Abstract
In this paper, a kitchen waste illegal component recognizer based on embedded device is proposed, which can intelligently identify and record illegal components in kitchen waste. The recognizer is based on SSD-MibileNetV2 algorithm. The Quantization-aware training model is established in TensorFlow framework. The whole model is quantized by uint8 and transformed into TensorFlow Lite structure, and then deployed to the embedded device based on raspberry Pi 4b, which can finally achieve 4.5FPS and 76.35mAP. The recognizer can meet the requirements of real-time and accuracy in detecting illegal components of kitchen waste, and can effectively reduce labor costs and meet the requirements of intelligence.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
