Please use this identifier to cite or link to this item:
|標題:||USEAQ: Ultra-fast Superpixel Extraction via Adaptive Sampling from Quantized Regions||作者:||Chun-Rong Huang
|關鍵字:||Superpixel extraction;image segmentation;joint spatial and color quantizations||出版社:||IEEE Transactions on Image Processing||Project:||IEEE transactions on image processing : a publication of the IEEE Signal Processing Society||摘要:||
We present a novel and highly efficient superpixel extraction method called 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 firstly 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 (MAP) 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 to the stateof- 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.
|Appears in Collections:||資訊科學與工程學系所|
Show full item record
Files in This Item:
TAIR Related Article
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.