A
Adrian Munteanu
Researcher at Vrije Universiteit Brussel
Publications - 325
Citations - 3958
Adrian Munteanu is an academic researcher from Vrije Universiteit Brussel. The author has contributed to research in topics: Wavelet & Data compression. The author has an hindex of 27, co-authored 305 publications receiving 3446 citations. Previous affiliations of Adrian Munteanu include VU University Amsterdam & iMinds.
Papers
More filters
Journal ArticleDOI
In-band motion compensated temporal filtering
Yiannis Andreopoulos,Adrian Munteanu,Joeri Barbarien,Mihaela van der Schaar,Jan Cornelis,Peter Schelkens +5 more
TL;DR: A novel framework for fully scalable video coding that performs open-loop motion-compensated temporal filtering (MCTF) in the wavelet domain (in-band) is presented, and inspired by recent work on advanced prediction techniques, an algorithm for optimized multihypothesis temporal filtering is proposed.
Journal ArticleDOI
Wavelet coding of volumetric medical datasets
TL;DR: In this paper, a 3D wavelet-based coding algorithm was proposed for medical volumetric data compression. But, the proposed algorithm is not suitable for medical applications and does not meet the requirements of quality and resolution scalability.
Journal ArticleDOI
Wavelet based volumetric medical image compression
TL;DR: A thorough objective investigation of the performance-complexity trade-offs offered by these techniques on medical data is carried out and a comparison of the presented techniques to H.265/MPEG-H HEVC, which is currently the most state-of-the-art video codec available is provided.
Journal ArticleDOI
Wavelet image compression - the quadtree coding approach
TL;DR: A new wavelet-based embedded compression technique that efficiently exploits the intraband dependencies and uses a quadtree-based approach to encode the significance maps is proposed, which produces a losslessly compressed embedded data stream, supports quality scalability and permits region-of-interest coding.
Journal ArticleDOI
Hourglass-ShapeNetwork Based Semantic Segmentation for High Resolution Aerial Imagery
TL;DR: A new convolution neural network architecture for semantic segmentation of high resolution aerial imagery is proposed, using the composed inception module to replace common convolutional layers, providing the network with multi-scale receptive areas with rich context.