In many ultrafast imaging applications, the reduced field-of-view（r FOV） technique is often used to enhance the spatial resolution and field inhomogeneity immunity of the images. The stationary-phase characteristic ...In many ultrafast imaging applications, the reduced field-of-view（r FOV） technique is often used to enhance the spatial resolution and field inhomogeneity immunity of the images. The stationary-phase characteristic of the spatiotemporallyencoded（SPEN） method offers an inherent applicability to r FOV imaging. In this study, a flexible r FOV imaging method is presented and the superiority of the SPEN approach in r FOV imaging is demonstrated. The proposed method is validated with phantom and in vivo rat experiments, including cardiac imaging and contrast-enhanced perfusion imaging. For comparison, the echo planar imaging（EPI） experiments with orthogonal RF excitation are also performed. The results show that the signal-to-noise ratios of the images acquired by the proposed method can be higher than those obtained with the r FOV EPI. Moreover, the proposed method shows better performance in the cardiac imaging and perfusion imaging of rat kidney, and it can scan one or more regions of interest（ROIs） with high spatial resolution in a single shot. It might be a favorable solution to ultrafast imaging applications in cases with severe susceptibility heterogeneities, such as cardiac imaging and perfusion imaging. Furthermore, it might be promising in applications with separate ROIs, such as mammary and limb imaging.展开更多
A new method based on a chirped optical pulse interferogram has been proposed to measure terahertz radiation. The frequency domain phase information of the interferogram is used to extract the time-domain terahertz pu...A new method based on a chirped optical pulse interferogram has been proposed to measure terahertz radiation. The frequency domain phase information of the interferogram is used to extract the time-domain terahertz pulse waveform. In principle, the resolution of our method can be as high as the unchirped probe pulse duration, with the advantages of relatively simple measurement setup and signal extracting techniques.展开更多
Occurrence of crimes has been on the constant rise despite the emerging discoveries and advancements in the technological field in the past decade.One of the most tedious tasks is to track a suspect once a crime is co...Occurrence of crimes has been on the constant rise despite the emerging discoveries and advancements in the technological field in the past decade.One of the most tedious tasks is to track a suspect once a crime is committed.As most of the crimes are committed by individuals who have a history of felonies,it is essential for a monitoring system that does not just detect the person’s face who has committed the crime,but also their identity.Hence,a smart criminal detection and identification system that makes use of the OpenCV Deep Neural Network(DNN)model which employs a Single Shot Multibox Detector for detection of face and an auto-encoder model in which the encoder part is used for matching the captured facial images with the criminals has been proposed.After detection and extraction of the face in the image by face cropping,the captured face is then compared with the images in the CriminalDatabase.The comparison is performed by calculating the similarity value between each pair of images that are obtained by using the Cosine Similarity metric.After plotting the values in a graph to find the threshold value,we conclude that the confidence rate of the encoder model is 0.75 and above.展开更多
Light springs(LSs) have played essential roles in particle rotation and manipulation, optical super-resolution imaging, and optical information coding. In related research areas, it is important to accurately measure ...Light springs(LSs) have played essential roles in particle rotation and manipulation, optical super-resolution imaging, and optical information coding. In related research areas, it is important to accurately measure spatiotemporal information on LSs to understand and analyze their applications. However, there is no experimental method that can accurately detect the drastic spatial evolution of ultrafast LSs to date. Therefore, in this study, we propose a compressed ultrafast photography(CUP) technique to observe LSs in spatial and temporal dimensions with a snapshot. Using our home-built CUP system, we successfully capture spatiotemporal information on picosecond LSs with two and four petals, involving spatial structure and rotation velocity;furthermore, the experimental measurements are in good agreement with theoretical simulations. This study provides a novel visualization method for specifically measuring the spatial structure and temporal evolution of LSs, thus establishing a new idea for accurately characterizing spatiotemporal information on complex ultrafast laser fields.展开更多
Temporal contrast(TC)is one of the most important parameters of an ultrahigh intense laser pulse.The third-order autocorrelator or cross correlator has been widely used in the past decades to characterize the TC of an...Temporal contrast(TC)is one of the most important parameters of an ultrahigh intense laser pulse.The third-order autocorrelator or cross correlator has been widely used in the past decades to characterize the TC of an ultraintense laser pulse.A novel and simple single-shot fourth-order autocorrelator(FOAC)to characterize the TC with higher time resolution and better pulse contrast fidelity in comparison to third-order correlators is proposed.The single-shot fourth-order autocorrelation consists of a frequency-degenerate four-wave mixing process and a sum-frequency mixing process.The proof-of-principle experiments show that a dynamic range of∼10^11 compared with the noise level,a time resolution of∼160 fs,and a time window of 65 ps can successfully be obtained using the single-shot FOAC,which is to-date the highest dynamic range with simultaneously high time resolution for single-shot TC measurement.Furthermore,the TC of a laser pulse from a petawatt laser system is successfully measured in single shot with a dynamic range of about 2×10^10 and simultaneously a time resolution of 160 fs.展开更多
A robust TV logo detection method based on the modified single shot multibox detector (SSD) is presented. Unlike most other existing methods which can only detect the TV logo from video frames, the proposed method can...A robust TV logo detection method based on the modified single shot multibox detector (SSD) is presented. Unlike most other existing methods which can only detect the TV logo from video frames, the proposed method can also detect the TV logo from photo pictures taken by smartphones or other smart terminals. Firstly, using a simple and effective way of collecting and labelling TV logo, a large-scale TV logo dataset used to train the detection model is built. Then, parameters and loss function of SSD are modified to make it more suitable for the task of TV logo detection. Moreover, a soft-NMS algorithm is introduced to remove the redundant overlapping boxes and obtain the final output box. And also an approach for hard example mining is designed to improve the detection accuracy. Finally, extensive comparison experiments are carried out which take into consideration different image resolutions, logo positions and environmental factors existing in real-world applications. Experimental results demonstrate that the proposed method achieve superior performances in robustness compared to other state-of-the-art methods.展开更多
Due to the promising applications of femtosecond laser filamentation in remote sensing,great demands exist for diagnosing the spatiotemporal dynamics of filamentation.However,until now,the rapid and accurate diagnosis...Due to the promising applications of femtosecond laser filamentation in remote sensing,great demands exist for diagnosing the spatiotemporal dynamics of filamentation.However,until now,the rapid and accurate diagnosis of a femtosecond laser filament remains a severe challenge.Here,a novel filament diagnosing method is proposed,which can measure the longitudinal spatial distribution of the filament by a single laser shot-induced acoustic pulse.The dependences of the point-like plasma acoustic emission on the detection distance and angle are obtained experimentally.The results indicate that the temporal profile of the acoustic wave is independent of the detection distance and detection angle.Using the measured relation among the acoustic emission and the detection distance and angle,a single measurement of the acoustic emission generated by a single laser pulse can diagnose the spatial distribution of the laser filament through the Wiener filter deconvolution(WFD)algorithm.The results obtained by this method are in good agreement with those of traditional point-by-point acoustic diagnosis methods.These findings provide a new solution and idea for the rapid diagnosis of filament,thereby laying a firm foundation for femtosecond laser filament-based promising applications.展开更多
To achieve automatic,fast,efficient and high-precision pavement distress classification and detection,road surface distress image classification and detection models based on deep learning are trained.First,a pavement...To achieve automatic,fast,efficient and high-precision pavement distress classification and detection,road surface distress image classification and detection models based on deep learning are trained.First,a pavement distress image dataset is built,including 9017pictures with distress,and 9620 pictures without distress.These pictures were captured from 4 asphalt highways of 3 provinces in China.In each pavement distress image,there exists one or more types of distress,including alligator crack,longitudinal crack,block crack,transverse crack,pothole and patch.The distresses are labeled by a rectangle bounding box on the pictures.Then ResNet networks and VGG networks are used respectively as binary classification models for distressed and non-distressed imagines classification,and as multi-label classification models for six types of distress classification.Training techniques,such as data augmentation,batch normalization,dropout,momentum,weight decay,transfer learning,and discriminative learning rate are used in training the model.Among the 4 CNNs considered in this study,namely ResNet 34 and 50,and VGG 16 and 19,for the binary classification,ResNet 50 has the highest Accuracy of 96.243%,Precision of 95.183%,and ResNet 34 has the highest Recall of 97.824%,and F2 score of 97.052%.For multi-label classification,ResNet 50 has the best performance,with the highest Accuracy of 90.257%,higher than 90%required by the Chinese standard(JTG H20-2018)for road distresses detection,F2 score-82.231%,and Precision-76.509%,and ResNet34 has the highest Recall of 87.32%.To locate and quantify the distress areas in the images,the single shot multibox detector(SSD)model is developed,in which the ResNet 50 is used as the base network to extract features.When the intersection over union(IoU)is set to 0,0.25,0.50,0.75,the mean average precision(mAP)of the model are found to be 74.881%,50.511%,28.432%,3.969%,respectively.展开更多
A method of multi-block Single Shot Multi Box Detector(SSD)based on small object detection is proposed to the railway scene of unmanned aerial vehicle surveillance.To address the limitation of small object detection,a...A method of multi-block Single Shot Multi Box Detector(SSD)based on small object detection is proposed to the railway scene of unmanned aerial vehicle surveillance.To address the limitation of small object detection,a multi-block SSD mechanism,which consists of three steps,is designed.First,the original input images are segmented into several overlapped patches.Second,each patch is separately fed into an SSD to detect the objects.Third,the patches are merged together through two stages.In the first stage,the truncated object of the sub-layer detection result is spliced.In the second stage,a sub-layer suppression and filtering algorithm applying the concept of non-maximum suppression is utilized to remove the overlapped boxes of sub-layers.The boxes that are not detected in the main-layer are retained.In addition,no sufficient labeled training samples of railway circumstance are available,thereby hindering the deployment of SSD.A two-stage training strategy leveraging to transfer learning is adopted to solve this issue.The deep learning model is preliminarily trained using labeled data of numerous auxiliaries,and then it is refined using only a few samples of railway scene.A railway spot in China,which is easily damaged by landslides,is investigated as a case study.Experimental results show that the proposed multi-block SSD method produces an overall accuracy of 96.6%and obtains an improvement of up to 9.2%compared with the traditional SSD.展开更多
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11474236,81171331,and U1232212)
文摘In many ultrafast imaging applications, the reduced field-of-view（r FOV） technique is often used to enhance the spatial resolution and field inhomogeneity immunity of the images. The stationary-phase characteristic of the spatiotemporallyencoded（SPEN） method offers an inherent applicability to r FOV imaging. In this study, a flexible r FOV imaging method is presented and the superiority of the SPEN approach in r FOV imaging is demonstrated. The proposed method is validated with phantom and in vivo rat experiments, including cardiac imaging and contrast-enhanced perfusion imaging. For comparison, the echo planar imaging（EPI） experiments with orthogonal RF excitation are also performed. The results show that the signal-to-noise ratios of the images acquired by the proposed method can be higher than those obtained with the r FOV EPI. Moreover, the proposed method shows better performance in the cardiac imaging and perfusion imaging of rat kidney, and it can scan one or more regions of interest（ROIs） with high spatial resolution in a single shot. It might be a favorable solution to ultrafast imaging applications in cases with severe susceptibility heterogeneities, such as cardiac imaging and perfusion imaging. Furthermore, it might be promising in applications with separate ROIs, such as mammary and limb imaging.
基金supported by National Natural Science Foundation of China(Nos.10925421,10734130)National Basic Research Program of China(973Program)(Nos.2007CB815100,2007CB310406)
文摘A new method based on a chirped optical pulse interferogram has been proposed to measure terahertz radiation. The frequency domain phase information of the interferogram is used to extract the time-domain terahertz pulse waveform. In principle, the resolution of our method can be as high as the unchirped probe pulse duration, with the advantages of relatively simple measurement setup and signal extracting techniques.
文摘针对学生注意力分配困难和对学习影响等问题,提出一种基于机器视觉的精准注意力追踪系统。该系统包括图像采集装置和精准的注意力追踪算法。图像采集装置可以获得更清晰的眼部区域图像。瞳孔中心定位算法用轻量级的MobileNet v3替换VGG16(visual geometry group network),采用两级特征融合和中心关键点预测技术,提高了检测速度和准确率。该算法检测速度可达36帧/s,准确率为97.42%。视线追踪算法旨在解决头部偏移的影响,实现对视线的精确追踪。研发了一款面向学龄儿童的阅读认知评价交互软件。该软件利用采集到的视线坐标计算相关眼动指标,再通过心理学理论分析建模来评估学龄儿童的思维认知能力,为心理学和教育学相关领域研究提供了参考和借鉴。
文摘Occurrence of crimes has been on the constant rise despite the emerging discoveries and advancements in the technological field in the past decade.One of the most tedious tasks is to track a suspect once a crime is committed.As most of the crimes are committed by individuals who have a history of felonies,it is essential for a monitoring system that does not just detect the person’s face who has committed the crime,but also their identity.Hence,a smart criminal detection and identification system that makes use of the OpenCV Deep Neural Network(DNN)model which employs a Single Shot Multibox Detector for detection of face and an auto-encoder model in which the encoder part is used for matching the captured facial images with the criminals has been proposed.After detection and extraction of the face in the image by face cropping,the captured face is then compared with the images in the CriminalDatabase.The comparison is performed by calculating the similarity value between each pair of images that are obtained by using the Cosine Similarity metric.After plotting the values in a graph to find the threshold value,we conclude that the confidence rate of the encoder model is 0.75 and above.
基金supported by the National Natural Science Foundation of China(Grant Nos.91850202,12074121,11774094,11804097,62105101,62175066,92050203,11727810,and 12034008)Science and Technology Commission of Shanghai Municipality(Grant Nos.19560710300,20ZR1417100,and 21XD1400900)。
文摘Light springs(LSs) have played essential roles in particle rotation and manipulation, optical super-resolution imaging, and optical information coding. In related research areas, it is important to accurately measure spatiotemporal information on LSs to understand and analyze their applications. However, there is no experimental method that can accurately detect the drastic spatial evolution of ultrafast LSs to date. Therefore, in this study, we propose a compressed ultrafast photography(CUP) technique to observe LSs in spatial and temporal dimensions with a snapshot. Using our home-built CUP system, we successfully capture spatiotemporal information on picosecond LSs with two and four petals, involving spatial structure and rotation velocity;furthermore, the experimental measurements are in good agreement with theoretical simulations. This study provides a novel visualization method for specifically measuring the spatial structure and temporal evolution of LSs, thus establishing a new idea for accurately characterizing spatiotemporal information on complex ultrafast laser fields.
基金the National Natural Science Foundation of China(NSFC)(Nos.61527821 and 61521093)the Instrument Developing Project(No.YZ201538)+1 种基金the Strategic Priority Research Program(No.XDB160106)the Chinese Academy of Sciences(CAS),and Shanghai Municipal Science and Technology Major Project(No.2017SHZDZX02)。
文摘Temporal contrast(TC)is one of the most important parameters of an ultrahigh intense laser pulse.The third-order autocorrelator or cross correlator has been widely used in the past decades to characterize the TC of an ultraintense laser pulse.A novel and simple single-shot fourth-order autocorrelator(FOAC)to characterize the TC with higher time resolution and better pulse contrast fidelity in comparison to third-order correlators is proposed.The single-shot fourth-order autocorrelation consists of a frequency-degenerate four-wave mixing process and a sum-frequency mixing process.The proof-of-principle experiments show that a dynamic range of∼10^11 compared with the noise level,a time resolution of∼160 fs,and a time window of 65 ps can successfully be obtained using the single-shot FOAC,which is to-date the highest dynamic range with simultaneously high time resolution for single-shot TC measurement.Furthermore,the TC of a laser pulse from a petawatt laser system is successfully measured in single shot with a dynamic range of about 2×10^10 and simultaneously a time resolution of 160 fs.
基金Supported by the National Natural Science Foundationof China(No.61702466)“Double Tops” Discipline Construction Project
文摘A robust TV logo detection method based on the modified single shot multibox detector (SSD) is presented. Unlike most other existing methods which can only detect the TV logo from video frames, the proposed method can also detect the TV logo from photo pictures taken by smartphones or other smart terminals. Firstly, using a simple and effective way of collecting and labelling TV logo, a large-scale TV logo dataset used to train the detection model is built. Then, parameters and loss function of SSD are modified to make it more suitable for the task of TV logo detection. Moreover, a soft-NMS algorithm is introduced to remove the redundant overlapping boxes and obtain the final output box. And also an approach for hard example mining is designed to improve the detection accuracy. Finally, extensive comparison experiments are carried out which take into consideration different image resolutions, logo positions and environmental factors existing in real-world applications. Experimental results demonstrate that the proposed method achieve superior performances in robustness compared to other state-of-the-art methods.
基金supported by the National Natural Science Foundation of China(Nos.12074198,12061131010,and 12304381)the Russian Science Foundation(RSF)(No.21-49-00023).
文摘Due to the promising applications of femtosecond laser filamentation in remote sensing,great demands exist for diagnosing the spatiotemporal dynamics of filamentation.However,until now,the rapid and accurate diagnosis of a femtosecond laser filament remains a severe challenge.Here,a novel filament diagnosing method is proposed,which can measure the longitudinal spatial distribution of the filament by a single laser shot-induced acoustic pulse.The dependences of the point-like plasma acoustic emission on the detection distance and angle are obtained experimentally.The results indicate that the temporal profile of the acoustic wave is independent of the detection distance and detection angle.Using the measured relation among the acoustic emission and the detection distance and angle,a single measurement of the acoustic emission generated by a single laser pulse can diagnose the spatial distribution of the laser filament through the Wiener filter deconvolution(WFD)algorithm.The results obtained by this method are in good agreement with those of traditional point-by-point acoustic diagnosis methods.These findings provide a new solution and idea for the rapid diagnosis of filament,thereby laying a firm foundation for femtosecond laser filament-based promising applications.
基金supported by the National Key R&D Program of China(Grant number 2018YFC0705604)。
文摘To achieve automatic,fast,efficient and high-precision pavement distress classification and detection,road surface distress image classification and detection models based on deep learning are trained.First,a pavement distress image dataset is built,including 9017pictures with distress,and 9620 pictures without distress.These pictures were captured from 4 asphalt highways of 3 provinces in China.In each pavement distress image,there exists one or more types of distress,including alligator crack,longitudinal crack,block crack,transverse crack,pothole and patch.The distresses are labeled by a rectangle bounding box on the pictures.Then ResNet networks and VGG networks are used respectively as binary classification models for distressed and non-distressed imagines classification,and as multi-label classification models for six types of distress classification.Training techniques,such as data augmentation,batch normalization,dropout,momentum,weight decay,transfer learning,and discriminative learning rate are used in training the model.Among the 4 CNNs considered in this study,namely ResNet 34 and 50,and VGG 16 and 19,for the binary classification,ResNet 50 has the highest Accuracy of 96.243%,Precision of 95.183%,and ResNet 34 has the highest Recall of 97.824%,and F2 score of 97.052%.For multi-label classification,ResNet 50 has the best performance,with the highest Accuracy of 90.257%,higher than 90%required by the Chinese standard(JTG H20-2018)for road distresses detection,F2 score-82.231%,and Precision-76.509%,and ResNet34 has the highest Recall of 87.32%.To locate and quantify the distress areas in the images,the single shot multibox detector(SSD)model is developed,in which the ResNet 50 is used as the base network to extract features.When the intersection over union(IoU)is set to 0,0.25,0.50,0.75,the mean average precision(mAP)of the model are found to be 74.881%,50.511%,28.432%,3.969%,respectively.
基金supported by Beijing Natural Science Foundation,China(No.4182020)Open Fund of State Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,China(No.17E01)Key Laboratory for Health Monitoring and Control of Large Structures,Shijiazhuang,China(No.KLLSHMC1901)。
文摘A method of multi-block Single Shot Multi Box Detector(SSD)based on small object detection is proposed to the railway scene of unmanned aerial vehicle surveillance.To address the limitation of small object detection,a multi-block SSD mechanism,which consists of three steps,is designed.First,the original input images are segmented into several overlapped patches.Second,each patch is separately fed into an SSD to detect the objects.Third,the patches are merged together through two stages.In the first stage,the truncated object of the sub-layer detection result is spliced.In the second stage,a sub-layer suppression and filtering algorithm applying the concept of non-maximum suppression is utilized to remove the overlapped boxes of sub-layers.The boxes that are not detected in the main-layer are retained.In addition,no sufficient labeled training samples of railway circumstance are available,thereby hindering the deployment of SSD.A two-stage training strategy leveraging to transfer learning is adopted to solve this issue.The deep learning model is preliminarily trained using labeled data of numerous auxiliaries,and then it is refined using only a few samples of railway scene.A railway spot in China,which is easily damaged by landslides,is investigated as a case study.Experimental results show that the proposed multi-block SSD method produces an overall accuracy of 96.6%and obtains an improvement of up to 9.2%compared with the traditional SSD.
