I&T Solution |
Intelligent motorcycles counting system
(REF: S-0726) |
Trial Project |
|
Solution Feature |
- Implementing non-camera based edge AI computing to analyse material and feature information from radar sensing technology for detecting motorcycle and non-motorcycle items, e.g. traffic cones, rubbish bin or carton box.
- Counting the number of the motorcycle based on the analysed result from the edge AI computing system and transmit the data to 3rd party platforms/systems by LPWAN technology for data sharing.
- Hardware implementation platform will be used in order to provide edge AI computing in real-time.
- The radar sensing technology can achieve advantages in privacy protection and detection through variety of material, e.g. rain cover, when comparing to the traditional video computing counting system.
|
Trial Application and Expected Outcome |
- Before the field trial, data set of motorcycle and non-motorcycle items need to be built up first. After getting enough data samples, a machine learning model will be trained and implemented on hardware platform. When the accuracy is acceptable, field trial will be conducted.
- For the field trial, non-camera counting system will be implemented to the target carpark. Based on the material and feature information, the system will detect and count the number of the motorcycle with edge AI computing.
- The counting system will then transmit the number of the motorcycle to a 3rd party platforms/system through LPWAN technology for further action.
- After the field trial with acceptable result, the intelligent motorcycles counting system could be implemented to more locations of Hong Kong government through Public Sector Trial Scheme (PSTS).
- The system will further promote to private carparks, e.g. shopping mall.
|
Additional Solution Information |
UMEC(HK) Introduction_20200121.pdf
|
Info on I&T Solution Provider |
Solution Provider | : | United Microelectronics Centre (Hong Kong) Limited | Address | : | Units 1512-1513, 15/F, Building 19W, 19 Science Park West Avenue, Hong Kong Science Park, Shatin, N.T., Hong Kong | Contact Person | : | Mark MOK |
Position | : | Director, Research and Development | Tel | : | 96739327 | Email | : |
markmok@umechk.com | Webpage | : | www.umechk.com |
|