6 December 2024 in Expert Systems with Applications
20 February 2023 in IEEE Transactions on Instrumentation and Measurement
Currently, reliable and accurate object detection in high-resolution remote sensing images still faces significant challenges such as color, aspect ratio, complex background, and scale variations. Even the detection results obtained based on the latest convolutional neural network (CNN) methods are not satisfactory. To obtain more accurate detection results from large-scale remote sensing images, we proposed a multiscale object detection algorithm oriented to adaptively attentional feature fusion based on the YOLOX algorithm. Firstly, a multiscale attentional feature fusion (MSAFF) structure was added to the YOLOX network to increase the perceptual field and aggregate the contextual information to obtain a feature map with richer semantic information. Secondly, an adaptively spatial feature fusion (ASFF) structure was introduced to process the fused feature maps, to which spatial feature weights were assigned at different levels to enhance the feature representation of remote sensing objects and reduce feature loss. Finally, the aligned convolutional network was used in the object classification and localization task to achieve a more accurate localization of densely arranged objects with arbitrary orientation. The algorithm proposed in this paper was extensively experimented on the PASCAL VOC and the DIOR datasets, and the average accuracy reached 89.2% and 75.3%, respectively. Compared with some current mainstream two-stage and one-stage object detection algorithms, the experimental results demonstrated that our method performed well in both accuracy and speed. At the same time, it reduced the leakage rate of remote sensing objects to a certain extent.
10 February 2025 in IEEE Transactions on Power Delivery
To address the limited single-image information-processing method, insufficient global knowledge-processing capability of the traditional model, and the lack of explainability in detection results for the task of transmission line pin-missing bolts detection, the researchers propose a pin-missing bolts detection method based on cross-media and knowledge reasoning (CMKR-PBDM). First, we construct a fitting-bolt image-text pair dataset and a bolt knowledge graph (BoltKG). Subsequently, a cross-media bolt knowledge fusion model (CBKFM) is proposed, thus generating the image's overall text description by fusing the global knowledge extracted by the FB-GPT with the local knowledge captured by YOLOv8. Finally, the study proposes a large language reasoning model based on the knowledge graph (LLRM-KG), which utilizes BoltKG to guide the big language model in performing knowledge reasoning on the CBKFM output information; thus, explainable pin-missing bolts detection results are obtained. In the experimental stage, the researchers select bolts on four types of background fittings as experimental objects. The experimental results indicate that the method not only improves the accuracy of pin-missing bolts detection, but also makes the pin-missing bolts detection results explainable.