Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks

Simple item page
dc.contributor.authorMousavian, Arsalan
dc.contributor.authorPirsiavash, Hamed
dc.contributor.authorKošecká, Jana
dc.date.accessioned2019-07-01T18:05:07Z
dc.date.available2019-07-01T18:05:07Z
dc.date.issued2016-12-19
dc.description.abstractMulti-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple tasks. These networks are typically trained independently for each task by varying the output layer(s) and training objective. In this work we present a new model for simultaneous depth estimation and semantic segmentation from a single RGB image. Our approach demonstrates the feasibility of training parts of the model for each task and then fine tuning the full, combined model on both tasks simultaneously using a single loss function. Furthermore we couple the deep CNN with fully connected CRF, which captures the contextual relationships and interactions between the semantic and depth cues improving the accuracy of the final results. The proposed model is trained and evaluated on NYUDepth V2 dataset [23] outperforming the state of the art methods on semantic segmentation and achieving comparable results on the task of depth estimation.en_US
dc.description.sponsorshipWe also acknowledge support from NSF NRI grant 1527208. Some of the experiments were run on ARGO, a research computing cluster provided by the Office of Research Computing at George Mason University.en_US
dc.description.urihttps://ieeexplore.ieee.org/abstract/document/7785137en_US
dc.format.extent9 pagesen_US
dc.genreconference papers and proceedings preprintsen_US
dc.identifierdoi:10.13016/m2uswx-e8bj
dc.identifier.citationArsalan Mousavian, et.al, Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks, 2016 Fourth International Conference on 3D Vision (3DV), DOI: 10.1109/3DV.2016.69en_US
dc.identifier.urihttps://doi.org/10.1109/3DV.2016.69
dc.identifier.urihttp://hdl.handle.net/11603/14328
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.rights© 2016 IEEE
dc.subjectconvolutionen_US
dc.subjectimage segmentationen_US
dc.subjectlearning (artificial intelligence)en_US
dc.subjectneural netsen_US
dc.subjectjoint semantic segmentationen_US
dc.subjectdeep convolutional networksen_US
dc.subjectmultiscale deep CNNsen_US
dc.subjectpixel mappingen_US
dc.subjectindependent trainingen_US
dc.subjectcontextual relationshipsen_US
dc.titleJoint Semantic Segmentation and Depth Estimation with Deep Convolutional Networksen_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1604.07480.pdf
Size:
1.56 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection