INDOOR SEMANTIC SEGMENTATION FROM RGB-D IMAGES BY INTEGRATING FULLY CONVOLUTIONAL NETWORK WITH HIGHER-ORDER MARKOV RANDOM FIELD

Yang, J.; Kang, Z.

Indoor scenes have the characteristics of abundant semantic categories, illumination changes, occlusions and overlaps among objects, which poses great challenges for indoor semantic segmentation. Therefore, we in this paper develop a method based on higher-order Markov random field model for indoor semantic segmentation from RGB-D images. Instead of directly using RGB-D images, we first train and perform RefineNet model only using RGB information for generating the high-level semantic information. Then, the spatial location relationship from depth channel and the spectral information from color channels are integrated as a prior for a marker-controlled watershed algorithm to obtain the robust and accurate visual homogenous regions. Finally, higher-order Markov random field model encodes the short-range context among the adjacent pixels and the long-range context within each visual homogenous region for refining the semantic segmentations. To evaluate the effectiveness and robustness of the proposed method, experiments were conducted on the public SUN RGB-D dataset. Experimental results indicate that compared with using RGB information alone, the proposed method remarkably improves the semantic segmentation results, especially at object boundaries.

Zitieren

Zitierform:

Yang, J. / Kang, Z.: INDOOR SEMANTIC SEGMENTATION FROM RGB-D IMAGES BY INTEGRATING FULLY CONVOLUTIONAL NETWORK WITH HIGHER-ORDER MARKOV RANDOM FIELD. 2018. Copernicus Publications.

Zugriffsstatistik

Gesamt:
Volltextzugriffe:
Metadatenansicht:
12 Monate:
Volltextzugriffe:
Metadatenansicht:

Grafik öffnen

Rechte

Rechteinhaber: J. Yang

Nutzung und Vervielfältigung:

Export