An Integrated Bud Detection and Localization System for Application in Greenhouse Automation

Tea chrysanthemum detection under unstructured environments using the TC-YOLO model

“…Research on machine learning-based chrysanthemum detection is currently still not fully explored. Traditional machine learning-based chrysanthemum detection has non-negligible drawbacks in terms of reliability in fields and inference speed (Kondo et al, 1996;Tarry et al, 2014;Tete&Kamlu, 2017;Warren, 2000;Yang et al, 2018;Yang et al, 2019;Yuan et al, 2018). Among them, the fastest inference speed is the robotic chrysanthemum picking system for Hangzhou white chrysanthemums developed by Yang et al (2018) in 2018, recognizing an image with an inference speed of 0.4 s (2.5 FPS).…”

“…For the system, the precision of detection was up to 75%, and generally, its running speed was roughly the same as the manual running speed. Tarry et al (2014) developed an integrated system for chrysanthemum bud detection by extracting color characteristics. The system can be utilized to automate labor-intensive work in flower greenhouses with a detection precision of 78.2%.…”