With the rising number of vehicle ownership nationwide and consequent increase in traffic accidents, detection for surveillance video is an effective method to reduce accidents. However, existing methods suffer from high computational load, low accuracy, excessive reliance on large-scale computing servers. Therefore, research will try fuse coordinate attention mechanism improve YOLOv5 network, ...

Abstract Efficient detection and classification of power quality disturbances is required with the increasing penetration multi-energy systems such as microgrids features from renewable energy resources. Machine learning approach popular to generate useful optimal data improve performance. This paper aims analyse performance using hybrid model multi-resolution analysis long short-term memory ne...

Recently, deep-learning-based methods have become the current mainstream of remote sensing image super-resolution (SR) due to their powerful fitting ability. However, they are still unsatisfactory in large-scale factor SR scenarios. The more complicated information distribution images further increases difficulty reconstruction. In this paper, we propose a novel residual split attention group (...