Recently, ViTAE-RVSA, the first large-scale Vision Transformer (ViT) tailored for remote sensing, has demonstrated the potential of ViTs by integrating window attention with a convolutional branch. However, as this branch still adopts isotropic square kernels and conventional Feature Pyramid Networks neglect directional priors in multi-scale fusion, the resulting representations remain suboptimal for arbitrarily oriented, high-aspect-ratio, and small objects. To overcome these limitations, we propose Strip-ViTAE, a transformer-based detector that embeds a rotation-equivariant convolution (R2Conv) in the backbone to capture orientation-consistent local features. Moreover, we introduce a Parallel Strip Convolution Module (PSCM) employing horizontal and vertical strip kernels to adaptively enlarge the receptive field and strengthen local feature modeling for elongated and small objects. Finally, we design a Strip Feature Pyramid Network (StripFPN) composed of a Bottom-Up Reflow Module (Bottom-Up RM), a Strip-Based Enhancement Module (SBEM), and a Self-Attention Excitation Module (SAEM) to achieve direction-consistent cross-scale fusion. Experiments on the DOTA-v1.5 dataset show that Strip-ViTAE attains 72.82% mAP, surpassing the state-of-the-art (SOTA) by 1.35% and improving the mAP for high-aspect-ratio and small objects by 3.20%, validating the effectiveness of our method.

We present a new approach to address the challenges associated with maintaining the functionality of triboelectric vibration sensors in smart plywood during woodworking operations involving nails and screws. The current state-of-the-art sensor design employs non-overlapping electrodes, which unfortunately leads to significant compromises in terms of signal strength and clarity, particularly in real-world scenarios that involve electromagnetic (EM) interference. To overcome these limitations, we propose a method that enables the woodworker to manually isolate short-circuited electrodes. This method facilitates the creation of sensors using overlapping electrodes, while also incorporating EM shielding, thereby resulting in a substantial improvement in the sensor’s robustness when detecting user activities. To validate the effectiveness of our proposed approach, we conducted a series of experiments, which not only shed light on the drawbacks of non-overlapping electrode designs but also demonstrated the significant improvements achieved through our method.