Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Mickey Aleksic"'
Publikováno v:
2018 1st Workshop on Energy Efficient Machine Learning and Cognitive Computing for Embedded Applications (EMC2).
As deep learning (DL) is being rapidly pushed to edge computing, researchers invented various ways to make inference computation more efficient on mobile/IoT devices, such as network pruning, parameter compression, and etc. Quantization, as one of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc3cb9c701b5aa8b86765e416f3193b9
https://doi.org/10.1109/emc2.2018.00011
https://doi.org/10.1109/emc2.2018.00011
Publikováno v:
SPIE Proceedings.
The MIPI standard has adopted DPCM compression for RAW data images streamed from mobile cameras. This DPCM is line based and uses either a simple 1 or 2 pixel predictor. In this paper, we analyze the DPCM compression performance as MTF degradation. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8660c6b1451bf80b0d2b4d2a24cc2ce5
https://doi.org/10.1117/12.872637
https://doi.org/10.1117/12.872637
Autor:
Sergio Goma, Mickey Aleksic
Publikováno v:
2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers.
We propose a novel 8bpp subsampling YUV pattern based on a checkerboard subsampling of the luminance component that explicitly preserves the edge. The proposed pattern uses 1bit to encode edge direction in the missing luminance pixel and this bit is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f3cdcdadf963f16a7d5a435a975854b
https://doi.org/10.1109/acssc.2010.5757688
https://doi.org/10.1109/acssc.2010.5757688
Publikováno v:
SPIE Proceedings.
We describe design of a low-complexity lossless and near-lossless image compression system with random access, suitable for embedded memory compression applications. This system employs a block-based DPCM coder using variable-length encoding for the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ed052a0bb0820d75b6eb897300de06e
https://doi.org/10.1117/12.862254
https://doi.org/10.1117/12.862254