Building compact 3D maps of the environment models has become an important research topic. This paper presented an efficient stream decimation algorithm of massive meshes. The algorithm adapted the pre-processing step...Building compact 3D maps of the environment models has become an important research topic. This paper presented an efficient stream decimation algorithm of massive meshes. The algorithm adapted the pre-processing step leading to lower in-corn memory consumption. This algorithm is applied to reconstructing compact terrain with mobile robot, achieving satisfying results.展开更多
Image mosaicking is widely used in Geographic Information Systems(GISs)for largescale ground surface analysis.However,most existing mosaicking methods can only be used in offline processing due to the enormous amounts...Image mosaicking is widely used in Geographic Information Systems(GISs)for largescale ground surface analysis.However,most existing mosaicking methods can only be used in offline processing due to the enormous amounts of computation.In this paper,we propose a novel and practical algorithm for real-time infrared video mosaicking.To achieve this,a novel fast template matching algorithm based on Sum of Cosine Differences(SCD)is proposed to coarsely match the sequential images.The high speed of the proposed template matching algorithm is obtained by computing correlation with Fast Fourier Transform(FFT).We also propose a novel fast Least Squares Matching(LSM)algorithm for inter-frame fine registration,which can significantly reduce the computation without degrading the matching accuracy.In addition,the proposed fast LSM can effectively adapt for noise degradation and geometric distortion.Based on the proposed fast template matching algorithm and fine registration algorithm,we develop a practical real-time mosaicking approach which can produce seamless mosaic image highly efficiently.Experiments on synthetic and real-world datasets demonstrate that the proposed algorithm is not just computationally efficient but also robust against various noise distortions.展开更多
We consider qualitatively robust predictive mappings of stochastic environmental models, where protection against outlier data is incorporated. We utilize digital representations of the models and deploy stochastic bi...We consider qualitatively robust predictive mappings of stochastic environmental models, where protection against outlier data is incorporated. We utilize digital representations of the models and deploy stochastic binary neural networks that are pre-trained to produce such mappings. The pre-training is implemented by a back propagating supervised learning algorithm which converges almost surely to the probabilities induced by the environment, under general ergodicity conditions.展开更多
This paper proposes a new rapid and efficient method for woolen textile simulation- mapping synthesize. This method uses a stochastic function to simulate fuzz on some types of wool textile. The wool yarns are simulat...This paper proposes a new rapid and efficient method for woolen textile simulation- mapping synthesize. This method uses a stochastic function to simulate fuzz on some types of wool textile. The wool yarns are simulated on the basis of Phong illumination model. In order to obtain a visual effect of the wool textile with fuzz, the light intensity of fuzz is synthesized as a color parameter in the Phong illumination model after the yams have been simulated. The model of woolen textile with fuzz can be built eventually.With synthesis mapping methods, user can choose his favorite fuzz density on the wool by controlling some appropriate parameters.展开更多
With the continuous improvement of the performance and the increasing variety of optical mapping and remote sensing satellites,they have become an important support for obtaining global accurate surveying and mapping ...With the continuous improvement of the performance and the increasing variety of optical mapping and remote sensing satellites,they have become an important support for obtaining global accurate surveying and mapping remote sensing information.At present,optical mapping and remote sensing satellites already have sub-meter spatial resolution capabilities,but there is a serious lag problem in mapping and remote sensing information services.It is urgent to develop intelligent mapping and remote sensing satellites to promote the transformation and upgrading to real-time intelligent services.Firstly,based on the three imaging systems of the optical mapping and remote sensing satellites and their realization methods and application characteristics,this paper analyzes the applicable system of the intelligent mapping and remote sensing satellites.Further,according to the application requirements of real-time,intelligence,and popularization,puts forward the design concept of integrated intelligent remote sensing satellite integrating communication,navigation,and remote sensing and focuses on the service mode and integrated function composition of intelligent remote sensing satellite.Then expounds on the performance and characteristics of the Luojia-301 satellite,a new generation of intelligent surveying and mapping remote sensing scientific test satellite.And finally summarizes and prospects the development and mission of intelligent mapping remote sensing satellites.Luojia-301 satellite integrates remote sensing and communication functions.It explores an efficient and intelligent service mode of mapping and remote sensing information from data acquisition to the application terminal and provides a real service verification platform for on-orbit processing and real-time transmission of remote sensing data based on space-ground internet,which is of great significance to the construction of China’s spatial information network.展开更多
This paper describes GPS Workstation, a general purpose navigation software which requires a low-cost GPS connected to the computer. It provides an integrated display of positioning data along with satellite positions...This paper describes GPS Workstation, a general purpose navigation software which requires a low-cost GPS connected to the computer. It provides an integrated display of positioning data along with satellite positions, their signal strengths and data quality parameters. The software can be used for static point averaging of GPS data to get more precise positioning and real-time mapping of roads and tracks. It supports output of data in keyhole markup language (KML) as well as other formats for visualization of acquired data on Google Earth and geographic information systems. It can also be used to determine geo-referencing errors in Google Earth imagery for an area and can compensate the error by applying a constant X, Y shift. The software is available for distribution under the free software license.展开更多
Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance o...Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.展开更多
With the support by the National Natural Science Foundation of China and East China Normal University,the research team led by Prof.Tian Yang(田阳)at the Shanghai Key Laboratory of Green Chemistry and Chemical Process...With the support by the National Natural Science Foundation of China and East China Normal University,the research team led by Prof.Tian Yang(田阳)at the Shanghai Key Laboratory of Green Chemistry and Chemical Processes,East China Normal University,developed a novel SERS Optophysiological probe for brain research,which was published in Angew Chem Int Ed(2019,58:5256—5260).展开更多
Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportatio...Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.展开更多
With the dramatic development of spatial data in- frastructure, CyberGIS has become significant for geospatial data sharing. Due to the large number of concurrent users and large volume of vector data, CyberGIS faces ...With the dramatic development of spatial data in- frastructure, CyberGIS has become significant for geospatial data sharing. Due to the large number of concurrent users and large volume of vector data, CyberGIS faces a great chal- lenge in how to improve performance. The real-time visual- ization of vector maps is the most common function in Cyber- GIS applications, and it is time-consuming especially when the data volume becomes large. So, how to improve the effi- ciency of visualization of large vector maps is still a signif- icant research direction for GIScience scientists. In this re- search, we review the existing three optimization strategies, and determine that the third category strategy （i.e., parallel optimization） is appropriate for the real-time visualization of large vector maps. One of the key issues of parallel optimiza- tion is how to decompose the real-time visualization tasks into balanced sub tasks while taking into consideration the spatial heterogeneous characteristics. We put forward some rules that the decomposition should conform to, and design a real-time visualization framework for large vector maps. We focus on a balanced decomposition approach that can assure efficiency and effectiveness. Considering the spatial hetero- geneous characteristic of vector data, we use a ＂horizontal grid, vertical multistage＂ approach to construct a spatial point distribution information grid. The load balancer analyzes the spatial characteristics of the map requests and decomposes the real-time viewshed into multiple balanced sub viewsheds.Then, all the sub viewsheds are distributed to multiple server nodes to be executed in parallel, so as to improve the real- time visualization efficiency of large vector maps. A group of experiments have been conducted by us. The analysis results demonstrate that the approach proposed in this research has the ability of balanced decomposition, and it is efficient and effective for all geometry types of vector data.展开更多
Complete and efficient detection of unknown targets is the most popular application of UAV swarms. Under most situations, targets have directional characteristics so that they can only be successfully detected within ...Complete and efficient detection of unknown targets is the most popular application of UAV swarms. Under most situations, targets have directional characteristics so that they can only be successfully detected within specific angles. In such cases, how to coordinate UAVs and allocate optimal paths for them to efficiently detect all the targets is the primary issue to be solved. In this paper, an intelligent target detection method is proposed for UAV swarms to achieve real-time detection requirements. First, a target-feature-information-based disintegration method is built up to divide the search space into a set of cubes. Theoretically, when the cubes are traversed, all the targets can be detected. Then, a Kuhn-Munkres(KM)-algorithm-based path planning method is proposed for UAVs to traverse the cubes. Finally, to further improve search efficiency, a 3 D realtime probability map is established over the search space which estimates the possibility of detecting new targets at each point. This map is adopted to modify the weights in KM algorithm, thereby optimizing the UAVs’ paths during the search process. Simulation results show that with the proposed method, all targets, with detection angle limitations, can be found by UAVs. Moreover, by implementing the 3 D probability map, the search efficiency is improved by 23.4%–78.1%.展开更多
Retinoic acid can cause many types of cells,including mouse neuroblastoma Neuro-2 A cells,to differentiate into neurons.However,it is still unknown whether microRNAs(miRNAs)play a role in this neuronal differentiation...Retinoic acid can cause many types of cells,including mouse neuroblastoma Neuro-2 A cells,to differentiate into neurons.However,it is still unknown whether microRNAs(miRNAs)play a role in this neuronal differentiation.To address this issue,real-time polymerase chain reaction assays were used to detect the expression of several differentiation-related miRNAs during the differentiation of retinoic acid-treated Neuro-2 A cells.The results revealed that miR-124 and miR-9 were upregulated,while miR-125 b was downregulated in retinoic acid-treated Neuro-2 A cells.To identify the miRNA that may play a key role,miR-124 expression was regulated by transfection of miRNA mimics or inhibitors.Morphological analysis results showed that inhibition of miR-124 expression reversed the effects of retinoic acid on neurite outgrowth.Moreover,miR-124 overexpression alone caused Neuro-2 A cells to differentiate into neurons,and its inhibitor could block this effect.These results suggest that miR-124 plays an important role in retinoic acid-induced differentiation of Neuro-2 A cells.展开更多
An Augmented virtual environment(AVE)is concerned with the fusion of real-time video with 3D models or scenes so as to augment the virtual environment.In this paper,a new approach to establish an AVE with a wide field...An Augmented virtual environment(AVE)is concerned with the fusion of real-time video with 3D models or scenes so as to augment the virtual environment.In this paper,a new approach to establish an AVE with a wide field of view is proposed,including real-time video projection,multiple video texture fusion and 3D visualization of moving objects.A new diagonally weighted algorithm is proposed to smooth the apparent gaps within the overlapping area between the two adjacent videos.A visualization method for the location and trajectory of a moving virtual object is proposed to display the moving object and its trajectory in the 3D virtual environment.The experimental results showed that the proposed set of algorithms are able to fuse multiple real-time videos with 3D models efficiently,and the experiment runs a 3D scene containing two million triangles and six real-time videos at around 55 frames per second on a laptop with 1GB of graphics card memory.In addition,a realistic AVE with a wide field of view was created based on the Digital Earth Science Platform by fusing three videos with a complex indoor virtual scene,visualizing a moving object and drawing its trajectory in the real time.展开更多
Virtual Reality provides a new approach for geographical research. In this paper, a framework of the Virtual Huanghe （Yellow） River System was first presented from the view of technology, which included five main mo...Virtual Reality provides a new approach for geographical research. In this paper, a framework of the Virtual Huanghe （Yellow） River System was first presented from the view of technology, which included five main modules——data sources, 3D simulation terrain database, 3D simulation model database, 3D simulation implementation and application system. Then the key technoiogies of constructing Virtual Huanghe River System were discussed in detail： 1） OpenGL technology, the 3D graphics developing instrument, was employed in Virtual Huanghe River System to realize the function of dynamic real-time navigation. 2） MO and OpenGL technologies were used to make the mutual response between 3D scene and 2D electronic map available, which made use of the advantages of both 3D scene and 2D electronic map, with the macroscopic view, integrality and conciseness of 2D electronic map combined with the locality, reality and visualization of 3D scene. At the same time the disadvantages of abstract and ambiguity of 2D electronic map and the direction losing of virtual navigation in 3D scene were overcome.展开更多
Nowadays, inter-task interferences are the main difficulty in analyzing the timing behavior of multicores. The timing predictable embedded multicore architecture MERASA, which allows safe worst-case execution time （W...Nowadays, inter-task interferences are the main difficulty in analyzing the timing behavior of multicores. The timing predictable embedded multicore architecture MERASA, which allows safe worst-case execution time （WCET） estimations, has emerged as an attractive solution. In the architecture, WCET can be estimated by the upper bound delay （UBD） which can be bounded by the interference-aware bus arbiter （IABA） and the dynamic cache partitioning such as columnization or bankization. However, this architecture faces a dilemma between decreasing UBD and efficient shared cache utilization. To obtain tighter WCET estimation, we propose a novel approach that reduces UBD by optimizing bank-to-core mapping on the multicore system with IABA and the two-level partitioned cache. For this, we first present a new UBD computation model based on the analysis of inter-task interference delay, and then put forward the core-sequence optimization method of bank-to-core mapping and the optimizing algorithms with the minimum UBD. Experimental results demonstrate that our approach can reduce WCET from 4% to 37%.展开更多
We present results of real-time and sensitive MR Thermometry (MRT) using a paramagnetic lanthanide complex thulium 1,4,7,10-tetraazacyclododecane-1,4,7,10-tetramethyl-1,4,7,10-tetraa-cetate (Tm-DOTMA) to study radio f...We present results of real-time and sensitive MR Thermometry (MRT) using a paramagnetic lanthanide complex thulium 1,4,7,10-tetraazacyclododecane-1,4,7,10-tetramethyl-1,4,7,10-tetraa-cetate (Tm-DOTMA) to study radio frequency (RF) heating induced by a copper wire and a titanium bone screw in an agarose gel phantom. The temperature dependent chemical shift coefficient (TDCSC) of the methyl resonance was found to be 0.7 ± 0.03 ppm/°;C in agarose gel. The methyl protons of Tm-DOTMA were imaged using 2D chemical shift imaging (CSI) and 3D phase mapping methods (PMM), approximately 7 sec long, and compared with conventional water proton resonance frequency (PRF) method. Two RF-induced heating approaches were tested: 1) using a prescan before the MRT;or 2) using the heating caused by the imaging pulse during continuous imaging. Both approaches allowed detection of temperature changes which are less than 1°;C and continuously mapping temperature changes around the copper wire. Using a heating pre-scan, the Tm-DOTMA 2D-CSI allowed better qualitative visualization of the temperature changes around the titanium screw compared with water phase shift thermometry. Numerical electromagnetic field simulations were also conducted for the evaluation of orientation dependency using the copper wire in 4.7 T (200 MHz). Thermometry approach using Tm-DOTMA can detect smaller temperature changes with decreased scanning time resulting in real-time and sensitive temperature mapping.展开更多
Limited by the sampling capacity of the mobile devices, many real-time indoor location systems have such problems as low accuracy, large variance, and non-smooth movement of the estimated position. A new positioning a...Limited by the sampling capacity of the mobile devices, many real-time indoor location systems have such problems as low accuracy, large variance, and non-smooth movement of the estimated position. A new positioning algorithm and a new processing method for sampled data are proposed. Firstly, a positioning algorithm is designed based on the cluster-based nearest neighbour or probability. Secondly, a weighted average method with sliding window is used to process the sampled data as to overcome the mobile devices’ weak capability of signal sampling. Experimental results show that, for the general mobile devices, the accuracy of indoor position estimation increases from 56.5% to 76.6% for a 2-meter precision, and from 77.4% to 90.9% for a 3-meter precision. Therefore, the proposed methods can significantly and stably improve the positioning accuracy.展开更多
This study focuses on the illumination and temperature at China’s next lunar candidate landing site Shackleton crater.We used the NASA’s SPICE system to evaluate the terrain obscuration effect on real-time illuminat...This study focuses on the illumination and temperature at China’s next lunar candidate landing site Shackleton crater.We used the NASA’s SPICE system to evaluate the terrain obscuration effect on real-time illumination;the resulting illumination map resembles previous studies,validating the methodologies used in our study.In addition,we estimated an accumulated illumination map for the period of likely rover movement.The map indicates the illuminated inner wall of the Shackleton crater is close to 27%of the whole,meaning that the rover will likely receive solar radiation during its movement.Using the real-time illumination and the distributed 1-D thermal diffusion model,we continuously evaluated the regolith temperature for more than 20 years to stabilize the temperature,and selected the temperature of the end time as the initial value used in a thermal study set for July 20,2023 and May 8,2027.Our results indicate the temperature in the permanent shadow region remains nearly constant,thus validating the stability of our estimated initial temperature.Our results also indicate that the surface temperature is more sensitive to transient illumination,but the subsurface temperature is more likely to be associated with the accumulated illumination.This difference indirectly implies that the conductivity of the lunar regolith is inefficient.The locations receiving more solar radiation show a temperature larger than the threshold(~112 K)of ice stability.The permanently shadowed regions can be as cold as 25 K,and such extreme coldness is a hazard to the rover.There are suitable temperature locations which have a warm surface but cold subsurface to preserve water ice.To further ensure normal rover movement,we provided a map of suitable temperature sites and found that these locations exist not only in the Shackleton crater’s inner wall,but also outside the crater.We suggested four trade-off sampling sites with suitable temperatures and gradual slopes.展开更多
文摘Building compact 3D maps of the environment models has become an important research topic. This paper presented an efficient stream decimation algorithm of massive meshes. The algorithm adapted the pre-processing step leading to lower in-corn memory consumption. This algorithm is applied to reconstructing compact terrain with mobile robot, achieving satisfying results.
基金supported by the National Natural Science Foundation of China(No.61802423)the Natural Science Foundation of Hunan Province,China(No.2019JJ50739)。
文摘Image mosaicking is widely used in Geographic Information Systems(GISs)for largescale ground surface analysis.However,most existing mosaicking methods can only be used in offline processing due to the enormous amounts of computation.In this paper,we propose a novel and practical algorithm for real-time infrared video mosaicking.To achieve this,a novel fast template matching algorithm based on Sum of Cosine Differences(SCD)is proposed to coarsely match the sequential images.The high speed of the proposed template matching algorithm is obtained by computing correlation with Fast Fourier Transform(FFT).We also propose a novel fast Least Squares Matching(LSM)algorithm for inter-frame fine registration,which can significantly reduce the computation without degrading the matching accuracy.In addition,the proposed fast LSM can effectively adapt for noise degradation and geometric distortion.Based on the proposed fast template matching algorithm and fine registration algorithm,we develop a practical real-time mosaicking approach which can produce seamless mosaic image highly efficiently.Experiments on synthetic and real-world datasets demonstrate that the proposed algorithm is not just computationally efficient but also robust against various noise distortions.
文摘We consider qualitatively robust predictive mappings of stochastic environmental models, where protection against outlier data is incorporated. We utilize digital representations of the models and deploy stochastic binary neural networks that are pre-trained to produce such mappings. The pre-training is implemented by a back propagating supervised learning algorithm which converges almost surely to the probabilities induced by the environment, under general ergodicity conditions.
文摘This paper proposes a new rapid and efficient method for woolen textile simulation- mapping synthesize. This method uses a stochastic function to simulate fuzz on some types of wool textile. The wool yarns are simulated on the basis of Phong illumination model. In order to obtain a visual effect of the wool textile with fuzz, the light intensity of fuzz is synthesized as a color parameter in the Phong illumination model after the yams have been simulated. The model of woolen textile with fuzz can be built eventually.With synthesis mapping methods, user can choose his favorite fuzz density on the wool by controlling some appropriate parameters.
基金National Natural Science Foundation of China(Nos.91738302,91838303)。
文摘With the continuous improvement of the performance and the increasing variety of optical mapping and remote sensing satellites,they have become an important support for obtaining global accurate surveying and mapping remote sensing information.At present,optical mapping and remote sensing satellites already have sub-meter spatial resolution capabilities,but there is a serious lag problem in mapping and remote sensing information services.It is urgent to develop intelligent mapping and remote sensing satellites to promote the transformation and upgrading to real-time intelligent services.Firstly,based on the three imaging systems of the optical mapping and remote sensing satellites and their realization methods and application characteristics,this paper analyzes the applicable system of the intelligent mapping and remote sensing satellites.Further,according to the application requirements of real-time,intelligence,and popularization,puts forward the design concept of integrated intelligent remote sensing satellite integrating communication,navigation,and remote sensing and focuses on the service mode and integrated function composition of intelligent remote sensing satellite.Then expounds on the performance and characteristics of the Luojia-301 satellite,a new generation of intelligent surveying and mapping remote sensing scientific test satellite.And finally summarizes and prospects the development and mission of intelligent mapping remote sensing satellites.Luojia-301 satellite integrates remote sensing and communication functions.It explores an efficient and intelligent service mode of mapping and remote sensing information from data acquisition to the application terminal and provides a real service verification platform for on-orbit processing and real-time transmission of remote sensing data based on space-ground internet,which is of great significance to the construction of China’s spatial information network.
文摘This paper describes GPS Workstation, a general purpose navigation software which requires a low-cost GPS connected to the computer. It provides an integrated display of positioning data along with satellite positions, their signal strengths and data quality parameters. The software can be used for static point averaging of GPS data to get more precise positioning and real-time mapping of roads and tracks. It supports output of data in keyhole markup language (KML) as well as other formats for visualization of acquired data on Google Earth and geographic information systems. It can also be used to determine geo-referencing errors in Google Earth imagery for an area and can compensate the error by applying a constant X, Y shift. The software is available for distribution under the free software license.
文摘Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.
文摘With the support by the National Natural Science Foundation of China and East China Normal University,the research team led by Prof.Tian Yang(田阳)at the Shanghai Key Laboratory of Green Chemistry and Chemical Processes,East China Normal University,developed a novel SERS Optophysiological probe for brain research,which was published in Angew Chem Int Ed(2019,58:5256—5260).
基金funded by the Deanship of Scientific Research at Northern Border University,Arar,Saudi Arabia through research group No.(RG-NBU-2022-1234).
文摘Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.
文摘With the dramatic development of spatial data in- frastructure, CyberGIS has become significant for geospatial data sharing. Due to the large number of concurrent users and large volume of vector data, CyberGIS faces a great chal- lenge in how to improve performance. The real-time visual- ization of vector maps is the most common function in Cyber- GIS applications, and it is time-consuming especially when the data volume becomes large. So, how to improve the effi- ciency of visualization of large vector maps is still a signif- icant research direction for GIScience scientists. In this re- search, we review the existing three optimization strategies, and determine that the third category strategy （i.e., parallel optimization） is appropriate for the real-time visualization of large vector maps. One of the key issues of parallel optimiza- tion is how to decompose the real-time visualization tasks into balanced sub tasks while taking into consideration the spatial heterogeneous characteristics. We put forward some rules that the decomposition should conform to, and design a real-time visualization framework for large vector maps. We focus on a balanced decomposition approach that can assure efficiency and effectiveness. Considering the spatial hetero- geneous characteristic of vector data, we use a ＂horizontal grid, vertical multistage＂ approach to construct a spatial point distribution information grid. The load balancer analyzes the spatial characteristics of the map requests and decomposes the real-time viewshed into multiple balanced sub viewsheds.Then, all the sub viewsheds are distributed to multiple server nodes to be executed in parallel, so as to improve the real- time visualization efficiency of large vector maps. A group of experiments have been conducted by us. The analysis results demonstrate that the approach proposed in this research has the ability of balanced decomposition, and it is efficient and effective for all geometry types of vector data.
文摘Complete and efficient detection of unknown targets is the most popular application of UAV swarms. Under most situations, targets have directional characteristics so that they can only be successfully detected within specific angles. In such cases, how to coordinate UAVs and allocate optimal paths for them to efficiently detect all the targets is the primary issue to be solved. In this paper, an intelligent target detection method is proposed for UAV swarms to achieve real-time detection requirements. First, a target-feature-information-based disintegration method is built up to divide the search space into a set of cubes. Theoretically, when the cubes are traversed, all the targets can be detected. Then, a Kuhn-Munkres(KM)-algorithm-based path planning method is proposed for UAVs to traverse the cubes. Finally, to further improve search efficiency, a 3 D realtime probability map is established over the search space which estimates the possibility of detecting new targets at each point. This map is adopted to modify the weights in KM algorithm, thereby optimizing the UAVs’ paths during the search process. Simulation results show that with the proposed method, all targets, with detection angle limitations, can be found by UAVs. Moreover, by implementing the 3 D probability map, the search efficiency is improved by 23.4%–78.1%.
基金supported by the Natural Science Foundation of Shanghai of China,No.16ZR1410500(to SZD)
文摘Retinoic acid can cause many types of cells,including mouse neuroblastoma Neuro-2 A cells,to differentiate into neurons.However,it is still unknown whether microRNAs(miRNAs)play a role in this neuronal differentiation.To address this issue,real-time polymerase chain reaction assays were used to detect the expression of several differentiation-related miRNAs during the differentiation of retinoic acid-treated Neuro-2 A cells.The results revealed that miR-124 and miR-9 were upregulated,while miR-125 b was downregulated in retinoic acid-treated Neuro-2 A cells.To identify the miRNA that may play a key role,miR-124 expression was regulated by transfection of miRNA mimics or inhibitors.Morphological analysis results showed that inhibition of miR-124 expression reversed the effects of retinoic acid on neurite outgrowth.Moreover,miR-124 overexpression alone caused Neuro-2 A cells to differentiate into neurons,and its inhibitor could block this effect.These results suggest that miR-124 plays an important role in retinoic acid-induced differentiation of Neuro-2 A cells.
基金Research presented in this paper was funded by the National Key Research and Development Program of China[grant numbers 2016YFB0501503 and 2016YFB0501502]Hainan Provincial Department of Science and Technology[grant number ZDKJ2016021].
文摘An Augmented virtual environment(AVE)is concerned with the fusion of real-time video with 3D models or scenes so as to augment the virtual environment.In this paper,a new approach to establish an AVE with a wide field of view is proposed,including real-time video projection,multiple video texture fusion and 3D visualization of moving objects.A new diagonally weighted algorithm is proposed to smooth the apparent gaps within the overlapping area between the two adjacent videos.A visualization method for the location and trajectory of a moving virtual object is proposed to display the moving object and its trajectory in the 3D virtual environment.The experimental results showed that the proposed set of algorithms are able to fuse multiple real-time videos with 3D models efficiently,and the experiment runs a 3D scene containing two million triangles and six real-time videos at around 55 frames per second on a laptop with 1GB of graphics card memory.In addition,a realistic AVE with a wide field of view was created based on the Digital Earth Science Platform by fusing three videos with a complex indoor virtual scene,visualizing a moving object and drawing its trajectory in the real time.
基金Under the auspices of the Science Data Sharing Pilot Project of Ministry of Science and Technology of China (No. 2003DEA2C010), Natural Science Fund of Henan University on Virtual City Construction Method (No. 04YBRW026)
文摘Virtual Reality provides a new approach for geographical research. In this paper, a framework of the Virtual Huanghe （Yellow） River System was first presented from the view of technology, which included five main modules——data sources, 3D simulation terrain database, 3D simulation model database, 3D simulation implementation and application system. Then the key technoiogies of constructing Virtual Huanghe River System were discussed in detail： 1） OpenGL technology, the 3D graphics developing instrument, was employed in Virtual Huanghe River System to realize the function of dynamic real-time navigation. 2） MO and OpenGL technologies were used to make the mutual response between 3D scene and 2D electronic map available, which made use of the advantages of both 3D scene and 2D electronic map, with the macroscopic view, integrality and conciseness of 2D electronic map combined with the locality, reality and visualization of 3D scene. At the same time the disadvantages of abstract and ambiguity of 2D electronic map and the direction losing of virtual navigation in 3D scene were overcome.
基金This work is supported by the National Natural Science Foundation of China under Grant No. 61370062.
文摘Nowadays, inter-task interferences are the main difficulty in analyzing the timing behavior of multicores. The timing predictable embedded multicore architecture MERASA, which allows safe worst-case execution time （WCET） estimations, has emerged as an attractive solution. In the architecture, WCET can be estimated by the upper bound delay （UBD） which can be bounded by the interference-aware bus arbiter （IABA） and the dynamic cache partitioning such as columnization or bankization. However, this architecture faces a dilemma between decreasing UBD and efficient shared cache utilization. To obtain tighter WCET estimation, we propose a novel approach that reduces UBD by optimizing bank-to-core mapping on the multicore system with IABA and the two-level partitioned cache. For this, we first present a new UBD computation model based on the analysis of inter-task interference delay, and then put forward the core-sequence optimization method of bank-to-core mapping and the optimizing algorithms with the minimum UBD. Experimental results demonstrate that our approach can reduce WCET from 4% to 37%.
文摘We present results of real-time and sensitive MR Thermometry (MRT) using a paramagnetic lanthanide complex thulium 1,4,7,10-tetraazacyclododecane-1,4,7,10-tetramethyl-1,4,7,10-tetraa-cetate (Tm-DOTMA) to study radio frequency (RF) heating induced by a copper wire and a titanium bone screw in an agarose gel phantom. The temperature dependent chemical shift coefficient (TDCSC) of the methyl resonance was found to be 0.7 ± 0.03 ppm/°;C in agarose gel. The methyl protons of Tm-DOTMA were imaged using 2D chemical shift imaging (CSI) and 3D phase mapping methods (PMM), approximately 7 sec long, and compared with conventional water proton resonance frequency (PRF) method. Two RF-induced heating approaches were tested: 1) using a prescan before the MRT;or 2) using the heating caused by the imaging pulse during continuous imaging. Both approaches allowed detection of temperature changes which are less than 1°;C and continuously mapping temperature changes around the copper wire. Using a heating pre-scan, the Tm-DOTMA 2D-CSI allowed better qualitative visualization of the temperature changes around the titanium screw compared with water phase shift thermometry. Numerical electromagnetic field simulations were also conducted for the evaluation of orientation dependency using the copper wire in 4.7 T (200 MHz). Thermometry approach using Tm-DOTMA can detect smaller temperature changes with decreased scanning time resulting in real-time and sensitive temperature mapping.
文摘Limited by the sampling capacity of the mobile devices, many real-time indoor location systems have such problems as low accuracy, large variance, and non-smooth movement of the estimated position. A new positioning algorithm and a new processing method for sampled data are proposed. Firstly, a positioning algorithm is designed based on the cluster-based nearest neighbour or probability. Secondly, a weighted average method with sliding window is used to process the sampled data as to overcome the mobile devices’ weak capability of signal sampling. Experimental results show that, for the general mobile devices, the accuracy of indoor position estimation increases from 56.5% to 76.6% for a 2-meter precision, and from 77.4% to 90.9% for a 3-meter precision. Therefore, the proposed methods can significantly and stably improve the positioning accuracy.
基金funded by the National Natural Science Foundation of China(Grant Nos.41864001 and 42030110)funded by a DAR Grant in Planetology from the France Space Agency(CNES)。
文摘This study focuses on the illumination and temperature at China’s next lunar candidate landing site Shackleton crater.We used the NASA’s SPICE system to evaluate the terrain obscuration effect on real-time illumination;the resulting illumination map resembles previous studies,validating the methodologies used in our study.In addition,we estimated an accumulated illumination map for the period of likely rover movement.The map indicates the illuminated inner wall of the Shackleton crater is close to 27%of the whole,meaning that the rover will likely receive solar radiation during its movement.Using the real-time illumination and the distributed 1-D thermal diffusion model,we continuously evaluated the regolith temperature for more than 20 years to stabilize the temperature,and selected the temperature of the end time as the initial value used in a thermal study set for July 20,2023 and May 8,2027.Our results indicate the temperature in the permanent shadow region remains nearly constant,thus validating the stability of our estimated initial temperature.Our results also indicate that the surface temperature is more sensitive to transient illumination,but the subsurface temperature is more likely to be associated with the accumulated illumination.This difference indirectly implies that the conductivity of the lunar regolith is inefficient.The locations receiving more solar radiation show a temperature larger than the threshold(~112 K)of ice stability.The permanently shadowed regions can be as cold as 25 K,and such extreme coldness is a hazard to the rover.There are suitable temperature locations which have a warm surface but cold subsurface to preserve water ice.To further ensure normal rover movement,we provided a map of suitable temperature sites and found that these locations exist not only in the Shackleton crater’s inner wall,but also outside the crater.We suggested four trade-off sampling sites with suitable temperatures and gradual slopes.
