Search

Aiming at computer resources was limited and the total overhead of the system processing tasks was too high, this paper proposed an offloading strategy based on dynamic perception-hybrid artificial fish swarm（DP-HAFS） algorithm. First, it constructed a "local-edge-cloud" three-layer network architecture and adopted a fine-grained partial offloading mode; then, for the scenario where a terminal device covered by multiple base stations, this paper proposed a base station selection strategy to select the optimal base station; finally, it used the DP-HAFS algorithm to dynamically modify the unloading decision and got the best uninstall strategy. The simulation results show that the proposed offloading strategy can effectively reduce the total system overhead in a scenario with a large number of tasks. [ABSTRACT FROM AUTHOR]

Object tracking is an important topic in computer visual directions, where scale changes, deformation and rotation are difficult to resolve in the field. For the challenging problems faced in the above track, based on existing Siamese network algorithms, this paper proposed multi-layer feature fusion and parallel self-attention Siamese networks (MPSiamRPN) for visual tracking. Firstly, MPSiamRPN used the modified ResNet50 to extract features from the template image and the search image. In order to deal with the loss of some features caused by the deep network, it proposed a multi-layer feature fusion module to fuse the features of the last three layers of ResNet. Secondly, it introduced the parallel self-attention module, which was composed of channel self-attention and spatial self-attention. The channel self-attention could selectively emphasize the beneficial channel features for tracking, and the spatial self-attention could learn the rich spatial information of the target. Finally, it proposed the region proposal network ( RPN) to perform classification and regression operations to determine the location and shape of the target. Experiments show that the MPSiamRPN can achieve competitive results on OTBlOO and VOT2018 test datasets. [ABSTRACT FROM AUTHOR]