首页|基于RealSense仓库货物体积计算方法的研究

基于RealSense仓库货物体积计算方法的研究

扫码查看
企业仓库中,查看可用空间量是调配货物过程中的重要环节,而对于固定的仓库,它的总容量是固定的,所以可以通过算出仓库中现有的货物量,然后两个相减即可得到剩余可用空间量。对于计算仓库货物的体积,首先使用RealSense深度相机获取货物场景的初始点云。由于获取的初始点云数据往往存在噪声,所以在进行货物体积计算时需要进行一些预处理。预处理过后得到了货物的点云,然后利用投影法和积分法对其进行计算测量。针对仓库货物堆的大小不一问题,提出了两种方案:第一种,对于小货物堆(体积小于2 立方米的货物),使用相机从上往下拍,获取货物的顶面和地面,然后通过统计分析法、投影与积分的结合得到货物体积;第二种,对于大货物堆(体积大于等于2 立方米的货物)不易获取货物的顶面,使用两个有一定距离的相机获取货物堆的两个侧面,然后对方案一的方法进行变形得到货物体积。实验结果表明:该方式测得的货物体积与实际的货物体积相差不超过3%,满足目前企业仓库的需求。
Research on Calculation Method of Warehouse Cargo Volume Based on RealSense
In the enterprise warehouse,viewing the amount of available space is an important link in the process of allocating cargo.As for the fixed warehouse,its total capacity is fixed,so you can calculate the existing amount of the warehouse cargo,and then the remaining available space can be obtained by reducing the two phases.For calculating the volume of the warehouse cargo,we first use the RealSense depth camera to obtain the initial point cloud of the cargo scene.Because the acquired initial point cloud data is often noisy,some preprocessing is needed during the cargo volume calculation.The point cloud of the cargo is obtained,and then calculated and measured by the projection method and integral method.In view of the different sizes of the warehouse,we propose two schemes.First,for small cargo piles(cargo with a volume less than 2 cubic meters),we use a camera to capture the top and ground of the cargo from top to bottom,and then use statistical analysis,projection,and integration to obtain the cargo volume.Second,for large cargo piles(cargo with a volume greater than or equal to 2 cubic meters),it is difficult to obtain the top surface of the cargo.Therefore,two cameras with a certain distance are used to obtain the two sides of the cargo pile,and then the method in Scheme 1 is deformed to obtain the cargo volume.The experimental results show that the difference between the volume of cargo measured by the proposed method and the actual volume of goods shall not exceed 3%,which meets the requirements of low cost and high precision measurement in the logistics site.

point cloud volumeprojection methodintegral methoddepth cameraRealSense

顿启鹏、毋涛

展开 >

西安工程大学 计算机科学学院,陕西 西安 710048

点云体积 投影法 积分法 深度相机 RealSense

国家自然科学基金(青年基金)

61806160

2024

计算机技术与发展
陕西省计算机学会

计算机技术与发展

CSTPCD
影响因子:0.621
ISSN:1673-629X
年,卷(期):2024.34(1)
  • 18