TIG-DETR: Enhancing Texture Preservation and Information Interaction for Target Detection

Timely fault diagnosis and localization of transmission lines is crucial for ensuring the reliable operation of increasingly complex power systems. This study proposes an optimized R-Net algorithm based on a feature pyramid network (FPN) and densely connected convolutional network (D-Net) for transmission line fault diagnosis and localization. The R-Net network is enhanced by reshaping the anchor points using an improved K-means algorithm and incorporating an FPN for multi-scale feature extraction. The backbone network is further optimized using D-Net to strengthen inter-layer connections and improve feature reuse. Experimental results demonstrate that the optimized R-Net achieves an overall average accuracy of 0.64, outperforming the original network by 1.30%. The accuracy improvement is particularly significant for ground wire defects (2.40%). The D-Net-based R-Net, despite having fewer parameters, maintains high accuracy (0.6502). Compared to other object detection algorithms, such as YOLO-v3 and Faster R-CNN, the optimized R-Net exhibits superior performance in terms of mean average precision (15.58% and 2.45% higher, respectively) and parameter efficiency (17M vs. 38M and 81M). Considering both performance and speed, the optimized R-Net achieves a processing rate of 10.5 frames per second. This study provides an efficient and accurate tool for transmission line fault diagnosis and localization, with significant practical implications for power system operation and maintenance.

The application of base on deep learning remote sensing image landslide detection has become a trend. In view of the, large difference in the scale of landslide objects and the very important characteristics of the shallow layer of the landslide object, we modified the original Faster RCNN. First compare the average accuracy values of different network models, and select the network ResNet50 with deeper layers, and then integrated into Feature Pyramid Network (FPN) on the basis of ResNet50, Fusion of FPN structure with RPN and Fast RCNN. Finally, it is verified on the public landslide dataset in BiJie City, Guizhou Province, China, and the average accuracy of the obtained model is 87.10%, which is 16.9% higher than the 70.20% of VGG16. Contrast experiments with different anchor ratios and different hyperparameters in the FPN part are carried out, and the generated results are analyzed and compared. The experimental results show that the proposed method has good robustness and high accuracy for the detection of landslide objects, in remote sensing images, which can provide a technical reference for further research on landslide detection in remote sensing images.

Given the wide diffusion of deep neural network architectures for computer vision tasks, several new applications are nowadays more and more feasible. Among them, a particular attention has been recently given to instance segmentation, by exploiting the results achievable by two-stage networks (such as Mask R-CNN or Faster R-CNN), derived from R-CNN. In these complex architectures, a crucial role is played by the Region of Interest (RoI) extraction layer, devoted to extracting a coherent subset of features from a single Feature Pyramid Network (FPN) layer attached on top of a backbone. This paper is motivated by the need to overcome the limitations of existing RoI extractors which select only one (the best) layer from FPN. Our intuition is that all the layers of FPN retain useful information. Therefore, the proposed layer (called Generic RoI Extractor - GRoIE) introduces non-local building blocks and attention mechanisms to boost the performance. A comprehensive ablation study at component level is conducted to find the best set of algorithms and parameters for the GRoIE layer. Moreover, GRoIE can be integrated seamlessly with every two-stage architecture for both object detection and instance segmentation tasks. Therefore, the improvements brought about by the use of GRoIE in different state-of-the-art architectures are also evaluated. The proposed layer leads up to gain a 1.1% AP improvement on bounding box detection and 1.7% AP improvement on instance segmentation. The code is publicly available on GitHub repository at https://github.com/IMPLabUniPr/mmdetection/tree/groie_dev

With the development of unmanned aerial vehicle (UAV) remote sensing technology, target detection based on UAV images has increasingly become a hot spot for research. Aiming at the problems of many small target instances, complex backgrounds and difficult feature extraction in UAV images, we propose a UAV aerial image target detection algorithm called BLUR-YOLO. First, the h-swish activation function is used in the backbone network and the neck network to increase the expressiveness of the model. Second, an attention mechanism (CoordAttention) is added to the bottleneck layer of the backbone network, thereby increasing the weight of valid information and suppressing background noise interference. Finally, by removing redundant nodes of the path aggregation network (PANet), adding additional connections, and using BlurPool instead of the downsampling method, a feature pyramid network (Blur-PANet) is proposed to effectively fuse multilayer features. Experimental results on the VisDrone public dataset show that the proposed drone image object detection model (BLUR-YOLO) is 1.2% better than the YOLOv4 algorithm, which proves the effectiveness of the method.

In general object detection, scale variation is always a big challenge. At present, feature pyramid networks are employed in numerous methods to alleviate the problems caused by large scale range of objects in object detection, which makes use of multi-level features extracted from the backbone for top-down upsampling and fusion to acquire a set of multi-scale depth image features. However, the feature pyramid network proposed by Ghiasi et al. adopts a simple fusion method, which fails to consider the fusion feature context, and therefore, it is difficult to acquire good features. In addition, the fusion of multi-scale features directly by traditional upsampling is prone to feature misalignment and loss of details. In this paper, an adaptive feature pyramid network is proposed based on the feature pyramid network to alleviate the foregoing potential problems, which includes two major designs, i.e., adaptive feature upsampling and adaptive feature fusion. The adaptive feature upsampling aims to predict a group of sampling points of each pixel through some models, and constitute feature representation of the pixel by feature combination of sampling points, while adaptive feature fusion is to construct pixel-level fusion weights between fusion features through attention mechanism. The experimental results verified the effectiveness of the method proposed in this paper. On the public object detection dataset MS-COCO test-dev, Faster R-CNN model achieved performance improvement of 1.2 AP by virtue of the adaptive feature pyramid network, and FCOS model could achieve performance improvement of 1.0 AP. What's more, the experiments also validated that the adaptive feature pyramid network proposed herein was more accurate for object localization.

Intelligent traffic surveillance (ITS) in nighttime has increasingly become important in advanced-driving-assisted-systems (ADAS). ITS relies on efficient detection of objects and adaptability to changing environments in the nighttime. However, detecting the visual features of the objects in nighttime poses challenge due to insufficient illumination conditions. With the development of deep learning object detectors, higher accuracies have been achieved in object detection from nighttime images. In this paper, we employ convolutional neural network (CNN) object detectors such as Faster R-CNN (with various feature extractors), Feature Pyramid Network, and Single Shot Detector to analyse their performance in terms of speed and accuracy using our datasets for nighttime object detection. We carry out the image quality assessment of our datasets and perform an automatic parameter tuning for re-training the object detectors. Experimental results show that the Faster R-CNN with inception has higher detection performance compared with other CNN based detectors.

The localization of multiple interference sources in Global Navigation Satellite Systems (GNSS) can be achieved using carrier-to-noise ratio (C/N0) information provided by GNSS receivers, such as those embedded in smartphones. However, in increasingly prevalent complex scenarios—such as the coexistence of multiple directional interferences, increased diversity and density of GNSS interference, and the presence of multiple low-power interference sources—conventional localization methods often fail to provide reliable results, thereby limiting their applicability in real-world environments. This paper presents a multi-interference sources localization method using object detection in GNSS C/N0 distribution maps. The proposed method first exploits the similarity between C/N0 data reported by GNSS receivers and image grayscale values to construct C/N0 distribution maps, thereby transforming the problem of multi-source GNSS interference localization into an object detection and localization task based on image processing techniques. Subsequently, an Oriented Squeeze-and-Excitation-based Faster Region-based Convolutional Neural Network (OSF-RCNN) framework is proposed to process the C/N0 distribution maps. Building upon the Faster R-CNN framework, the proposed method integrates an Oriented RPN (Region Proposal Network) to regress the orientation angles of directional antennas, effectively addressing their rotational characteristics. Additionally, the Squeeze-and-Excitation (SE) mechanism and the Feature Pyramid Network (FPN) are integrated at key stages of the network to improve sensitivity to small targets, thereby enhancing detection and localization performance for low-power interference sources. The simulation results verify the effectiveness of the proposed method in accurately localizing multiple interference sources under the increasingly prevalent complex scenarios described above.

The effective use of multi-scale features remains an open problem for object detection tasks. Recently, proposed object detectors have usually used Feature Pyramid Networks (FPN) to fuse multi-scale features. Since Feature Pyramid Networks use a relatively simple feature map fusion approach, it can lead to the loss or misalignment of semantic information in the fusion process. Several works have demonstrated that using a bottom-up structure in a Feature Pyramid Network can shorten the information path between lower layers and the topmost feature, allowing an adequate exchange of semantic information from different layers. We further enhance the bottom-up path by proposing a multi-scale residual aggregation Feature Pyramid Network (MSRA-FPN), which uses a unidirectional cross-layer residual module to aggregate features from multiple layers bottom-up in a triangular structure to the topmost layer. In addition, we introduce a Residual Squeeze and Excitation Module to mitigate the aliasing effects that occur when features from different layers are aggregated. MSRA-FPN enhances the semantic information of the high-level feature maps, mitigates the information decay during feature fusion, and enhances the detection capability of the model for large objects. It is experimentally demonstrated that our proposed MSRA-FPN improves the performance of the three baseline models by 0.5–1.9% on the PASCAL VOC dataset and is also quite competitive with other state-of-the-art FPN methods. On the MS COCO dataset, our proposed method can also improve the performance of the baseline model by 0.8% and the baseline model’s performance for large object detection by 1.8%. To further validate the effectiveness of MSRA-FPN for large object detection, we constructed the Thangka Figure Dataset and conducted comparative experiments. It is experimentally demonstrated that our proposed method improves the performance of the baseline model by 2.9–4.7% on this dataset and can reach up to 71.2%.

Feature pyramid network (FPN) has dominated the task of object detection for many years with its congenital capability of semantic information interaction between different feature levels. Satisfactory performance can be easily achieved via the heavy backbones or tricky designs of anchors. However, the heavy structure brings about a huge increase of parameters and calculation. To address this challenge, this paper proposes a novel Hint Pyramid Learning(HPL) strategy to optimize a lightweight FPN-based detector such as one based on ResNet18. In HPL, the hint feature representation is learnt via salient semantic mining based on the teacher-student learning mechanism and self learning mechanism. Besides minimizing of the discrepancy of features belonging to the same feature pyramid layer, HPL also focuses on the relationships between feature pyramid layers. Unlike the popular mimicking algorithms such as hint learning and knowledge distillation which achieve comparable performance on classification tasks but failed to generalize to the detection tasks with FPN, HPL can be easily plugged into different FPN-based pipelines such as one-stage RetinaNet or two-stage Faster R-CNN and improves the performance straightforwardly. Without any meticulous designing, when the backbone of students is ResNet18 and the backbone of teachers is ResNet50, HPL effectively improves the performance by 2.1 AP for RetinaNet and 1.0 AP for Faster R-CNN on COCO benchmark.

Deep learning target detection based on faster regions with convolutional neural network (Faster R-CNN) features has been applied in image processing successfully, however, it is rarely introduced to the field of hyperspectral image (HSI) target detection due to the tensor characteristics and the lack of training samples of HSI data. In this paper, the target detection based on Faster R-CNN is proposed to HSI with data set adjustment and parameter turning. As a typical tensor data, HSIs contain two-dimensional (2-D) spatial information and one dimensional (1-D) spectral information. It contains more information than ordinary images, and has unique advantages in the field of ground object and sea target detection. Therefore, the original HSI is firstly adjusted to the data set format required by the model, and the final Faster R-CNN sample data set can be achieved by combining the data set of Google Earth images. Next, a Faster R-CNN network suitable for HSI data could be built. Finally, to improve the accuracy of target detection, some parameters of Faster R-CNN would be tuned. The numerical results show that the method has the potential advantages of high precision and high speed in HSI target detection, and will have broad application prospects.

YOLOv3 is a deep learning-based real-time object detector and is mainly used in applications such as video surveillance and autonomous vehicles. In this paper, we proposed an improved YOLOv3 (You Only Look Once version 3) applied Duplex FPN, which enhanced large object detection by utilizing low-level feature information. The conventional YOLOv3 improved the small object detection performance by applying FPN (Feature Pyramid Networks) structure to YOLOv2. However, YOLOv3 with an FPN structure specialized in detecting small objects, so it is difficult to detect large objects. Therefore, this paper proposed an improved YOLOv3 applied Duplex FPN, which can utilize low-level location information in high-level feature maps instead of the existing FPN structure of YOLOv3. This improved the detection accuracy of large objects. Also, an extra detection layer was added to the top-level feature map to prevent failure of detection of parts of large objects. Further, dimension clusters of each detection layer were reassigned to learn quickly how to accurately detect objects. The proposed method was compared and analyzed in the PASCAL VOC dataset. The experimental results showed that the bounding box accuracy of large objects improved owing to the Duplex FPN and extra detection layer, and the proposed method succeeded in detecting large objects that the existing YOLOv3 did not.

Ship target detection on the sea surface is one of the most common scenes in the field of target detection. The accuracy of target detection plays an important role in the field of sea rescue and defense. However, complex infrared sea surface scenes, such as island shore, fish scale wave, sea surface bright band and other disturbances, bring great challenges to target detection. In this paper, we propose an improved YOLOV5 model by analyzing the characteristics of infrared image imaging and ship target on the sea surface. Aiming at the problem of information loss of small targets in the deep layer of the network, we redesigned the backbone network, which was composed of four Multi-scale residual blocks, and each block was connected by CBAM (Convolutional Block Attention Module) attention mechanism to improve information transmission and fusion between different feature layers. Aiming at the problem of complex sea surface scene interference, we use FPN and PAN (Feature Pyramid Network and Personal Area Network) mechanism to construct feature fusion network in neck, and add shallow feature fusion in FPN. Our model achieves good performance both in terms of latency and accuracy. In a self-collected sea surface scene dataset, multiple SOTAs for detection tasks are compared and the results demonstrate the superiority of the proposed method.

Side-scan sonar (SSS) images present unique challenges to computer vision due to their lower resolution, smaller targets, and fewer features. Although the mainstream backbone networks have shown promising results on traditional vision tasks, they utilize traditional convolution to reduce the dimensionality of feature maps, which may cause information loss for small targets and decrease performance in SSS images. To address this problem, based on the yolov8 network, we proposed a new underwater target detection model based on upsampling and downsampling. Firstly, we introduced a new general downsampling module called shallow robust feature downsampling (SRFD) and a receptive field convolution (RFCAConv) in the backbone network. Thereby multiple feature maps extracted by different downsampling techniques can be fused to create a more robust feature map with a complementary set of features. Additionally, an ultra-lightweight and efficient dynamic upsampling module (Dysample) is introduced to improve the accuracy of the feature pyramid network (FPN) in fusing different levels of features. On the underwater shipwreck dataset, our improved model’s mAP50 increased by 4.4% compared to the baseline model.

In this paper, an efficient instance segmentation scheme based on deep convolutional neural networks is proposed to deal with unconstrained psoriasis images for computer-aided diagnosis. To achieve instance segmentation, the You Only Look At CoefficienTs (YOLACT) network composed of backbone, feature pyramid network (FPN), Protonet, and prediction head is used to deal with psoriasis images. The backbone network is used to extract feature maps from an image, and FPN is designed to generate multiscale feature maps for effectively classifying and localizing objects with multiple sizes. The prediction head is used to predict the classification information, bounding box information, and mask coefficients of objects. Some prototypes generated by Protonet are combined with mask coefficients to estimate the pixel-level shapes for objects. To achieve instance segmentation for unconstrained psoriasis images, YOLACT++ with a pretrained model is retrained via transfer learning. To evaluate the performance of the proposed scheme, unconstrained psoriasis images with different severity levels are collected for testing. As for subjective testing, the psoriasis regions and normal skin areas can be located and classified well. The four performance indices of the proposed scheme were higher than 93% after cross validation. About object localization, the Mean Average Precision (mAP) rates of the proposed scheme were at least 85.9% after cross validation. As for efficiency, the frames per second (FPS) rate of the proposed scheme reached up to 15. In addition, the F1_score and the execution speed of the proposed scheme were higher than those of the Mask Region-Based Convolutional Neural Networks (R-CNN)-based method. These results show that the proposed scheme based on YOLACT++ can not only detect psoriasis regions but also distinguish psoriasis pixels from background and normal skin pixels well. Furthermore, the proposed instance segmentation scheme outperforms the Mask R-CNN-based method for unconstrained psoriasis images.

With the increasing aging of the society, a series of consequences caused by falls of the elderly have become a serious medical problem and a real social problem. Aiming at the fall behavior of the elderly, the research and development of human fall recognition technology has practical application value. This paper proposes a method to recognize human targets in indoor images using target detection technology, and then use the trained neural network based on Self-attention technique named Vision Transformer (ViT) to recognize the falling posture of the elderly. Firstly, the target detection model is optimized and trained for indoor scene, so that the model can accurately detect human targets in indoor scene; Next, the indoor scene human target image is preprocessed, and the indoor human pose image data set is constructed; Then, the data set is used to train the ViT depth network, and enable it to correctly classify five postures (standing, sitting, lying, bending and crawling). The experimental results show that ViT network achieves high accuracy and excellent generalization capacity for the above 5 human posture and can realize the recognition of elderly falls.