From announce at list.ipol.im Wed Jun 7 19:12:45 2023 From: announce at list.ipol.im (announcements about the IPOL journal) Date: Wed, 7 Jun 2023 19:12:45 +0200 Subject: [IPOL discuss] [IPOL announce] new article: Semantic Segmentation: A Zoology of Deep Architectures Message-ID: A new article is available in IPOL: https://www.ipol.im/pub/art/2023/447/ Aitor Artola, Semantic Segmentation: A Zoology of Deep Architectures, Image Processing On Line, 13 (2023), pp. 167?182. https://doi.org/10.5201/ipol.2023.447 Abstract In this paper we review the evolution of deep architectures for semantic segmentation. The first successful model was fully convolutional network (FCN) published in CVPR in 2015. Since then, the subject has become very popular and many methods have been published, mainly proposing improvements of FCN. We describe in detail the Pyramid Scene Parsing Network (PSPnet) and DeepLabV3, in addition to FCN, which provide a multi-scale description and increase the resolution of segmentation. In recent years, convolutional architectures have reached a bottleneck and have been surpassed by transformers from natural language processing (NLP), even though these models are generally larger and slower. We have chosen to discuss about the Segmentation Transformer (SETR), a first architecture with a transformer backbone. We also discuss SegFormer, that includes a multi-scale interpretation and tricks to decrease the size and inference time of the network. The networks presented in the demo come from the MM-Segmentation library, an open source semantic segmentation toolbox based on PyTorch. We propose to compare these methods qualitatively on individual images, and not on global metrics on databases as is usually the case. We compare these architectures on images outside of their training set. We also invite the readers to make their own comparison and derive their own conclusions. -- IPOL - Image Processing On Line - http://ipol.im/ contact edit at ipol.im - http://www.ipol.im/meta/contact/ news+feeds twitter @IPOL_journal - http://www.ipol.im/meta/feeds/ announces announce at list.ipol.im - http://tools.ipol.im/mm/announce/ discussions discuss at list.ipol.im - http://tools.ipol.im/mm/discuss/ From announce at list.ipol.im Sat Jun 10 13:08:54 2023 From: announce at list.ipol.im (announcements about the IPOL journal) Date: Sat, 10 Jun 2023 11:08:54 -0000 Subject: [IPOL discuss] [IPOL announce] new article: A Two-stage Signal Decomposition into Jump, Oscillation and Trend using ADMM Message-ID: A new article is available in IPOL: http://www.ipol.im/pub/art/2023/417/ Martin Huska, Antonio Cicone, Sung Ha Kang, and Serena Morigi, A Two-stage Signal Decomposition into Jump, Oscillation and Trend using ADMM, Image Processing On Line, 13 (2023), pp. 153?166. https://doi.org/10.5201/ipol.2023.417 Abstract We present a thorough implementation of the two-stage framework proposed in [A. Cicone, M. Huska, S.H. Kang and S. Morigi, JOT: a Variational Signal Decomposition into Jump, Oscillation and Trend, IEEE Transactions on Signal Processing, 2022]. The method assumes as input a 1D signal represented by a finite-dimensional vector in RN. In the first stage the signal is decomposed into Jump (piece-wise constant), Oscillation, and Trend (smooth) components, and in the second stage the results are refined using residuals of other components. We propose an efficient numerical solution for the first stage based on alternating direction method of multipliers, and a solid algorithm for the solution of the second stage. -- IPOL - Image Processing On Line - http://ipol.im/ contact edit at ipol.im - http://www.ipol.im/meta/contact/ news+feeds twitter @IPOL_journal - http://www.ipol.im/meta/feeds/ announces announce at list.ipol.im - http://tools.ipol.im/mm/announce/ discussions discuss at list.ipol.im - http://tools.ipol.im/mm/discuss/ From announce at list.ipol.im Wed Jun 28 20:36:31 2023 From: announce at list.ipol.im (announcements about the IPOL journal) Date: Wed, 28 Jun 2023 20:36:31 +0200 Subject: [IPOL discuss] [IPOL announce] new article: Fast Chromatic Aberration Correction with 1D Filters Message-ID: A new article is available in IPOL: https://www.ipol.im/pub/art/2023/443/ Thomas Eboli, Fast Chromatic Aberration Correction with 1D Filters, Image Processing On Line, 13 (2023), pp. 198?214. https://doi.org/10.5201/ipol.2023.443 Abstract This article presents an implementation of the chromatic aberration correction technique of Chang et al. [Correction of Axial and Lateral Chromatic Aberration with False Color Filtering, IEEE Transactions on Image Processing, 2013]. This method decomposes aberration correction into a cascade of two 1D filters. The first one locally sharpens the red and blue edges such that they have similar profiles to that of the green channel serving as guiding image throughout restoration. The second one shifts the red and blue corrected edges to the location of the green ones to remove the color fringes. These two successive estimates are ultimately merged into a final prediction, free of most chromatic aberrations. -- IPOL - Image Processing On Line - http://ipol.im/ contact edit at ipol.im - http://www.ipol.im/meta/contact/ news+feeds twitter @IPOL_journal - http://www.ipol.im/meta/feeds/ announces announce at list.ipol.im - http://tools.ipol.im/mm/announce/ discussions discuss at list.ipol.im - http://tools.ipol.im/mm/discuss/ From announce at list.ipol.im Wed Jun 28 20:14:25 2023 From: announce at list.ipol.im (announcements about the IPOL journal) Date: Wed, 28 Jun 2023 20:14:25 +0200 Subject: [IPOL discuss] [IPOL announce] new article: A Data Set for Fall Detection with Smart Floor Sensors Message-ID: A new article is available in IPOL: https://www.ipol.im/pub/art/2023/389/ Charles Truong, Mounir Atiq, Ludovic Minvielle, Renan Serra, Mathilde Mougeot, and Nicolas Vayatis, A Data Set for Fall Detection with Smart Floor Sensors, Image Processing On Line, 13 (2023), pp. 183?197. https://doi.org/10.5201/ipol.2023.389 Abstract This article describes a data set of falls and activities of daily living recorded with a pressure floor sensor. These signals have been recorded under two settings, one constrained - with volunteers following a predefined protocol, and one unconstrained - where data were collected in a partner nursing home. Overall 157 hours of signal are made available along with 563 manually annotated falls and 333 manually annotated activities (e.g. running, walking). For ease of use, code snippets and an online interface are also provided. -- IPOL - Image Processing On Line - http://ipol.im/ contact edit at ipol.im - http://www.ipol.im/meta/contact/ news+feeds twitter @IPOL_journal - http://www.ipol.im/meta/feeds/ announces announce at list.ipol.im - http://tools.ipol.im/mm/announce/ discussions discuss at list.ipol.im - http://tools.ipol.im/mm/discuss/