Although the image dehazing problem has received considerable attention over recent years,the existing models often prioritise performance at the expense of complexity,making them unsuitable for real-world application...Although the image dehazing problem has received considerable attention over recent years,the existing models often prioritise performance at the expense of complexity,making them unsuitable for real-world applications,which require algorithms to be deployed on resource constrained-devices.To address this challenge,we propose WaveLiteDehaze-Network(WLD-Net),an end-to-end dehazing model that delivers performance comparable to complex models while operating in real time and using significantly fewer parameters.This approach capitalises on the insight that haze predominantly affects low-frequency infor-mation.By exclusively processing the image in the frequency domain using discrete wavelet transform(DWT),we segregate the image into high and low frequencies and process them separately.This allows us to preserve high-frequency details and recover low-frequency components affected by haze,distinguishing our method from existing approaches that use spatial domain processing as the backbone,with DWT serving as an auxiliary component.DWT is applied at multiple levels for better in-formation retention while also accelerating computation by downsampling feature maps.Subsequently,a learning-based fusion mechanism reintegrates the processed frequencies to reconstruct the dehazed image.Experiments show that WLD-Net out-performs other low-parameter models on real-world hazy images and rivals much larger models,achieving the highest PSNR and SSIM scores on the O-Haze dataset.Qualitatively,the proposed method demonstrates its effectiveness in handling a diverse range of haze types,delivering visually pleasing results and robust performance,while also generalising well across different scenarios.With only 0.385 million parameters(more than 100 times smaller than comparable dehazing methods),WLD-Net processes 1024×1024 images in just 0.045 s,highlighting its applicability across various real-world scenarios.The code is available at https://github.com/AliMurtaza29/WLD-Net.展开更多
Seismological Bureau of Sichuan Province, Chengdu 610041, China2) Center for Analysis and Prediction, State Seismological Bureau, Beijing 100036, China3) Observation Center for Prediction of Earthquakes and Volcanic E...Seismological Bureau of Sichuan Province, Chengdu 610041, China2) Center for Analysis and Prediction, State Seismological Bureau, Beijing 100036, China3) Observation Center for Prediction of Earthquakes and Volcanic Eruptions, Faculty of Sciences, Tohoku University, Sendai 98077, Japan展开更多
A simple way of interpolation for real time processing is pres -ented. For passive localization, the time delay between two signals can be determined by the peak of their cross-correlation. It is more efficient to est...A simple way of interpolation for real time processing is pres -ented. For passive localization, the time delay between two signals can be determined by the peak of their cross-correlation. It is more efficient to estimate a cross-correlation function by the inverse FFT of the cross-spectral density. The original smapling rate is usually very low to reduce computation. The sampling rate of the cross-correlation so computed is too low to estimate satisfactorily and an interpolation procedure is therefore needed. The interpolation by zero augmented spectrum is concise, fast and accurate. The results of the computer simulation and real nuderwater signal processing are given in the paper.展开更多
In our previous work, a novel algorithm to perform robust pose estimation was presented. The pose was estimated using points on the object to regions on image correspondence. The laboratory experiments conducted in th...In our previous work, a novel algorithm to perform robust pose estimation was presented. The pose was estimated using points on the object to regions on image correspondence. The laboratory experiments conducted in the previous work showed that the accuracy of the estimated pose was over 99% for position and 84% for orientation estimations respectively. However, for larger objects, the algorithm requires a high number of points to achieve the same accuracy. The requirement of higher number of points makes the algorithm, computationally intensive resulting in the algorithm infeasible for real-time computer vision applications. In this paper, the algorithm is parallelized to run on NVIDIA GPUs. The results indicate that even for objects having more than 2000 points, the algorithm can estimate the pose in real time for each frame of high-resolution videos.展开更多
Imaging flow cytometry(IFC)combines the imaging capabilities of microscopy with the high throughput of flow cytometry,offering a promising solution for high-precision and high-throughput cell analysis in fields such a...Imaging flow cytometry(IFC)combines the imaging capabilities of microscopy with the high throughput of flow cytometry,offering a promising solution for high-precision and high-throughput cell analysis in fields such as biomedicine,green energy,and environmental monitoring.However,due to limitations in imaging framerate and realtime data processing,the real-time throughput of existing IFC systems has been restricted to approximately 1000-10,000 events per second(eps),which is insufficient for large-scale cell analysis.In this work,we demonstrate IFC with real-time throughput exceeding 1,000,000 eps by integrating optical time-stretch(OTS)imaging,microfluidic-based cell manipulation,and online image processing.Cells flowing at speeds up to 15 m/s are clearly imaged with a spatial resolution of 780 nm,and images of each individual cell are captured,stored,and analyzed.The capabilities and performance of our system are validated through the identification of malignancies in clinical colorectal samples.This work sets a new record for throughput in imaging flow cytometry,and we believe it has the potential to revolutionize cell analysis by enabling highly efficient,accurate,and intelligent measurement.展开更多
A real time algorithm is presented here to recognize and analyze 8 channel simultaneous electro cardiograph(ECG). The algorithm transforms 8 channel simultaneous ECG into three orthogonal vectors and spatial veloc...A real time algorithm is presented here to recognize and analyze 8 channel simultaneous electro cardiograph(ECG). The algorithm transforms 8 channel simultaneous ECG into three orthogonal vectors and spatial velocity first, then forms the spatial velocity sample, and uses this spatial velocity sample to recognize each beat. The algorithm computes the averaged parameters by using averaged spatial velocity and the averaged ECG and the current parameters by using the current beat period and current width of QRS. The algorithm can recognize P, QRS and T onsets and ends of simultaneous 12 lead ECG precisely, and some arrhythmias such as premature ventricular beat, ventricular escape beat, R on T, bigeminy, trigeminy. The algorithm software works well on a real 8 channel ECG system and meets the demands of designing.展开更多
A multi-GPU system designed for high-speed,real-time signal processing of optical coherencetomography(OCT)is described herein.For the OCT data sampled in linear wave numbers,themaximum procesing rates reached 2.95 MHz...A multi-GPU system designed for high-speed,real-time signal processing of optical coherencetomography(OCT)is described herein.For the OCT data sampled in linear wave numbers,themaximum procesing rates reached 2.95 MHz for 1024-OCT and 1.96 MHz for 2048-OCT.Data sampled using linear wavelengths were re-sampled using a time-domain interpolation method and zero-padding interpolation method to improve image quality.The maximum processing rates for1024-OCT reached 2.16 MHz for the time-domain method and 1.26 MHz for the zero-paddingmethod.The maximum processing rates for 2048-0CT reached_1.58 MHz,and 0.68 MHz,respectively.This method is capable of high-speed,real-time processing for O CT systems.展开更多
Simple GNSS navigation receivers, developed for the mass market, can be used for positioning with sub centimeter accuracy in a wireless sensor network if the read-out of the carrier phase data is possible and all data...Simple GNSS navigation receivers, developed for the mass market, can be used for positioning with sub centimeter accuracy in a wireless sensor network if the read-out of the carrier phase data is possible and all data is permanently broadcast to a central computer for near real time processing of the respective base lines. Experiences gained in two research projects related to landslide monitoring are depicted in terms of quality and reliability of the results by the developed approach. As far as possible a modular system set up with commercial off-the-shelf components, e.g., standard WLAN fur commtmication, solar batteries with solar panels for autarkic power supply and in cooperation of existing proofed program tools is chosen. The challenge of the still ongoing development is to have a flexible and robust GNSS based sensor network available - concerned not only for landslide monitoring in future.展开更多
Compared to small molecule process analytical technology （PAT） applications, biotechnology product PAT applications have certain unique challenges and opportunities. Understanding process dynamics of bioreactor cell...Compared to small molecule process analytical technology （PAT） applications, biotechnology product PAT applications have certain unique challenges and opportunities. Understanding process dynamics of bioreactor cell culture process is essential to establish an appropriate process control strategy for biotechnology product PAT applications. Inline spectroscopic techniques for real time monitoring of bioreactor cell culture process have the distinct potential to develop PAT approaches in manufac- turing biotechnology drug products. However, the use of inline Fourier transform infrared （FTIR） spectroscopic techniques for bioreactor cell culture process monitoring has not been reported. In this work, real time inline FTIR Spectroscopy was applied to a lab scale bioreactor mAb IgG3 cell culture fluid biomolecular dynamic model. The technical feasibility of using FTIR Spectroscopy for real time tracking and monitoring four key cell culture metabolites （including glucose, glutamine, lactate, and ammonia） and protein yield at increasing levels of complexity （simple binary system, fully formulated media, actual bioreactor cell culture process） was evaluated via a stepwise approach. The FTIR fingerprints of the key metabolites were identified. The multivariate partial least squares （PLS） calibration models were established to correlate the process FTIR spectra with the concentrations of key metabolites and protein yield of in-process samples, either individually for each metabolite and protein or globally for all four metabolites simultaneously. Applying the 2＇ld derivative pre-processing algorithm to the FTIR spectra helps to reduce the number of PLS latent variables needed significantly and thus simplify the interpretation of the PLS models. The validated PLS models show promise in predicting the concentration profiles of glucose, glutamine, lactate, and ammonia and protein yield over the course of the bioreactor cell culture process. Therefore, this work demonstrated the technical feasibility of real time monitoring of the bioreactor cell culture process via FTIR spectroscopy. Its implications for enabling cell culture PAT were discussed.展开更多
基金Japan International Cooperation Agency(JICA)via Malaysia-Japan Linkage Research Grant 2024.
文摘Although the image dehazing problem has received considerable attention over recent years,the existing models often prioritise performance at the expense of complexity,making them unsuitable for real-world applications,which require algorithms to be deployed on resource constrained-devices.To address this challenge,we propose WaveLiteDehaze-Network(WLD-Net),an end-to-end dehazing model that delivers performance comparable to complex models while operating in real time and using significantly fewer parameters.This approach capitalises on the insight that haze predominantly affects low-frequency infor-mation.By exclusively processing the image in the frequency domain using discrete wavelet transform(DWT),we segregate the image into high and low frequencies and process them separately.This allows us to preserve high-frequency details and recover low-frequency components affected by haze,distinguishing our method from existing approaches that use spatial domain processing as the backbone,with DWT serving as an auxiliary component.DWT is applied at multiple levels for better in-formation retention while also accelerating computation by downsampling feature maps.Subsequently,a learning-based fusion mechanism reintegrates the processed frequencies to reconstruct the dehazed image.Experiments show that WLD-Net out-performs other low-parameter models on real-world hazy images and rivals much larger models,achieving the highest PSNR and SSIM scores on the O-Haze dataset.Qualitatively,the proposed method demonstrates its effectiveness in handling a diverse range of haze types,delivering visually pleasing results and robust performance,while also generalising well across different scenarios.With only 0.385 million parameters(more than 100 times smaller than comparable dehazing methods),WLD-Net processes 1024×1024 images in just 0.045 s,highlighting its applicability across various real-world scenarios.The code is available at https://github.com/AliMurtaza29/WLD-Net.
文摘Seismological Bureau of Sichuan Province, Chengdu 610041, China2) Center for Analysis and Prediction, State Seismological Bureau, Beijing 100036, China3) Observation Center for Prediction of Earthquakes and Volcanic Eruptions, Faculty of Sciences, Tohoku University, Sendai 98077, Japan
文摘A simple way of interpolation for real time processing is pres -ented. For passive localization, the time delay between two signals can be determined by the peak of their cross-correlation. It is more efficient to estimate a cross-correlation function by the inverse FFT of the cross-spectral density. The original smapling rate is usually very low to reduce computation. The sampling rate of the cross-correlation so computed is too low to estimate satisfactorily and an interpolation procedure is therefore needed. The interpolation by zero augmented spectrum is concise, fast and accurate. The results of the computer simulation and real nuderwater signal processing are given in the paper.
文摘In our previous work, a novel algorithm to perform robust pose estimation was presented. The pose was estimated using points on the object to regions on image correspondence. The laboratory experiments conducted in the previous work showed that the accuracy of the estimated pose was over 99% for position and 84% for orientation estimations respectively. However, for larger objects, the algorithm requires a high number of points to achieve the same accuracy. The requirement of higher number of points makes the algorithm, computationally intensive resulting in the algorithm infeasible for real-time computer vision applications. In this paper, the algorithm is parallelized to run on NVIDIA GPUs. The results indicate that even for objects having more than 2000 points, the algorithm can estimate the pose in real time for each frame of high-resolution videos.
基金supported by the National Key R&D Program of China(2023YFF0723300)National Natural Science Foundation of China(62475198,62075200,12374295)+8 种基金Fundamental Research Funds for the Central Universities(2042024kf0003,2042024kf1010,2042023kf0105)Hubei Provincial Natural Science Foundation of China(2023AFB133)Jiangsu Science and Technology Program(BK20221257)Shenzhen Science and Technology Program(JCYJ20220530140601003,JCYJ20230807090207014)Translational Medicine and Multidisciplinary Research Project of Zhongnan Hospital of Wuhan University(ZNJC202217,ZNJC202232)The Interdisciplinary Innovative Talents Foundation from Renmin Hospital of Wuhan University(JCRCYR-2022-006)Hubei Province Young Science and Technology Talent Morning Hight Lift Project(202319)The Fund of National Key Laboratory of Plasma Physics(6142A04230201)We gratefully acknowledge Serendipity Lab for facilitating collaboration opportunities.
文摘Imaging flow cytometry(IFC)combines the imaging capabilities of microscopy with the high throughput of flow cytometry,offering a promising solution for high-precision and high-throughput cell analysis in fields such as biomedicine,green energy,and environmental monitoring.However,due to limitations in imaging framerate and realtime data processing,the real-time throughput of existing IFC systems has been restricted to approximately 1000-10,000 events per second(eps),which is insufficient for large-scale cell analysis.In this work,we demonstrate IFC with real-time throughput exceeding 1,000,000 eps by integrating optical time-stretch(OTS)imaging,microfluidic-based cell manipulation,and online image processing.Cells flowing at speeds up to 15 m/s are clearly imaged with a spatial resolution of 780 nm,and images of each individual cell are captured,stored,and analyzed.The capabilities and performance of our system are validated through the identification of malignancies in clinical colorectal samples.This work sets a new record for throughput in imaging flow cytometry,and we believe it has the potential to revolutionize cell analysis by enabling highly efficient,accurate,and intelligent measurement.
文摘A real time algorithm is presented here to recognize and analyze 8 channel simultaneous electro cardiograph(ECG). The algorithm transforms 8 channel simultaneous ECG into three orthogonal vectors and spatial velocity first, then forms the spatial velocity sample, and uses this spatial velocity sample to recognize each beat. The algorithm computes the averaged parameters by using averaged spatial velocity and the averaged ECG and the current parameters by using the current beat period and current width of QRS. The algorithm can recognize P, QRS and T onsets and ends of simultaneous 12 lead ECG precisely, and some arrhythmias such as premature ventricular beat, ventricular escape beat, R on T, bigeminy, trigeminy. The algorithm software works well on a real 8 channel ECG system and meets the demands of designing.
基金the support from the union project of Peking University third hospital&Chinese Academy of Sciences(Grant No.7490-04,Grant No.KJZD-EW-TZ-L03)the Sichuan Youth Science&Technology Foundation(Grant No.13QNJJ0034)+1 种基金the West Light Foundation of the Chinese Academy of Sciences,the National Major Scientific Equipment program(Grant No.2012YQ120080)the National Science Foundation of China(Grant No.6118082).
文摘A multi-GPU system designed for high-speed,real-time signal processing of optical coherencetomography(OCT)is described herein.For the OCT data sampled in linear wave numbers,themaximum procesing rates reached 2.95 MHz for 1024-OCT and 1.96 MHz for 2048-OCT.Data sampled using linear wavelengths were re-sampled using a time-domain interpolation method and zero-padding interpolation method to improve image quality.The maximum processing rates for1024-OCT reached 2.16 MHz for the time-domain method and 1.26 MHz for the zero-paddingmethod.The maximum processing rates for 2048-0CT reached_1.58 MHz,and 0.68 MHz,respectively.This method is capable of high-speed,real-time processing for O CT systems.
文摘Simple GNSS navigation receivers, developed for the mass market, can be used for positioning with sub centimeter accuracy in a wireless sensor network if the read-out of the carrier phase data is possible and all data is permanently broadcast to a central computer for near real time processing of the respective base lines. Experiences gained in two research projects related to landslide monitoring are depicted in terms of quality and reliability of the results by the developed approach. As far as possible a modular system set up with commercial off-the-shelf components, e.g., standard WLAN fur commtmication, solar batteries with solar panels for autarkic power supply and in cooperation of existing proofed program tools is chosen. The challenge of the still ongoing development is to have a flexible and robust GNSS based sensor network available - concerned not only for landslide monitoring in future.
文摘Compared to small molecule process analytical technology （PAT） applications, biotechnology product PAT applications have certain unique challenges and opportunities. Understanding process dynamics of bioreactor cell culture process is essential to establish an appropriate process control strategy for biotechnology product PAT applications. Inline spectroscopic techniques for real time monitoring of bioreactor cell culture process have the distinct potential to develop PAT approaches in manufac- turing biotechnology drug products. However, the use of inline Fourier transform infrared （FTIR） spectroscopic techniques for bioreactor cell culture process monitoring has not been reported. In this work, real time inline FTIR Spectroscopy was applied to a lab scale bioreactor mAb IgG3 cell culture fluid biomolecular dynamic model. The technical feasibility of using FTIR Spectroscopy for real time tracking and monitoring four key cell culture metabolites （including glucose, glutamine, lactate, and ammonia） and protein yield at increasing levels of complexity （simple binary system, fully formulated media, actual bioreactor cell culture process） was evaluated via a stepwise approach. The FTIR fingerprints of the key metabolites were identified. The multivariate partial least squares （PLS） calibration models were established to correlate the process FTIR spectra with the concentrations of key metabolites and protein yield of in-process samples, either individually for each metabolite and protein or globally for all four metabolites simultaneously. Applying the 2＇ld derivative pre-processing algorithm to the FTIR spectra helps to reduce the number of PLS latent variables needed significantly and thus simplify the interpretation of the PLS models. The validated PLS models show promise in predicting the concentration profiles of glucose, glutamine, lactate, and ammonia and protein yield over the course of the bioreactor cell culture process. Therefore, this work demonstrated the technical feasibility of real time monitoring of the bioreactor cell culture process via FTIR spectroscopy. Its implications for enabling cell culture PAT were discussed.
