Small Object Tracking in High Density Crowd Scenes
Small Object Tracking in High Density Crowd Scenes
复制标题
高密度人群场景中的小物体跟踪
DOI：
10.1007/978-3-030-04946-1_48
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Shinya Takahashi:
中科院分区：
文献类型：
--
作者：
Yujie Li;Shinya Takahashi:
近年来，用于自动识别和跟踪动物的计算机视觉已经发展成为量化行为的流行工具。蜜蜂是学习和记忆的流行模型，因此由于密集的种群、相似的目标外观和大部分殖民地频繁离开蜂巢，在蜂群内跟踪蜜蜂是一项特别的任务。本文针对蜜蜂的跟踪问题，提出了一种基于改进的三帧差分法和VIBE算法的检测方法和一种基于卡尔曼滤波的跟踪方法。我们评估了所提出的方法的性能数据集，其中包含视频与人群蜂群。实验结果表明，该方法具有良好的检测和跟踪性能。
In recent years, computer vision for automatically identification and tracking of animals has evolved into a popular tool for quantifying behavior. Honeybees are a popular model for learning and memory, so tracking of honeybees within a colony is a particularly task due to dense populations, similar target appearance and a significant portion of the colony frequently leaving the hive. In this paper we present a detection method based on improved three-frame difference method and VIBE algorithm and one tracking method based on Kalman filtering for honeybees tracking. We evaluate the performance of the proposed methods on datasets which contains videos with crowd honeybee colony. The experimental results show that the proposed method performs good performance in detection and tracking.