Pengyu Yin

Accurate detection of small transmission towers in remote sensing images is critical for low-altitude aviation safety and power-grid monitoring, yet it remains challenging due to complex backgrounds, weak target responses, and severe feature submersion. To address these issues, we propose a Semantic Boundary-Guided Dynamic Detection Network (SBG-DDN) that integrates a semantic boundary-guided representation framework with a dynamic detection and localization optimization scheme. Specifically, the proposed method combines a frozen DINOv3 backbone to provide global semantic priors and a CSPDarknet backbone to capture local boundary-sensitive details while further enhancing their interaction through the Semantic-Boundary Fusion Module (SBFM). In addition, a Dynamic Semantic-Boundary Optimization Head (DSBOH) and an Adaptive Structure-Aware Transmission Tower IoU (ASTIoU) loss are introduced to improve multi-scale feature adaptation and geometry-aware localization for sparse and elongated transmission towers. To support broader evaluation in this area, we constructed the Power Transmission Tower Object Detection (PTTOD) dataset, which covers multiple countries and diverse geographic environments. Experimental results on the public SRSPTD dataset and the proposed PTTOD dataset demonstrate the effectiveness of the proposed method. On SRSPTD, SBG-DDN achieves 74.3% mAP@0.5 and 35.1% mAP@0.5:0.95, outperforming existing state-of-the-art detectors.

Detection of planted tree seedlings at the individual level is crucial for monitoring forest ecosystems and supporting silvicultural management. The combination of deep learning (DL) object detection algorithms and remote sensing (RS) data from unmanned aerial vehicles (UAVs) offers efficient and cost-effective solutions. However, current methods predominantly rely on unimodal RS data sources, overlooking the multi-source nature of RS data, which may result in an insufficient representation of target features. Moreover, there is a lack of multimodal frameworks tailored explicitly for detecting planted tree seedlings. Consequently, we propose a multimodal object detection framework for this task by integrating texture information from digital orthophoto maps (DOMs) and geometric information from digital surface models (DSMs). We introduce alternate scanning fusion (ASF), a novel multimodal fusion module based on state space models (SSMs). The ASF can achieve global feature fusion while maintaining linear computational complexity. We embed ASF modules into a dual-backbone YOLOv5 object detection framework, enabling feature-level fusion between DOM and DSM for end-to-end detection. To train and evaluate the proposed framework, we establish the planted tree seedling (PTS) dataset. On the PTS dataset, our method achieves an AP50 of 72.6% for detecting planted tree seedlings, significantly outperforming the original YOLOv5 on unimodal data: 63.5% on DOM and 55.9% on DSM. Within the YOLOv5 framework, comparative experiments on both our PTS dataset and the public VEDAI benchmark demonstrate that the ASF surpasses representative fusion methods in multimodal detection accuracy while maintaining relatively low computational cost.

Detection of damaged buildings is a form of object detection and is essential for disaster emergency response efforts. In recent years, deep learning has been widely used in object detection, with successful target detection models such as Faster-Rcnn and YOLO being proposed. However, training deep learning models usually requires a large amount of labeled data. Due to the high threshold for aerial remote sensing data collection, labeled aerial data of collapsed buildings is very sparse. In addition, the limited area of damage in a single scene leads to insufficient feature diversity, which can easily lead to model overfitting. These issues restrict the development of deep learning in emergency response applications. To solve these problems, we propose a paradigm named cross-domain teacher-student mutual training. By using the Cycle-GAN generated style transfer data through teacher network, pseudo-labels are generated to train the student network. Then, the student network slowly updates the parameters of the teacher network to indirectly learn the generalization information of the satellite data domain. Networks trained in this way can achieve good results in detecting collapsed houses in aviation and satellite data. We tested the results on our self-built dataset, DB-ARSD, which includes bounding box labeling of the damaged buildings, and found that our method outperforms other object detection methods in both collapsed house prediction accuracy and domain transfer generalization performance.

Synthetic aperture radar (SAR) is an active coherent microwave remote sensing system. SAR systems working in different bands have different imaging results for the same area, resulting in different advantages and limitations for SAR image classification. Therefore, to synthesize the classification information of SAR images into different bands, an SAR image fusion classification method based on the decision-level combination of multi-band information is proposed in this paper. Within the proposed method, the idea of Dempster–Shafer evidence theory is introduced to model the uncertainty of the classification result of each pixel and used to combine the classification results of multiple band SAR images. The convolutional neural network is used to classify single-band SAR images. Calculate the belief entropy of each pixel to measure the uncertainty of single-band classification, and generate the basic probability assignment function. The idea of the term frequency-inverse document frequency in natural language processing is combined with the conflict coefficient to obtain the weight of different bands. Meanwhile, the neighborhood classification of each pixel in different band sensors is considered to obtain the total weight of each band sensor, generate weighted average BPA, and obtain the final ground object classification result after fusion. The validity of the proposed method is verified in two groups of multi-band SAR image classification experiments, and the proposed method has effectively improved the accuracy compared to the modified average approach.