The range-gated laser imaging instrument can capture face images in a dark environment, which provides a new idea for long-distance face recognition at night. However, the laser image has low ...contrast, low SNR and no color information, which affects observation and recognition. Therefore, it becomes important to convert laser images into visible images and then identify them. For image translation, we propose a laser-visible face image translation model combined with spectral normalization (SN-CycleGAN). We add spectral normalization layers to the discriminator to solve the problem of low image translation quality caused by the difficulty of training the generative adversarial network. The content reconstruction loss function based on the Y channel is added to reduce the error mapping. The face generated by the improved model on the self-built laser-visible face image dataset has better visual quality, which reduces the error mapping and basically retains the structural features of the target compared with other models. The FID value of evaluation index is 36.845, which is 16.902, 13.781, 10.056, 57.722, 62.598 and 0.761 lower than the CycleGAN, Pix2Pix, UNIT, UGATIT, StarGAN and DCLGAN models, respectively. For the face recognition of translated images, we propose a laser-visible face recognition model based on feature retention. The shallow feature maps with identity information are directly connected to the decoder to solve the problem of identity information loss in network transmission. The domain loss function based on triplet loss is added to constrain the style between domains. We use pre-trained FaceNet to recognize generated visible face images and obtain the recognition accuracy of Rank-1. The recognition accuracy of the images generated by the improved model reaches 76.9%, which is greatly improved compared with the above models and 19.2% higher than that of laser face recognition.
This paper proposes a photoelectric target detection algorithm for NVIDIA Jeston Nano embedded devices, exploiting the characteristics of active and passive differential images of lasers after ...denoising. An adaptive threshold segmentation method was developed based on the statistical characteristics of photoelectric target echo light intensity, which effectively improves detection of the target area. The proposed method’s effectiveness is compared and analyzed against a typical lightweight network that was knowledge-distilled by ResNet18 on target region detection tasks. Furthermore, TensorRT technology was applied to accelerate inference and deploy on hardware platforms the lightweight network Shuffv2_x0_5. The experimental results demonstrate that the developed method’s accuracy rate reaches 97.15%, the false alarm rate is 4.87%, and the detection rate can reach 29 frames per second for an image resolution of 640 × 480 pixels.
CycleGAN is widely used in various image translations, such as thermal-infrared-visible-image translation, near-infrared-visible-image translation, and shortwave-infrared-visible-image translation. ...However, most image translations are used for infrared-to-visible translation, and the wide application of laser imaging has an increasingly strong demand for laser-visible image translation. In addition, the current image translation is mainly aimed at frontal face images, which cannot be effectively utilized to translate faces at a certain angle. In this paper, we construct a laser-visible face mapping dataset; in case of the gradient dispersion of the objective function of the original adversarial loss, the least squares loss function is used to replace the cross-entropy loss function and an identity loss function is added to strengthen the network constraints on the generator. The experimental results indicate that the SSIM value of the improved model increases by 1.25%, 8%, 0, 8%, the PSNR value is not much different, and the FID value decreases by 11.22, 12.85, 43.37 and 72.19, respectively, compared with the CycleGAN, Pix2pix, U-GAN-IT and StarGAN models. In the profile image translation, in view of the poor extraction effect of CycleGAN's original feature extraction module ResNet, the RRDB module is used to replace it based on the first improvement. The experimental results show that, compared with the CycleGAN, Pix2pix, U-GAN-IT, StarGAN and the first improved model, the SSIM value of the improved model increased by 3.75%, 10.67%, 2.47%, 10.67% and 2.47%, respectively; the PSNR value increased by 1.02, 2.74, 0.32, 0.66 and 0.02, respectively; the FID value reduced by 26.32, 27.95, 58.47, 87.29 and 15.1, respectively. Subjectively, the contour features and facial features were better conserved.
LiDAR offers a wide range of uses in autonomous driving, remote sensing, urban planning, and other areas. The laser 3D point cloud acquired by LiDAR typically encounters issues during registration, ...including laser speckle noise, Gaussian noise, data loss, and data disorder. This work suggests a novel Student’s t-distribution point cloud registration algorithm based on the local features of point clouds to address these issues. The approach uses Student’s t-distribution mixture model (SMM) to generate the probability distribution of point cloud registration, which can accurately describe the data distribution, in order to tackle the problem of the missing laser 3D point cloud data and data disorder. Owing to the disparity in the point cloud registration task, a full-rank covariance matrix is built based on the local features of the point cloud during the objective function design process. The combined penalty of point-to-point and point-to-plane distance is then added to the objective function adaptively. Simultaneously, by analyzing the imaging characteristics of LiDAR, according to the influence of the laser waveform and detector on the LiDAR imaging, the composite weight coefficient is added to improve the pertinence of the algorithm. Based on the public dataset and the laser 3D point cloud dataset acquired in the laboratory, the experimental findings demonstrate that the proposed algorithm has high practicability and dependability and outperforms the five comparison algorithms in terms of accuracy and robustness.
Aiming at the application of laser active imaging detection technology, this paper studied the beam homogenization system of a semiconductor laser based on a homogenizing pipe. Firstly, the principle ...of the homogenizing pipe was introduced. Secondly, the homogenization effect, which was influenced by several geometric parameters (aperture size, length, and taper) of the homogenizing pipe using the optical design software, was simulated for the fiber-coupled semiconductor laser. Finally, according to the simulated results, a laser illumination system composed of a fiber-coupled semiconductor laser, a homogenizing pipe, and an aspheric lens was designed, which can obtain a rectangular uniform light spot in a long distance. The effectiveness of the illumination system was verified by simulation and experiment, respectively. Simulation results suggested that the uniformity of the spot at a distance of 20 m was 85.6%, while divergence angle was 10 mrad. The uniformity of the spot at a distance of 120 m was 91.5%, while divergence angle was 10 mrad. Experimental results showed that the uniformity of the spot at a distance of 20 m was 87.7%, while divergence angle was 13 mrad. The uniformity of the spot at a distance of 120 m was 93.3%, while divergence angle was 15 mrad. The laser illumination system designed in this paper was simple and easy to assemble, and has strong practicability. The results in this paper have certain reference value and guiding significance for the homogenization design of semiconductor lasers.
In this paper, a range-gated LIDAR system utilizing an LN crystal as the electro-optical switch and a SCMOS (scientific complementary metal oxide semiconductor) imaging device is designed. To achieve ...range-gated operations, we utilize two polarizers and an LN (LiNbO3) crystal to form an electro-optical switch. The optical switch is realized by applying a pulse voltage at both ends of the crystal due to the crystal’s conoscopic interference effect and electro-optical effect. The advantage of this system is that low-bandwidth detectors, such as a CMOS and a CCD (charge-coupled device), can be used to replace conventional high-bandwidth detectors, such as an ICCD (intensified charge-coupled device), and it displays better imaging performance under specific conditions at the same time. However, after using an electro-optical crystal as an optical switch, a new inhomogeneity error will be introduced due to the conoscopic interference effect of the electro-optical crystal, resulting in a range error for the LIDAR system. To reduce the influence of inhomogeneity error on the system, this paper analyzes the sources of inhomogeneity error caused by the electro-optical crystal and calculates the crystal’s inhomogeneity mathematical expression. A compensation method is proposed based on the above inhomogeneity mathematical expression. An experimental LIDAR system is constructed in this paper to verify the validity of the compensation method. The experimental results of the range-gated LIDAR system show that in a specific field of view (2.6 mrad), the LIDAR system has good imaging performance; its ranging standard deviation is 3.86 cm and further decreases to 2.86 cm after compensation, which verifies the accuracy of the compensation method.
Laser active imaging technology has important practical value and broad application prospects in military fields such as target detection, radar reconnaissance, and precise guidance. However, factors ...such as uneven laser illuminance, atmospheric backscatter, and the imaging system itself will introduce noise, which will affect the quality of the laser active imaging image, resulting in image contrast decline and blurring image edges and details. Therefore, an image denoising algorithm based on homomorphic filtering and total variation cascade is proposed in this paper, which strives to reduce the noise while retaining the edge features of the image to the maximum extent. Firstly, the image type is determined according to the characteristics of the laser image, and then the speckle noise in the low-frequency region is suppressed by adaptive homomorphic filtering. Finally, the image denoising method of minimizing the total variation is adopted for the impulse noise and Gaussian noise. Experimental results show that compared with separate homomorphic filtering, total variation filtering, and median filtering, the proposed algorithm significantly improves the contrast, retains edge details, achieves the expected effect. It can better adjust the image brightness and is beneficial for subsequent processing.
In order to analyze the performance of a light detection and ranging system based on polarization modulation, it is necessary to theoretically analyze and model the polarization scattering ...characteristics of common target materials. In this paper, the shortcomings of the classical Hyde pBRDF (polarization bidirectional reflectance distribution function) model are analyzed. Based on the research results of many researchers in recent years, a new six-parameter pBRDF model is proposed. To verify the accuracy of the proposed model, this paper builds a measurement system for the polarization scattering characteristics of the target surface in the laser active imaging scene, and the polarization scattering characteristics of two common materials, namely a white paint coating and an aluminum plate, are measured. Based on the measurement results of the DOP (degree of polarization) of the scattered light of the target material and the BBO-FA (biogeography-based optimization-Firefly algorithm) algorithm, we performed inversion calculations on the key parameters of the target material. Using the parameters of the target material obtained via inversion, we use the model to simulate the Stokes vectors of the target and compare the simulated values of Stokes vectors with the measured values to verify the accuracy of the model. The verification results show that the simulation results of Stokes vectors are in good agreement with the measurement results for these two materials, and the introduction of various improvements to the model can effectively improve the accuracy of the model, which provides a tool for studying the performance parameters of a laser three-dimensional imaging system based on polarization modulation.
Deep learning has better detection efficiency than typical methods in photoelectric target detection. However, classical CNNs on GPU frameworks consume too much computing power and memory resources. ...We propose a multi-stream inference-optimized TensorRT (MSIOT) method to solve this problem effectively. MSIOT uses knowledge distillation to effectively reduce the number of model parameters by layer guidance between CNNs and lightweight networks. Moreover, we use the TensorRT and multi-stream mode to reduce the number of model computations. MSIOT again increases inference speed by 9.3% based on the 4.3–7.2× acceleration of TensorRT. The experimental results show that the model’s mean average accuracy, precision, recall, and F1 score after distillation can reach up to 94.20%, 93.16%, 95.4%, and 94.27%, respectively. It is of great significance for designing a real-time photoelectric target detection system.
Highly dispersed CuFe19Ox catalysts with different shapes were prepared and further characterized by X-ray diffraction (XRD), transmission electron microscopy (TEM), H2 temperature-programmed ...reduction (H2-TPR), and in-situ XRD. XRD and TEM results showed that the synthesized CuFe19Ox nanoparticles consisted of CuO and Fe2O3, while CuFe19Ox nanorods consisted of CuFe2O4 and Fe2O3. The reduction properties of CuFe19Ox samples were finely studied by H2-TPR, and the phase composition was identified by in-situ XPS, HR-TEM, and surface TPR (s-TPR). In-situ X-ray photoelectroscopy (XPS) indicated that the metallic Cu and Fe3O4 were the main species after reduction. Moreover, s-TPR studies showed that the reduction performance of copper was significantly affected by the shapes of the Fe3O4 supports. Low-temperature water gas shift (LT-WGS) was chosen to characterize the Cu species on the surface. It was found that reduced CuFe19Ox nanorods had no activity. On the contrary, reduced CuFe19Ox particles showed higher initial WGS activity, where the active Cu0 should originate from the reduction of Cu2O at lower temperatures, as confirmed by the s-TPR profiles.
PDF
