Robotic Automation With 3D Guiding Camera For Randomly Picking And Uploading

XEMA A low cost, full featured open source, industrial 3D camera This project is an open source industrial 3D camera. The goal at current stage is to create a low cost 3D camera with capability of current generation industrial cameras. It is also a computer with GPU computing capability, which makes running 3D point cloud recognition algorithms and robotic arm control programs possible. This camera can be used in scenarios such as bin-picking, assembly, 3D inspection and many others. Our ultimate goal is to continuously reduce the cost of industrial 3D cameras with the help of deeplearning's capabilities of abstract representation, and allow machine vision and AI to penetrate all aspects of this carbon-based world. High Scan Quality Open Hardware Easy-To-Start The camera is designed for industrial use. High accuracy of 50 micron or better is achievable All of our developement is open-source, that anyone can use and improve it. A growing number of detailed tutorials will help getting started.   Parameter Value Calibration Accuracy 0.05mm Point Cloud Resolusion 1920x1200 Image Resolusion 1920x1200 Frame Rate 1fps Baseline 150mm Working Distance 400 ~ 2000mm Data Interface Ethernet HFOV 40° VFOV 23° Dimensions 207 x 127.5 x 50.5 mm Weight 1230g CPU Quad-core Arm A57 processor @ 1.43 GHz GPU 128-core Maxwell GPU Memory 4GB 64-bit LPDDR4 Parameter Xema L Xema S Xema P Dimensions(mm) 433X133x51 207x127.5x50.5 126x146x61 Baseline Length(mm) 350 145 70 Working Distance(mm) 1000-3000 400-1000 100-150 Near Field Of View (mm) 769x432 307x173 92x53 Far Field Of View (mm) 2307x1298 769x432 123x76 Measurement Accuracy  0.5mmm@2.5m   0.05mm@0.8m   6um@130mm   Resolution   1920x1200   2448x2048  Output Result Point cloud image, depth image, grayscale image