Published Paper Details:

Computer vision is a central task in smart city construction, as city managers constantly spend money and energy cleaning street garbage due to the random occurrence of street garbage, The amount of training data available often limits the depth and complexity of deep network solutions. To spur advances in analyzing and understanding images, OpenCV or Google AI have made the Open Images dataset public. Open Images continues the tradition of PASCAL VOC, Image Net, and COCO, but on an unprecedented scale. Consequently, visual street cleanliness assessment is very important in this project. However, existing assessment approaches have some clear disadvantages, such as the collection of street garbage information is not automated, and street cleanliness information is not real-time best performing algorithm for automatically detecting objects. Finally, the results are incorporated into the street cleanliness calculation framework to ultimately visualize street cleanliness levels, which provides convenience for city managers to arrange clean-up personnel effectively.