Search

Hardware/software (HW/SW) partitioning is a vital aspect of HW/SW co-design. With the development of the design complexity in heterogeneous computing systems, existing partitioning algorithms have demonstrated inadequate performance in addressing problems relating to large-scale task nodes. This paper presents a novel HW/SW partitioning algorithm based on node resource attributes hovering swarm particle swarm optimization (HSPSO). First, the system task graph is initialized via the node resource urgency partitioning algorithm; then, the iterative solution produced by HSPSO algorithm yields the partitioning result. We present new initialization by combining node resource attribute information and introduce two improvements to the learning strategy of HSPSO algorithm. For the main swarm, a directed sample set and the addition of perturbation particles are designed to direct the main swarm's particle search process. For the secondary swarm, a dynamic particle update equation is formulated. Iterative updates are performed based on previous rounds' prior information using adaptive inertia weight. The experimental results illustrate that, in large-scale systems task graph partitioning with more than 400 nodes, when compared with mainstream partitioning algorithms, the proposed algorithm improves partitioning performance by no less than 10% for compute-intensive task graphs and no <5% for communication-intensive task graphs, with higher solution stability. [ABSTRACT FROM AUTHOR]

The infrared small target detection technology has a wide range of applications in maritime defense warning and maritime border reconnaissance, especially in the maritime and sky scenes for detecting potential terrorist attacks and monitoring maritime borders. However, due to the weak nature of infrared targets and the presence of background interferences such as wave reflections and islands in maritime scenes, targets are easily submerged in the background, making small infrared targets hard to detect. We propose the multidimensional information fusion network(MIFNet) that can learn more information from limited data and achieve more accurate target segmentation. The multidimensional information fusion module calculates semantic information through the attention mechanism and fuses it with detailed information and edge information, enabling the network to achieve more accurate target position detection and avoid detecting one target as multiple ones, especially in high-precision scenes such as maritime target detection, thus effectively improving the accuracy and reliability of detection. Moreover, experiments on our constructed dataset for small infrared targets in maritime scenes demonstrate that our algorithm has advantages over other state-of-the-art algorithms, with an IoU of 79.09%, nIoU of 79.43%, F1 score of 87.88%, and AuC of 95.96%. [ABSTRACT FROM AUTHOR]

Highlights • A simple but effective spatial filter is proposed to obtain the SLCM. • An enhanced time difference method is proposed to obtain the TLCM. • The STLCM is defined by multiplying the SLCM and TLCM. • An enhanced threshold segmentation method is proposed. Abstract Infrared (IR) moving point target detection is an important technique in many onboard applications such as remote sensing, IR searching and tracking (IRST) and early warning system. However, it has been facing great challenges due to the complicated background and the limited processing resources in the onboard system. In this paper, a novel spatial-temporal local contrast method is proposed for moving point target detection in space-based IR imaging system. Firstly, a simple but effective spatial filter based on multi-direction filtering fusion is designed to obtain the spatial local contrast map (SLCM). An enhanced time domain difference method is also proposed to obtain the temporal local contrast map (TLCM). Then, the spatial–temporal local contrast map (STLCM) is obtained by multiplying the newly defined SLCM and TLCM. Finally, an enhanced threshold segmentation method is proposed for target detection and false alarm suppression. To verify the performance of our detection algorithm, we conduct several groups of experiments on four different real IR image sequences with simulated targets. The final experimental results show that our algorithm significantly outperforms other methods in terms of background suppression and target detection. [ABSTRACT FROM AUTHOR]

As one of important physical properties of exo-atmosphere objects, micro-motion dynamics provides extra information for objects discrimination. In this paper, a model and theoretical analysis of time sequence of infrared (IR) signature considering different inertial parameters of micro-motion objects are presented. It overcomes the shortcoming of the existing methods, which depend on the assumption of specific micro-motion types. Firstly, an inertial model of exo-atmosphere micro-motion object is constructed. Next, the relationship between inertial parameters and IR signature model is derived. Finally, power spectral density transformed from the time sequence of IR signature is obtained. Four groups of simulations are conducted demonstrating the effects of inertial parameters posed on IR signature. Simulation results show that inertial parameters including moments of inertia (MOI) and initial angular rate (IAR) determine the period of motion, thus the frequency of time-varying radiant intensity received by the sensor. The proposed method exploits more explicit physical meaning of exo-atmosphere micro-motion objects and provides a novel approach to characterize exo-atmosphere micro-motion objects irrespective of their specific micro-motion types, which exhibits a greater flexibility in IR objects discrimination tasks. [ABSTRACT FROM AUTHOR]

Based on the random finite set (RFS) framework and the probability hypothesis density (PHD) filter, the extended target PHD (ET‐PHD) filter is proposed for multiple extended target tracking. However, the clutter process in the ET‐PHD filter is modelled as Poisson RFS, which is reasonable for only some scenarios in reality. An easily implemented ET‐PHD filter for arbitrary clutter process, has not yet been studied. In this work, another form of the general PHD filter, suitable for arbitrary clutter and target measurement is derived using a probability generating functional (PGFL)‐based RFS framework. The proposed filter is equivalent to the general PHD filter proposed by Clark and Mahler, but it is easily implemented in an arbitrary clutter process because its clutter process is denoted by the probability density function. Then, an arbitrary clutter ET‐PHD (AC‐ET‐PHD) filter is simplified from the general PHD filter derived by us. To reduce the computational complexity of the proposed filter, a variant of the distance partitioning algorithm is put forward. Simulation results show that the AC‐ET‐PHD filter can be applied to the scenarios with the non‐Poisson clutter process, which means that it will be useful for multiple extended targets tracking in a more complicated clutter process. [ABSTRACT FROM AUTHOR]

Abstract: To reduce the influences of the heavy clutter on infrared small target detection, a new background suppression algorithm is presented in this paper which depends on fusion of two different filters. The Nucleus Similarity Degree (NSD) of each pixel is analyzed first, then morphological Open filter which favors point target enhancement and the Nucleus Similar Pixels Bilateral Filter (NSPBF) which favors background prediction are fused. The complex background suppression and target enhancement can be accomplished more effectively by the fusion. Experimental results indicates that the method is efficient for background suppression under the condition of heavy clutter. [Copyright &y& Elsevier]