International Conference on Automatic Face and Gesture Recognition是研究基于图像和视频的人脸、手势和身体运动识别的首要国际论坛。其广泛的范围包括:计算机视觉、模式识别和计算机图形学的基础进展;与面部、手势和身体运动相关的机器学习技术;新的算法和应用。官网链接:http://fg2019.org/

最新内容

While multiple studies have proposed methods for the formation control of unmanned aerial vehicles (UAV), the trajectories generated are generally unsuitable for tracking targets where the optimum coverage of the target by the formation is required at all times. We propose a path planning approach called the Flux Guided (FG) method, which generates collision-free trajectories while maximising the coverage of one or more targets. We show that by reformulating an existing least-squares flux minimisation problem as a constrained optimisation problem, the paths obtained are $1.5 \times$ shorter and track directly toward the target. Also, we demonstrate that the scale of the formation can be controlled during flight, and that this feature can be used to track multiple scattered targets. The method is highly scalable since the planning algorithm is only required for a sub-set of UAVs on the open boundary of the formation's surface. Finally, through simulating a 3d dynamic particle system that tracks the desired trajectories using a PID controller, we show that the resulting trajectories after time-optimal parameterisation are suitable for robotic controls.

0
0
下载
预览

最新论文

While multiple studies have proposed methods for the formation control of unmanned aerial vehicles (UAV), the trajectories generated are generally unsuitable for tracking targets where the optimum coverage of the target by the formation is required at all times. We propose a path planning approach called the Flux Guided (FG) method, which generates collision-free trajectories while maximising the coverage of one or more targets. We show that by reformulating an existing least-squares flux minimisation problem as a constrained optimisation problem, the paths obtained are $1.5 \times$ shorter and track directly toward the target. Also, we demonstrate that the scale of the formation can be controlled during flight, and that this feature can be used to track multiple scattered targets. The method is highly scalable since the planning algorithm is only required for a sub-set of UAVs on the open boundary of the formation's surface. Finally, through simulating a 3d dynamic particle system that tracks the desired trajectories using a PID controller, we show that the resulting trajectories after time-optimal parameterisation are suitable for robotic controls.

0
0
下载
预览
Top