KEYWORDS: Robotics, Detection and tracking algorithms, Image processing, Data modeling, Target recognition, Solar cells, Sensors, Signal processing, Servomechanisms, Visual process modeling
In order to solve the problems of low accuracy and low labor efficiency in garbage classification, an intelligent classification trash bin equipped with robot arm and 110-degree wide-angle camera is designed. A fast identification and positioning algorithm based on deep learning is proposed. The PASCAL VOC 2007 dataset is applied, which consists of 600 images containing 4000 different types of garbage in different situations. 20% of the images is randomly selected as the validation set, and the remaining 80% as the training set. The dataset is trained using the YOLOv5 model. After training, the model is tested on the garbage can system, automatically identification and classification the type of garbage is achieved and the robotic arm realizes the automatic positioning, grabbing and sorting. The experimental test results show that the error of the positioning algorithm is less than 0.8 mm, the fastest recognition speed is 2.6ms/piece, and the recognition accuracy can be maintained above 90% in the experimental environment, indicating that the algorithm has good accuracy and stability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.