Abstract
Garbage classification is a social issue related to people’s livelihood and sustainable development, so letting service robots autonomously perform intelligent garbage classification has important research significance. Aiming at the problems of complex systems with data source and cloud service center data transmission delay and untimely response, at the same time, in order to realize the perception, storage, and analysis of massive multisource heterogeneous data, a garbage detection and classification method based on visual scene understanding is proposed. This method uses knowledge graphs to store and model items in the scene in the form of images, videos, texts, and other multimodal forms. The ESA attention mechanism is added to the backbone network part of the YOLOv5 network, aiming to improve the feature extraction ability of the network, combining with the built multimodal knowledge graph to form the YOLOv5-Attention-KG model, and deploying it to the service robot to perform real-time perception on the items in the scene. Finally, collaborative training is carried out on the cloud server side and deployed to the edge device side to reason and analyze the data in real time. The test results show that, compared with the original YOLOv5 model, the detection and classification accuracy of the proposed model is higher, and the real-time performance can also meet the actual use requirements. The model proposed in this paper can realize the intelligent decision-making of garbage classification for big data in the scene in a complex system and has certain conditions for promotion and landing.
Highlights
In recent years, as the global garbage production has shown a cliff-like growth, my country has introduced a series of policies. e latest revision of the “Law of the People’s Republic of China on the Prevention and Control of Environmental Pollution by Fixed Wastes” in 2020 requires that local people’s governments at or above the county level should speed up the establishment of a domestic waste management system for classified release, recycling, transportation, and treatment
In order to achieve the intelligent decision of whether items are garbage in the home environment, this paper proposes a garbage detection and classification method based on visual scene understanding. e main contributions of this paper are as follows: first, the construction of the scene multimodal knowledge graph
Combining the improved YOLOv5m detection algorithm with the knowledge graph and deploying it to the edge device home service robot, the system has the ability to associate similar to people, which is the key to improving the system’s intelligent garbage classification
Summary
As the global garbage production has shown a cliff-like growth, my country has introduced a series of policies. e latest revision of the “Law of the People’s Republic of China on the Prevention and Control of Environmental Pollution by Fixed Wastes” in 2020 requires that local people’s governments at or above the county level should speed up the establishment of a domestic waste management system for classified release, recycling, transportation, and treatment. In order to achieve the intelligent decision of whether items are garbage in the home environment, this paper proposes a garbage detection and classification method based on visual scene understanding. Aiming at the problem of rich and diverse semantics of items in the home environment, which is difficult to model, the knowledge graph is used to uniformly represent and store the input multimodal information; the second is to propose a garbage classification and detection model YOLOv5-Attention-KG based on visual scene understanding. Combining the improved YOLOv5m detection algorithm with the knowledge graph and deploying it to the edge device home service robot, the system has the ability to associate similar to people, which is the key to improving the system’s intelligent garbage classification.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
