A heterogeneous attention fusion mechanism for the cross-environment scene classification of the home service robot

Zhu, Bo; Fan, Ximing; Gao, Xiang; Xu, Guozheng; Xie, Junzhe

doi:10.1016/j.robot.2024.104619

Cited by 2 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They can be integrated into various home appliances. Inspired by neuroscience, Zhu et al [223] presented scene classification in the application of home service robots. Yang et al [224] benefited from the diversity of available data representations and used a set of numerous formats of maps to create an autonomous navigation and landing system for an Unmanned Aerial Vehicle (UAV).…”

Section: Newest Trends and Place For Future Workmentioning

confidence: 99%

Methods and Applications of Space Understanding in Indoor Environment—A Decade Survey

Pokuciński,

Mrozek

2024

Applied Sciences

View full text Add to dashboard Cite

The demand for digitizing manufacturing and controlling processes has been steadily increasing in recent years. Digitization relies on different techniques and equipment, which produces various data types and further influences the process of space understanding and area recognition. This paper provides an updated view of these data structures and high-level categories of techniques and methods leading to indoor environment segmentation and the discovery of its semantic meaning. To achieve this, we followed the Systematic Literature Review (SLR) methodology and covered a wide range of solutions, from floor plan understanding through 3D model reconstruction and scene recognition to indoor navigation. Based on the obtained SLR results, we identified three different taxonomies (the taxonomy of underlying data type, of performed analysis process, and of accomplished task), which constitute different perspectives we can adopt to study the existing works in the field of space understanding. Our investigations clearly show that the progress of works in this field is accelerating, leading to more sophisticated techniques that rely on multidimensional structures and complex representations, while the processing itself has become focused on artificial intelligence-based methods.

show abstract

Section: Newest Trends and Place For Future Workmentioning

confidence: 99%