Yi-Hsiang ChenNae-Chyun ChenYu-Hsiang KaoYu-Cheng LiYi-Chang LuYI-CHANG LU2019-10-312019-10-312016https://scholars.lib.ntu.edu.tw/handle/123456789/429934https://www.scopus.com/inward/record.uri?eid=2-s2.0-85010369831&doi=10.1109%2fGCCE.2016.7800346&partnerID=40&md5=60fb4349e8cd7806de1e406691ca20d7In this paper, we propose a hardware compatible queue-based image segmentation algorithm for refining initial depth maps obtained from light field cameras. In the algorithm, an array is created to record the ranges of positions and intensities of possible segments, which make following segment merging steps much more efficient. An ASIC chip based on the proposed algorithm with a plane fitting calculator is implemented using TSMC 90 nm technology. A 20X speed-up is achieved when comparing the results to the software version. © 2016 IEEE.Cameras; Refining; 90 nm technology; ASIC chips; Depth Map; Image segmentation algorithm; Light fields; Segmentation algorithms; Software versions; Speed up; Image segmentationconference paper10.1109/gcce.2016.78003462-s2.0-85010369831