Redirigiendo al acceso original de articulo en 20 segundos...
Inicio  /  Drones  /  Vol: 3 Par: 1 (2019)  /  Artículo
ARTÍCULO
TITULO

Vision-Based Indoor Scene Recognition from Time-Series Aerial Images Obtained Using a MAV Mounted Monocular Camera

Hirokazu Madokoro    
Kazuhito Sato and Nobuhiro Shimoi    

Resumen

This paper presents a vision-based indoor scene recognition method from aerial time-series images obtained using a micro air vehicle (MAV). The proposed method comprises two procedures: a codebook feature description procedure, and a recognition procedure using category maps. For the former procedure, codebooks are created automatically as visual words using self-organizing maps (SOMs) after extracting part-based local features using a part-based descriptor from time-series scene images. For the latter procedure, category maps are created using counter propagation networks (CPNs) with the extraction of category boundaries using a unified distance matrix (U-Matrix). Using category maps, topologies of image features are mapped into a low-dimensional space based on competitive and neighborhood learning. We obtained aerial time-series image datasets of five sets for two flight routes: a round flight route and a zigzag flight route. The experimentally obtained results with leave-one-out cross-validation (LOOCV) revealed respective mean recognition accuracies for the round flight datasets (RFDs) and zigzag flight datasets (ZFDs) of 71.7% and 65.5% for 10 zones. The category maps addressed the complexity of scenes because of segmented categories. Although extraction results of category boundaries using U-Matrix were partially discontinuous, we obtained comprehensive category boundaries that segment scenes into several categories.

 Artículos similares

       
 
Md Monowar Hossain, A. H. M. Faisal Anwar, Nikhil Garg, Mahesh Prakash and Mohammed Abdul Bari    
The fidelity of the decadal experiment in Coupled Model Intercomparison Project Phase-5 (CMIP5) has been examined, over different climate variables for multiple temporal and spatial scales, in many previous studies. However, most of the studies were for ... ver más
Revista: Hydrology

 
Djouhaina Brella, Lazhar Belkhiri, Ammar Tiri, Hichem Salhi, Fatma Elhadj Lakouas, Razki Nouibet, Adeltif Amrane, Ryma Merdoud and Lotfi Mouni    
In this study, we analyzed the quality and the potential noncarcinogenic health risk of nitrate in groundwater in the El Milia plain, Kebir Rhumel Basin, Algeria. Moran?s I and the ordinary kriging (OK) interpolation technique were used to examine the sp... ver más
Revista: Hydrology

 
Husam Musa Baalousha, Anis Younes, Mohamed A. Yassin and Marwan Fahs    
Flood risk assessment is an important tool for urban planning, land development, and hydrological analysis. The flood risks are very high in arid countries due to the nature of the rainfall resulting from thunderstorms and the land cover, which comprises... ver más
Revista: Hydrology

 
Jesus GomezRomero-Borquez, J. Alberto Del Puerto-Flores and Carolina Del-Valle-Soto    
This work presents a study in which the cognitive concentration levels of participants were evaluated using electroencephalogram (EEG) measures while they were playing three different categories of virtual reality (VR) video games: Challenging Puzzlers, ... ver más
Revista: Future Internet

 
Niranjan Ravi and Mohamed El-Sharkawy    
Three-dimensional object detection involves estimating the dimensions, orientations, and locations of 3D bounding boxes. Intersection of Union (IoU) loss measures the overlap between predicted 3D box and ground truth 3D bounding boxes. The localization t... ver más
Revista: Future Internet