Search Results (14)

Autonomous UAV landing in urban scenes requires a perception module that can identify candidate landing surfaces, reject structural and dynamic hazards, and express uncertainty before a downstream controller commits to a landing maneuver. This study reformulates UAV landing perception as a unified three-class landing-safety segmentation problem by relabeling UAVid, UDD6, and VDD into candidate landing area, structural obstacle, and critical hazard classes. The Landing3 dataset is constructed with an implementation-consistent relabeling protocol in which critical hazards override other labels and only sufficiently large connected components of source-specific candidate classes are retained as landing candidates. Two real-time segmentation models are evaluated under this unified task: PIDNet, a CNN-based multi-branch model with explicit boundary modeling, and SCTNet, a Transformer-guided model with semantic alignment for long-range context modeling. A post hoc conformal prediction (CP) module then converts softmax outputs into pixel-wise prediction sets, and the final candidate landing region is extracted only from pixels whose prediction set is the singleton candidate-landing class. Experiments compare the two models in terms of best validation mIoU, class-wise IoU, resolution-dependent accuracy–speed trade-offs, power-constrained FPS and complexity, qualitative candidate-area visualization, and CP-derived safe-area quality. A fixed-checkpoint sensitivity analysis further shows that the comparative model ranking remains stable across the tested connected-component threshold settings. SCTNet provides a lighter model and higher throughput under most tested resolutions and power limits, whereas PIDNet preserves higher safe-area recall, safe IoU, and spatial coherence after CP filtering. These results show that reliable UAV landing perception requires joint consideration of cross-dataset task definition, real-time model efficiency, and uncertainty-aware candidate-area extraction, rather than semantic segmentation accuracy alone. Full article

Accurate localization of the visible track region is essential for perception using front-mounted cameras on underground rail-guided mine vehicles. The task is difficult because the track foreground occupies only a small image area, and its boundary appearance changes with illumination, water, dust, and scene clutter. This study formulates local perception of the track corridor as binary semantic segmentation of the surface bounded by the two visible rails. RailDLA is a lightweight encoder–decoder network. It combines track context preconditioning, RDLA directional strip propagation, context-guided feature fusion, and track axis proxy decoding. On a self-constructed dataset of underground mine vehicle imagery, RailDLA achieves 96.50% mIoU, 92.10% track IoU, 97.50% track accuracy, and 99.70% pixel accuracy. On the working split, its track IoU exceeds those of FastSCNN, PIDNet-S, DDRNet-23-slim, and SegNeXt-S by absolute margins of 6.06, 1.70, 1.56, and 0.37 percentage points, respectively. Under the unified runtime protocol, RailDLA reaches 120.00 FPS on an NVIDIA GeForce RTX 3070 Laptop GPU. These results demonstrate accurate, real-time inference for underground mine vehicle perception. Full article

Accurate semantic segmentation of slender curvilinear structures, such as tree branches, in complex natural scenes remains challenging. The main difficulties arise from frequent occlusions, ambiguous boundaries, and limited edge computing resources. To address these issues, we propose LDS-Net, a lightweight dual-branch network designed for thin and continuous branch structures. The Detail-Aware Branch uses the Dynamic Snake Convolution (DSConv) to model irregular local geometry, while the Context-Aware Branch uses a Spatial Efficient Separable Pyramid module (SESP) to capture multi-scale context. To improve segmentation under occlusion and boundary ambiguity, we further integrate a Global Topology Transformer module (GTT) and a boundary guidance mechanism (BG). These features are fused via a Pixel-Wise Attention Fusion module (PAF) and optimized using a multi-head compound loss. Experiments on USTD and N-ABSD show that LDS-Net outperforms six representative networks. It also requires only 14.19 G FLOPs, a 24% reduction compared with PIDNet-s. These results suggest that LDS-Net has potential for future deployment on resource-constrained agricultural and ecological monitoring platforms. Full article

Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real-world environments often requires the ability to learn novel classes incrementally without retraining on the entire dataset. This capability is known as continual learning. In this regard, standard fine-tuning methods often suffer from catastrophic forgetting, where the model learns new information but loses accuracy on previously learned classes. The severity of this effect depends on the incremental setup, the available data, and the fine-tuning strategy. Contributing to this crucial domain, this paper proposes a novel continual learning framework tailored for PIDNet, which is a widely cited state-of-the-art real-time semantic segmentation model. Our method, PILOT (Parallel Incremental Learning Over Time), introduces a real-time and lightweight strategy by implementing a parallel Derivative branch (D-branch) designed to capture the high-frequency boundary information of novel classes while freezing the trained parameters of the original segmentation network. This novel setup allows the model to adapt to new semantic categories while preserving the knowledge of previously learned classes. By using only data associated with the new class, our model significantly reduces training overhead. Experimental results demonstrate that our approach successfully segments new classes while maintaining a high mean Intersection over Union (mIoU) on the original base classes, thereby outperforming prior continual learning approaches in this real-time segmentation setting. Overall, PILOT is shown to effectively mitigate catastrophic forgetting with minimal impact on inference latency, adding fewer than 5% additional parameters and reducing the frame rate by only about 9%, thus maintaining real-time performance. Full article

Accurate delineation of inland waterbodies is critical for applications such as hydrological monitoring, disaster response preparedness and response, and environmental management. While optical satellite imagery is hindered by cloud cover or low-light conditions, Synthetic Aperture Radar (SAR) provides consistent surface observations regardless of weather or illumination. This study introduces a deep learning-based ensemble framework for precise inland waterbody detection using high-resolution X-band Capella SAR imagery. To improve the discrimination of water from spectrally similar non-water surfaces (e.g., roads and urban structures), an 8-channel input configuration was developed by incorporating auxiliary geospatial features such as height above nearest drainage (HAND), slope, and land cover classification. Four advanced deep learning segmentation models—Proportional–Integral–Derivative Network (PIDNet), Mask2Former, Swin Transformer, and Kernel Network (K-Net)—were systematically evaluated via cross-validation. Their outputs were combined using a weighted average ensemble strategy. The proposed ensemble model achieved an Intersection over Union (IoU) of 0.9422 and an F1-score of 0.9703 in blind testing, indicating high accuracy. While the ensemble gains over the best single model (IoU: 0.9371) were moderate, the enhanced operational reliability through balanced Precision–Recall performance provides significant practical value for flood and water resource monitoring with high-resolution SAR imagery, particularly under data-constrained commercial satellite platforms. Full article

In order to address challenges in small object recognition for remote sensing imagery—including high model complexity, overfitting with small samples, and insufficient cross-scenario generalization—this study proposes CAGM-Seg, a lightweight recognition model integrating multi-attention mechanisms. The model systematically enhances the U-Net architecture: First, the encoder adopts a pre-trained MobileNetV3-Large as the backbone network, incorporating a coordinate attention mechanism to strengthen spatial localization of min targets. Second, an attention gating module is introduced in skip connections to achieve adaptive fusion of cross-level features. Finally, the decoder fully employs depthwise separable convolutions to significantly reduce model parameters. This design embodies a symmetry-aware philosophy, which is reflected in two aspects: the structural symmetry between the encoder and decoder facilitates multi-scale feature fusion, while the coordinate attention mechanism performs symmetric decomposition of spatial context (i.e., along height and width directions) to enhance the perception of geometrically regular small targets. Regarding training strategy, a hybrid loss function combining Dice Loss and Focal Loss, coupled with the AdamW optimizer, effectively enhances the model’s sensitivity to small objects while suppressing overfitting. Experimental results on the Xingtai black and odorous water body identification task demonstrate that CAGM-Seg outperforms comparison models in key metrics including precision (97.85%), recall (98.08%), and intersection-over-union (96.01%). Specifically, its intersection-over-union surpassed SegNeXt by 11.24 percentage points and PIDNet by 8.55 percentage points; its F1 score exceeded SegFormer by 2.51 percentage points. Regarding model efficiency, CAGM-Seg features a total of 3.489 million parameters, with 517,000 trainable parameters—approximately 80% fewer than the baseline U-Net—achieving a favorable balance between recognition accuracy and computational efficiency. Further cross-task validation demonstrates the model’s robust cross-scenario adaptability: it achieves 82.77% intersection-over-union and 90.57% F1 score in landslide detection, while maintaining 87.72% precision and 86.48% F1 score in cloud detection. The main contribution of this work is the effective resolution of key challenges in few-shot remote sensing small-object recognition—notably inadequate feature extraction and limited model generalization—via the strategic integration of multi-level attention mechanisms within a lightweight architecture. The resulting model, CAGM-Seg, establishes an innovative technical framework for real-time image interpretation under edge-computing constraints, demonstrating strong potential for practical deployment in environmental monitoring and disaster early warning systems. Full article

Accurate and non-invasive monitoring of dairy cows is a cornerstone of precision livestock farming, paving the way for proactive health management and earlier disease detection. The development of robust, AI-driven diagnostic tools, however, is hindered by a dual challenge: scarce realistic video datasets and a lack of standardized benchmarks for deep learning models. To confront these issues, this study puts forward SideCow-VSS, a video semantic segmentation dataset comprising 921 side-view clips with dense, pixel-level annotations of dairy cows under variable on-farm conditions. We systematically evaluated eight deep learning architectures, from classic convolutional neural networks to state-of-the-art Transformers. The evaluation highlighted a clear performance trade-off: the Mask2Former model with a Swin-L backbone yielded the highest mIoU at 97.32%, making it well-suited for detailed morphological analysis. In contrast, the lightweight PIDNet-s model achieved the fastest inference speed of 59.5 FPS, demonstrating its potential for real-time behavioral alerting systems. This work delivers a foundational resource and quantitative framework to inform model selection, accelerating the creation of computer vision systems for automated health monitoring and adopting preventive strategies against key metabolic and immunological disorders in dairy production. Full article

Image dehazing is a critical task in image restoration, aiming to retrieve clear images from hazy scenes. This process is vital for various applications, including machine recognition, security monitoring, and aerial photography. Current dehazing algorithms often encounter challenges in multi-scale feature extraction, detail preservation, effective haze removal, and maintaining color fidelity. To address these limitations, this paper introduces a novel Parallel Image-Dehazing Network (PID-Net). PID-Net uniquely combines a Convolutional Neural Network (CNN) for precise local feature extraction and a Vision Transformer (ViT) to capture global contextual information, overcoming the shortcomings of methods relying solely on either local or global features. A multi-scale CNN branch effectively extracts diverse local details through varying receptive fields, thereby enhancing the restoration of fine textures and details. To optimize the ViT component, a lightweight attention mechanism with CNN compensation is integrated, maintaining performance while minimizing the parameter count. Furthermore, a Redundant Feature Filtering Module is incorporated to filter out noise and haze-related artifacts, promoting the learning of subtle details. Our extensive experiments on public datasets demonstrated PID-Net’s significant superiority over state-of-the-art dehazing algorithms in both quantitative metrics and visual quality. Full article

Semantic segmentation, as a critical technology in intelligent transportation and autonomous driving, plays a significant role in accurately parsing scene information and enhancing environmental perception capabilities. However, the complexity of road environments poses challenges to the robustness and real-time performance of existing algorithms. Although PIDNet achieves a certain balance between performance and efficiency, it still falls short in fine-grained object segmentation and multi-scale feature fusion. To address these issues, this paper proposes an improved algorithm based on PIDNet. The proposed method includes the following: (1) introducing a multi-branch high-resolution feature extraction module to reduce information loss; (2) adopting a dense atrous spatial pyramid pooling module to enhance multi-scale feature fusion capabilities; and (3) incorporating cross-attention mechanisms into the Bag module to optimize feature interaction. Experimental results on the CityScapes dataset show that the improved algorithm increases the mean intersection-over-union (MIoU) from 78.6% to 81.1%, demonstrating higher segmentation accuracy and robustness in complex scenarios while maintaining real-time performance, thereby validating the effectiveness of the approach. Full article

The interior problem, a persistent ill-posed challenge in CT imaging, gives rise to truncation artifacts capable of distorting CT values, thereby significantly impacting clinical diagnoses. Traditional methods have long struggled to effectively solve this issue until the advent of supervised models built on deep neural networks. However, supervised models are constrained by the need for paired data, limiting their practical application. Therefore, we propose a simple and efficient unsupervised method based on the Cycle-GAN framework. Introducing an implicit disentanglement strategy, we aim to separate truncation artifacts from content information. The separated artifact features serve as complementary constraints and the source of generating simulated paired data to enhance the training of the sub-network dedicated to removing truncation artifacts. Additionally, we incorporate polar transformation and an innovative constraint tailored specifically for truncation artifact features, further contributing to the effectiveness of our approach. Experiments conducted on multiple datasets demonstrate that our unsupervised network outperforms the traditional Cycle-GAN model significantly. When compared to state-of-the-art supervised models trained on paired datasets, our model achieves comparable visual results and closely aligns with quantitative evaluation metrics. Full article

South China is dominated by mountainous agriculture and croplands that are at risk of flood disasters, posing a great threat to food security. Synthetic aperture radar (SAR) has the advantage of being all-weather, with the ability to penetrate clouds and monitor cropland inundation information. However, SAR data may be interfered with by noise, i.e., radar shadows and permanent water bodies. Existing cropland data derived from open-access landcover data are not accurate enough to mask out these noises mainly due to insufficient spatial resolution. This study proposed a method that extracted cropland inundation with a high spatial resolution cropland mask. First, the Proportional–Integral–Derivative Network (PIDNet) was applied to the sub-meter-level imagery to identify cropland areas. Then, Sentinel-1 dual-polarized water index (SDWI) and change detection (CD) were used to identify flood area from open water bodies. A case study was conducted in Fujian province, China, which endured several heavy rainfalls in summer 2022. The result of the Intersection over Union (IoU) of the extracted cropland data reached 89.38%, and the F1-score of cropland inundation achieved 82.35%. The proposed method provides support for agricultural disaster assessment and disaster emergency monitoring. Full article

The identification and classification of obstacles in navigable and non-navigable regions, as well as the measurement of distances, are crucial topics of investigation in the field of autonomous navigation for unmanned surface vehicles (USVs). Currently, USVs mostly rely on LiDAR and ultrasound technology for the purpose of detecting impediments that exist on water surfaces. However, it is worth noting that these approaches lack the capability to accurately discern the precise nature or classification of those obstacles. Nevertheless, the limited optical range of unmanned vessels hinders their ability to comprehensively perceive the entirety of the surrounding information. A cooperative USV-UAV system is proposed to ensure the visual perception ability of USVs. The multi-object recognition, semantic segmentation, and obstacle ranging through USV and unmanned aerial vehicle (UAV) perspectives are selected to validate the performance of a cooperative USV-UAV system. The you only look once-X (YOLOX) model, the proportional–integral–derivative-NET (PIDNet) model, and distance measurements based on a monocular camera are utilized to realize these problems. The results indicate that by integrating the viewpoints of USVs and UAVs, a collaborative USV-UAV system, employing the aforementioned methods, can successfully detect and classify different objects surrounding the USV. Additionally, it can differentiate between navigable and non-navigable regions for unmanned vessels through visual recognition, while accurately determining the distance between the USV and obstacles. Full article

Multi-class geospatial object detection in high-resolution remote sensing images has significant potential in various domains such as industrial production, military warning, disaster monitoring, and urban planning. However, the traditional process of remote sensing object detection involves several time-consuming steps, including image acquisition, image download, ground processing, and object detection. These steps may not be suitable for tasks with shorter timeliness requirements, such as military warning and disaster monitoring. Additionally, the transmission of massive data from satellites to the ground is limited by bandwidth, resulting in time delays and redundant information, such as cloud coverage images. To address these challenges and achieve efficient utilization of information, this paper proposes a comprehensive on-board multi-class geospatial object detection scheme. The proposed scheme consists of several steps. Firstly, the satellite imagery is sliced, and the PID-Net (Proportional-Integral-Derivative Network) method is employed to detect and filter out cloud-covered tiles. Subsequently, our Manhattan Intersection over Union (MIOU) loss-based YOLO (You Only Look Once) v7-Tiny method is used to detect remote-sensing objects in the remaining tiles. Finally, the detection results are mapped back to the original image, and the truncated NMS (Non-Maximum Suppression) method is utilized to filter out repeated and noisy boxes. To validate the reliability of the scheme, this paper creates a new dataset called DOTA-CD (Dataset for Object Detection in Aerial Images-Cloud Detection). Experiments were conducted on both ground and on-board equipment using the AIR-CD dataset, DOTA dataset, and DOTA-CD dataset. The results demonstrate the effectiveness of our method. Full article

This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder–decoder architecture. The pixel interval down-sampling operations are concatenated with max-pooling operations to combine the sparse and dense features. This addresses the limitation of contour conglutination of dense objects while counting. The evaluation was conducted using classical segmentation metrics (the Dice, Jaccard and Hausdorff distance) as well as counting metrics. The experimental results show that the proposed PID-Net had the best performance and potential for dense tiny object counting tasks, which achieved 96.97% counting accuracy on the dataset with 2448 yeast cell images. By comparing with the state-of-the-art approaches, such as Attention U-Net, Swin U-Net and Trans U-Net, the proposed PID-Net can segment dense tiny objects with clearer boundaries and fewer incorrect debris, which shows the great potential of PID-Net in the task of accurate counting. Full article