Search Results (1,051)

Camera traps offer enormous new opportunities in ecological studies, but current automated image analysis methods often lack the contextual richness needed to support impactful conservation outcomes. Integrating vision–language models into these workflows could address this gap by providing enhanced contextual understanding and enabling advanced queries across temporal and spatial dimensions. Here, we present an integrated approach that combines deep learning-based vision and language models to improve ecological reporting using data from camera traps. We introduce a two-stage system: YOLOv10-X to localise and classify species (mammals and birds) within images and a Phi-3.5-vision-instruct model to read YOLOv10-X bounding box labels to identify species, overcoming its limitation with hard-to-classify objects in images. Additionally, Phi-3.5 detects broader variables, such as vegetation type and time of day, providing rich ecological and environmental context to YOLO’s species detection output. When combined, this output is processed by the model’s natural language system to answer complex queries, and retrieval-augmented generation (RAG) is employed to enrich responses with external information, like species weight and IUCN status (information that cannot be obtained through direct visual analysis). Combined, this information is used to automatically generate structured reports, providing biodiversity stakeholders with deeper insights into, for example, species abundance, distribution, animal behaviour, and habitat selection. Our approach delivers contextually rich narratives that aid in wildlife management decisions. By providing contextually rich insights, our approach not only reduces manual effort but also supports timely decision making in conservation, potentially shifting efforts from reactive to proactive. Full article

Early identification of concrete cracks and multi-class detection can help to avoid future deformation or collapse in concrete structures. Available traditional detection and methodologies require enormous effort and time. To overcome such difficulties, current vision-based deep learning models can effectively detect and classify various concrete cracks. This study introduces a novel multi-stage deep learning framework for crack detection and type classification. First, the recently developed YOLOV10 model is trained to detect possible defective regions in concrete images. After that, a modified vision transformer (ViT) model is trained to classify concrete images into three main types: normal, simple cracks, and multi-branched cracks. The evaluation process includes feeding concrete test images into the trained YOLOV10 model, identifying the possible defect regions, and finally delivering the detected regions into the trained ViT model, which decides the appropriate crack type of those detected regions. Experiments are conducted using the individual ViT model and the proposed multi-stage framework. To improve the generation ability, multi-source datasets of concrete structures are used. For the classification part, a concrete crack dataset consisting of 12,000 images of three classes is utilized, while for the detection part, a dataset composed of various materials from historical buildings containing 1116 concrete images with their corresponding bounding boxes, is utilized. Results prove that the proposed multi-stage model accurately classifies crack types with 90.67% precision, 90.03% recall, and 90.34% F1-score. The results also show that the proposed model outperforms the individual classification model by 10.9%, 19.99%, and 19.2% for precision, recall, and F1-score, respectively. The proposed multi-stage YOLOV10-ViT model can be integrated into the construction systems which are based on crack materials to obtain early warning of possible future deformation in concrete structures. Full article

This study presents a novel method for automatically analyzing archery shooting time using AI and computer vision technologies, with a particular focus on the critical anchoring to release phase, which directly influences performance. The proposed approach detects the start of the anchoring phase using pose estimation and accurately measures the shooting time by detecting the bowstring within the athlete’s facial bounding box, utilizing Canny edge detection and the probabilistic Hough transform. To ensure stability, low-pass filtering was applied to both the facial bounding box and pose estimation results, and an algorithm was implemented to handle intermittent bowstring detection due to various external factors. The proposed method was validated by comparing its results with expert manual measurements obtained using Dartfish software v2022 achieving a mean absolute error (MAE) of 0.34 s and an $R^2$ score of 0.95. This demonstrates a significant improvement compared to the bowstring-only method, which resulted in an MAE of 1.4 s and an $R^2$ score of 0.89. Previous research has demonstrated a correlation between shooting time and arrow accuracy. Therefore, this method can provide real-time feedback to athletes, overcoming the limitations of traditional manual measurement techniques. It enables immediate technical adjustments during training, which can contribute to overall performance improvement. Full article

Autonomous driving (AD) technology has seen significant advancements in recent years; however, challenges remain, particularly in achieving reliable performance under adverse weather conditions such as heavy fog. In response, we propose a multi-class fog density classification approach to enhance the AD system performance. By categorizing fog density into multiple levels (25%, 50%, 75%, and 100%) and generating separate datasets for each class using the CARLA simulator, we improve the perception accuracy for each specific fog density level and analyze the effects of varying fog intensities. This targeted approach offers benefits such as improved object detection, specialized training for each fog class, and increased generalizability. Our results demonstrate enhanced perception of various objects, including cars, buses, trucks, vans, pedestrians, and traffic lights, across all fog densities. This multi-class fog density method is a promising advancement toward achieving reliable AD performance in challenging weather, improving both the precision and recall of object detection algorithms under diverse fog conditions. Full article

The problem is that existing aircraft detection datasets rarely simultaneously consider the diversity of target features and the complexity of environmental factors, which has become an important factor restricting the effectiveness and reliability of aircraft detection algorithms. Although a large amount of research has been devoted to breaking through few-sample-driven aircraft detection technology, most algorithms still struggle to effectively solve the problems of missed target detection and false alarms caused by numerous environmental interferences in bird-eye optical remote sensing scenes. To further aircraft detection research, we have established a new dataset, Aircraft Detection in Complex Optical Scene (ADCOS), sourced from various platforms including Google Earth, Microsoft Map, Worldview-3, Pleiades, Ikonos, Orbview-3, and Jilin-1 satellites. It integrates 3903 meticulously chosen images of over 400 famous airports worldwide, containing 33,831 annotated instances employing the oriented bounding box (OBB) format. Notably, this dataset encompasses a wide range of various targets characteristics including multi-scale, multi-direction, multi-type, multi-state, and dense arrangement, along with complex relationships between targets and backgrounds like cluttered backgrounds, low contrast, shadows, and occlusion interference conditions. Furthermore, we evaluated nine representative detection algorithms on the ADCOS dataset, establishing a performance benchmark for subsequent algorithm optimization. The latest dataset will soon be available on the Github website. Full article

Vending machines have evolved into a critical element of the intelligent healthcare service system. To enhance the precision of pill box detection counting and cater to the lightweight requirements of its internal embedded controller for deep learning frameworks, an enhanced lightweight YOLOv8n model is introduced. A dataset comprising 4080 images is initially compiled for model training and assessment purposes. The refined YOLOv8n-ShuffleNetV2 model is crafted, featuring the integration of ShuffleNetv2 as the new backbone network, the incorporation of the VoVGSCSP module to bolster feature extraction capabilities, and the utilization of the Wise-IoU v3 loss function for bounding box regression enhancement. Moreover, a model pruning strategy based on structured pruning (SFP) and layer-wise adaptive magnitude pruning (LAMP) is implemented. Comparative experimental findings demonstrate that the enhanced and pruned model has elevated the mean Average Precision (mAP) rate from 94.5% to 95.1%. Furthermore, the model size has been reduced from 11.1 MB to 6.0 MB, and the inference time has been notably decreased from 1.97 s to 0.34 s. The model’s accuracy and efficacy are validated through experiments conducted on the Raspberry Pi 4B platform. The outcomes of the experiments underscore how the refined model significantly amplifies the deployment efficiency of the deep learning model on resource-limited devices, thus greatly supporting the advancement of intelligent medicine management and medical vending machine applications. Full article

This study proposes an autonomous recognition and approach method for unmanned aerial vehicles (UAVs) targeting linear splicing sleeves. By integrating deep learning and active stereo vision, this method addresses the navigation challenges faced by UAVs during the identification, localization, and docking of splicing sleeves on overhead power transmission lines. First, a two-stage localization strategy, LC (Local Clustering)-RB (Reparameterization Block)-YOLO (You Only Look Once)v8n (OBB (Oriented Bounding Box)), is developed for linear target splicing sleeves. This strategy ensures rapid, accurate, and reliable recognition and localization while generating precise waypoints for UAV docking with splicing sleeves. Next, virtual reality technology is utilized to expand the splicing sleeve dataset, creating the D_SS dataset tailored to diverse scenarios. This enhancement improves the robustness and generalization capability of the recognition model. Finally, a UAV approach splicing sleeve (UAV-ASS) visual navigation simulation platform is developed using the Robot Operating System (ROS), the PX4 open-source flight control system, and the GAZEBO 3D robotics simulator. This platform simulates the UAV’s final approach to the splicing sleeves. Experimental results demonstrate that, on the D_SS dataset, the RB-YOLOv8n(OBB) model achieves a mean average precision (mAP0.5) of 96.4%, with an image inference speed of 86.41 frames per second. By incorporating the LC-based fine localization method, the five rotational bounding box parameters (x, y, w, h, and angle) of the splicing sleeve achieve a mean relative error (MRE) ranging from 3.39% to 4.21%. Additionally, the correlation coefficients (ρ) with manually annotated positions improve to 0.99, 0.99, 0.98, 0.95, and 0.98, respectively. These improvements significantly enhance the accuracy and stability of splicing sleeve localization. Moreover, the developed UAV-ASS visual navigation simulation platform effectively validates high-risk algorithms for UAV autonomous recognition and docking with splicing sleeves on power transmission lines, reducing testing costs and associated safety risks. Full article

Agricultural loss due to the overpopulation of Sika deer poses a significant challenge in Japan, leading to frequent human–wildlife conflicts. We conducted a study in Muroran, Hokkaido (42°22′56.1″ N–141°01′51.5″ E), with the objective of monitoring Sika deer and notifying farmers and locals. We deployed a Sika deer detection model (YOLOv8-nano) on a Raspberry Pi, integrated with an infrared camera that captured images only when a PIR sensor was triggered. To further understand the timing of Sika deer visits and potential correlations with environmental temperature and humidity, respective sensors were installed on Raspberry Pi and the data were analyzed using an ANOVA test. In addition, a buzzer was deployed to deter Sika deer from the study area. The buzzer was deactivated in the first 10 days after deployment and was activated in the following 20 days. The Sika deer detection model demonstrated excellent performance, with precision and recall values approaching 1, and a bounding box creation latency of 0.82 frames per second. Once a bounding box was established after Sika deer detection, alert notifications were automatically sent via email and the LINE messaging application, with an average notification time of 0.32 s. Regarding the buzzer’s impact on Sika deer, 35% of the detected individuals reacted by standing upright with alert ears, while 65% immediately fled the area. Analysis revealed that the time of day for Sika deer visits was significantly correlated with humidity (F = 8.95, p < 0.05), but no significant association with temperature (F = 0.681, p > 0.05). These findings represent a significant step toward mitigating human–wildlife conflicts and reducing agricultural production losses through effective conservation measures. Full article

Three-dimensional object detection has been a key area of research in recent years because of its rich spatial information and superior performance in addressing occlusion issues. However, the performance of 3D object detection still lags significantly behind that of 2D object detection, owing to challenges such as difficulties in feature extraction and a lack of texture information. To address this issue, this study proposes a 3D object detection network, CaLiJD (Camera and Lidar Joint Contender for 3D object Detection), guided by two-dimensional detection results. CaLiJD creatively integrates advanced channel attention mechanisms with a novel bounding-box filtering method to improve detection accuracy, especially for small and occluded objects. Bounding boxes are detected by the 2D and 3D networks for the same object in the same scene as an associated pair. The detection results that satisfy the criteria are then fed into the fusion layer for training. In this study, a novel fusion network is proposed. It consists of numerous convolutions arranged in both sequential and parallel forms and includes a Grouped Channel Attention Module for extracting interactions among multi-channel information. Moreover, a novel bounding-box filtering mechanism was introduced, incorporating the normalized distance from the object to the radar as a filtering criterion within the process. Experiments were conducted using the KITTI 3D object detection benchmark. The results showed that a substantial improvement in mean Average Precision (mAP) was achieved by CaLiJD compared with the baseline single-modal 3D detection model, with an enhancement of 7.54%. Moreover, the improvement achieved by our method surpasses that of other classical fusion networks by an additional 0.82%. In particular, CaLiJD achieved mAP values of 73.04% and 59.86%, respectively, thus demonstrating state-of-the-art performance for challenging small-object detection tasks such as those involving cyclists and pedestrians. Full article

Background: Given the severe economic burden that citrus greening disease imposes on fruit farmers and related industries, rapid and accurate disease detection is particularly crucial. This not only effectively curbs the spread of the disease, but also significantly reduces reliance on manual detection within extensive citrus planting areas. Objective: In response to this challenge, and to address the issues posed by resource-constrained platforms and complex backgrounds, this paper designs and proposes a novel method for the recognition and localization of citrus greening disease, named the HHS-RT-DETR model. The goal of this model is to achieve precise detection and localization of the disease while maintaining efficiency. Methods: Based on the RT-DETR-r18 model, the following improvements are made: the HS-FPN (high-level screening-feature pyramid network) is used to improve the feature fusion and feature selection part of the RT-DETR model, and the filtered feature information is merged with the high-level features by filtering out the low-level features, so as to enhance the feature selection ability and multi-level feature fusion ability of the model. In the feature fusion and feature selection sections, the HWD (hybrid wavelet-directional filter banks) downsampling operator is introduced to prevent the loss of effective information in the channel and reduce the computational complexity of the model. Through using the ShapeIoU loss function to enable the model to focus on the shape and scale of the bounding box itself, the prediction of the bounding box of the model will be more accurate. Conclusions and Results: This study has successfully developed an improved HHS-RT-DETR model which exhibits efficiency and accuracy on resource-constrained platforms and offers significant advantages for the automatic detection of citrus greening disease. Experimental results show that the improved model, when compared to the RT-DETR-r18 baseline model, has achieved significant improvements in several key performance metrics: the precision increased by 7.9%, the frame rate increased by 4 frames per second (f/s), the recall rose by 9.9%, and the average accuracy also increased by 7.5%, while the number of model parameters reduced by ${0.137\times 10}^7$. Moreover, the improved model has demonstrated outstanding robustness in detecting occluded leaves within complex backgrounds. This provides strong technical support for the early detection and timely control of citrus greening disease. Additionally, the improved model has showcased advanced detection capabilities on the PASCAL VOC dataset. Discussions: Future research plans include expanding the dataset to encompass a broader range of citrus species and different stages of citrus greening disease. In addition, the plans involve incorporating leaf images under various lighting conditions and different weather scenarios to enhance the model’s generalization capabilities, ensuring the accurate localization and identification of citrus greening disease in diverse complex environments. Lastly, the integration of the improved model into an unmanned aerial vehicle (UAV) system is envisioned to enable the real-time, regional-level precise localization of citrus greening disease. Full article

In recent years, marine structures have been widely used in the world, making significant contributions to the utilization of marine resources. In the design of marine structures, there is a hybrid reliability problem arising from aleatory uncertainty and epistemic uncertainty. In many cases, epistemic uncertainty is estimated by interval parameters. Traditional methods for hybrid reliability analysis usually require a nested optimization framework, which will lead to too many calls to the limit state function (LSF) and result in poor computational efficiency. In response to this problem, this paper proposes a de-nesting hybrid reliability analysis method creatively. Firstly, it uses the p-box model to describe the epistemic uncertainty variables, and then the linear approximation (LA) model and the two-point adaptive nonlinear approximation (TANA) model are combined to approximate the upper and lower bounds of LSF with epistemic uncertainty. Based on the first-order reliability method (FORM), an iterative operation is used to obtain the interval of the non-probability hybrid reliability index. The traditional nested optimization structure is effectively eliminated by the above approximation method, which efficiently reduces the times of LSF calls and increases the calculation speed while preserving sufficient accuracy. Finally, one numerical example and two engineering examples are provided to show the greater effectiveness of this method than the traditional nested optimization method. Full article

Offshore mariculture is critical for global food security and economic development. Advances in deep learning and data-driven approaches, enable the rapid and effective monitoring of offshore mariculture distribution and changes. However, detector performance depends heavily on training data quality. The lack of standardized classifications and public datasets for offshore mariculture facilities currently hampers effective monitoring. Here, we propose to categorize offshore mariculture facilities into six types: TCC, DWCC, FRC, LC, RC, and BC. Based on these categories, we introduce a benchmark dataset called OMAD-6. This dataset includes over 130,000 instances and more than 16,000 high-resolution remote sensing images. The images with a spatial resolution of 0.6 m were sourced from key regions in China, Chile, Norway, and Egypt, from the Google Earth platform. All instances in OMAD-6 were meticulously annotated manually with horizontal bounding boxes and polygons. Compared to existing remote sensing datasets, OMAD-6 has three notable characteristics: (1) it is comparable to large, published datasets in instances per category, image quantity, and sample coverage; (2) it exhibits high inter-class similarity; (3) it shows significant intra-class diversity in facility sizes and arrangements. Based on the OMAD-6 dataset, we evaluated eight state-of-the-art methods to establish baselines for future research. The experimental results demonstrate that the OMAD-6 dataset effectively represents various real-world scenarios, which have posed considerable challenges for current instance segmentation algorithms. Our evaluation confirms that the OMAD-6 dataset has the potential to improve offshore mariculture identification. Notably, the QueryInst and PointRend algorithms have distinguished themselves as top performers on the OMAD-6 dataset, robustly identifying offshore mariculture facilities even with complex environmental backgrounds. Its ongoing development and application will play a pivotal role in future offshore mariculture identification and management. Full article

In traffic scenes, pedestrian target detection faces significant issues of misdetection and omission due to factors such as crowd density and obstacle occlusion. To address these challenges and enhance detection accuracy, we propose an improved CCW-YOLO algorithm. The algorithm first introduces a lightweight convolutional layer using GhostConv and incorporates an enhanced C2f module to improve the network’s detection performance. Additionally, it integrates the Coordinate Attention module to better capture key points of the targets. Next, the bounding box loss function CIoU loss at the output of YOLOv5 is replaced with WiseIoU loss to enhance adaptability to various detection scenarios, thereby further improving accuracy. Finally, we develop a pedestrian count detection system using PyQt5 to enhance human–computer interaction. Experimental results on the INRIA public dataset showed that our algorithm achieved a detection accuracy of 98.4%, representing a 10.1% improvement over the original YOLOv5s algorithm. This advancement significantly enhances the detection of small objects in images and effectively addresses misdetection and omission issues in complex environments. These findings have important practical implications for ensuring traffic safety and optimizing traffic flow. Full article

AI-based breast cancer detection can improve the sensitivity and specificity of detection, especially for small lesions, which has clinical value in realizing early detection and treatment so as to reduce mortality. The two-stage detection network performs well; however, it adopts an imprecise ROI during classification, which can easily include surrounding tumor tissues. Additionally, fuzzy noise is a significant contributor to false positives. We adopted Faster RCNN as the architecture, introduced ROI aligning to minimize quantization errors and feature pyramid network (FPN) to extract different resolution features, added a bounding box quadratic regression feature map extraction network and three convolutional layers to reduce interference from tumor surrounding information, and extracted more accurate and deeper feature maps. Our approach outperformed Faster R-CNN, Mask R-CNN, and YOLOv9 in breast cancer detection across 485 internal cases. We achieved superior performance in mAP, sensitivity, and false positive rate ((0.752, 0.950, 0.133) vs. (0.711, 0.950, 0.200) vs. (0.718, 0.880, 0.120) vs. (0.658, 0.680, 405)), which represents a 38.5% reduction in false positives compared to manual detection. Additionally, in a public dataset of 220 cases, our model also demonstrated the best performance. It showed improved sensitivity and specificity, effectively assisting doctors in diagnosing cancer. Full article

Facial analysis is an important area of research in computer vision and machine learning, with applications spanning security, healthcare, and user interaction systems. The data-centric AI approach emphasizes the importance of high-quality, diverse, and well-annotated datasets in driving advancements in this field. However, current facial datasets, such as Flickr-Faces-HQ (FFHQ), lack detailed annotations for detecting facial accessories, particularly eyeglasses. This work addresses this limitation by extending the FFHQ dataset with precise bounding box annotations for eyeglasses detection, enhancing its utility for data-centric AI applications. The extended dataset comprises 70,000 images, including over 16,000 images containing eyewear, and it exceeds the CelebAMask-HQ dataset in size and diversity. A semi-automated protocol was employed to efficiently generate accurate bounding box annotations, minimizing the demand for extensive manual labeling. This enriched dataset serves as a valuable resource for training and benchmarking eyewear detection models. Additionally, the baseline benchmark results for eyeglasses detection were presented using deep learning methods, including YOLOv8 and MobileNetV3. The evaluation, conducted through cross-dataset validation, demonstrated the robustness of models trained on the extended FFHQ dataset with their superior performances over existing alternative CelebAMask-HQ. The extended dataset, which has been made publicly available, is expected to support future research and development in eyewear detection, contributing to advancements in facial analysis and related fields. Full article