Explore the vast range of titles available.

Performing low-latency, high-precision object detection on unmanned aerial vehicles (UAVs) equipped with vision sensors holds significant importance. However, the current limitations of embedded UAV devices present challenges in balancing accuracy and speed, particularly in the analysis of high-precision remote sensing images. This challenge is particularly pronounced in scenarios involving numerous small objects, intricate backgrounds, and occluded overlaps. To address these issues, we introduce the Drone-DETR model, which is based on RT-DETR. To overcome the difficulties associated with detecting small objects and reducing redundant computations arising from complex backgrounds in ultra-wide-angle images, we propose the Effective Small Object Detection Network (ESDNet). This network preserves detailed information about small objects, reduces redundant computations, and adopts a lightweight architecture. Furthermore, we introduce the Enhanced Dual-Path Feature Fusion Attention Module (EDF-FAM) within the neck network. This module is specifically designed to enhance the network’s ability to handle multi-scale objects. We employ a dynamic competitive learning strategy to enhance the model’s capability to efficiently fuse multi-scale features. Additionally, we incorporate the P2 shallow feature layer from the ESDNet into the neck network to enhance the model’s ability to fuse small-object features, thereby enhancing the accuracy of small object detection. Experimental results indicate that the Drone-DETR model achieves an mAP50 of 53.9% with only 28.7 million parameters on the VisDrone2019 dataset, representing an 8.1% enhancement over RT-DETR-R18.

Human pose estimation has long been a fundamental problem in computer vision and artificial intelligence. Prominent among the 2D human pose estimation (HPE) methods are the regression-based approaches, which have been proven to achieve excellent results. However, the ground-truth labels are usually inherently ambiguous in challenging cases such as motion blur, occlusions, and truncation, leading to poor performance measurement and lower levels of accuracy. In this paper, we propose Cofopose, which is a two-stage approach consisting of a person and keypoint detection transformers for 2D human pose estimation. Cofopose is composed of conditional cross-attention, a conditional DEtection TRansformer (conditional DETR), and an encoder-decoder in the transformer framework; this allows it to achieve person and keypoint detection. In a significant departure from other approaches, we use conditional cross-attention and fine-tune conditional DETR for our person detection, and encoder-decoders in the transformers for our keypoint detection. Cofopose was extensively evaluated using two benchmark datasets, MS COCO and MPII, achieving an improved performance with significant margins over the existing state-of-the-art frameworks.

For the problem of low detection accuracy of every type of defect on the surface of steel, proposes an algorithm based on the improvement of RT-DETR on the surface of steel. To solve the defect feature extraction difficulties, the P6 feature fusion layer is added and introduced into the feature fusion stage, which effectively expands the sensory field area in the defect image, and fuse defective features more effectively in the feature fusion stage. To address the problem of lack of effective interaction between features at various scales, the CAT module is creatively introduced in the neck, and the multihead cross-attention mechanism in the CAT module is used to perform cross-scale feature interactions on the feature maps extracted at different layers to optimize the feature representation capability. The PPN replace the CCFM structure to selectively aggregate boundary features and semantic information. To verify the effect of the improved RT-DETR, the NEU-DET dataset and the GC10-DET dataset are selected. The experimental results show that the mean average accuracy of the algorithm proposed in this paper on the two datasets is improved by 2.5% and 4.5% over the original RT-DETR algorithm to 85.7% and 76.0%, respectively, which verifies the improved algorithm is feasible.

Fire is a significant security threat that can lead to casualties, property damage, and environmental damage. Despite the availability of object-detection algorithms, challenges persist in detecting fires, smoke, and humans. These challenges include poor performance in detecting small fires and smoke, as well as a high computational cost, which limits deployments. In this paper, we propose an end-to-end object detector for fire, smoke, and human detection based on Deformable DETR (DEtection TRansformer) called FSH-DETR. To effectively process multi-scale fire and smoke features, we propose a novel Mixed Encoder, which integrates SSFI (Separate Single-scale Feature Interaction Module) and CCFM (CNN-based Cross-scale Feature Fusion Module) for multi-scale fire, smoke, and human feature fusion. Furthermore, we enhance the convergence speed of FSH-DETR by incorporating a bounding box loss function called PIoUv2 (Powerful Intersection of Union), which improves the precision of fire, smoke, and human detection. Extensive experiments on the public dataset demonstrate that the proposed method surpasses state-of-the-art methods in terms of the mAP (mean Average Precision), with mAP and mAP50 reaching 66.7% and 84.2%, respectively.

Detecting bearing defects accurately and efficiently is critical for industrial safety and efficiency. This paper introduces Bearing-DETR, a deep learning model optimised using the Real-Time Detection Transformer (RT-DETR) architecture. Enhanced with Dysample Dynamic Upsampling, Efficient Model Optimization (EMO) with Meta-Mobile Blocks (MMB), and Deformable Large Kernel Attention (D-LKA), Bearing-DETR offers significant improvements in defect detection while maintaining a lightweight framework suitable for low-resource devices. Validated on a dataset from a chemical plant, Bearing-DETR outperformed the standard RT-DETR, achieving a mean average precision (mAP) of 94.3% at IoU = 0.5 and 57.5% at IoU = 0.5–0.95. It also reduced floating-point operations (FLOPs) to 8.2 G and parameters to 3.2 M, underscoring its enhanced efficiency and reduced computational demands. These results demonstrate the potential of Bearing-DETR to transform maintenance strategies and quality control across manufacturing environments, emphasising adaptability and impact on sustainability and operational costs.

Tomatoes, widely cherished for their high nutritional value, necessitate precise ripeness identification and selective harvesting of mature fruits to significantly enhance the efficiency and economic benefits of tomato harvesting management. Previous studies on intelligent harvesting often focused solely on identifying tomatoes as the target, lacking fine-grained detection of tomato ripeness. This deficiency leads to the inadvertent harvesting of immature and rotten fruits, resulting in economic losses. Moreover, in natural settings, uneven illumination, occlusion by leaves, and fruit overlap hinder the precise assessment of tomato ripeness by robotic systems. Simultaneously, the demand for high accuracy and rapid response in tomato ripeness detection is compounded by the need for making the model lightweight to mitigate hardware costs. This study proposes a lightweight model named PDSI-RTDETR to address these challenges. Initially, the PConv_Block module, integrating partial convolution with residual blocks, replaces the Basic_Block structure in the legacy backbone to alleviate computing load and enhance feature extraction efficiency. Subsequently, a deformable attention module is amalgamated with intra-scale feature interaction structure, bolstering the capability to extract detailed features for fine-grained classification. Additionally, the proposed slimneck-SSFF feature fusion structure, merging the Scale Sequence Feature Fusion framework with a slim-neck design utilizing GSConv and VoVGSCSP modules, aims to reduce volume of computation and inference latency. Lastly, by amalgamating Inner-IoU with EIoU to formulate Inner-EIoU, replacing the original GIoU to expedite convergence while utilizing auxiliary frames enhances small object detection capabilities. Comprehensive assessments validate that the PDSI-RTDETR model achieves an average precision mAP50 of 86.8%, marking a 3.9% enhancement over the original RT-DETR model, and a 38.7% increase in FPS. Furthermore, the GFLOPs of PDSI-RTDETR have been diminished by 17.6%. Surpassing the baseline RT-DETR and other prevalent methods regarding precision and speed, it unveils its considerable potential for detecting tomato ripeness. When applied to intelligent harvesting robots in the future, this approach can improve the quality of tomato harvesting by reducing the collection of immature and spoiled fruits.

For drone-based detection tasks, accurately identifying small-scale targets like people, bicycles, and pedestrians remains a key challenge. In this paper, we propose DV-DETR, an improved detection model based on the Real-Time Detection Transformer (RT-DETR), specifically optimized for small target detection in high-density scenes. To achieve this, we introduce three main enhancements: (1) ResNet18 as the backbone network to improve feature extraction and reduce model complexity; (2) the integration of recalibration attention units and deformable attention mechanisms in the neck network to enhance multi-scale feature fusion and improve localization accuracy; and (3) the use of the Focaler-IoU loss function to better handle the imbalanced distribution of target scales and focus on challenging samples. Experimental results on the VisDrone2019 dataset show that DV-DETR achieves an mAP@0.5 of 50.1%, a 1.7% improvement over the baseline model, while increasing detection speed from 75 FPS to 90 FPS, meeting real-time processing requirements. These improvements not only enhance the model’s accuracy and efficiency but also provide practical significance in complex, high-density urban environments, supporting real-world applications in UAV-based surveillance and monitoring tasks.

In foggy weather, outdoor safety helmet detection often suffers from low visibility and unclear objects, hindering optimal detector performance. Moreover, safety helmets typically appear as small objects at construction sites, prone to occlusion and difficult to distinguish from complex backgrounds, further exacerbating the detection challenge. Therefore, the real-time and precise detection of safety helmet usage among construction personnel, particularly in adverse weather conditions such as foggy weather, poses a significant challenge. To address this issue, this paper proposes the DST-DETR, a framework for foggy weather safety helmet detection. The DST-DETR framework comprises a dehazing module, PAOD-Net, and an object detection module, ST-DETR, for joint dehazing and detection. Initially, foggy images are restored within PAOD-Net, enhancing the AOD-Net model by introducing a novel convolutional module, PfConv, guided by the parameter-free average attention module (PfAAM). This module enables more focused attention on crucial features in lightweight models, therefore enhancing performance. Subsequently, the MS-SSIM + ℓ2 loss function is employed to bolster the model’s robustness, making it adaptable to scenes with intricate backgrounds and variable fog densities. Next, within the object detection module, the ST-DETR model is designed to address small objects. By refining the RT-DETR model, its capability to detect small objects in low-quality images is enhanced. The core of this approach lies in utilizing the variant ResNet-18 as the backbone to make the network lightweight without sacrificing accuracy, followed by effectively integrating the small-object layer into the improved BiFPN neck structure, resulting in CCFF-BiFPN-P2. Various experiments were conducted to qualitatively and quantitatively compare our method with several state-of-the-art approaches, demonstrating its superiority. The results validate that the DST-DETR algorithm is better suited for foggy safety helmet detection tasks in construction scenarios.

To address the inefficiencies and inaccuracies of traditional ore grade identification methods in complex mining environments, and the challenge of balancing accuracy and speed on edge devices, this paper proposes a lightweight, high-precision, and high-speed detection model named GOG-RT-DETR. Built on the RT-DETR framework, the model incorporates a Faster-Rep-EMA module in the backbone network to reduce computational redundancy and enhance feature extraction. Additionally, a BiFPN-GLSA module replaces the CCFM module in the Neck network, improving feature fusion between the backbone and Neck networks, thus strengthening the model’s ability to capture both global and local spatial features. A Wise-Inner-Shape-IoU loss function is introduced to optimize the bounding box regression, accelerating convergence and improving localization accuracy. The model is evaluated on a custom-built graphite ore dataset with simulated data augmentation. Experimental results show that, compared to the baseline model, the mAP and FPS of GOG-RT-DETR are improved by 2.5% and 8.2%, with a 26.0% reduction in model parameters and a 23.37% reduction in FLOPs. This model enhances detection accuracy and reduces computational complexity, offering an efficient solution for ore grade detection in industrial applications.

To mitigate the technical challenges associated with small-object detection, feature degradation, and spatial-contextual misalignment in UAV-acquired imagery, this paper proposes UAV-DETR, an enhanced Transformer-based object detection model designed for aerial scenarios. Specifically, UAV imagery often suffers from feature degradation due to low resolution and complex backgrounds and from semantic-spatial misalignment caused by dynamic shooting conditions. This work addresses these challenges by enhancing feature perception, semantic representation, and spatial alignment. Architecturally extending the RT-DETR framework, UAV-DETR incorporates three novel modules: the Channel-Aware Sensing Module (CAS), the Scale-Optimized Enhancement Pyramid Module (SOEP), and the newly designed Context-Spatial Alignment Module (CSAM), which integrates the functionalities of contextual and spatial calibration. These components collaboratively strengthen multi-scale feature extraction, semantic representation, and spatial-contextual alignment. The CAS module refines the backbone to improve multi-scale feature perception, while SOEP enhances semantic richness in shallow layers through lightweight channel-weighted fusion. CSAM further optimizes the hybrid encoder by simultaneously correcting contextual inconsistencies and spatial misalignments during feature fusion, enabling more precise cross-scale integration. Comprehensive comparisons with mainstream detectors, including Faster R-CNN and YOLOv5, demonstrate that UAV-DETR achieves superior small-object detection performance in complex aerial scenarios. The performance is thoroughly evaluated in terms of mAP@0.5, parameter count, and computational complexity (GFLOPs). Experiments on the VisDrone2019 dataset benchmark demonstrate that UAV-DETR achieves an mAP@0.5 of 51.6%, surpassing RT-DETR by 3.5% while reducing the number of model parameters from 19.8 million to 16.8 million.