TY - GEN
T1 - Semantic Segmentation with Enhanced Temporal Smoothness Using CRF in Aerial Videos
AU - Girisha, S.
AU - Manohara Pai, M. M.
AU - Verma, Ujjwal
AU - Pai, Radhika M.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - UAV videos are attracting widespread interest due to their cost effectiveness and wide applications in monitoring environmental changes, disaster management etc. Recently, computer vision algorithms are utilized to analyse UAV videos and act as decision support systems. To this end, the context of the scene plays a prominent role in improving the performance of the decision support systems. The context of the video scenes is generally realized by using a video semantic segmentation algorithm. The success of video semantic segmentation algorithms relies on temporal consistency for which estimation of temporal correspondence is a necessity. Optical flow based methods are popularly used in literature for establishing temporal correspondence which are expensive for video semantic segmentation. In this regard, a new Conditional Random Field frame work is presented in this paper for UAV video semantic segmentation. A new pairwise potential energy term is proposed which uses long range temporal information required for temporally consistent labels. Further, the proposed method selectively applies CRF inference which reduces the CRF computation and is independent of optical flow estimation. The proposed algorithm achieved an mIoU of 0.89 on ManipalUAVid dataset.
AB - UAV videos are attracting widespread interest due to their cost effectiveness and wide applications in monitoring environmental changes, disaster management etc. Recently, computer vision algorithms are utilized to analyse UAV videos and act as decision support systems. To this end, the context of the scene plays a prominent role in improving the performance of the decision support systems. The context of the video scenes is generally realized by using a video semantic segmentation algorithm. The success of video semantic segmentation algorithms relies on temporal consistency for which estimation of temporal correspondence is a necessity. Optical flow based methods are popularly used in literature for establishing temporal correspondence which are expensive for video semantic segmentation. In this regard, a new Conditional Random Field frame work is presented in this paper for UAV video semantic segmentation. A new pairwise potential energy term is proposed which uses long range temporal information required for temporally consistent labels. Further, the proposed method selectively applies CRF inference which reduces the CRF computation and is independent of optical flow estimation. The proposed algorithm achieved an mIoU of 0.89 on ManipalUAVid dataset.
UR - http://www.scopus.com/inward/record.url?scp=85126197746&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126197746&partnerID=8YFLogxK
U2 - 10.1109/MASCON51689.2021.9563599
DO - 10.1109/MASCON51689.2021.9563599
M3 - Conference contribution
AN - SCOPUS:85126197746
T3 - Proceedings of the IEEE Madras Section International Conference 2021, MASCON 2021
BT - Proceedings of the IEEE Madras Section International Conference 2021, MASCON 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Madras Section International Conference, MASCON 2021
Y2 - 27 August 2021 through 28 August 2021
ER -