Change detection (CD) stands out as a pivotal yet challenging task in the interpretation of remote sensing images. Significant developments have been witnessed, particularly with the rapid advancements in deep learning techniques. Nevertheless, challenges such as incomplete detection targets and unsmooth boundaries remain as most CD methods suffer from ineffective feature fusion. Therefore, this paper presents a multi-scale gated fusion network (MSGFNet) to improve the accuracy of CD results. To effectively extract bi-temporal features, the EfficientNetB4 model based on a Siamese network is employed. Subsequently, we propose a multi-scale gated fusion module (MSGFM) that comprises a multi-scale progressive fusion (MSPF) unit and a gated weight adaptive fusion (GWAF) unit, aimed at fusing bi-temporal multi-scale features to maintain boundary details and detect completely changed targets. Finally, we use the simple yet efficient UNet structure to recover the feature maps and predict results. To demonstrate the effectiveness of the MSGFNet, the LEVIR-CD, WHU-CD, and SYSU-CD datasets were utilized, and the MSGFNet achieved F1 scores of 90.86%, 92.46%, and 80.39% on the three datasets, respectively. Furthermore, the low computational costs and small model size have validated the superior performance of the MSGFNet.
To address the challenges of discontinuous heterogeneous image matching, significant matching errors in specific regions, and poor real-time performance in GNSS-denied environments for unmanned aerial vehicles (UAVs), we propose an integrated navigation method based on the strapdown inertial navigation system (SINS)/scene-matching navigation system (SMNS). First, we designed a heterogeneous image-matching and positioning approach using infrared images to obtain an estimation of the UAV’s position. Then, we established a mathematical model for the integrated SINS/SMNS navigation system. Finally, a Kalman filter (KF) was employed to fuse the inertial navigation data with absolute position data from scene matching, achieving high-precision and highly reliable navigation positioning. We constructed a navigation data acquisition platform and conducted simulation studies using flight data collected from this platform. The results demonstrate that the integrated SINS/SMNS navigation method significantly outperforms standalone scene-matching navigation in horizontal positioning accuracy, improving latitude accuracy by 52.34% and longitude accuracy by 45.54%.