SiamDLA: Dynamic Label Assignment for Siamese Visual Tracking

Label assignment refers to determining positive/negative labels foreach sample to supervise the training process. Existing Siamese-based trackersprimarily use fixed label assignment strategies according to human priorknowledge;thus, they can be sensitive to predefined hyperparameters and failto fit the spatial and scale variations of samples. In this study, we first developa novel dynamic label assignment (DLA) module to handle the diverse datadistributions and adaptively distinguish the foreground from the backgroundbased on the statistical characteristics of the target in visual object tracking.The core of DLA module is a two-step selection mechanism. The first stepselects candidate samples according to the Euclidean distance between trainingsamples and ground truth, and the second step selects positive/negativesamples based on the mean and standard deviation of candidate samples.The proposed approach is general-purpose and can be easily integrated intoanchor-based and anchor-free trackers for optimal sample-label matching.According to extensive experimental findings, Siamese-based trackers withDLA modules can refine target locations and outperformbaseline trackers onOTB100, VOT2019, UAV123 and LaSOT. Particularly, DLA-SiamRPN++improves SiamRPN++ by 1% AUC and DLA-SiamCAR improves Siam-CAR by 2.5% AUC on OTB100. Furthermore, hyper-parameters analysisexperiments show that DLA module hardly increases spatio-temporal complexity,the proposed approach maintains the same speed as the originaltracker without additional overhead.

Global Calibration Method of Multi-sensor Vision System Using Skew Laser Lines

Multi-sensor vision system plays an important role in the 3D measurement of large objects.However,due to the widely distribution of sensors,the problem of lacking common fields of view（FOV） arises frequently,which makes the global calibration of the vision system quite difficult.The primary existing solution relies on large-scale surveying equipments,which is ponderous and inconvenient for field calibrations.In this paper,a global calibration method of multi-sensor vision system is proposed and investigated.The proposed method utilizes pairs of skew laser lines,which are generated by a group of laser pointers,as the calibration objects.Each pair of skew laser lines provides a unique coordinate system in space which can be reconstructed in certain vision sensor＇s coordinates by using a planar pattern.Then the geometries of sensors are computed under rigid transformation constrains by taking coordinates of each skew lines pair as the intermediary.The method is applied on both visual cameras with synthetic data and a real two-camera vision system;results show the validity and good performance.The prime contribution of this paper is taking skew laser lines as the global calibration objects,which makes the method simple and flexible.The method need no expensive equipments and can be used in large-scale calibration.

Measurement of nonuniform temperature distribution by combining line-of-sight TDLAS with regularization methods

Regularization methods were combined with line-of-sight tunable diode laser absorption spectroscopy(TDLAS)to measure nonuniform temperature distribution.Relying on measurements of 12 absorption transitions of water vapor from 1300 nm to 1350 nm,the temperature probability distribution of nonuniform temperature distribution,for which a parabolic temperature profile is selected as an example in this paper,was retrieved by making the use of regularization methods.To examine the effectiveness of regularization methods,truncated singular value decomposition(TSVD),Tikhonov regularization and a revised Tikhonov regularization method were implemented to retrieve the temperature probability distribution.The results derived by using the three regularization methods were compared with that by using constrained linear least-square fitting.The results show that regularization methods not only generate closer temperature probability distributions to the original,but also are less sensitive to measurement noise.Particularly,the revised Tikhonov regularization method generate solutions in better agreement with the original ones than those obtained by using TSVD and Tikhonov regularization methods.The results obtained in this work can enrich the temperature distribution information,which is expected to play a more important role in combustion diagnosis.

用于竖直油井测井的侵入式电阻层析成像图像重建(英文)

An invasive electrical resistance tomographic sensor was proposed for production logging in vertical oil well.The sensor consists of 24 electrodes that are fixed to the logging tool,which can move in the pipeline to acquire data on the conductivity distribution of oil/water mixture flow at different depths.A sensitivity-based algorithm was introduced to reconstruct the cross-sectional images.Analysis on the sensitivity of the sensor to the distribution of oil/water mixture flow was carried out to optimize the position of the imaging cross-section.The imaging results obtained using various boundary conditions at the pipe wall and the logging tool were compared.Eight typical models with various conductivity distributions were created and the measurement data were obtained by solving the forward problem of the sensor system.Image reconstruction was then implemented by using the simulation data for each model.Comparisons between the models and the reconstructed images show that the number and spatial distribution of the oil bubbles can be clearly identified.

Application of camera calibrating model to space manipulator with multi-objective genetic algorithm

The multi-objective genetic algorithm(MOGA) is proposed to calibrate the non-linear camera model of a space manipulator to improve its locational accuracy. This algorithm can optimize the camera model by dynamic balancing its model weight and multi-parametric distributions to the required accuracy. A novel measuring instrument of space manipulator is designed to orbital simulative motion and locational accuracy test. The camera system of space manipulator, calibrated by MOGA algorithm, is used to locational accuracy test in this measuring instrument. The experimental result shows that the absolute errors are [0.07, 1.75] mm for MOGA calibrating model, [2.88, 5.95] mm for MN method, and [1.19, 4.83] mm for LM method. Besides, the composite errors both of LM method and MN method are approximately seven times higher that of MOGA calibrating model. It is suggested that the MOGA calibrating model is superior both to LM method and MN method.

Modeling and analysis for the image mapping spectrometer

The snapshot image mapping spectrometer（IMS） has advantages such as high temporal resolution,high throughput,compact structure and simple reconstructed algorithm.In recent years,it has been utilized in biomedicine,remote sensing,etc.However,the system errors and various factors can cause cross talk,image degradation and spectral distortion in the system.In this research,a theoretical model is presented along with the point response function（PRF） for the IMS,and the influence of the mirror tilt angle error of the image mapper and the prism apex angle error are analyzed based on the model.The results indicate that the tilt angle error causes loss of light throughput and the prism apex angle error causes spectral mixing between adjacent sub-images.The light intensity on the image plane is reduced to 95%when the mirror tilt angle error is increased to ±100 ＂（≈ 0.028°）.The prism apex error should be controlled within the range of 0-36＂（0.01°）to ensure the designed number of spectral bands,and avoid spectral mixing between adjacent images.

Calibration and data restoration of light field modulated imaging spectrometer

A light field modulated imaging spectrometer （LFMIS） can acquire the spatial-spectral datacube of targets of interest or a scene in a single shot. The spectral information of a point target is imaged on the pixels covered by a microlens. The pixels receive spectral information from different spectral filters to the diffraction and misalignments of the optical components. In this paper, we present a linear spectral multiplexing model of the acquired target spectrum. A calibration method is proposed for calibrating the center wavelengths and bandwidths of channels of an LFMIS system based on the liner-variable filter （LVF） and for determining the spectral multiplexing matrix. In order to improve the accuracy of the restored spectral data, we introduce a reconstruction algorithm based on the total least square （TLS） approach. Simulation and experimental results confirm the performance of the spectrum reconstruction algorithm and validate the feasibility of the proposed calibrating scheme.

铁路货车闸瓦钎故障的实时监控（英文）

目的:面向铁路货车关键机械部件的健康状态监控,针对铁路货车闸瓦钎这种复杂机械部件,实现基于视觉图像的户外全天候实时自动故障检测。创新点:针对闸瓦钎这种复杂目标机械部件的故障检测,提出一种新颖的实时精确故障检测方法。鉴于目标部件故障样本和无故障样本存在极强的类间相似性和类内差异性,情况相对复杂,提出采用多特征多层级方式。多特征避免单一特征的局限性和片面性,满足系统高精度要求,而多层级级联方式可事先排除大量无关背景信息,满足系统实时性需求。方法:采用层次化故障检测思路,在ROI分割上(图10),提出采用多尺度中心变换编码(MSCT),通过构建改进的空间金字塔方式实现。在闸瓦钎定位上,在梯度域对闸瓦钎部位进行中心变换编码,以梯度编码直方图(HEG)特征构建特征向量,采用SVM训练生成定位分类器。故障状态分类器的构建与之相似,但编码是建立在灰度图像基础上,最终在分割出的ROI中通过定位和判别分类器级联方式实现闸瓦钎丢失故障的全自动检测,无需任何人工参与过程。结论:针对现有铁路故障检测技术存在的不足,提供一种铁路货车闸瓦钎丢失故障的自动检测方法,既可降低铁路货车故障检测成本,又可提高铁路货车故障检测效率,为铁路提速提供了可靠的安全保障。相应实验表明该系统故障检测率达到了99.2%(表2),而检测速度接近5帧/秒,具有很好的实时性和很高的检测精度。

The quantitative evaluation of application of hyperspectral data based on multi-parameters joint optimization

In order to evaluate the mineral identification of the hyperspectral data and make a trade-off of the imaging system parameters,a quantitative evaluation approach based on the multi-parameters joint optimization is proposed for the hyperspectral remote sensing.In the proposed approach,the mineral identification is defined as the number of the minerals identified and the key imaging parameters employed include ground sample distance(GSD)and spectral resolution(SR).Certain limitations are found among parameters that are used for analyzing the imaging processes.The constraints include the industrial manufacturing level,application requirements and the quantitative relationship among the GSD,the SR and the signal-to-noise ratio(SNR).Regression analysis is used to investigate the quantitative relationship between the mineral identification and the key imaging system parameters.Then,an optimization model for the trade-off study is established by combining the regression equation with the constraints.The airborne hyperspectral image collected by Hymap is applied to evaluate the performance of the proposed approach.The experimental results reveal that the approach can achieve the evaluation of the mineral identification and the trade-off of key imaging system parameters.The error of the prediction is within one kind of mineral.

Pre-locate net for object detection in high-resolution images

Small-object detection has long been a challenge.High-megapixel cameras are used to solve this problem in industries.However,current detectors are inefficient for high-resolution images.In this work,we propose a new module called Pre-Locate Net,which is a plug-and-play structure that can be combined with most popular detectors.We inspire the use of classification ideas to obtain candidate regions in images,greatly reducing the amount of calculation,and thus achieving rapid detection in high-resolution images.Pre-Locate Net mainly includes two parts,candidate region classification and behavior classification.Candidate region classification is used to obtain a candidate region,and behavior classification is used to estimate the scale of an object.Different follow-up processing is adopted according to different scales to balance the variance of the network input.Different from the popular candidate region generation method,we abandon the idea of regression of a bounding box and adopt the concept of classification,so as to realize the prediction of a candidate region in the shallow network.We build a high-resolution dataset of aircraft and landing gears covering complex scenes to verify the effectiveness of our method.Compared to state-of-the-art detectors(e.g.,Guided Anchoring,Libra-RCNN,and FASF),our method achieves the best m AP of 94.5 on 1920×1080 images at 16.7 FPS.

Femtosecond fiber laser at 780 nm for two-photon autofluorescence imaging

We present an Er-doped fiber(Er:fiber)-based femtosecond laser at 780 nm with 256 MHz repetition rate, 191 fs pulse duration, and over 1 W average power.Apart from the careful third-order dispersion management, we introduce moderate self-phase modulation to broaden the output spectrum of the Er:fiber amplifier and achieve 193 fs pulse duration and 2.43W average power.Over 40% frequency doubling efficiency is obtained by a periodically poled lithium niobate crystal.Delivering through a hollow-core photonic bandgap fiber, this robust laser becomes an ideal and convenient light source for two-photon autofluorescence imaging.

Particle size influence on effective permittivity of particle-gas mixture with particle clusters

The influence of particle size on the effective permittivity of a particle-gas mixture in the presence of particle clusters was studied using numerical analysis involving the three-dimensional finite element method. The effective permittivity of the mixture was obtained by calculating the electrostatic energy generated in the computation domain, Numerical results show that for fixed volume fraction of particles in the mixture, the effective permittivity of the mixture increases with decreasing particle size, Static experiments were carried out by using a differential capacitance sensor with parallel plates. The variation of the effective permittivity with particle size is shown by experimental data to agree with the numerical results. The methodology described and the results obtained in this paper may be used to help modify the measurement of particles volume fraction in the presence of particle clusters when a capacitance sensor is used.

Phase retrieval from double axially displaced holograms for dual-wavelength in-line holography

A phase retrieval method for dual-wavelength in-line digital holography is presented with double axially displaced holograms.A synthetic wavelength is used during iterative propagations to retrieve wrap-free phase distributions with a much extended measurement range.The simulation and experimental results demonstrate a better elimination of the twin image,a faster rate of convergence of the iterative routine and less number of wavelengths are compared with previously reported multiple-wavelength in-line holography.

Enhanced reconstruction of partially occluded objects with occlusion removal in synthetic aperture integral imaging

Synthetic aperture integral imaging provides the ability to reconstruct partially occluded objects from multi-view images. However, the reconstructed images suffer from degraded contrast due to the superimposition of foreground defocus blur. We propose an algorithm to remove foreground occlusions before reconstructing backgrounds. Occlusions are identified by estimating the color variance on elemental images and then deleting it in the final synthetic image. We demonstrate the superiority of our method by presenting experimental results as well as comparing our method with other approaches.

Three-dimensional catadioptric vision sensor using omnidirectional dot matrix projection

In order to solve the problem of low measurement accuracy caused by uneven imaging resolutions,we develop a three-dimensional catadioptric vision sensor using 20 to 100 lasers arranged in a circular array called omnidirectional dot maxtric projection（ODMP）.Based on the imaging characteristic of the sensor,the ODMP can image the area with a high image resolution.The proposed sensor with ODMP can minimize the loss of the detail information by adjusting the projection density.In evaluating the performance of the sensor,real experiments show the designed sensor has high efficiency and high precision for the measurement of the inner surfaces of pipelines.

Single-camera active stereo vision system using fiber bundles

We propose an approach for realizing 3D reconstruction in small field of view or some extreme environments. We combine the stereo vision and the structured light technologies and change the traditional ways of applying them by employing two fiber bundles. The processes of calibration and 3D reconstruction are also introduced. Experiments are performed to verify the feasibility and effectiveness of our proposed approach.

Two-dimensional vision measurement approach based on local sub-plane mapping

The existing two-dimensional vision measurement methods ignore lens distortion, require the plane to be perpendicular to the optical axis, and demand a complex operation. To address these issues, a new approach based on local sub-plane mapping is presented. The plane calibration is performed by dividing the calibration plane into sub-planes, and there exists an approximate affine invariance between each small sub-plane and the corresponding image plane. Thus, the coordinate transformation can be performed precisely, without lens distortion correction. The real comparative experiments show that the proposed approach is robust and yields a higher accuracy than the traditional methods.

Reduced thermal sensitivity of hybrid air-core photonic band-gap fiber ring resonator

A novel hybrid air-core photonic band-gap fiber(PBF) ring resonator with twin 90° polarization-axis rotated splices is proposed and demonstrated. Frist, we measure the temperature dependent birefringence coefficient of air-core PBF and Panda fiber. Experimental results show that the relative temperature dependent birefringence coefficient of air-core PBF is 1.42×10^(-8)/℃, which is typically ~16 times less than that of Panda fiber. Then, we extract the geometry profile of air-core PBF from scanning electron microscope(SEM) images. Numerical modal is built to distinguish the fast axis and slow axis in the fiber. By precisely setting the length difference in air-core PBF and Panda fiber between two 90° polarization-axis rotated splicing points, the hybrid air-core PBF ring resonator is constructed, and the finesse of the resonator is 8.4. Environmental birefringence variation induced by temperature change can be well compensated, and experimental results show an 18-fold reduction in thermal sensitivity, compared with resonator with twin 0° polarization-axis rotated splices.