Multi‐object tracking in autonomous driving is a non‐linear problem.To better address the tracking problem,this paper leveraged an unscented Kalman filter to predict the object's state.In the association stage,t...Multi‐object tracking in autonomous driving is a non‐linear problem.To better address the tracking problem,this paper leveraged an unscented Kalman filter to predict the object's state.In the association stage,the Mahalanobis distance was employed as an affinity metric,and a Non‐minimum Suppression method was designed for matching.With the detections fed into the tracker and continuous‘predicting‐matching’steps,the states of each object at different time steps were described as their own continuous trajectories.We conducted extensive experiments to evaluate tracking accuracy on three challenging datasets(KITTI,nuScenes and Waymo).The experimental results demon-strated that our method effectively achieved multi‐object tracking with satisfactory ac-curacy and real‐time efficiency.展开更多
A wave-current-sediment coupled numerical model is employed to study the responses of suspended sediment transport in the wet season to changes in shoreline and bathymetry in the Zhujiang(Pearl)River Estuary(ZRE)from ...A wave-current-sediment coupled numerical model is employed to study the responses of suspended sediment transport in the wet season to changes in shoreline and bathymetry in the Zhujiang(Pearl)River Estuary(ZRE)from 1971 to 2012.It is shown that,during the wavy period,the large wave-induced bottom stress enhances sediment resuspension,resulting in an increase in the area of suspended sediment concentration(SSC)greater than 100 mg/L by 183.4%.On one hand,in spring tide,the change in shoreline reduces the area of SSC greater than 100 mg/L by 17.8%in the west shoal(WS)but increases the SSC,owing to the closer sediment source to the offshore and the stronger residual current at the Hengmeng(HEM)and Hongqili(HQL)outlets.The eastward Eulerian transport is enhanced in the WS and west channel(WC),resulting in a higher SSC there.The reclamation of Longxue Island(LXI)increases SSC on its east side and east shoal(ES)but decreases the SSC on its west and south sides.Moreover,in the WC,the estuarine turbidity maximum(ETM)is located near the saltwater wedge and moves southward,which is caused by the southward movement of the maximum longitudinal Eulerian transport.In neap tide,the changes are similar but relatively weaker.On the other hand,in spring tide,the change in bathymetry makes the SSC in the WS increase,and the area of SSC greater than 100 mg/L increases by 11.4%and expands eastward and southward,which is caused by the increases in wave-induced bottom stress and eastward Eulerian transport.On the east side of the WC,the eastward Eulerian transport decreases significantly,resulting in a smaller SSC in the middle shoal(MS).In addition,in the WC,the maximum SSC is reduced,which is caused by the smaller wave-induced bottom stress and a significant increase of 109.88%in southward Eulerian transport.The results in neap tide are similar to those in spring tide but with smaller changes,and the sediment transports northward in the WC owing to the northward Eulerian transport and vertical shear transport.This study may provide some references for marine ecological environment security and coastal management in the ZRE and other estuaries worldwide affected by strong human interventions.展开更多
As one of the key operations in Wireless Sensor Networks(WSNs), the energy-efficient data collection schemes have been actively explored in the literature. However, the transform basis for sparsifing the sensed data i...As one of the key operations in Wireless Sensor Networks(WSNs), the energy-efficient data collection schemes have been actively explored in the literature. However, the transform basis for sparsifing the sensed data is usually chosen empirically, and the transformed results are not always the sparsest. In this paper, we propose a Data Collection scheme based on Denoising Autoencoder(DCDA) to solve the above problem. In the data training phase, a Denoising AutoEncoder(DAE) is trained to compute the data measurement matrix and the data reconstruction matrix using the historical sensed data. Then, in the data collection phase, the sensed data of whole network are collected along a data collection tree. The data measurement matrix is utilized to compress the sensed data in each sensor node, and the data reconstruction matrix is utilized to reconstruct the original data in the sink.Finally, the data communication performance and data reconstruction performance of the proposed scheme are evaluated and compared with those of existing schemes using real-world sensed data. The experimental results show that compared to its counterparts, the proposed scheme results in a higher data compression rate, lower energy consumption, more accurate data reconstruction, and faster data reconstruction speed.展开更多
Visual object tracking （VOT） is an important sub- field of computer vision. It has widespread application do- mains, and has been considered as an important part of surveillance and security system. VOA facilitates ...Visual object tracking （VOT） is an important sub- field of computer vision. It has widespread application do- mains, and has been considered as an important part of surveillance and security system. VOA facilitates finding the position of target in image coordinates of video frames. While doing this, VOA also faces many challenges such as noise, clutter, occlusion, rapid change in object appearances, highly maneuvered （complex） object motion, illumination changes. In recent years, VOT has made significant progress due to availability of low-cost high-quality video cameras as well as fast computational resources, and many modern techniques have been proposed to handle the challenges faced by VOT. This article introduces the readers to 1） VOT and its applica- tions in other domains, 2） different issues which arise in it, 3） various classical as well as contemporary approaches for object tracking, 4） evaluation methodologies for VOT, and 5） online resources, i.e., annotated datasets and source code available for various tracking techniques.展开更多
Most previous studies have mainly focused on the analyses of one entire network(graph) or the giant connected components of networks. In this paper, we investigate the disconnected components(non-giant connected compo...Most previous studies have mainly focused on the analyses of one entire network(graph) or the giant connected components of networks. In this paper, we investigate the disconnected components(non-giant connected component) of some real social networks, and report some interesting discoveries about structural properties of disconnected components. We study three diverse, real networks and compute the significance profile of each component. We discover some similarities in the local structure between the giant connected component and disconnected components in diverse social networks. Then we discuss how to detect network attacks based on the local structure properties of networks. Furthermore, we propose an empirical generative model called i Friends to generate networks that follow our observed patterns.展开更多
文摘Multi‐object tracking in autonomous driving is a non‐linear problem.To better address the tracking problem,this paper leveraged an unscented Kalman filter to predict the object's state.In the association stage,the Mahalanobis distance was employed as an affinity metric,and a Non‐minimum Suppression method was designed for matching.With the detections fed into the tracker and continuous‘predicting‐matching’steps,the states of each object at different time steps were described as their own continuous trajectories.We conducted extensive experiments to evaluate tracking accuracy on three challenging datasets(KITTI,nuScenes and Waymo).The experimental results demon-strated that our method effectively achieved multi‐object tracking with satisfactory ac-curacy and real‐time efficiency.
基金The National Natural Science Foundation of China under contract No.41890851the Key Research Program of Frontier Sciences+3 种基金Chinese Academy of Sciences,under contract No.QYZDJ-SSW-DQC034the Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou)under contract No.GML2019ZD0304the fund of Chinese Academy of Sciences under contract No.ISEE2021PY01the project of Department of Natural Resources of Guangdong Province under contract No.[2020]017。
文摘A wave-current-sediment coupled numerical model is employed to study the responses of suspended sediment transport in the wet season to changes in shoreline and bathymetry in the Zhujiang(Pearl)River Estuary(ZRE)from 1971 to 2012.It is shown that,during the wavy period,the large wave-induced bottom stress enhances sediment resuspension,resulting in an increase in the area of suspended sediment concentration(SSC)greater than 100 mg/L by 183.4%.On one hand,in spring tide,the change in shoreline reduces the area of SSC greater than 100 mg/L by 17.8%in the west shoal(WS)but increases the SSC,owing to the closer sediment source to the offshore and the stronger residual current at the Hengmeng(HEM)and Hongqili(HQL)outlets.The eastward Eulerian transport is enhanced in the WS and west channel(WC),resulting in a higher SSC there.The reclamation of Longxue Island(LXI)increases SSC on its east side and east shoal(ES)but decreases the SSC on its west and south sides.Moreover,in the WC,the estuarine turbidity maximum(ETM)is located near the saltwater wedge and moves southward,which is caused by the southward movement of the maximum longitudinal Eulerian transport.In neap tide,the changes are similar but relatively weaker.On the other hand,in spring tide,the change in bathymetry makes the SSC in the WS increase,and the area of SSC greater than 100 mg/L increases by 11.4%and expands eastward and southward,which is caused by the increases in wave-induced bottom stress and eastward Eulerian transport.On the east side of the WC,the eastward Eulerian transport decreases significantly,resulting in a smaller SSC in the middle shoal(MS).In addition,in the WC,the maximum SSC is reduced,which is caused by the smaller wave-induced bottom stress and a significant increase of 109.88%in southward Eulerian transport.The results in neap tide are similar to those in spring tide but with smaller changes,and the sediment transports northward in the WC owing to the northward Eulerian transport and vertical shear transport.This study may provide some references for marine ecological environment security and coastal management in the ZRE and other estuaries worldwide affected by strong human interventions.
基金Acknowledgments This work was supported by the National Natural Science Foundation of China （Grant No. 60873241 and 60673178） and the National High Technology Research and Development Program of China （863 Program, Grant No. 2008AA01 Z217 and 2007AA01A127）.
基金supported by the National Natural Science Foundation of China (Nos. 61402094, 61572060, and 61702089)the Natural Science Foundation of Hebei Province (Nos. F2016501076 and F2016501079)+3 种基金the Natural Science Foundation of Liaoning Province (No. 201602254)the Fundamental Research Funds for the Central Universities (No. N172304022)the Science and Technology Plan Project of Guangzhou (No. 201804010433)the Bidding Project of Laboratory of Language Engineering and Computing (No. LEC2017ZBKT001)
文摘As one of the key operations in Wireless Sensor Networks(WSNs), the energy-efficient data collection schemes have been actively explored in the literature. However, the transform basis for sparsifing the sensed data is usually chosen empirically, and the transformed results are not always the sparsest. In this paper, we propose a Data Collection scheme based on Denoising Autoencoder(DCDA) to solve the above problem. In the data training phase, a Denoising AutoEncoder(DAE) is trained to compute the data measurement matrix and the data reconstruction matrix using the historical sensed data. Then, in the data collection phase, the sensed data of whole network are collected along a data collection tree. The data measurement matrix is utilized to compress the sensed data in each sensor node, and the data reconstruction matrix is utilized to reconstruct the original data in the sink.Finally, the data communication performance and data reconstruction performance of the proposed scheme are evaluated and compared with those of existing schemes using real-world sensed data. The experimental results show that compared to its counterparts, the proposed scheme results in a higher data compression rate, lower energy consumption, more accurate data reconstruction, and faster data reconstruction speed.
文摘Visual object tracking （VOT） is an important sub- field of computer vision. It has widespread application do- mains, and has been considered as an important part of surveillance and security system. VOA facilitates finding the position of target in image coordinates of video frames. While doing this, VOA also faces many challenges such as noise, clutter, occlusion, rapid change in object appearances, highly maneuvered （complex） object motion, illumination changes. In recent years, VOT has made significant progress due to availability of low-cost high-quality video cameras as well as fast computational resources, and many modern techniques have been proposed to handle the challenges faced by VOT. This article introduces the readers to 1） VOT and its applica- tions in other domains, 2） different issues which arise in it, 3） various classical as well as contemporary approaches for object tracking, 4） evaluation methodologies for VOT, and 5） online resources, i.e., annotated datasets and source code available for various tracking techniques.
基金supported by the National Natural Science Foundation of China (Grant Nos. 61572060, 61190125, 61472024)CERNET Innovation Project 2015 (Grant No. NGII20151004)
文摘Most previous studies have mainly focused on the analyses of one entire network(graph) or the giant connected components of networks. In this paper, we investigate the disconnected components(non-giant connected component) of some real social networks, and report some interesting discoveries about structural properties of disconnected components. We study three diverse, real networks and compute the significance profile of each component. We discover some similarities in the local structure between the giant connected component and disconnected components in diverse social networks. Then we discuss how to detect network attacks based on the local structure properties of networks. Furthermore, we propose an empirical generative model called i Friends to generate networks that follow our observed patterns.
