, 2018)
      Post-processing schemes are crucial for object detection algorithms to improve the performance of detection in wide-area aerial imagery. We select appropriate parameters for three algorithms (variational minimax optimisation (Saha and Ray, 2009), feature density estimation (Gleason et al., 2011) and Zheng's scheme by morphological filtering (Zheng et al., 2013)) to achieve the highest average F-score on random sample frames, and then follow the same procedure to implement five post-processing schemes on each algorithm. Two low-resolution aerial videos are used as our datasets to compare automatic detection results with the ground truth objects on each frame. The performance analysis of post-processing schemes on each algorithm are presented under two sets of evaluation metrics.