Semantic segmentation is the pixel-wise labeling of an image. Boosted by the extraordinary ability of convolutional neural networks (CNN) in creating semantic, high-level and hierarchical image features; several deep learning-based 2D semantic segmentation approaches have been proposed within the last decade. In this survey, we mainly focus on the recent scientific developments in semantic segmentation, specifically on deep learning-based methods using 2D images. We started with an analysis of the public image sets and leaderboards for 2D semantic segmentation, with an overview of the techniques employed in performance evaluation. In examining the evolution of the field, we chronologically categorized the approaches into three main periods, namely pre-and early deep learning era, the fully convolutional era, and the post-FCN era. We technically analyzed the solutions put forward in terms of solving the fundamental problems of the field, such as fine-grained localization and scale invariance. Before drawing our conclusions, we present a table of methods from all mentioned eras, with a summary of each approach that explains their contribution to the field. We conclude the survey by discussing the current challenges of the field and to what extent they have been solved.
31 August 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Forests can be efficiently monitored by automatic semantic segmentation of trees using satellite and/or aerial images. Still, several challenges can make the problem difficult, including the varying spectral signature of different trees, lack of sufficient labelled data, and geometrical occlusions. In this paper, we address the tree segmentation problem using multispectral imagery. While we carry out large-scale experiments on several deep learning architectures using various spectral input combinations, we also attempt to explore whether hand-crafted spectral vegetation indices can improve the performance of deep learning models in the segmentation of trees. Our experiments include benchmarking a variety of multispectral remote sensing image sets, deep semantic segmentation architectures, and various spectral bands as inputs, including a number of hand-crafted spectral vegetation indices. From our large-scale experiments, we draw several useful conclusions. One particularly important conclusion is that, with no additional computation burden, combining different categories of multispectral vegetation indices, such as NVDI, ARVI, and SAVI, within a single three-channel input, and using the state-of-the-art semantic segmentation architectures, tree segmentation accuracy can be improved under certain conditions, compared to using high-resolution visible and/or nearinfrared input.
28 May 2024 in Journal of Real-Time Image Processing
Lightweight multiscale-feature-fusion network (LMFFNet), a proficient real-time CNN architecture, adeptly achieves a balance between inference time and accuracy. Capturing the intricate details of precision agriculture target objects in remote sensing images requires deep SEM-B blocks in the LMFFNet model design. However, employing numerous SEM-B units leads to instability during backward gradient flow. This work proposes the novel residual-LMFFNet (ResLMFFNet) model for ensuring smooth gradient flow within SEM-B blocks. By incorporating residual connections, ResLMFFNet achieves improved accuracy without affecting the inference speed and the number of trainable parameters. The results of the experiments demonstrate that this architecture has achieved superior performance compared to other real-time architectures across diverse precision agriculture applications involving UAV and satellite images. Compared to LMFFNet, the ResLMFFNet architecture enhances the Jaccard Index values by 2.1% for tree detection, 1.4% for crop detection, and 11.2% for wheat-yellow rust detection. Achieving these remarkable accuracy levels involves maintaining almost identical inference time and computational complexity as the LMFFNet model. The source code is available on GitHub: https://github.com/iremulku/Semantic-Segmentation-in-Precision-Agriculture.
26 August 2024 in IEEE Geoscience and Remote Sensing Letters
Plant health can be monitored dynamically using multispectral sensors that measure Near-Infrared reflectance (NIR). Despite this potential, obtaining and annotating high-resolution NIR images poses a significant challenge for training deep neural networks. Typically, large networks pre-trained on the RGB domain are utilized to fine-tune infrared images. This practice introduces a domain shift issue because of the differing visual traits between RGB and NIR images. As an alternative to fine-tuning, a method called low-rank adaptation (LoRA) enables more efficient training by optimizing rank-decomposition matrices while keeping the original network weights frozen. However, existing parameter-efficient adaptation strategies for remote sensing images focus on RGB images and overlook domain shift issues in the NIR domain. Therefore, this study investigates the potential benefits of using vision transformer (ViT) backbones pre-trained in the RGB domain, with low-rank adaptation for downstream tasks in the NIR domain. Extensive experiments demonstrate that employing LoRA with pre-trained ViT backbones yields the best performance for downstream tasks applied to NIR images.
Background/Objectives: Furcation defects pose a significant challenge in the diagnosis and treatment planning of periodontal diseases. Accurate clinical identification of furcation involvement is essential for improving treatment outcomes. This study aimed to evaluate the accuracy and effectiveness of various artificial intelligence (AI) algorithms in detecting furcation defects (FD) in mandibular molars. Methods: A total of 654 panoramic radiographs were randomly selected from patients who visited the Department of Oral and Maxillofacial Radiology at the Faculty of Dentistry, Ankara University. Each image was labeled as either “healthy” or “FD” and subsequently preprocessed. The performance of different deep learning algorithms in identifying FD was subsequently evaluated. Results: In the classification models employed, the highest scores were calculated as accuracy 97.9%, precision 97.10%, sensitivity 97.08%, and F1 score 97.09% in the Xception model. In the segmentation tests, the highest scores were calculated as accuracy 99.96%, precision 99.26%, sensitivity 97.57%, and F1 score 98.41% in the ENet model. Conclusions: Results of this study indicated that the use of artificial intelligence systems in detecting furcation involvement in mandibular molar teeth in panoramic radiography images is promising. Further studies covering larger data sets, including maxillary molar teeth, will increase the success rates in detecting furcation involvement.