Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods
来自移动无人机的视频个体计数与跟踪:基准与方法
机构 * School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院) ; school of Computer Science and Engineering, Hong Kong University of Science and Technology(香港科学与技术大学计算机科学与工程学院) ; Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系) ; School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)计算机科学与技术学院) ; Chinese University of Hong Kong(香港中文大学)
AI总结 针对大规模密集人群场景,提出移动无人机视频数据集MovingDroneCrowd++,并设计基于最优传输和描述子投票的计数与跟踪方法GD3A和DVTrack,显著降低计数误差并提升跟踪精度。