TY - JOUR
T1 - USEAQ
T2 - Ultra-Fast Superpixel Extraction via Adaptive Sampling from Quantized Regions
AU - Huang, Chun Rong
AU - Wang, Wei Cheng
AU - Wang, Wei An
AU - Lin, Szu Yu
AU - Lin, Yen Yu
N1 - Funding Information:
Manuscript received September 25, 2017; revised March 30, 2018 and June 1, 2018; accepted June 3, 2018. Date of publication June 18, 2018; date of current version July 9, 2018. This work was supported by the Ministry of Science and Technology, Taiwan, under Grant MOST104-2221-E-005-027-MY3 and Grant MOST105-2221-E-001-030-MY2. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Yonggang Shi. (Corresponding author: Yen-Yu Lin.) C.-R. Huang, W.-A. Wang, and S.-Y. Lin are with the Department of Computer Science and Engineering, National Chung Hsing University, Taichung 402, Taiwan (e-mail: [email protected]).
Publisher Copyright:
© 2018 IEEE.
PY - 2018/10
Y1 - 2018/10
N2 - We present a novel and highly efficient superpixel extraction method called ultra-fast superpixel extraction via adaptive sampling from quantized regions (USEAQ) to generate regular and compact superpixels in an image. To reduce the computational cost of iterative optimization procedures adopted in most recent approaches, the proposed USEAQ for superpixel generation works in a one-pass fashion. It first performs joint spatial and color quantizations and groups pixels into regions. It then takes into account the variations between regions, and adaptively samples one or a few superpixel candidates for each region. It finally employs maximum a posteriori estimation to assign pixels to the most spatially consistent and perceptually similar superpixels. It turns out that the proposed USEAQ is quite efficient, and the extracted superpixels can precisely adhere to boundaries of objects. Experimental results show that USEAQ achieves better or equivalent performance compared with the state-of-the-art superpixel extraction approaches in terms of boundary recall, undersegmentation error, achievable segmentation accuracy, the average miss rate, average undersegmentation error, and average unexplained variation, and it is significantly faster than these approaches. The source code of USEAQ is available at https://github.com/nchucvml/USEAQ.
AB - We present a novel and highly efficient superpixel extraction method called ultra-fast superpixel extraction via adaptive sampling from quantized regions (USEAQ) to generate regular and compact superpixels in an image. To reduce the computational cost of iterative optimization procedures adopted in most recent approaches, the proposed USEAQ for superpixel generation works in a one-pass fashion. It first performs joint spatial and color quantizations and groups pixels into regions. It then takes into account the variations between regions, and adaptively samples one or a few superpixel candidates for each region. It finally employs maximum a posteriori estimation to assign pixels to the most spatially consistent and perceptually similar superpixels. It turns out that the proposed USEAQ is quite efficient, and the extracted superpixels can precisely adhere to boundaries of objects. Experimental results show that USEAQ achieves better or equivalent performance compared with the state-of-the-art superpixel extraction approaches in terms of boundary recall, undersegmentation error, achievable segmentation accuracy, the average miss rate, average undersegmentation error, and average unexplained variation, and it is significantly faster than these approaches. The source code of USEAQ is available at https://github.com/nchucvml/USEAQ.
UR - http://www.scopus.com/inward/record.url?scp=85048637130&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048637130&partnerID=8YFLogxK
U2 - 10.1109/TIP.2018.2848548
DO - 10.1109/TIP.2018.2848548
M3 - Article
AN - SCOPUS:85048637130
SN - 1057-7149
VL - 27
SP - 4916
EP - 4931
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 10
ER -