Low-latency Visual Servoing with Event-cameras

The dataset can be used to test your event-based tracking algorithm in open-loop. In the experiment, a static event-camera (640x480 pixels) placed in front of an Alienware laptop displaying videos that recorded different motion types and target speeds, including a cluttered moving background. The dataset includes event-driven data and ground truth of 8 shapes: arrow, flag, oval, pacman, puzzle, square, star, and triangle. To import .log files containing events, we suggest bimvee Python library. Specifically, use the functions to import .log files: data = importIitYarp(filePathOrName=input_path) Ground-truth .csv files have 5 columns, each one corresponding to a different measure: timestamp | u | v | theta | scale u and v refer to the target position in the image plane [pix]

本数据集可用于开环场景下基于事件的跟踪算法测试。实验中，将一台静态事件相机（event-camera，分辨率640×480像素）放置于Alienware笔记本电脑前方，该笔记本屏幕播放记录了不同运动类型与目标速度的视频，视频包含杂乱移动的背景。本数据集包含事件驱动数据与8种形状的真实标注（ground truth）：箭头、旗帜、椭圆、吃豆人、拼图、正方形、星形与三角形。若需导入存储事件数据的.log格式文件，推荐使用bimvee Python库。具体而言，可通过如下函数完成.log文件的导入：data = importIitYarp(filePathOrName=input_path)。真实标注的.csv格式文件包含5列数据，每一列对应一项不同的测量指标：时间戳（timestamp）、u、v、theta与scale。其中u与v代表图像平面内的目标位置，单位为像素（pix）。