Cargando…

A similarity-guided segmentation model for garbage detection under road scene

The development of computer vision technology provides a possible path for realizing intelligent control of road sweepers to reduce energy waste in urban street cleaning work. For garbage segmentation of seven categories under road scene, we introduce an efficient deep-learning-based method. Our mod...

Descripción completa

Detalles Bibliográficos
Autores principales: Zheng, Caiyun, Cao, Danhua, Hu, Cheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Higher Education Press 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9756228/
https://www.ncbi.nlm.nih.gov/pubmed/36637526
http://dx.doi.org/10.1007/s12200-022-00004-9
Descripción
Sumario:The development of computer vision technology provides a possible path for realizing intelligent control of road sweepers to reduce energy waste in urban street cleaning work. For garbage segmentation of seven categories under road scene, we introduce an efficient deep-learning-based method. Our model follows a lightweight structure with a feature pyramid attention (FPA) module employed in the decoder to enhance feature integration at multi-levels. Besides, a similarity guidance (SG) module is added to the decoder branches, which calculates the cosine distance between learned prototypes and feature maps to guide the segmentation results from a metric learning perspective. Our model has less than 3 M parameters and can run at over 65 FPS in an RTX 2070 GPU. Experimental results demonstrate that our method can yield competitive results in terms of speed and accuracy trade-off, with overall mean intersection-over-union (mIoU) reaching 0.87 and 0.67, respectively, on two garbage data sets we built. Besides, our model can perform acceptable category-balanced segmentation from less than 20 annotated images per category by introducing the SG module. GRAPHICAL ABSTRACT: [Image: see text]