Abstract:This study presents the design of an erbium-doped fiber laser (EDFL) featuring switchable wavelength intervals achieved through the implementation of cascaded and parallel Lyot filters. The proposed laser system utilizes a cascaded and parallel configuration of three Lyot filters, facilitated by a polarization beam splitter (PBS) for branch switching. The transmission properties of the filter are analyzed through theoretical modeling and experimental validation using the transmission matrix method. The experimental results are found to be consistent with the theoretical predictions, demonstrating the effectiveness of the proposed design. By adjusting the polarization controllers (PCs), the proposed laser can switch between wavelength spacings of 0.46 nm, 0.27 nm, and 0.76 nm, with a maximum optical signal-to-noise ratio (OSNR) of 38 dB. However, the stability of the laser with a 0.27 nm spacing is not high due to wavelength competition. Power fluctuation for 0.46 nm and 0.76 nm intervals is less than 0.93 dB and 0.78 dB in 1 h, with wavelength fluctuation less than 0.068 nm and 0.19 nm, respectively. This EDFL has the advantages of simple structure, great flexibility, and switchability, which can be applied to fiber optic sensing, wavelength division multiplexing (WDM) networks, and other fields that require a very flexible light source.

Abstract:In this paper, we have demonstrated an Er-doped ultrafast laser with a single mode fiber-gradient index multimode fiber-single mode fiber (SMF-GIMF-SMF, SMS) structure as saturable absorber (SA), which can generate not only stable single-pulse state, but also special mode-locked pulses with the characteristics of high energy and noisy behaviors at proper pump power and cavity polarization state. In addition, we have deeply investigated the real-time spectral evolutions of the mode-locked pulses through the dispersive Fourier transformation (DFT) technique. It can be found that the pulse regime can actually consist of a lot of small noise pulses with randomly varying intensities. We believe that these results will further enrich the nonlinear dynamical processes in the ultrafast lasers.

Abstract:To identify coatings and analyze the anti-detection capabilities of camouflage patterns, material samples can be prepared using the super-pixel segmentation method. A spectral polarization imaging system is developed, based on the principle of bidirectional reflectance distribution function (BRDF), to obtain spectral reflection intensities of coatings at full spatial angles, and use polarization images to calculate the refractive index by the Fresnel equation. The index is then coupled into Torrance-Sparrow model to simulate the spectral scattering intensity to mutually verify the experimental results. The spectral scattering characteristics of standard camouflage patterns are then revealed and pinpoint the signature band and the angle of reflecting sensitivity.

Abstract:A non-orthogonal multiple access (NOMA) power allocation scheme on the basis of the sparrow search algorithm (SSA) is proposed in this work. Specifically, the logarithmic utility function is utilized to address the potential fairness issue that may arise from the maximum sum-rate based objective function and the optical power constraints are set considering the non-negativity of the transmit signal, the requirement of the human eyes safety and all users’ quality of service (QoS). Then, the SSA is utilized to solve this optimization problem. Moreover, to demonstrate the superiority of the proposed strategy, it is compared with the fixed power allocation (FPA) and the gain ratio power allocation (GRPA) schemes. Results show that regardless of the number of users considered, the sum-rate achieved by SSA consistently outperforms that of FPA and GRPA schemes. Specifically, compared to FPA and GRPA schemes, the sum-rate obtained by SSA is increased by 40.45% and 53.44% when the number of users is 7, respectively. The proposed SSA also has better performance in terms of user fairness. This work will benefit the design and development of the NOMA-visible light communication (VLC) systems.

Abstract:We present a gain adaptive tuning method for fiber Raman amplifier (FRA) using two-stage neural networks (NNs) and double weights updates. After training the connection weights of two-stage NNs separately in training phase, the connection weights of the unified NN are updated again in verification phase according to error between the predicted and target gains to eliminate the inherent error of the NNs. The simulation results show that the mean of root mean square error (RMSE) and maximum error of gains are 0.131 dB and 0.281 dB, respectively. It shows that the method can realize adaptive adjustment function of FRA gain with high accuracy.

Abstract:Embodied visual exploration is critical for building intelligent visual agents. This paper presents the neural exploration with feature-based visual odometry and tracking-failure-reduction policy (NeOR), a framework for embodied visual exploration that possesses the efficient exploration capabilities of deep reinforcement learning (DRL)-based exploration policies and leverages feature-based visual odometry (VO) for more accurate mapping and positioning results. An improved local policy is also proposed to reduce tracking failures of feature-based VO in weakly textured scenes through a refined multi-discrete action space, keyframe fusion, and an auxiliary task. The experimental results demonstrate that NeOR has better mapping and positioning accuracy compared to other entirely learning-based exploration frameworks and improves the robustness of feature-based VO by significantly reducing tracking failures in weakly textured scenes.

Abstract:Accurately identifying building distribution from remote sensing images with complex background information is challenging. The emergence of diffusion models has prompted the innovative idea of employing the reverse denoising process to distill building distribution from these complex backgrounds. Building on this concept, we propose a novel framework, building extraction diffusion model (BEDiff), which meticulously refines the extraction of building footprints from remote sensing images in a stepwise fashion. Our approach begins with the design of booster guidance, a mechanism that extracts structural and semantic features from remote sensing images to serve as priors, thereby providing targeted guidance for the diffusion process. Additionally, we introduce a cross-feature fusion module (CFM) that bridges the semantic gap between different types of features, facilitating the integration of the attributes extracted by booster guidance into the diffusion process more effectively. Our proposed BEDiff marks the first application of diffusion models to the task of building extraction. Empirical evidence from extensive experiments on the Beijing building dataset demonstrates the superior performance of BEDiff, affirming its effectiveness and potential for enhancing the accuracy of building extraction in complex urban landscapes.

Abstract:Aiming at the problems of low detection efficiency and difficult positioning of traditional steel surface defect detection methods, a lightweight steel surface defect detection model based on you only look once version 7 (YOLOv7) is proposed. First, a cascading style sheets (CSS) block module is proposed, which uses more lightweight operations to obtain redundant information in the feature map, reduces the amount of computation, and effectively improves the detection speed. Secondly, the improved spatial pyramid pooling with cross stage partial convolutions (SPPCSPC) structure is adopted to ensure that the model can also pay attention to the defect location information while predicting the defect category information, obtain richer defect features. In addition, the convolution operation in the original model is simplified, which significantly reduces the size of the model and helps to improve the detection speed. Finally, using efficient intersection over union (EIOU) loss to focus on high-quality anchors, speed up convergence and improve positioning accuracy. Experiments were carried out on the Northeastern University-defect (NEU-DET) steel surface defect dataset. Compared with the original YOLOv7 model, the number of parameters of this model was reduced by 40%, the frames per second (FPS) reached 112, and the average accuracy reached 79.1%, the detection accuracy and speed have been improved, which can meet the needs of steel surface defect detection.

Abstract:There is a problem of real-time detection difficulty in road surface damage detection. This paper proposes an improved lightweight model based on you only look once version 5 (YOLOv5). Firstly, this paper fully utilized the convolutional neural network (CNN) + ghosting bottleneck (G_bneck) architecture to reduce redundant feature maps. Afterwards, we upgraded the original upsampling algorithm to content-aware reassembly of features (CARAFE) and increased the receptive field. Finally, we replaced the spatial pyramid pooling fast (SPPF) module with the basic receptive field block (BasicRFB) pooling module and added dilated convolution. After comparative experiments, we can see that the number of parameters and model size of the improved algorithm in this paper have been reduced by nearly half compared to the YOLOv5s. The frame rate per second (FPS) has been increased by 3.25 times. The mean average precision (mAP@0.5:0.95) has increased by 8%—17% compared to other lightweight algorithms.