Journal Article

Deep LBLS: Accelerated Sky Region Segmentation Using Hybrid Deep CNNs and Lattice Boltzmann Level-Set Model

Ismail, Yasser, Elmedany, Wael, Al-Ammal, Hesham, Qader, M. R., Asari, Vijayan K., Albalooshi, Fatema A., Rajarajan, Muttukrishnan

2025

Overview

Accurate segmentation of the sky region is crucial for various applications, including object detection, tracking, and recognition, as well as augmented reality (AR) and virtual reality (VR) applications. However, sky region segmentation poses significant challenges due to complex backgrounds, varying lighting conditions, and the absence of clear edges and textures. In this paper, we present a new hybrid fast segmentation technique for the sky region that learns from object components to achieve rapid and effective segmentation while preserving precise details of the sky region. We employ Convolutional Neural Networks (CNNs) to guide the active contour and extract regions of interest. Our algorithm is implemented by leveraging three types of CNNs, namely DeepLabV3+, Fully Convolutional Network (FCN), and SegNet. Additionally, we utilize a local image fitting level-set function to characterize the region-based active contour model. Finally, the Lattice Boltzmann approach is employed to achieve rapid convergence of the level-set function. This forms a deep Lattice Boltzmann Level-Set (deep LBLS) segmentation approach that exploits deep CNN, the level-set method (LS), and the lattice Boltzmann method (LBM) for sky region separation. The performance of the proposed method is evaluated on the CamVid dataset, which contains images with a wide range of object variations due to factors such as illumination changes, shadow presence, occlusion, scale differences, and cluttered backgrounds. Experiments conducted on this dataset yield promising results in terms of computation time and the robustness of segmentation when compared to state-of-the-art methods. Our deep LBLS approach demonstrates better performance, with an improvement in mean recall value reaching up to 14.45%.

• Publisher: MDPI AG
• Subject: Accuracy / Algorithms / Architecture / Artificial neural networks / Augmented reality / Contours / convolutional neural networks (CNNs) / Datasets / Deep learning / DeepLabV3 / fully convolutional network (FCN) / Illumination / Image retrieval / level-set function / Neural networks / Object recognition / Occlusion / SegNet / Semantics / Surveillance / Virtual reality