https://github.com/opplieam/crew2-obj-detection

The Crew 2 and object detection
https://github.com/opplieam/crew2-obj-detection

deep-learning object-detection

Last synced: 14 days ago
JSON representation

The Crew 2 and object detection

• Host: GitHub
• URL: https://github.com/opplieam/crew2-obj-detection
• Owner: opplieam
• License: apache-2.0
• Created: 2019-03-17T10:52:25.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2024-12-07T20:19:09.000Z (about 2 months ago)
• Last Synced: 2024-12-07T21:19:33.551Z (about 2 months ago)
• Topics: deep-learning, object-detection
• Language: Jupyter Notebook
• Homepage:
• Size: 105 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
## This project contains 2 modules; ~~Self-Driving~~ and Object detection

Self-Driving part still not success. The latest work collecting data by 66x200 in YUV format for 500k images (25 GB). Driving from Miami -> Newyork and Los Angeles -> Las Vegas (In game).

And Nvidia Pilotnet for DL model. Possibly need to find another way to deal with bias data or re-collecting with other format and new modeling (Transfer learning ?).

Will revisit later. 

## Object Detection

### Youtube

[![Result](https://img.youtube.com/vi/6K_p0OdTjFI/0.jpg)](https://www.youtube.com/watch?v=6K_p0OdTjFI)

**Deep Learning Framework:** Tensorflow

**NN Architecture:** SSD Mobilenet COCO dataset

**Game:** The Crew 2