A Novel Intelligent Garbage Classification System Based on Deep Learning and an Embedded Linux System

Ouyang

Mathematical Problems in Engineering

et al. 2022

Garbage is an underutilized resource, and garbage classification is one of the effective ways to make full use of these resources. In order to realize the automation of garbage classification, some deep learning models are used for garbage images recognition. A novel garbage image recognition model Garbage Classification Net (GCNet) based on transfer learning and model fusion is proposed in this paper. After extracting garbage image features, EfficientNetv2, Vision Transformer, and DenseNet, respectively, are combined to construct the neural network model of GCNet. Data augmentation is used to expand the dataset and 41,650 garbage images are contained in the new dataset. Compared with other models through experiments, the results show that the proposed model has good convergence, high recall rate and accuracy, and short recognition time.

“…Fu et al proposed a new migration learning-based GNet model for rubbish classification and an improved Mobile-NetV3 model, with an average accuracy of 92.62% [21].…”

Section: Rabano Et Al Applied the Mobilenet Model To The Trashnetmentioning

confidence: 99%

Image Recognition for Garbage Classification Based on Transfer Learning and Model Fusion

Ouyang

Mathematical Problems in Engineering

et al. 2022

“…Meanwhile, some researchers [17] use technologies including AI and IoT to manage the whole garbage classification process. Chuang et al [18] proposed an intelligent classifier and an environment monitor system to realize automatic classification and supervision.…”

Section: Related Workmentioning

confidence: 99%

Waste Collection and Transportation Supervision Based on Improved YOLOv3 Model

Chen

et al. 2022

IEEE Access

Supervising the process of garbage collection and transportation is a very crucial task with significance implication to the reusing and the recycle of the garbage. Previous works mainly focus on the detection of certain kind of garbage instead of overseeing the whole process. This paper proposed a supervision approach based on the improved YOLOv3 to decrease the incidence of unexpected mixing of the different kinds of garbage during the transportation and the collection which will cause the inferior performance of waste classification. Firstly, to reduce the parameters and arithmetic operations of YOLOv3 and improving the model's detection speed, we displaced the standard convolution in YOLOv3 by depthwise separable convolution. Secondly, to solve the problem that YOLOv3 has poor location accuracy and performs poorly in muti-targets, triplet attention is introduced into the backbone, which increases almost no parameters to automatically learn cross-dimensional interactions, enhance the effective feature channel weights, and strengthen the feature extraction capability. Finally, we built a dataset of waste classification supervision using the images provided by a city environmental protection bureau on which we did massive experiments. The experimental result shows that compared with other detection algorithms, the improved YOLO v3 algorithm has better performance. The mAP is 98.5%, which is 0.7% and 1.1% higher than the YOLOv5l and the EfficientDet-B0, respectively, and the average detection speed of the model is 14.6ms/it, which meets the requirements of regulatory real-time and environment complexity of the supervision system.

Rev. iberoam. autom. inform. ind.

“…También, ha habido intentos de implementar CNNs más ligeras con pocas capas para reducir tiempos de entrenamiento e inferencia como en (Altikat et al, 2022) con bastante peor tasa de reconocimiento, o incluso de embeber este tipo de CNNs en sistemas de CPU integrada del tipo Raspberry Pi 4 como en (Fu et al, 2021), para así diseñar sistemas portables y poder controlar actuadores desde la salida del reconocimiento. ticulares de una mano Allegro y los valores de presión de los sensores resistivos colocados sobre los dedos.…”

Section: Trabajos Relacionadosunclassified

Manipulación visual-táctil para la recogida de residuos domésticos en exteriores

Castaño-Amorós

Páez-Ubieta

Gil

et al. 2022

Este artículo presenta un sistema de percepcion orientado a la manipulación robótica, capaz de asistir en tareas de navegación, clasificacion y recogida de residuos domésticos en exterior. El sistema está compuesto de sensores táctiles ópticos, cámaras RGBD y un LiDAR. Estos se integran en una plataforma móvil que transporta un robot manipulador con pinza. El sistema consta de tres modulos software, dos visuales y uno táctil. Los módulos visuales implementan arquitecturas CNNs para la localización y reconocimiento de residuos sólidos, además de estimar puntos de agarre. El módulo táctil, también basado en CNNs y procesamiento de imagen, regula la apertura de la pinza para controlar el agarre a partir de informacion de contacto. Nuestra propuesta tiene errores de localizacion entorno al 6 %, una precisión de reconocimiento del 98 %, y garantiza estabilidad de agarre el 91 % de las veces. Los tres modulos trabajan en tiempos inferiores a los 750 ms.