TY - GEN
T1 - Semantic Line Detection and Its Applications
AU - Lee, Jun Tae
AU - Kim, Han Ul
AU - Lee, Chul
AU - Kim, Chang-Su
N1 - Funding Information:
This work was supported partly by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. NRF2015R1A2A1A10055037), partly by the NRF grant funded by the Korea government (MSIP) (No. NRF-2016R1C1B2010319), and partly by the Agency for Defense Development (ADD) and Defense Acquisition Program Administration (DAPA) of Korea (UC160016FD).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/12/22
Y1 - 2017/12/22
N2 - Semantic lines characterize the layout of an image. Despite their importance in image analysis and scene understanding, there is no reliable research for semantic line detection. In this paper, we propose a semantic line detector using a convolutional neural network with multi-task learning, by regarding the line detection as a combination of classification and regression tasks. We use convolution and max-pooling layers to obtain multi-scale feature maps for an input image. Then, we develop the line pooling layer to extract a feature vector for each candidate line from the feature maps. Next, we feed the feature vector into the parallel classification and regression layers. The classification layer decides whether the line candidate is semant ic or not. In case of a semantic line, the regression layer determines the offset for refining the line location. Experimental results show that the proposed detector extracts semantic lines accurately and reliably. Moreover, we demonstrate that the proposed detector can be used successfully in three applications: horizon estimation, composition enhancement, and image simplification.
AB - Semantic lines characterize the layout of an image. Despite their importance in image analysis and scene understanding, there is no reliable research for semantic line detection. In this paper, we propose a semantic line detector using a convolutional neural network with multi-task learning, by regarding the line detection as a combination of classification and regression tasks. We use convolution and max-pooling layers to obtain multi-scale feature maps for an input image. Then, we develop the line pooling layer to extract a feature vector for each candidate line from the feature maps. Next, we feed the feature vector into the parallel classification and regression layers. The classification layer decides whether the line candidate is semant ic or not. In case of a semantic line, the regression layer determines the offset for refining the line location. Experimental results show that the proposed detector extracts semantic lines accurately and reliably. Moreover, we demonstrate that the proposed detector can be used successfully in three applications: horizon estimation, composition enhancement, and image simplification.
UR - http://www.scopus.com/inward/record.url?scp=85041920591&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2017.350
DO - 10.1109/ICCV.2017.350
M3 - Conference contribution
AN - SCOPUS:85041920591
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 3249
EP - 3257
BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017
Y2 - 22 October 2017 through 29 October 2017
ER -