Garbage localization based on weakly supervised learning in Deep Convolutional Neural Network

Anjum, Mohd; Umar, M. Sarosh

doi:10.1109/icacccn.2018.8748568

Cited by 14 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [30], the authors created a dataset of 450 street-level garbage images and applied the AlexNet [44] architecture for binary classification, obtaining 87.7% average accuracy. In [23], the authors proposed a semi-supervised method for creating a segmentation mask for the garbage in the image. For the evaluation, 25 volunteers rated the segmentation masks yielding an average score of 4.1/5 for 500 images.…”

Section: Image Classification For Street-level Visual Contentmentioning

confidence: 99%

Learning to Identify Illegal Landfills through Scene Classification in Aerial Images

Torres

Fraternali

2021

Remote Sensing

View full text Add to dashboard Cite

Illegal landfills are uncontrolled disposals of waste that cause severe environmental and health risk. Discovering them as early as possible is of prominent importance for preventing hazards, such as fire pollution and leakage. Before the digital era, the only means to detect illegal waste dumps was the on site inspection of potentially suspicious sites, a procedure extremely costly and impossible to scale to a vast territory. With the advent of Earth observation technology, scanning the territory via aerial images has become possible. However, manual image interpretation remains a complex and time-consuming task that requires expert skill. Photo interpretation can be partially automated by embedding the expert knowledge within a data driven classifier trained with samples provided by human annotators. In this paper, the detection of illegal landfills is formulated as a multi-scale scene classification problem. Scene elements positioning and spatial relations constitute hints of the presence of illegal waste dumps. A dataset of ≈3000 images (20 cm resolution per pixel) was created with the help of expert photo interpreters. A combination of ResNet50 and Feature Pyramid Network (FPN) elements accounting for different object scales achieves 88% precision with an 87% of recall in a test area. The results proved the feasibility of applying convolutional neural networks for scene classification in this scenario to optimize the process of waste dumps detection.

show abstract

Section: Image Classification For Street-level Visual Contentmentioning

confidence: 99%

Learning to Identify Illegal Landfills through Scene Classification in Aerial Images

Torres

Fraternali

2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In addition, they also used a tactile touch sensor to calculate the pressure that can be applied on the plastic object. Based on the same principles, Anjum and Umar [5] deal with the problem of collecting garbage in residential area through an automated process, which requires the autonomous detection and localization of garbage by the vehicles. In this case, the proposed solution is based on the use of a CNN trained on images labeled as garbage or non-garbage.…”

Section: Related Workmentioning

confidence: 99%

A cloud-based cognitive computing solution with interoperable applications to counteract illegal dumping in smart cities

Coccoli

Francesco

Fusco³

et al. 2021

Multimed Tools Appl

View full text Add to dashboard Cite

The study presented in this paper is the outcome of the activity carried on within the program “Party Cloud Challenge per Genova”, promoted by IBM in collaboration with the city municipality of Genoa, Italy. This challenge aimed to show how using cognitive computing solutions in an integrated cloud-based development environment enables the rapid deployment of advanced services with interoperable applications. Specifically, we investigated a solution to cope with the problem of illegal dumping prevention in a smart city. In this respect, we will describe the study of the prototype of an automated visual recognition and alerting system. The presented solution relies on the use of cognitive computing technologies to analyze videos provided by cameras installed in urban areas, to identify trash, especially bulky waste, where it should not be, and trigger an alarm to the municipality. In particular, we want to take advantage of the pictures, frames and videos continuously recorded by cameras installed for traffic monitoring, for surveillance, etc. in smart cities where the waste management system is supposed to be integrated with other municipality services for environment control and management. Besides, an organization plan is also proposed for intelligent waste collection as well as some organizational ideas for scalability.

show abstract

“…Dabholkar et al [3] used deep learning classification network to recognize various types of wastes, which is similar in SpotGargabe [4]. Anjum et al [5] designed a deep CNN to classify segmented garbage and non-garbage for garbage region localization. Additionally, Richard A. Marcum et al [6] proposed a representative pipeline for the This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.…”

Section: Introductionmentioning

confidence: 99%

Thermal Power Plant Detection in Remote Sensing Images With Saliency Enhanced Feature Representation

et al. 2021

View full text Add to dashboard Cite

Garbage localization based on weakly supervised learning in Deep Convolutional Neural Network

Cited by 14 publications

References 16 publications

Learning to Identify Illegal Landfills through Scene Classification in Aerial Images

Learning to Identify Illegal Landfills through Scene Classification in Aerial Images

A cloud-based cognitive computing solution with interoperable applications to counteract illegal dumping in smart cities

Thermal Power Plant Detection in Remote Sensing Images With Saliency Enhanced Feature Representation

Contact Info

Product

Resources

About