Unmanned Aerial Vehicle (UAV) vehicle-tracking technology has extensive potential for application in various fields. In the actual tracking process, the relative movement of the UAV and vehicles will bring large target-scale variations (i.e., size and aspect ratio change), which leads to missed detection and ID switching. Traditional tracking methods usually use multi-scale estimation to adaptively update the target scale for variable-scale detection and tracking. However, this approach requires selecting multiple scaling factors and generating a large number of bounding boxes, which results in high computational costs and affects real-time performance. To tackle the above issue, we propose a novel multi-target tracking method based on the BoT-SORT framework. Firstly, we propose an FB-YOLOv8 framework to solve the missed detection problem. This framework incorporates a Feature Alignment Aggregation Module (FAAM) and a Bidirectional Path Aggregation Network (BPAN) to enhance the multi-scale feature fusion. Secondly, we propose a multi-scale feature-fusion network (MSFF-OSNet) to extract appearance features, which solves the ID switching problem. This framework integrates the Feature Pyramid Network (FPN) and Convolutional Block Attention Module (CBAM) into OSNet to capture multilevel pixel dependencies and combine low-level and high-level features. By effectively integrating the FB-YOLOv8 and MSFF-OSNet modules into the tracking pipeline, the accuracy and stability of tracking are improved. Experiments on the UAVDT dataset achieved 46.1% MOTA and 65.3% IDF1, which outperforms current state-of-the-art trackers. Furthermore, experiments conducted on sequences with scale variations have substantiated the improved tracking stability of our proposed method under scale-changing conditions.

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.