Infrared small target detection (IRSTD) has been a long challenging task in infrared detection technology due to the inherently low contrast and absence of discernible texture in such targets. To address this issue, a new U-shaped segmentation network (CN-UNet) is proposed in this article. CN-UNet first employs the ConvNeXt module as the encoder, which implements a self-attention mechanism through pure convolutional operations, mirroring the Swin Transformer’s functionality while expanding the receptive field interactions of target features. This design not only optimizes computational efficiency but also enables multiscale feature identification across diverse dimensional contexts. Besides, a multiscale local contrast learning module (MSLCLM) is integrated into the encoder-decoder cross layer connections to selectively filter features aligned with human visual priors, thereby directing the network’s attention toward precise target localization. Finally, during the model inference, a slicing-aided hypersegmentation module is introduced to dynamically rescale output images through adaptive slicing operations, which could furtherly improve infrared target detection and segmentation performance. Comprehensive evaluations across three typical benchmarks demonstrate that the proposed CN-UNet is superior to other state-of-the-art IRSTD methods, with better visual quality and index evaluation metrics.

Infrared small target detection (IRSTD) remains a long challenging problem in infrared imaging technology. To enhance detection performance while more effectively exploiting target-specific characteristics, a novel U-shaped segmentation network called knowledge-embedded CSwin-UNet (KECS-Net) is proposed in this letter. KECS-Net first incorporates a CSwin transformer module into the encoder of the UNet backbone, enabling the extraction of multiscale features from infrared targets within an expanded receptive field, while achieving higher computational efficiency compared to the original Swin transformer. Besides, a multiscale local contrast enhancement module (MLCEM) is introduced, which utilizes hand-crafted dilated convolution operators to amplify locally salient target responses and suppress background noise, thereby guiding the model to focus on potential target regions. Finally, a slicing-aided hypersegmentation (SAHS) method is also designed to resize and rescale the output image, increasing the relative size of small targets and improving segmentation accuracy during inference. Extensive experiments on three benchmark datasets demonstrate that the proposed KECS-Net outperforms the state-of-the-art (SOTA) methods in both quantitative metrics and visual quality. Relevant code will be available at https://github.com/Lilingxiao-image/KECS-Net

Chromatic dispersion-enhanced signal-signal beating interference (SSBI) considerably affects the performance of intensity-modulation and direct-detection (IM/DD) fiber transmission systems. For recovering optical fields from received double sideband signals after propagating through IM/DD transmission systems, Gerchberg-Saxton (G-S) iterative algorithms are promising, which, however, suffers slow convergence speeds and local optimization problems. In this paper, we propose a multi-constraint iterative algorithm (MCIA) to extend the Gerchberg-Saxton-based linearized detection. The proposed technique can accelerate the convergence speed and realize nonlinear-equalization-free detection. Based on the data-aided iterative algorithm (DIA) and the decision-directed data-aided iterative algorithm (DD-DIA), the proposed technique reuses redundant bits from channel coding to not only correct decision errors but also enforce the constraints on the task function to further accelerate the whole optical field retrieval processing. Simulation results show that, compared with the DD-DIA, the MCIA reduces the received optical power (ROP) by about 1.5-dB for a 100-Gb/s over 50-km SSMF PAM-4 signal transmission at the symbol error rate (SER) of 2×10⁻². For a 100-Gb/s over 400-km SSMF transmission system, just 30 MCIA iterations is needed, which is 30% reduction in iteration count compared with the DD-DIA. For further increased transmission capacities, the MCIA can improve the SER by two orders of magnitude compared with the conventional IA. To validate the effectiveness of the MCIA, we also conduct experiments to transmit 92-Gb/s PAM-4 signals over 50-km IM/DD fibre systems. We find that the MCIA has a 1-dB ROP improvement compared with the DD-DIA. Compared with Volterra nonlinear equalization, the BERs of the MCIA with a simple linear equalizer are reduced by more than one order of magnitude with only 52 MCIA iterations.

Infrared imaging systems are widely used across industries. However, their output images often exhibit striped noise due to the nonuniform response of the detection system, which significantly affects image quality and visual fidelity. To address challenges such as incomplete stripe removal, potential loss of image details and textures, and the generation of artificial artifacts during destriping, we propose a novel stripe removal method based on a knowledge-embedded diffusion model (KEDM). This approach effectively integrates the spatial distribution characteristics of stripe noise with an innovative, data-driven diffusion network model, creating a hybrid knowledge and data-driven framework for stripe correction. The core components of KEDM are the latent diffusion model (LDM) architecture and the directional wavelet convolution module (DWCM). Specifically, LDM leverages a pretrained variational autoencoder (VAE) to transform the input image into latent feature space for efficient diffusion propagation, reducing computational complexity while preserving image restoration quality. Meanwhile, DWCM uses wavelet convolution operations to construct prior loss functions for stripe noise, precisely guiding the diffusion reconstruction process to achieve a clean, stripe-free image. Empirical evaluations on several benchmark datasets demonstrate that the proposed KEDM outperforms other state-of-the-art destriping algorithms in terms of visual quality and quantitative metrics, validating its excellent performance.

In PON-based mobile fronthauls, direct inter-ONU communications without passing end-user traffic to the OLT offer a promising solution for fulfilling the stringent latency and bandwidth requirements of 5G and beyond networks. In this paper, with slight modifications to the PON remote node, a concurrent inter-ONU and upstream communication technique is proposed and experimentally demonstrated in 101.6Gbit/s multipoint-to-point hybrid SSB OFDM digital filter multiple access (DFMA) IMDD PONs over 25km SSMFs. Multiple gapless inter-ONU and upstream SSB signals are aggregated by digital orthogonal filtering in each ONU transmitter. A single FFT operation is applied for demultiplex and demodulation in the OLT/ONU receivers. The results show that for both the inter-ONU and upstream transmissions, the optimum length of digital filters is 32, based on which the power penalties due to the fiber transmission and ONU channel interference are <1dB and 30% improvements in aggregated signal transmission capacity. In addition, detailed experimental investigations are also undertaken of the trade-off between differential ONU optical launch power dynamic range and aggregated signal transmission capacity. An approximately 1dB increase in ONU launch power dynamic range is achievable by reducing the aggregated signal transmission capacity by 5Gbit/s.

Known hybrid orthogonal frequency division multiplexing-digital filter multiple access (OFDM-DFMA) PONs show promise of seamless and cost-effective convergence of optical and mobile networks for 5G and beyond. This paper reports, for the first time, a new hybrid OFDM-DFMA PON based on intensity modulation and direct detection (IMDD), obtained by modifying digital signal processing (DSP) algorithms embedded in both the OLT and ONUs. The proposed PON allows two spectrally overlapped sub-bands to occupy each individual sub-wavelength spectral region to independently transmit upstream ONU information. A model of the proposed PON is developed and its upstream transmission performances are numerically explored for different application scenarios. Compared with the previously published PON, the proposed PON doubles the number of supported ONUs and provides >1.7-fold aggregate upstream signal transmission capacity increases with 2.2-fold aggregate upstream signal transmission capacity increases and >0.7dB upstream power budget improvements are achievable. The performance improvements vary by <18% for a transmission distance range as large as 50km. In addition, the proposed PON is tolerant to finite digital filter tap length-induced channel interferences.