Integrated electromagnetic sensing system based on a deep-neural-network-intervened genetic algorithm
Borui Wu, Tonghao Liu, Guangming Wang, Xingshuo Cui, Yuxin Jia, Yani Wang, and Huiqing Zhai
With the deepening integration of artificial intelligence (AI) and the Internet of Things (IoT) in daily life, electromagnetic sensing presents both attraction and increasing challenges, especially in the diversification, accuracy, and integration of sensing technologies. The remarkable ability of metasurfaces to manipulate electromagnetic waves offers promising solutions to these challenges. Herein, an integrated system for electromagnetic sensing and beam shaping is proposed. Improved genetic algorithms (GAs) are employed to design the metasurface with desired beams, while spatial electromagnetic signals sensitized by the metasurface are input into the GA enhanced by deep neural networks to sense the number of targets, their azimuths, and elevations. Subsequently, the metasurface device is designed as the hybrid mode combining tracking and avoidance in alignment with practical requirements and sensing outcomes. Simulation and experimental results validate the efficiency and accuracy of each module within the integrated system. Notably, the target sensing module demonstrates the capability to precisely sense more than 10 targets simultaneously, achieving an accuracy exceeding 98% and a minimum angular resolution of 0.5°. Our work opens, to our knowledge, a new avenue for electromagnetic sensing, and has tremendous application potential in smart cities, smart homes, autonomous driving, and secure communication.
  • Jan. 28, 2025
  • Photonics Research
  • Vol. 13, Issue 2, 387 (2025)
  • DOI:10.1364/PRJ.538732
Optical neural networks based on perovskite solar cells
Kaicheng Zhang, Jonathon Harwell, Davide Pierangeli, Claudio Conti, and Andrea Di Falco
Optical neural networks (ONNs) are a class of emerging computing platforms that leverage the properties of light to perform ultra-fast computations with ultra-low energy consumption. ONNs often use CCD cameras as the output layer. In this work, we propose the use of perovskite solar cells as a promising alternative to imaging cameras in ONN designs. Solar cells are ubiquitous, versatile, highly customizable, and can be fabricated quickly in laboratories. Their large acquisition area and outstanding efficiency enable them to generate output signals with a large dynamic range without the need for amplification. Here we have experimentally demonstrated the feasibility of using perovskite solar cells for capturing ONN output states, as well as the capability of single-layer random ONNs to achieve excellent performance even with a very limited number of pixels. Our results show that the solar-cell-based ONN setup consistently outperforms the same setup with CCD cameras of the same resolution. These findings highlight the potential of solar-cell-based ONNs as an ideal choice for automated and battery-free edge-computing applications.
  • Jan. 28, 2025
  • Photonics Research
  • Vol. 13, Issue 2, 382 (2025)
  • DOI:10.1364/PRJ.542564
Photonic-frequency-interleaving-enabled broadband receiver with high reconfigurability and scalability
Jianwei Liu, Ruixuan Wang, Jiyao Yang, Weichao Ma, Henan Zeng, Chenyu Liu, Wen Jiang, Xiangpeng Zhang, Qinyu Xie, and Wangzhe Li
The photonic frequency-interleaving (PFI) technique has shown great potential for broadband signal acquisition, effectively overcoming the challenges of clock jitter and channel mismatch in the conventional time-interleaving paradigm. However, current comb-based PFI schemes have complex system architectures and face challenges in achieving large bandwidth, dense channelization, and flexible reconfigurability simultaneously, which impedes practical applications. In this work, we propose and demonstrate a broadband PFI scheme with high reconfigurability and scalability by exploiting multiple free-running lasers for dense spectral slicing with high crosstalk suppression. A dedicated system model is developed through a comprehensive analysis of the system non-idealities, and a cross-channel signal reconstruction algorithm is developed for distortion-free signal reconstruction, based on precise calibrations of intra- and inter-channel impairments. The system performance is validated through the reception of multi-format broadband signals, both digital and analog, with a detailed evaluation of signal reconstruction quality, achieving inter-channel phase differences of less than 2°. The reconfigurability and scalability of the scheme are demonstrated through a dual-band radar imaging experiment and a three-channel interleaving implementation with a maximum acquisition bandwidth of 4 GHz. To the best of our knowledge, this is the first demonstration of a practical radio-frequency (RF) application enabled by PFI. Our work provides an innovative solution for next-generation software-defined broadband RF receivers.
  • Jan. 28, 2025
  • Photonics Research
  • Vol. 13, Issue 2, 395 (2025)
  • DOI:10.1364/PRJ.533960
Optical polarized orthogonal matrix
Shujun Zheng, Jiaren Tan, Xianmiao Xu, Hongjie Liu, Yi Yang, Xiao Lin, and Xiaodi Tan
Multiplexing technology serves as an effective approach to increase both information storage and transmission capability. However, when exploring multiplexing methods across various dimensions, the polarization dimension encounters limitations stemming from the finite orthogonal combinations. Given that only two mutually orthogonal polarizations are identifiable on the basic Poincaré sphere, this poses a hindrance to polarization modulation. To overcome this challenge, we propose a construction method for the optical polarized orthogonal matrix (OPOM), which is not constrained by the number of orthogonal combinations. Furthermore, we experimentally validate its application in high-dimensional multiplexing of polarization holography. We explore polarization holography technology, capable of recording amplitude, phase, and polarization, for the purpose of recording and selective reconstruction of polarization multi-channels. Our research reveals that, despite identical polarization states, multiple images can be independently manipulated within distinct polarization channels through orthogonal polarization combinations, owing to the orthogonal selectivity among information. By selecting the desired combination of input polarization states, the reconstructed image can be switched with negligible crosstalk. This non-square matrix composed of polarization unit vectors provides prospects for multi-channel information retrieval and dynamic display, with potential applications in optical communication, optical storage, logic devices, anti-counterfeiting, and optical encryption.
  • Jan. 28, 2025
  • Photonics Research
  • Vol. 13, Issue 2, 373 (2025)
  • DOI:10.1364/PRJ.540120
Single-Image Super-Resolution Reconstruction Based on Improved Attention in A2N
Hualiang Cao, and Wei Zhuang
The study on attention in attention network (A2N) in single-image super-resolution has revealed that all attention modules are not beneficial to the network. Therefore, in the design of the network, input features can be divided into attention and nonattention branches. The weights on these branches can be adaptively adjusted using dynamic attention modules based on the input features so that the network can strengthen useful features and suppress unimportant features. In practical applications, lightweight networks are suitable to be run on resource-constrained devices. Based on A2N, the number of attention in attention block (A2B) in the original network is reduced and lightweight receptive field modules are introduced to enhance the overall performance of the network. In addition, by adjusting the L1 loss to a combination loss based on Fourier transform, the spatial domain of the image is transformed into the frequency domain, enabling the network to learn the frequency characteristics of the image. The experimental results show that the improved A2N reduces parameter count by about 25%, computational complexity by about 20%, and inference speed by 15%, thereby enhancing the performance.
  • Jan. 25, 2025
  • Laser & Optoelectronics Progress
  • Vol. 62, Issue 2, 0237010 (2025)
  • DOI:10.3788/LOP241193
GELAN-YOLOv8 Algorithm for Contraband Detection in X-Ray Image
Yuanxiang Luo, Chunlin Liu, and Xiang Li
Aiming at the problems of low detection accuracy and missed detection caused by complex contour information, large change of shape and small size contraband in X-ray images, an improved GELAN-YOLOv8 model based on YOLOv8 is proposed. First, the RepNCSPELAN module based on generalized efficient layer aggregation network (GELAN) is introduced to improve the feature extract ability for contraband. Second, the GELAN-RD module is proposed by combining deformable convolution v3 (DCNv3) and RepNCSPELAN module to adapt contraband with different postures and serious changes in size and angle. Third, the spatial pyramid pooling is improved, so that the model can pay more attention to the feature information of small target contraband. Finally, the Inner-ShapeIoU is proposed by combining inner-intersection over union (Inner-IoU) and Shape-IoU to reduce the false detection and missed detection and speed up the convergence of the model. Results on the SIXray dataset show that the mAP@0.5 of the improved algorithm are 2.8 percentage points higher than YOLOv8n, and the performance is better than YOLOv8s. The GELAN-YOLOv8 effectively realizes the real-time detection of contraband in X-ray images.
  • Jan. 25, 2025
  • Laser & Optoelectronics Progress
  • Vol. 62, Issue 2, 0237008 (2025)
  • DOI:10.3788/LOP241080
Hierarchical Transformer with Multi-Scale Parallel Aggregation for Breast Tumor Segmentation
Ping Xia, Yudie Wang, Bangjun Lei, Cheng Peng, Guangyi Zhang, and Tinglong Tang
The problems of breast tumor segmentation from ultrasound images, such as low contrast between the tumor and the normal tissue, blurred boundaries, complex shapes and positions of tumors, and high noise in images, are a concern for researchers. This paper presents a hierarchical transformer with a multiscale parallel aggregation network for breast tumor segmentation. The encoder uses MiT-B2 to establish long-range dependencies and effectively extract features at different resolutions. At the skip connection between the encoder and the decoder, a cascaded module incorporating a multi-scale receptive field block and shuffle attention (SA) mechanism is constructed. receptive field block is used to capture multi-scale local information of the tumor, addressing the problem of high similarity between the lesion and surrounding normal tissue. The SA mechanism accurately identifies and localizes tumors while suppressing noise interference. In the decoder, an aggregation module is constructed to progressively fuse features from parallel branches to enhance segmentation accuracy. The experimental results on the BUSI dataset show that, compared to TransFuse, the proposed model achieves improvements of 3.21% and 3.19% in the Dice and intersection over union metrics, respectively. The model also shows excellent results for the other two datasets.
  • Jan. 25, 2025
  • Laser & Optoelectronics Progress
  • Vol. 62, Issue 2, 0217001 (2025)
  • DOI:10.3788/LOP240836
Three-Dimensional Measurement of Light-Field Polarization Vector
Boyu Cui, Zebin He, Qiannan Wu, Kewu Li, and Zhibin Wang
We propose a novel method and develop a device for the three-dimensional measurement of light-field polarization vectors. The device can analyze the polarization state at each point in the light field and measure the wavefront distribution using a polarization analysis system comprising a polarizer, waveplate, and Shack-Hartmann wavefront sensor, thereby enabling the reconstruction of a three-dimensional polarization-vector distribution. Using a polarization modulation device and spatial-light modulator, we experimentally generate laser beams with varying polarization states and wavefronts, which are subsequently tested under four light-field conditions. Results show the device performs excellently, with the root-mean-square (RMS) error of the Stokes vector below 0.05, and the RMS and peak-to-valley (PV) values of wavefront error below 0.1 μm. This method effectively overcomes the limitations of conventional two-dimensional detections. It accurately restores three-dimensional polarization information as well as provides high-spatial-resolution and precise polarization-vector measurements, thus offering an effective option for optical measurement with broad application prospects.
  • Jan. 25, 2025
  • Laser & Optoelectronics Progress
  • Vol. 62, Issue 2, 0212002 (2025)
  • DOI:10.3788/LOP241940
Multiplexed Fusion Deep Aggregate Learning for Underwater Image Enhancement
Yan Chen, Ao Xiao, Yun Li, Xiaochun Hu, and Peiguang Jing
This paper proposes a multiplexed fusion deep aggregate learning algorithm for underwater image enhancement. First, the image preprocessing algorithm is used to obtain the image attribute information of three branches (contrast, brightness, and colour) respectively. Then, the image attribute dependency module is designed to obtain fusion features of multiplexed using a fusion network, and then explore the potential fused image attribute correlations through parallel graph convolution. A self-attention deep aggregate learning module is introduced to deeply mine the interaction information between the private and public domains of the multiplexed using sequential self-attention and global attribute iteration mechanisms, and also effectively extract and integrate the important information between image attributes by means of aggregation bottlenecks to achieve more accurate feature representation. Finally, skip connections are introduced to continue enhancing the image output to further improve the effect of image enhancement. Numerous experiments have demonstrated that the proposed method can effectively remove colour bias and blurring, and improve image clarity, as well as facilitate underwater image segmentation and key point detection tasks. The peak signal-to-noise ratio and structural similarity metrics can reach the highest values of 23.01 dB and 0.90, which are improved by 5.0% and 4.7% compared with the suboptimal method, while the underwater colour image quality metrics and information entropy metrics have the highest values of 0.93 and 14.33, which are improved by 2.2% and 0.5% compared with the suboptimal method.
  • Jan. 25, 2025
  • Laser & Optoelectronics Progress
  • Vol. 62, Issue 2, 0237002 (2025)
  • DOI:10.3788/LOP241036
Multiview 3D Object Detection Based on Improved DETR3D
Yuhan Zhang, Miaohua Huang, Gengyao Chen, Yanzhou Li, and Yiming Wu
To overcome the limitations of current multicamera 3D object detection methods, which often struggle to balance precision and computational speed, we propose an enhanced version of DETR3D. The algorithm framework is based on the encoder-decoder architecture of DETR3D. We incorporate a 3D position encoder alongside the image feature extraction branch to enhance image features. Object queries are initialized with two components, representing the object's bounding box and instance features. In the decoder stage, we introduce a multiscale adaptive attention mechanism based on Euclidean distance, allowing the algorithm to effectively capture multiscale information in 3D space, which significantly improves detection performance for complex and diverse objects in autonomous driving scenarios. During feature sampling, we integrate temporal information to align features across consecutive frames, improving detection accuracy. Additionally, multipoint sampling is employed to strengthen the robustness of the sampling process. Experiments conducted on the nuScenes dataset indicate that compared to the baseline algorithm, our proposed approach achieves a 17.1% improvement in detection accuracy and a 4.22-fold increase in computational speed. Moreover, it proves effective in detecting objects even in occluded environments.
  • Jan. 25, 2025
  • Laser & Optoelectronics Progress
  • Vol. 62, Issue 2, 0212001 (2025)
  • DOI:10.3788/LOP240912