室内写字楼动态目标检测数据

面向基于视觉的机器人环境建模与定位导航基础研究，为突破复杂环境下机器人动态目标检测技术瓶颈，基于双目RGB彩色相机，在中科院空天院办公楼（场地占地面积约3000平方米，存在动态目标，光线条件较为复杂，以自然光和人工光照混合条件为主）进行数据采集。该数据集包含285张彩色影像（分辨率为1280×720像素,采样频率2Hz），数据量为268M，主要构建复杂场景下的办公室场景动态目标检测标准数据集。This dataset is intended for fundamental research on vision-based robotic environment modeling, localization and navigation, aiming to break through the technical bottlenecks of dynamic target detection for robots in complex environments. Data collection was carried out using a binocular RGB color camera at the office building of the Aerospace Information Research Institute, Chinese Academy of Sciences. The test site covers an area of approximately 3,000 square meters, with dynamic targets present and complex lighting conditions mainly consisting of a mix of natural and artificial illumination. This dataset contains 285 color images with a resolution of 1280×720 pixels and a sampling frequency of 2 Hz, with a total data volume of 268 MB. It is primarily constructed as a standard dataset for dynamic target detection in complex office scenarios.

搜集汇总

背景与挑战

背景概述

该数据集面向机器人环境建模与定位导航研究，旨在解决复杂环境下动态目标检测技术问题。数据通过双目RGB彩色相机采集于中科院空天院办公楼，包含285张分辨率为1280×720像素的彩色影像，总数据量约268MB。它主要用于构建室内写字楼场景的动态目标检测标准数据集，以支持相关基础研究。