The Research of Indoor Positioning Based on Visible Light Communication

The key techniques in indoor positioning based on visible light communication and the state of the art of this research were surveyed. First, the significance of indoor positioning based on visible light communication from two aspects of the limitations of current indoor positioning technology and the advantages of visible light communication was discussed; And then, the main four technology of indoor positioning based on visible light communication were summarized and the triangulation of RSS method and the principle of image positioning were introduced in detail; Next, the performance characteristics of various typical algorithms were compared and analyzed; In the end, several suggestions on future research of indoor positioning based on visible light communication were given.

A Visible Light Imaging System for the Estimation of Plasma Vertical Displacement in J-TEXT

A wide-viewing-angle visible light imaging system （VLIS） was mounted on the Joint Texas Experimental Tokamak （J-TEXT） to monitor the discharge process. It is proposed that by using the film data recorded the plasma vertical displacement can be estimated. In this paper installation and operation of the VLIS are presented in detailed. The estimated result is further compared with that measured by using an array of magnetic pickup coils. Their consistency verifies that the estimation of the plasma vertical displacement in J-TEXT by using the imaging data is promising.

CAEFusion: A New Convolutional Autoencoder-Based Infrared and Visible Light Image Fusion Algorithm

To address the issues of incomplete information,blurred details,loss of details,and insufficient contrast in infrared and visible image fusion,an image fusion algorithm based on a convolutional autoencoder is proposed.The region attention module is meant to extract the background feature map based on the distinct properties of the background feature map and the detail feature map.A multi-scale convolution attention module is suggested to enhance the communication of feature information.At the same time,the feature transformation module is introduced to learn more robust feature representations,aiming to preserve the integrity of image information.This study uses three available datasets from TNO,FLIR,and NIR to perform thorough quantitative and qualitative trials with five additional algorithms.The methods are assessed based on four indicators:information entropy(EN),standard deviation(SD),spatial frequency(SF),and average gradient(AG).Object detection experiments were done on the M3FD dataset to further verify the algorithm’s performance in comparison with five other algorithms.The algorithm’s accuracy was evaluated using the mean average precision at a threshold of 0.5(mAP@0.5)index.Comprehensive experimental findings show that CAEFusion performs well in subjective visual and objective evaluation criteria and has promising potential in downstream object detection tasks.

Deep learning-assisted common temperature measurement based on visible light imaging

Real-time,contact-free temperature monitoring of low to medium range(30℃-150℃)has been extensively used in industry and agriculture,which is usually realized by costly infrared temperature detection methods.This paper proposes an alternative approach of extracting temperature information in real time from the visible light images of the monitoring target using a convolutional neural network(CNN).A mean-square error of<1.119℃was reached in the temperature measurements of low to medium range using the CNN and the visible light images.Imaging angle and imaging distance do not affect the temperature detection using visible optical images by the CNN.Moreover,the CNN has a certain illuminance generalization ability capable of detection temperature information from the images which were collected under different illuminance and were not used for training.Compared to the conventional machine learning algorithms mentioned in the recent literatures,this real-time,contact-free temperature measurement approach that does not require any further image processing operations facilitates temperature monitoring applications in the industrial and civil fields.

A nondestructive method for estimating the total green leaf area of individual rice plants using multi-angle color images

Total green leaf area(GLA)is an important trait for agronomic studies.However,existing methods for estimating the GLA of individual rice plants are destructive and labor-intensive.A nondestructive method for estimating the total GLA of individual rice plants based on multi-angle color images is presented.Using projected areas of the plant in images,linear,quadratic,exponential and power regression models for estimating total GLA were evaluated.Tests demonstrated that the side-view projected area had a stronger relationship with the actual total leaf area than the top-projected area.And power models fit better than other models.In addition,the use of multiple side-view images was an efficient method for reducing the estimation error.The inclusion of the top-view projected area as a seoond predictor provided only a slight improvement of the total leaf area est imation.When the projected areas from multi angle images were used,the estimated leaf area(ELA)using the power model and the actual leaf area had a high correlation cofficient(R2>0.98),and the mean absolute percentage error(MAPE)was about 6%.The method was capable of estimating the total leaf area in a nondestructive,accurate and eficient manner,and it may be used for monitoring rice plant growth.

FY-3D Sent Back First Visible Light Images

China successfully launched FY-3D by a LM-4C carrier rocket from the Taiyuan Satellite Launch Center at 02：35 Beijing time on November 15.The mission also carried the HEAD-1experiment satellite which was developed by SAST.The LM-4C carrier rocket was developed by SAST.22 technological improvements were made for this launch mission to meet the satellite’s requirement and improve the flight reliability.So far,

Intelligent Fusion of Infrared and Visible Image Data Based on Convolutional Sparse Representation and Improved Pulse-Coupled Neural Network

Multi-source information can be obtained through the fusion of infrared images and visible light images,which have the characteristics of complementary information.However,the existing acquisition methods of fusion images have disadvantages such as blurred edges,low contrast,and loss of details.Based on convolution sparse representation and improved pulse-coupled neural network this paper proposes an image fusion algorithm that decompose the source images into high-frequency and low-frequency subbands by non-subsampled Shearlet Transform(NSST).Furthermore,the low-frequency subbands were fused by convolutional sparse representation(CSR),and the high-frequency subbands were fused by an improved pulse coupled neural network(IPCNN)algorithm,which can effectively solve the problem of difficulty in setting parameters of the traditional PCNN algorithm,improving the performance of sparse representation with details injection.The result reveals that the proposed method in this paper has more advantages than the existing mainstream fusion algorithms in terms of visual effects and objective indicators.

Visibility enhancement in two-dimensional lensless ghost imaging with true thermal light

We report an experimental demonstration of two-dimensional（2D） lensless ghost imaging with true thermal light. An electrodeless discharge lamp with a higher light intensity than the hollow cathode lamp used before is employed as a light source. The main problem encountered by the 2D lensless ghost imaging with true thermal light is that its coherence time is much shorter than the resolution time of the detection system. To overcome this difficulty we derive a method based on the relationship between the true and measured values of the second-order optical intensity correlation, by which means the visibility of the ghost image can be dramatically enhanced. This method would also be suitable for ghost imaging with natural sunlight.

The Delayed Images in a Hot Rubidium Atomic Vapor

We report an experimental realization of the delayed images in a hot rubidium atomic vapor. With a rubidium atomic vapor cell as slow light medium, the image quality of the experiment could be improved greatly, compared with the results without a slow light medium. By analyzing the results about the image visibility of the slow light imaging system under three different conditions, the image visibility becomes better with the increment of the temperature, during the time that the wavelength of the laser is within dispersion range.

Intelligent MRI Room Design Using Visible Light Communication with Range Augmentation

Radio waves and strong magneticfields are used by Magnetic Reso-nance Imaging(MRI)scanners to detect tumours,wounds and visualize detailed images of the human body.Wi-Fi and other medical devices placed in the MRI procedure room produces RF noise in MRI Images.The RF noise is the result of electromagnetic emissions produced by Wi-Fi and other medical devices that interfere with the operation of the MRI scanner.Existing techniques for RF noise mitigation involve RF shielding techniques which induce eddy currents that affect the MRI image quality.RF shielding techniques are complex and lead to RF leak-age.VLC(Visible light Communication)is an emerging and efficient technology to avoid RF interference near MRI scanners.Range augmentation with power conservation of the LED is a big challenge in existing VLC systems.The major objective of the proposed work is to develop an intelligent-MRI room design without RF interference using visible light communication and enhance the distance between VLC transmitter and VLC receiver.In this paper,it is proposed to implement VLC using On-Off keying modulation and enhance distance using large active area photodiodes with Automatic Gain Control Circuit(AGC)using software and hardware.The performance of the proposed intelligent MRI-VLC system is analyzed by calculating Bit Error Rate at an inclined distance of 50 cm away from line of sight of the LED.The Experimental results showed that the maximum distance achieved was 400 cm at Bit Error Rate(BER)of 1.5×10^(-5).

Multiscale method for identifying and marking the multiform fractures from visible-light rock-mass images

Multiform fractures have a direct impact on the mechanical performance of rock masses.To accurately identify multiform fractures,the distribution patterns of grayscale and the differential features of fractures in their neighborhoods are summarized.Based on this,a multiscale processing algorithm is proposed.The multiscale process is as follows.On the neighborhood of pixels,a grayscale continuous function is constructed using bilinear interpolation,the smoothing of the grayscale function is realized by Gaussian local filtering,and the grayscale gradient and Hessian matrix are calculated with high accuracy.On small-scale blocks,the pixels are classified by adaptively setting the grayscale threshold to identify potential line segments and mini-fillings.On the global image,potential line segments and mini-fillings are spliced together by progressing the block frontier layer-by-layer to identify and mark multiform fractures.The accuracy of identifying multiform fractures is improved by constructing a grayscale continuous function and adaptively setting the grayscale thresholds on small-scale blocks.And the layer-by-layer splicing algorithm is performed only on the domain of the 2-layer small-scale blocks,reducing the complexity.By using rock mass images with different fracture types as examples,the identification results show that the proposed algorithm can accurately identify the multiform fractures,which lays the foundation for calculating the mechanical parameters of rock masses.

基于尺度自适应CoF的红外与可见光图像融合算法研究

针对红外和可见光图像在传统多尺度域融合规则下容易损失图像边缘信息的问题,提出一种基于尺度自适应共现滤波器(Co-occurrence Filter,CoF)的非下采样剪切波变换(Non-subsampled Shearlet Transform,NSST)图像融合方法.这种尺度自适应CoF利用图像的归一化梯度调整滤波尺度,在保留原始CoF结构信息保持能力和去噪能力的基础上,保持密集的大梯度边缘信息.然后将其作为预处理步骤与NSST图像融合算法相结合,实现具有良好边缘保持性能的红外与可见光图像融合.实验表明,本文算法能有效保留源图像的边缘信息,并且通过对比实验分析验证了该算法的有效性.

Ghost Imaging with High Visibility Using Classical Light Source

We experimentally demonstrate a novel ghost imaging experiment utilizing a classical light source, capable of resolving objects with a high visibility. The experimental results show that our scheme can indeed realize ghost imaging with high visibility for a relatively complicated object composed of three near-ellipse-shaped holes with different dimensions. In our experiment, the largest hole is -36 times of the smMlest one in area. Each of the three holes exhibits high-visibility in excess of 80%. The high visibility and high spatial-resolution advantages of this technique could have applications in remote sensing.

基于改进YOLO v7-tiny的玉米种质资源雄穗检测方法

针对玉米种质资源遗传多样性丰富导致雄穗大小、形态结构及颜色呈现较大差异,无人机搭载可见光传感器相比地面采集图像分辨率低,以及图像中部分雄穗过小、与背景相似度高、被遮挡、相互交错等情况带来的雄穗检测精度低的问题,提出了一种改进YOLO v7-tiny模型的玉米种质资源雄穗检测方法。该方法通过在YOLO v7-tiny中引入SPD-Conv模块和VanillaBlock模块,以及添加ECA-Net模块的方式,增强模型对雄穗特征的提取能力。利用自建的玉米种质资源雄穗数据集,训练并测试改进模型。结果表明,改进YOLO v7-tiny的平均精度均值为94.6%,相比YOLO v7-tiny提升1.5个百分点,相比同等规模的轻量级模型YOLO v5s、YOLO v8s分别提升1.0、3.1个百分点,显著降低了图像中雄穗漏检及背景误检为雄穗的发生,有效减少了单穗误检为多穗和交错状态下雄穗个数误判的情况。改进YOLO v7-tiny模型内存占用量为17.8 MB,推理速度为231 f/s。本文方法在保证模型轻量化的前提下提升了雄穗检测精度,为玉米种质资源雄穗实时、精准检测提供了技术支撑。

无人机可见光遥感影像地物目标提取技术研究

无人机可见光遥感影像中地物目标边界清晰度较低,容易导致地物目标与背景之间的区分度降低,进而难以提取地物目标;为此,提出无人机可见光遥感影像地物目标提取方法;从光谱特征、纹理特征和边缘特征3个方面分析无人机可见光遥感影像特征;结合3种影像特征对无人机可见光遥感影像数据集实行增广处理;对完成增广后的数据集定义影像编码标签,以此确定地物目标增强权重,通过参量化处理地物目标光谱特征,计算光谱吸收指数,获取地物目标提取表达式,从而实现无人机可见光遥感影像地物目标提取;实验结果表明,所提方法能够保证地物目标边界的清晰度,具有较强的地物目标提取能力。

基于自编码器的红外与可见光图像融合算法

针对目前红外与可见光图像融合过程中,图像特征提取不充分、中间层信息丢失以及融合图像细节不够清晰的问题,提出了一种基于自编码器的端到端图像融合网络结构。该网络由编码器、融合网络和解码器3部分组成。将高效通道注意力机制和混合注意力机制引入到编码器和融合网络中,利用卷积残差网络(convolutional residual network,CRN)基本块来提取并融合红外图像和可见光图像的基本特征,然后将融合后的特征图输入到解码器进行解码,重建出融合图像。选取目前具有典型代表性的5种方法在主客观方面进行对比。在客观方面,较第2名平均梯度、空间频率和视觉保真度分别提升了21%、10.2%、7.2%。在主观方面,融合后的图像目标清晰、细节突出、轮廓明显,符合人类视觉感受。

基于特征相似性的红外与可见光图像融合方法

单一图像无法全面描述目标的信息,实际应用价值低,针对当前红外与可见光图像融合方法存在的一些不足,如:融合质量差等,为了获得更加理想的红外与可见光图像融合效果,提出了基于特征相似性的红外与可见光图像融合方法。首先分析当前红外与可见光图像融合的研究进展,指出各种方法的局限性,然后采用红外图像和可见光图像,并对它们进行图像去噪、增强处理,采用卷积神经网络提取红外与可见光图像的特征,最后根据特征相似性进行红外与可见光图像融合,并对红外与可见光图像融合效果进行了测试,结果表明,本方法提升了红外与可见光图像融合质量,融合效果要明显优于其他红外与可见光图像融合方法。

深度学习与图像融合的行人检测算法研究

为解决智能辅助驾驶技术中可见光摄像机受光照和气候影响而导致行人目标识别困难的问题。通过研究图像融合技术,结合深度卷积神经网络,实现并改进了一种道路行人目标检测算法。方法是利用多源传感器图像融合技术,采用可见光相机与红外热成像相机融合的策略,以Faster RCNN算法为基础,从改进网络结构、特征融合、优化模型训练等方面展开研究,对复杂环境下的行人检测与定位跟踪展开研究,提出一种基于图像融合技术和改进的深度卷积神经网络的道路行人目标检测算法。实验结果表明,该算法对复杂气候环境下行人目标检测提高了检测效率和准确率,增加了智能辅助驾驶汽车的安全性。

基于大数据分析的可见光图像融合质量评价研究

在复杂可见光图像下图像融合质量受到遮挡和重叠等因素影响,需要进行图像融合质量评价优化设计,提出基于大数据分析的可见光图像融合质量评价模型,采用相应图像块之间的视觉特征提取方法建立可见光图像的深度立体匹配模型,将不同光照强下采集的图像像素值显示映射到嵌入特征空间中,完成预处理,构建可见光图像的动态像素大数据融合模型,通过端到端的视差融合估计实现对可见光图像的动态融合,采用超分辨重建方法获得真实配对图像,分析SR结果与LR图像中的相似内容,以特征级别的图像分布域反映可见光图像融合质量评价,实现可见光图像融合质量评价。仿真结果表明,采用该方法进行可见图像融合的匹配性能较好,图像的对比度、饱和度高,提高了可见光的成像质量,耗时为0.012 s,平均迭代次数为1.569,并且均方误差仅为1.071,总误差仅为4.646,该方法有效提高了图像融合质量的同时,提高了评估效果。

基于无人机影像的冬小麦株高提取与LAI估测模型构建

株高和叶面积指数(Leaf Area Index,LAI)反映着作物的生长发育状况。为了探究基于无人机可见光遥感提取冬小麦株高的可靠性,以及利用株高和可见光植被指数估算LAI的精度,本文获取了拔节期、抽穗期、灌浆期的无人机影像,提取了冬小麦株高与可见光植被指数,使用逐步回归、偏最小二乘、随机森林、人工神经网络四种方法建立LAI估测模型,并对株高提取及LAI估测情况进行精度评价。结果显示:(1)株高提取值Hc与实测值Hd高度拟合(R^(2)=0.894,RMSE=6.695,NRMSE=9.63%),株高提取效果好;(2)与仅用可见光植被指数相比,基于株高与可见光植被指数构建的LAI估测模型精度更高,且随机森林为最优建模方法,当其决策树个数为50时模型估测效果最好(R^(2)=0.809,RMSE=0.497,NRMSE=13.85%,RPD=2.336)。利用无人机可见光遥感方法,高效、准确、无损地实现冬小麦株高及LAI提取估测可行性较高,该研究结果可为农情遥感监测提供参考。