In this paper, we consider the problem of irregular shapes tracking for multiple extended targets by introducing the Gaussian surface matrix（GSM） into the framework of the random finite set（RFS） theory. The Gaussi...In this paper, we consider the problem of irregular shapes tracking for multiple extended targets by introducing the Gaussian surface matrix（GSM） into the framework of the random finite set（RFS） theory. The Gaussian surface function is constructed first by the measurements, and it is used to define the GSM via a mapping function. We then integrate the GSM with the probability hypothesis density（PHD） filter, the Bayesian recursion formulas of GSM-PHD are derived and the Gaussian mixture implementation is employed to obtain the closed-form solutions. Moreover, the estimated shapes are designed to guide the measurement set sub-partition, which can cope with the problem of the spatially close target tracking. Simulation results show that the proposed algorithm can effectively estimate irregular target shapes and exhibit good robustness in cross extended target tracking.展开更多
Cognitive decline is a feature of normal and pathological aging. As the proportion of the global aged population continues to grow, it is imperative to understand the molecular and cellular substrates of cognitive agi...Cognitive decline is a feature of normal and pathological aging. As the proportion of the global aged population continues to grow, it is imperative to understand the molecular and cellular substrates of cognitive aging for therapeutic discovery. This review focuses on the critical role of neural extracellular matrix in the regulation of neuroplasticity underlying learning and memory in another under-investigated "critical period": the aging process. The fascinating ideas of neural extracellular matrix forming a synaptic cradle in the tetrapartite synapse and possibly serving as a substrate for storage of very long-term memories will be introduced. We emphasize the distinct functional roles of diffusive neural extracellular matrix and perineuronal nets and the advantage of the coexistence of two structures for the adaptation to the ever-changing external and internal environments. Our study of striatal neural extracellular matrix supports the idea that chondroitin sulfate proteoglycan-associated extracellular matrix is restrictive on synaptic neuroplasticity, which plays important functional and pathogenic roles in early postnatal synaptic consolidation and aging-related cognitive decline. Therefore, the chondroitin sulfate proteoglycan-associated neural extracellular matrix can be targeted for normal and pathological aging. Future studies should focus on the cell-type specificity of neural extracellular matrix to identify the endogenous, druggable targets to restore juvenile neuroplasticity and confer a therapeutic benefit to neural circuits affected by aging.展开更多
为了更好地应对多目标跟踪联合检测算法面对的场景遮挡问题,通过结合注意力机制,提出基于Transformer的运动预测和数据关联(Transformer-based motion prediction and data association,TrMPDA)联合检测跟踪方法。首先,考虑到置信度检...为了更好地应对多目标跟踪联合检测算法面对的场景遮挡问题,通过结合注意力机制,提出基于Transformer的运动预测和数据关联(Transformer-based motion prediction and data association,TrMPDA)联合检测跟踪方法。首先,考虑到置信度检测框的质量以及深度特征的视觉表示能力对遮挡场景下跟踪效果的影响,重新设计TrMPDA骨干网络中的ResNet卷积模块,利用相邻像素和长距离像素间丰富的上下文关系指导动态注意矩阵的学习,增强深度特征的视觉表示能力,并通过边界框的宽和高估计边界框位置,提高置信度检测框的质量。其次,在本文方法中保留所有的检测框,根据阈值大小划分高置信度检测框和低置信度检测框,分别执行数据关联匹配,以此来平衡由于遮挡导致的检测框低置信度。实验结果表明本文提出的TrMPDA方法与典型的Sort、JDE、Fairmot等多目标跟踪算法相比具有更好的跟踪效果,能够应对多目标跟踪中目标遮挡的问题。展开更多
基金supported by the National Natural Science Foundation of China(6130501761304264+1 种基金61402203)the Natural Science Foundation of Jiangsu Province(BK20130154)
文摘In this paper, we consider the problem of irregular shapes tracking for multiple extended targets by introducing the Gaussian surface matrix（GSM） into the framework of the random finite set（RFS） theory. The Gaussian surface function is constructed first by the measurements, and it is used to define the GSM via a mapping function. We then integrate the GSM with the probability hypothesis density（PHD） filter, the Bayesian recursion formulas of GSM-PHD are derived and the Gaussian mixture implementation is employed to obtain the closed-form solutions. Moreover, the estimated shapes are designed to guide the measurement set sub-partition, which can cope with the problem of the spatially close target tracking. Simulation results show that the proposed algorithm can effectively estimate irregular target shapes and exhibit good robustness in cross extended target tracking.
基金supported in part by National Alliance for Research on Schizophrenia & Depression(NARSAD)Young Investigator Grant from Brain Behavorial Research Foundation,No.21365(to XHL)Ike Muslow Predoctoral Fellowship from Louisiana State University Health Sciences Center-Shreveport(to ADR)
文摘Cognitive decline is a feature of normal and pathological aging. As the proportion of the global aged population continues to grow, it is imperative to understand the molecular and cellular substrates of cognitive aging for therapeutic discovery. This review focuses on the critical role of neural extracellular matrix in the regulation of neuroplasticity underlying learning and memory in another under-investigated "critical period": the aging process. The fascinating ideas of neural extracellular matrix forming a synaptic cradle in the tetrapartite synapse and possibly serving as a substrate for storage of very long-term memories will be introduced. We emphasize the distinct functional roles of diffusive neural extracellular matrix and perineuronal nets and the advantage of the coexistence of two structures for the adaptation to the ever-changing external and internal environments. Our study of striatal neural extracellular matrix supports the idea that chondroitin sulfate proteoglycan-associated extracellular matrix is restrictive on synaptic neuroplasticity, which plays important functional and pathogenic roles in early postnatal synaptic consolidation and aging-related cognitive decline. Therefore, the chondroitin sulfate proteoglycan-associated neural extracellular matrix can be targeted for normal and pathological aging. Future studies should focus on the cell-type specificity of neural extracellular matrix to identify the endogenous, druggable targets to restore juvenile neuroplasticity and confer a therapeutic benefit to neural circuits affected by aging.
文摘为了更好地应对多目标跟踪联合检测算法面对的场景遮挡问题,通过结合注意力机制,提出基于Transformer的运动预测和数据关联(Transformer-based motion prediction and data association,TrMPDA)联合检测跟踪方法。首先,考虑到置信度检测框的质量以及深度特征的视觉表示能力对遮挡场景下跟踪效果的影响,重新设计TrMPDA骨干网络中的ResNet卷积模块,利用相邻像素和长距离像素间丰富的上下文关系指导动态注意矩阵的学习,增强深度特征的视觉表示能力,并通过边界框的宽和高估计边界框位置,提高置信度检测框的质量。其次,在本文方法中保留所有的检测框,根据阈值大小划分高置信度检测框和低置信度检测框,分别执行数据关联匹配,以此来平衡由于遮挡导致的检测框低置信度。实验结果表明本文提出的TrMPDA方法与典型的Sort、JDE、Fairmot等多目标跟踪算法相比具有更好的跟踪效果,能够应对多目标跟踪中目标遮挡的问题。
