Household garbage images are usually faced with complex backgrounds,variable illuminations,diverse angles,and changeable shapes,which bring a great difficulty in garbage image classification.Due to the ability to disc...Household garbage images are usually faced with complex backgrounds,variable illuminations,diverse angles,and changeable shapes,which bring a great difficulty in garbage image classification.Due to the ability to discover problem-specific features,deep learning and especially convolutional neural networks(CNNs) have been successfully and widely used for image representation learning.However,available and stable household garbage datasets are insufficient,which seriously limits the development of research and application.Besides,the state-of-the-art in the field of garbage image classification is not entirely clear.To solve this problem,in this study,we built a new open benchmark dataset for household garbage image classification by simulating different lightings,backgrounds,angles,and shapes.This dataset is named 30 classes of household garbage images(HGI-30),which contains 18 000 images of 30 household garbage classes.The publicly available HGI-30 dataset allows researchers to develop accurate and robust methods for household garbage recognition.We also conducted experiments and performance analyses of the state-of-the-art deep CNN methods on HGI-30,which serves as baseline results on this benchmark.展开更多
MOHURD released the Notice on Accelerating the Household Garbage Sorting in Certain Key Cities,requiring pushing forward the household garbage sorting in 46 key cities such as Beijing,Tianjin,Shanghai,etc.,and establi...MOHURD released the Notice on Accelerating the Household Garbage Sorting in Certain Key Cities,requiring pushing forward the household garbage sorting in 46 key cities such as Beijing,Tianjin,Shanghai,etc.,and establishing demonstration areas for garbage sorting in these cities for 2018.展开更多
The present contribution aims at helping the Mayors to implement a less expensive and effective system of management of household refuse to Yopougon. Indeed, the incapacity of service providers to be assured the colle...The present contribution aims at helping the Mayors to implement a less expensive and effective system of management of household refuse to Yopougon. Indeed, the incapacity of service providers to be assured the collection of the garbage and the failure of their systems of pre-collection favored the emergence of the informal private precollectors in the municipality of Yopougon. The regularity of the interventions of these new actors, the affordable cost of their services and the living environment daily freed the garbage incites the households to request them because they succeed better where service providers failed. Such an activity will have to be better organized because of supplier employment.展开更多
基金supported by the National Natural Science Foundation of China (Nos. 12001523,11971046,12131003,and 11871081)the Scientific Research Project of Beijing Municipal Education Commission (No. KM201910005012)Beijing Natural Science Foundation Project (No. Z200002)。
文摘Household garbage images are usually faced with complex backgrounds,variable illuminations,diverse angles,and changeable shapes,which bring a great difficulty in garbage image classification.Due to the ability to discover problem-specific features,deep learning and especially convolutional neural networks(CNNs) have been successfully and widely used for image representation learning.However,available and stable household garbage datasets are insufficient,which seriously limits the development of research and application.Besides,the state-of-the-art in the field of garbage image classification is not entirely clear.To solve this problem,in this study,we built a new open benchmark dataset for household garbage image classification by simulating different lightings,backgrounds,angles,and shapes.This dataset is named 30 classes of household garbage images(HGI-30),which contains 18 000 images of 30 household garbage classes.The publicly available HGI-30 dataset allows researchers to develop accurate and robust methods for household garbage recognition.We also conducted experiments and performance analyses of the state-of-the-art deep CNN methods on HGI-30,which serves as baseline results on this benchmark.
文摘MOHURD released the Notice on Accelerating the Household Garbage Sorting in Certain Key Cities,requiring pushing forward the household garbage sorting in 46 key cities such as Beijing,Tianjin,Shanghai,etc.,and establishing demonstration areas for garbage sorting in these cities for 2018.
文摘The present contribution aims at helping the Mayors to implement a less expensive and effective system of management of household refuse to Yopougon. Indeed, the incapacity of service providers to be assured the collection of the garbage and the failure of their systems of pre-collection favored the emergence of the informal private precollectors in the municipality of Yopougon. The regularity of the interventions of these new actors, the affordable cost of their services and the living environment daily freed the garbage incites the households to request them because they succeed better where service providers failed. Such an activity will have to be better organized because of supplier employment.
