|   | 22 |  | 
          
          
            |   | 23 |  | 
          
          
            |   | 24 | ---- | 
          
          
            |   | 25 |  | 
          
          
            |   | 26 |  | 
          
          
            |   | 27 | **Week 1 Weekly Meeting Presentation:** https://docs.google.com/presentation/d/1Sf9hzpo3WQsEPwbhKfic2xWCskH1EViD-3SNb_foouA/edit?usp=sharing | 
          
          
            |   | 28 |  | 
          
          
            |   | 29 | == Week 2 Activities == | 
          
          
            |   | 30 |  | 
          
          
            |   | 31 | * Understand the concepts of object detection in 3D Point Cloud | 
          
          
            |   | 32 | * Gain an understanding of NVIDIA’s !DeepStream SDK | 
          
          
            |   | 33 | * Get comfortable deploying YOLOv3 on the COSMOS testbed | 
          
          
            |   | 34 | * Use existing datasets to play around with !DeepStream and YOLOv3 | 
          
          
            |   | 35 |  | 
          
          
            |   | 36 | ---- | 
          
          
            |   | 37 |  | 
          
          
            |   | 38 |  | 
          
          
            |   | 39 | **Week 2 Weekly Meeting Presentation:** https://docs.google.com/presentation/d/1Cl8MbsSU3ZAq5lpRuE0eVBSwnIX4jTUAci5uAgP7Vt8/edit?usp=sharing | 
          
          
            |   | 40 |  | 
          
          
            |   | 41 | **Week 2 Team Meeting Presentation:** https://docs.google.com/presentation/d/1O2yCze4fmVOAFGCi0u6WTZq8VTFhLc_J448skeygguw/edit?usp=sharing | 
          
          
            |   | 42 |  | 
          
          
            |   | 43 | == Week 3 Activities == | 
          
          
            |   | 44 |  | 
          
          
            |   | 45 | * Investigate existing RGB-D (RGB + depth map) object detectors whose models we can immediately put to use for inference | 
          
          
            |   | 46 | * Look into existing 3D Point Cloud object detection implementations | 
          
          
            |   | 47 | * Learn how to run !DeepStream's YOLOv3 implementation | 
          
          
            |   | 48 | * Investigate !DeepStream Python bindings for use with YOLO | 
          
          
            |   | 49 |  | 
          
          
            |   | 50 | ---- | 
          
          
            |   | 51 |  | 
          
          
            |   | 52 |  | 
          
          
            |   | 53 | **Week 3 Weekly Meeting Presentation:** https://docs.google.com/presentation/d/13vqiw0kkyT0_XPzPv3NiowIvxc22SapfxM_ZbAKn1Cc/edit?usp=sharing | 
          
          
            |   | 54 |  | 
          
          
            |   | 55 | **Week 3 Team Meeting Presentation:** https://docs.google.com/presentation/d/1jwq6h05mw1vHt6_C1Br4MM_0LQDZRlIEoSvEasJ5Rsg/edit?usp=sharing | 
          
          
            |   | 56 |  | 
          
          
            |   | 57 | == Week 4 Activities == | 
          
          
            |   | 58 |  | 
          
          
            |   | 59 | * Investigate YOLOv4 and its use with TensorRT | 
          
          
            |   | 60 | * Look into getting output/data processing based on the outputs from !DeepStream | 
          
          
            |   | 61 | * Look into the !DeepStream tracker to build on top of | 
          
          
            |   | 62 | * Build a presentation slide set to inform the intern class about !DeepStream and YOLOv3 | 
          
          
            |   | 63 |  | 
          
          
            |   | 64 | ''**Introduction to !DeepStream and YOLOv3 Presentation Slides:**'' ''To be posted at a later date'' | 
          
          
            |   | 65 |  | 
          
          
            |   | 66 | ---- | 
          
          
            |   | 67 |  | 
          
          
            |   | 68 | **Week 4 Weekly Meeting Presentation:** ''To be posted at a later date'' | 
          
          
            |   | 69 |  | 
          
          
            |   | 70 | **Week 4 Team Meeting Presentation:** ''To be posted at a later date'' |