Search Results (7)

Occlusion-aware vehicle detection in UAV imagery is challenging due to partial visibility from varied viewpoints, dense scenes, and limited features. To address this, we introduce two contributions. First, VOD-UAV, the first UAV-based vehicle detection dataset focused on occlusion, containing 712 synthetic and 1219 real-world images, each annotated with five discrete occlusion levels. These fine-grained labels enable structured supervision and detailed analysis under varying visibility conditions. Second, DOMino-YOLO, a YOLOv11-based detection framework, enhances occlusion robustness via three components: the Deformable Convolution Enhanced Module (DCEM) for spatial alignment, the Visibility-Aware Structural Aggregation (VASA) module for multi-scale feature extraction from partially visible regions, and the Context-Suppressed Implicit Modulation Head (CSIM-Head) for reducing false activations by adaptive channel reweighting. An Occlusion-Aware Repulsion Loss (OAR-Loss) combines Repulsion Loss and Visibility-Weighted Classification Loss to suppress redundant predictions and emphasize heavily occluded objects. Extensive experiments on VOD-UAV demonstrate that DOMino-YOLO significantly improves detection accuracy and robustness under occlusion. The dataset and code will publicly available to support future research. Full article

Robust visual perception and geometric alignment are crucial for intelligent automation in various domains, such as industrial processes and infrastructure monitoring. Accurately aligning structured visual elements, such as floor markings or road-marking templates, is essential for tasks like automated guidance, verification, and condition assessment. However, traditional feature-based methods struggle with templates that feature simple geometries and lack rich textures, making reliable feature matching and alignment difficult, even under controlled conditions. To address this, we propose GeoTemplateKPNet, a novel self-supervised deep-learning framework, built upon Convolutional Neural Networks (CNNs), designed to learn robust, geometrically consistent keypoints specifically in synthetic template images. The model is trained exclusively in a synthetic template dataset by enforcing equivariance to geometric transformations and utilizing self-supervised losses, including inside mask loss, peakiness loss, repulsion loss, and keypoint-driven image reprojection loss, thereby eliminating the need for manual keypoint annotations. We evaluate the method in a synthetic template test set, using metrics such as a keypoint-matching comparison, the Inside Mask Rate (IMR), and the Alignment Reconstruction Error (ARE). The results demonstrate that GeoTemplateKPNet successfully learns to predict meaningful keypoints on template structures, enabling accurate alignment between templates and their transformed counterparts. Ablation studies reveal that the number of keypoints (K) impacts the performance, with K = 3 providing the most suitable balance for the overall alignment accuracy, although the performance varies across different template geometries. GeoTemplateKPNet offers a foundational self-supervised solution for the robust geometric analysis of templates, which is crucial for downstream alignment tasks and applications. Full article

Multiview Clustering (MVC) plays a crucial role in the holistic analysis of complex data by leveraging complementary information from multiple perspectives, a necessity in the era of big data. Non-negative Matrix Factorization (NMF)-based methods have demonstrated their effectiveness and broad applicability in clustering tasks, as they generate meaningful attribute distributions and cluster assignments. However, existing shallow NMF approaches fail to capture the hierarchical structures inherent in real-world data, while deep NMF ones overlook the accumulation of reconstruction errors across layers by solely focusing on a global loss function. To address these limitations, this study aims to develop a novel method that integrates an autoencoder-inspired structure into the deep NMF framework, incorporating layerwise error-correcting constraints. This approach can facilitate the extraction of hierarchical features while effectively mitigating reconstruction error accumulation in deep architectures. Additionally, repulsion-attraction manifold learning is incorporated at each layer to preserve intrinsic geometric structures within the data. The proposed model is evaluated on five real-world multiview datasets, with experimental results demonstrating its effectiveness in capturing hierarchical representations and improving clustering performance. Full article

Counting the soybean pods automatically has been one of the key ways to realize intelligent soybean breeding in modern smart agriculture. However, the pod counting accuracy for whole soybean plants is still limited due to the crowding and uneven distribution of pods. In this paper, based on the VFNet detector, we propose a deformable attention recursive feature pyramid network for soybean pod counting (DARFP-SD), which aims to identify the number of soybean pods accurately. Specifically, to improve the feature quality, DARFP-SD first introduces the deformable convolutional networks (DCN) and attention recursive feature pyramid (ARFP) to reduce noise interference during feature learning. DARFP-SD further combines the Repulsion Loss to correct the error of predicted bboxse coming from the mutual interference between dense pods. DARFP-SD also designs a density prediction branch in the post-processing stage, which learns an adaptive soft distance IoU to assign suitable NMS threshold for different counting scenes with uneven soybean pod distributions. The model is trained on a dense soybean dataset with more than 5300 pods from three different shapes and two classes, which consists of a training set of 138 images, a validation set of 46 images and a test set of 46 images. Extensive experiments have verified the performance of proposed DARFP-SD. The final training loss is 1.281, and an average accuracy of 90.35%, an average recall of 85.59% and a F1 score of 87.90% can be achieved, outperforming the baseline method VFNet by 8.36%, 4.55% and 7.81%, respectively. We also validate the application effect for different numbers of soybean pods and differnt shapes of soybean. All the results show the effectiveness of the DARFP-SD, which can provide a new insight into the soybean pod counting task. Full article

The existing pedestrian detection algorithms cannot effectively extract features of heavily occluded targets which results in lower detection accuracy. To solve the heavy occlusion in crowds, we propose a multi-scale feature pyramid network based on ResNet (MFPN) to enhance the features of occluded targets and improve the detection accuracy. MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM). We propose the double FPN which improves the architecture to further enhance the semantic information and contours of occluded pedestrians, and provide a new way for feature extraction of occluded targets. The features extracted by our network can be more separated and clearer, especially those heavily occluded pedestrians. Repulsion loss is introduced to improve the loss function which can keep predicted boxes away from the ground truths of the unrelated targets. Experiments carried out on the public CrowdHuman dataset, we obtain 90.96% AP which yields the best performance, 5.16% AP gains compared to the FPN-ResNet50 baseline. Compared with the state-of-the-art works, the performance of the pedestrian detection system has been boosted with our method. Full article

We synthesized manganese ferrite (MnFe₂O₄) nanoparticles of different sizes by varying pH during chemical co-precipitation procedure and modified their surfaces with polysaccharide chitosan (CS) to investigate characteristics of hyperthermia and magnetic resonance imaging (MRI). Structural features were analyzed by X-ray diffraction (XRD), high-resolution transmission electron microscopy (TEM), selected area diffraction (SAED) patterns, and Mössbauer spectroscopy to confirm the formation of superparamagnetic MnFe₂O₄ nanoparticles with a size range of 5–15 nm for pH of 9–12. The hydrodynamic sizes of nanoparticles were less than 250 nm with a polydispersity index of 0.3, whereas the zeta potentials were higher than 30 mV to ensure electrostatic repulsion for stable colloidal suspension. MRI properties at 7T demonstrated that transverse relaxation (T₂) doubled as the size of CS-coated MnFe₂O₄ nanoparticles tripled in vitro. However, longitudinal relaxation (T₁) was strongest for the smallest CS-coated MnFe₂O₄ nanoparticles, as revealed by in vivo positive contrast MRI angiography. Cytotoxicity assay on HeLa cells showed CS-coated MnFe₂O₄ nanoparticles is viable regardless of ambient pH, whereas hyperthermia studies revealed that both the maximum temperature and specific loss power obtained by alternating magnetic field exposure depended on nanoparticle size and concentration. Overall, these results reveal the exciting potential of CS-coated MnFe₂O₄ nanoparticles in MRI and hyperthermia studies for biomedical research. Full article

In recent years, there has been a growing interest in the problem of multi-label streaming feature selection with no prior knowledge of the feature space. However, the algorithms proposed to handle this problem seldom consider the group structure of streaming features. Another shortcoming arises from the fact that few studies have addressed atomic feature models, and particularly, few have measured the attraction and repulsion between features. To remedy these shortcomings, we develop the streaming feature selection algorithm with dynamic sliding windows and feature repulsion loss (SF-DSW-FRL). This algorithm is essentially carried out in three consecutive steps. Firstly, within dynamic sliding windows, candidate streaming features that are strongly related to the labels in different feature groups are selected and stored in a fixed sliding window. Then, the interaction between features is measured by a loss function inspired by the mutual repulsion and attraction between atoms in physics. Specifically, one feature attraction term and two feature repulsion terms are constructed and combined to create the feature repulsion loss function. Finally, for the fixed sliding window, the best feature subset is selected according to this loss function. The effectiveness of the proposed algorithm is demonstrated through experiments on several multi-label datasets, statistical hypothesis testing, and stability analysis. Full article