The SAR system possesses the ability to carry out all-day and all-weather imaging, which is highly valuable in the application of aircraft identification. However, aircraft identification from SAR images still faces great challenges due to speckle noise interference, multiscale problems, and complex background interference. To solve these problems, an efficient bidirectional path multiscale fusion and attention network (EBMA-Net) is proposed in this paper. It employs bidirectional connectivity to fuse the features of aircraft with different scales to perform the accurate detection of aircraft even when the background is highly complex. In the presented EBMA-Net, a module called efficient multiscale channel attention fusion (EMCA) and three parallel squeeze efficient channel attention (SECA) modules are proposed. In the EMCA module, the bidirectional paths are created by stacking upper and lower fusion modules, which effectively integrate shallow detailed features and deep semantic information. So, the detection performance of aircraft at different scales is improved. In the SECA module, the dependency relationship between feature channels is explicitly modeled, which can automatically learn the importance of different channels, prioritize key features, so as to improve the precision and robustness of aircraft identification. In the experiment, the public dataset of aircraft identification (i.e., SAR-AIRcraft-1.0, which is generated from the GF-3 satellite) from high-resolution SAR systems is used, and several other excellent target-detection networks are used for performance comparison, namely, YOLOv5s, YOLOv7, MGCAN, and EBPA2N. According to the results, the average aircraft detection accuracy of EBMA-Net is 91.31%, which is 4.5% higher than YOLOv7; and the false alarm rate is decreased by 5%. Its accuracy in the identification of aircraft can reach 95.6%, which is about 3.7% higher than YOLOv7. Therefore, the EBMA-Net obviously outperforms the other networks for aircraft detection and identification. The proposed EBMA-Net, which can capture the detailed information and better restrain the background interference, could also be used to perform the detection and identification of dense targets with different scales and background from SAR images.

In category-level object pose estimation tasks, determining how to mitigate intra-class shape variations and improve pose estimation accuracy for complex objects remains a challenging problem to solve. To address this issue, this paper proposes a new network architecture, LA-Net, to efficiently ascertain object poses from features. Firstly, we extend the 3D graph convolution network architecture by introducing the LS-Layer (Linear Connection Layer), which enables the network to acquire features from different layers and perform multi-scale feature fusion. Secondly, LA-Net employs a novel attention mechanism (PSA) and a Max-Pooling layer to extract local and global geometric information, which enhances the network’s ability to perceive object poses. Finally, the proposed LA-Net recovers the rotation information of an object by decoupling the rotation mechanism. The experimental results show that LA-Net can has much better accuracy in object pose estimation compared to the baseline method (HS-Pose). Especially for objects with complex shapes, its performance is 8.2% better for the 10°5 cm metric and 5% better for the 10°2 cm metric.

Current deep learning-based camera position estimation methods fail to fully mine and utilize the effective information in the scene and are susceptible to motion blur and point-of-view variations, resulting in low accuracy of the estimated camera position. In order to solve the above problems, we design a new camera position estimation network—FusePose. FusePose realizes the fusion of odometry information and semantic information through the temporal-aware localization module (LSVO) and the semantic information-aware module (SEMA), which effectively achieves a more lightweight and high-precision pose estimation. Specifically, the LSVO module employs an improved double-helix network architecture to extract odometry information while incorporating an LSTM submodule to mitigate trajectory drift in visual odometry. The SEMA module utilizes a quad-branch network to extract semantic features from segmentation maps. It adopts an adaptive weighted fusion approach to integrate multi-scale semantic features, thereby optimizing the information contribution ratio across different feature scales. The experimental results show that the discrete points of the camera localization trajectory of FusePose on the 7-Scenes dataset are further reduced, the trajectory is clearer, and the errors are further reduced, including the translation error by 31.6% and the rotation error by 27%. It is worth noting that the 7-Scenes dataset does not provide semantic labeling, so we built our own semantic segmentation graph dataset based on the 7-Scenes dataset.