[论文解读] ConvoWaste: An Automatic Waste Segregation Machine Using Deep Learning

Md. Shahariar Nafiz, Shuvra Smaran Das+3 more|arXiv (Cornell University)|Feb 6, 2023

Municipal Solid Waste Management被引用 8

一句话总结

ConvoWaste 提出基于深度学习的垃圾分类系统，将垃圾分类到不同桶，并使用伺服电机、传感器、GSM 和 Android 应用进行远程控制和通知，达到 98% 的准确率。

ABSTRACT

Nowadays, proper urban waste management is one of the biggest concerns for maintaining a green and clean environment. An automatic waste segregation system can be a viable solution to improve the sustainability of the country and boost the circular economy. This paper proposes a machine to segregate waste into different parts with the help of a smart object detection algorithm using ConvoWaste in the field of deep convolutional neural networks (DCNN) and image processing techniques. In this paper, deep learning and image processing techniques are applied to precisely classify the waste, and the detected waste is placed inside the corresponding bins with the help of a servo motor-based system. This machine has the provision to notify the responsible authority regarding the waste level of the bins and the time to trash out the bins filled with garbage by using the ultrasonic sensors placed in each bin and the dual-band GSM-based communication technology. The entire system is controlled remotely through an Android app in order to dump the separated waste in the desired place thanks to its automation properties. The use of this system can aid in the process of recycling resources that were initially destined to become waste, utilizing natural resources, and turning these resources back into usable products. Thus, the system helps fulfill the criteria of a circular economy through resource optimization and extraction. Finally, the system is designed to provide services at a low cost while maintaining a high level of accuracy in terms of technological advancement in the field of artificial intelligence (AI). We have gotten 98% accuracy for our ConvoWaste deep learning model.

研究动机与目标

• 通过自动化垃圾分拣解决城市垃圾管理挑战，以支持循环经济。
• 开发基于 DCNN 的分类器，能够将垃圾准确地分拣至指定桶。
• 集成伺服电机、超声波传感器等硬件组件，实现自动桶填充与警报机制。
• 通过 Android 应用实现远程监控与控制。

提出的方法

• 应用深度卷积神经网络和图像处理进行垃圾分类。
• 利用伺服电机为将检测到的垃圾放入正确桶的机构。
• 引入超声波传感器监测桶内垃圾水平，以及双频段 GSM 通信。
• 通过 Android 应用提供远程控制和数据访问。

实验结果

研究问题

• RQ1 DCNN 基于的模型是否能够准确分类常见垃圾类型以实现自动分拣？
• RQ2 硬件执行（伺服）与传感器（超声波、GSM）在持续垃圾分拣中能多大程度上实现自动化？
• RQ3 集成系统是否支持及时通知与远程管理以提升回收工作流程？

主要发现

• 所提出的 ConvoWaste 系统在垃圾分类上达到 98% 的准确率。
• 垃圾检测结果驱动伺服驱动的分拣，将垃圾分拣到适当的桶中。
• 超声波传感器提供桶水平监测并在垃圾处理时触发通知。
• 双频段 GSM 实现状态更新和控制的通信。
• 系统架构支持通过 Android 应用实现远程操作。