Deep learning-based video watermarking is shown to be effective in improving robustness. However, existing methods neglect the enhancement of long-distance spatio-temporal features and the representation of the inter-frame difference and the intra-frame difference, which lead to poor robustness against H.264 compression and low compatibility with high-definition (HD) and full high-definition (FHD) videos for copyright protection, respectively. To address these issues, we propose a robust and compatible video watermarking network (RC-VWN) based on spatio-temporal enhancement and multiscale pyramid attention. For robustness, RC-VWN extracts long-distance spatio-temporal features using a central difference 3D U-Net and enhances them through multiscale spatio-temporal fusion, which alleviates the loss of the watermark caused by attacks through the association of long-distance spatio-temporal features. Then, the simulated compression network is developed to simulate H.264 compression with high-accuracy, which guides the decoder to recover the watermark accurately. For compatibility, a multiscale pyramid attention is designed to represent the intra-frame difference and the inter-frame difference effectively. Experimental results demonstrate that RC-VWN outperforms the state-of-the-art methods with higher robustness and imperceptibility under quantitative evaluation and visual quality. Furthermore, RC-VWN exhibits high compatibility with various videos, including HD and FHD videos, ensuring effective copyright protection.

Seafloor sediment surveys play a crucial role in providing invaluable information and guidance for ocean monitoring and management. In recent years, the combination of multibeam echosounder (MBES) data and field samples has become one of the most widespread approaches for seafloor sediment supervised classification. However, owing to the limitations of low efficiency, high complexity and high cost of seabed in situ sampling, ground truth sample data tend to have a small size, which impedes the training and deployment of classifiers. In light of the aforementioned issues, this paper proposed a seabed sediment sample enhancement method on the basis of superpixel segmentation and active learning. First, we introduce superpixel multi-resolution segmentation to effectively expand the training sample set, which takes into account the different weights of the input features. Subsequently, poor samples in the new sample set are removed using an active learning technique to improve the quality of labels. In the end, 33 original sample points are augmented to a total of 6097 valid sample points. To validate the effectiveness of our strategy, the new sample set is employed for the supervised classification of MBES data in the Southern North Sea, UK. The experimental results show that the classification accuracy of our sample enhancement method reaches 86.67%, which is a significant improvement over that of the original sample set and traditional sample enhancement methods.

In this study, the authors investigate the performance of iterative detection and decoding for non‐binary low‐density parity‐check (LDPC) coded partial‐response (PR) channels, where written‐in errors are present to introduce bit‐flipping to LDPC code bits prior to the transmission over PR channels. From a probabilistic perspective, the written‐in errors are modelled as the output of a binary symmetrical channel (BSC) with crossover probability equal to the write error probability. Several iterative receivers are presented for the considered system. Specifically, the authors propose a symbol‐level Bahl‐Cocke‐Jelinek‐Raviv (BCJR) channel detector based on a sectionalised representation of the joint BSC and PR trellis to produce directly the soft information of non‐binary LDPC code symbols, thus avoiding suboptimal symbol/bit log‐likelihood ratio conversions as required in bit‐level detection schemes. Simulation results show that the proposed symbol‐level iterative receiver provides much better bit‐error‐rate performance over bit‐level schemes. Moreover, the proposed receiver enables non‐binary LDPC codes to achieve a notable coding gain over their binary counterparts for channels affected with written‐in errors.

In this paper, we propose an iterative symbol-level detection and decoding scheme for nonbinary low-density parity-check (LDPC) coded generalized two-dimensional (2D) intersymbol interference (ISI) channels. The proposed 2D channel detector consists of two constituent detectors that work iteratively to mitigate downtrack and crosstrack interference. The downtrack detector is based on the nonbinary BCJR algorithm; while the crosstrack detector performs the sum-product algorithm (SPA) over a cycle-free symbol-level factor graph of the crosstrack channel, which can be directly concatenated to the nonbinary LDPC code graph without resorting to bit/symbol log-likelihood ratio (LLR) conversions. Simulation results show that the proposed symbol-level receiver outperforms bit-level schemes and also enables nonbinary LDPC codes to achieve a noticeable performance gain over binary codes when transmitted over severely ISI-distorted 2D channels.

This paper proposes efficient distance-enhancing constrained codes with parity-check (PC) constraints for data storage channels. We first propose simple and efficient finitestate encoding methods to design various distance-enhancing constrained codes, including a repeated minimum transition runlength (RMTR) code for optical recording channels, as well as a maximum transition run (MTR) code for magnetic recording channels. We further propose a general and systematic code design methodology, which can efficiently combine constrained codes with PC codes. The constrained codes can be any distanceenhancing constrained codes. The PC codes can be any linear binary PC codes. The rates of the designed codes are only a few tenths of a percent below the theoretical maximum. The proposed method enables soft information to be available to the PC decoder and soft decoding of PC codes. Examples of several newly designed distance-enhancing constrained PC codes are illustrated. Simulation results with blu-ray disc (BD) systems show that the proposed new RMTR code and RMTR constrained 4-bit PC code perform 0.2 dB and 0.85 dB better than the standard 17PP code, respectively, at error correction code (ECC) failure rate (EFR) of 10-12and high recording density.

This paper proposes distance-enhancing constrained codes for optical recording channels. The repeated minimum transition runlength (RMTR) constraints are first investigated, based on error event analysis and capacity calculation. A new RMTR constrained code is then proposed. Compared with the codes used in standard systems, it imposes the minimum achievable RMTR constraint on the channel bit stream with the least decoding window length, without introducing additional code rate loss. A systematic method is further proposed, which can efficiently combine the RMTR code with the parity-check (PC) codes. Simulation results show that the new RMTR constrained PC code performs 1.1 dB better than the 17PP code, at BER = 10-5and high recording density.

The full-complexity soft-input/soft-output (SISO) detector based on the BCJR algorithm for coded partial-response channels has a computational complexity growing exponentially with channel memory length. In this letter, we propose a low complexity soft-output channel detector based on the Chase decoding algorithm, which was previously applied to decode turbo product codes. At each iteration, the proposed detector forms a candidate list using all possible combinations of bit patterns in the weakest indices based on tentative hard estimates and a priori information fed back from the outer decoder. To demonstrate the performance/complexity tradeoff of the proposed detector, simulation results over rate-8/9 turbo-coded EPR4 and ME/sup 2/PR4 channels are presented, respectively. It is shown that the proposed detector can significantly reduce the computational complexity with only a small performance loss compared to the BCJR algorithm.

In this contribution, we consider iterative multiuser detection over coded code-division multiple-access (CDMA) channels from a combinatorial optimization viewpoint and propose a low-complexity soft-input/soft-output (SISO) multiuser detector based on the k-opt local search (LS) algorithm, which was previously used for solving the traveling salesperson problem (TSP). Simulation results and complexity analysis show that the proposed detector can approach closely the performance of the full-complexity a posteriori probability (APP) multiuser detector over highly correlated convolutionally coded channels.

The full-complexity soft-input/soft-output (SISO) multiuser detector based on the a posteriori probability (APP) algorithm has a computational complexity growing exponentially with the number of users. In this paper, we consider the multiuser detection problem from a combinatorial optimization viewpoint and develop a novel class of SISO multiuser detectors based on local search (LS) heuristics. By restricting the search to a small subset of the solution space and producing the APP based on a candidate list of potential solutions, the proposed detector can achieve bit-error-rate (BER) performance close to that of the APP algorithm with a significantly lower computational complexity.

The conventional multiuser detector (MUD) based on the a posteriori probability (APP) algorithm has an exponential computational complexity in terms of the number of users. In this paper, we propose a low-complexity iterative multiuser receiver for synchronous turbo-coded code-division multiple-access (CDMA) systems. The proposed receiver is based on the Chase decoding algorithm that was previously used to decode turbo product codes. Simulation results show that the proposed receiver can significantly reduce the computational complexity with slight performance degradation compared with the APP MUD over highly correlated channels. Moreover, in this paper, we develop a numerical approach to analyze the convergence behavior of iteratively decoded CDMA channels based on density evolution technique. Analytical results are presented and shown to provide a reasonable match with what is observed in simulation.

The conventional maximum a posteriori receiver for coded code-division multiple-access (CDMA) systems has exponential computational complexity in terms of the number of users and the memory of the channel code. In this letter, we propose a low-complexity soft-input soft-output (SISO) multiuser detector based on the reduced-state a posteriori probability algorithm. Per-survivor processing and soft interference cancellation are used to remove the residual past and future interference in the branch metric computation. The complexity of the proposed receiver is related to the reduced memory of the CDMA channel and can be adjusted according to the complexity/performance tradeoff. Simulation results show that for asynchronous convolutionally coded systems, the proposed receiver can achieve the near-single-user performance for moderate to high signal-to-noise ratios.

We propose iterative multiuser detectors for asynchronous code-division multiple-access with parallel-concatenated convolutional codes (turbo codes) and with serially concatenated convolutional codes (SCCC). At each iteration we update and exchange the extrinsic information from the multiuser detector and channel decoders and regenerate soft information between constituent convolutional decoders. Simulation results show that with the proposed structure, near-single-user performance can be achieved. We also propose two reduced-complexity techniques, i.e., the reduced-state iterative multiuser detector based on the T-MAP algorithm and the iterative interference canceler based on a noise-whitening filter. Simulation results show a small performance degradation for these two techniques, particularly for the T-MAP receiver.