Skip to main content

Neural Network

Three-branch neural network for No-Reference Quality assessment of Pan-Sharpened Images


Pan-Sharpening (PS) techniques aim to enhance the spatial resolution of low-resolution multispectral images by leveraging data from high-resolution panchromatic images. Their comparison typically relies on the quality assessment of the resulting Full-Resolution (FS) pan-sharpened images. However, in the absence of a reference image, a dedicated No-Reference (NR) method must be employed. Therefore, this paper introduces a novel approach called the Three-Branch Neural Network for No-Reference Quality Assessment of Pan-Sharpened Images (TBN-PSI).

The network consists of three subnetworks designed for perceptual processing of image channels, featuring shared extraction of low-level features and high-level semantics. Extensive experimental evaluation demonstrates the superiority of the approach over the state-of-the-art NR PS image quality assessment methods, using six datasets containing diverse satellite images that span urban areas, green vegetation, and water scenarios. Specifically, TBN-PSI outperforms the compared methods by 4% to 9% in terms of Spearman’s Rank-Order Correlation Coefficient (SRCC), Pearson’s Linear Correlation Coefficient (PLCC), and Kendall’s Rank Correlation Coefficient (KRCC) between the obtained scores and those of three representative full-reference methods.

Architecture

The proposed TBN-PSI uses a predefined number of blocks of layers from the deep learning backbone network to create three connected subnetworks. Specifically, the proposed architecture is based on the first 87 layers of the 315 layers in the Inception-v3 network. The set of useful layers, gathered into blocks, has been determined experimentally, taking into account the image quality assessment perspective (see ablation tests in Section 4). Sets of blocks have been duplicated to handle two.
The proposed approach is evaluated on the NBU PansharpRSData benchmark (Meng et al., 2021), which consists of six satellite datasets (see Fig. 2): IKONOS (Agudelo-Medina et al., 2019), Quickbird (Toutin and Cheng, 2002), Gaofen (Chen et al., 2022), WorldView-4 (WV4) (Sefercik et al., 2021), WorldView-3 (WV3) (Longbotham et al., 2015), and WorldView-2 (WV2) (Padwick et al., 2010). The distinct features of each satellite dataset included in the NBU PansharpRSData.
In this study, a new low-complexity NR IQA method for predicting the quality of pan-sharpened images was introduced. The method employs a three-branch neural network architecture specifically designed for assessing the quality of pan-sharpened images. Selected blocks of layers from a backbone network were utilized, with two branches processing the input images—one dedicated to the RGB channels and the other to the NIR GB channels. A central branch integrates information from both inputs.

network, data transmission, cloud networking, 5G connectivity, cybersecurity, wireless technology, IoT integration, SDN, communication efficiency, network infrastructure, scalability, automation, artificial intelligence, machine learning, reduced latency, data security, real-time analytics, hybrid networks, edge computing, VPNs

Comments

Post a Comment

Popular posts from this blog

Global Lighthouse Network

Smart, sustainable manufacturing: 3 lessons from the Global Lighthouse Network Launched in 2018, when more than 70% of factories struggled to scale digital transformation beyond isolated pilots, the Global Lighthouse Network set out to identify the world’s most advanced production sites and create a shared learning journey to up-level the global manufacturing community. In the past seven years, the network has grown from 16 to 201 industrial sites in more than 30 countries and 35 sectors, including the latest cohort of 13 new sites. This growing community of organizations is setting new standards for operational excellence, leveraging advanced technologies to drive growth, productivity, resilience and environmental sustainability. But what exactly is a Global Lighthouse and what has the network achieved? What is the Global Lighthouse Network? The Global Lighthouse Network is a community of operational facilities and value chains that harness digital technologies at scale to ac...
Post a Comment
Read more

Multi-Modal Data

Multi-Task Federated Split Learning Across Multi-Modal Data with Privacy Preservation With the advancement of federated learning (FL), there is a growing demand for schemes that support multi-task learning on multi-modal data while ensuring robust privacy protection, especially in applications like intelligent connected vehicles. Traditional FL schemes often struggle with the complexities introduced by multi-modal data and diverse task requirements, such as increased communication overhead and computational burdens. In this paper, we propose a novel privacy-preserving scheme for multi-task federated split learning across multi-modal data (MTFSLaMM). Our approach leverages the principles of split learning to partition models between clients and servers, employing a modular design that reduces computational demands on resource-constrained clients. To ensure data privacy, we integrate differential privacy to protect intermediate data and employ homomorphic encryption to safeguard client m...
Post a Comment
Read more

Satellite Communications

3D printed and circularly polarized 28 GHz patch antenna array for small satellite communications This paper presents the design, fabrication, and testing of a high-gain compact 2 × 2 circularly polarized patch antenna array using 3D printing technology for small satellite 5G communication at 28 GHz. The proposed antenna demonstrates high efficiency and a low profile, addressing the limitations in design flexibility associated with traditional PCB fabrication methods . The 2 × 2 array configuration, incorporating via fences, coaxial vertical feedlines, and a sequentially rotated phased feed network, enhances the antenna's bandwidth and axial ratio bandwidth while maintaining compactness, crucial for space-constrained satellite applications. Simulations optimized key antenna parameters, including reflection coefficient , gain, and axial ratio. Measurement results validated the simulations, showing an impedance bandwidth of 6.8 GHz and an axial ratio bandwidth of 3.1 GHz, with a ...
Post a Comment
Read more