Sensors

Uncomplicated application-level vehicular computing and networking (UAVCAN) is a higher-layer protocol built on the controller area network (CAN) bus to support control and status communication among electronic control units in unmanned aerial vehicles. Because CAN provides no native authentication or encryption, UAVCAN networks are vulnerable to message injection, replay, and flooding attacks. Most existing CAN intrusion detection systems, however, are designed for automotive networks and do not explicitly account for the transfer structure and tail-byte rules of UAVCAN. This paper proposes a protocol-aware intrusion detection framework that reconstructs UAVCAN transfers and extracts six payload features and four transfer features based on the CAN ID, transfer ID, toggle bit, and transfer-boundary information. The proposed feature set is evaluated using random forest, XGBoost, logistic regression, and multilayer perceptron classifiers on ten attack scenarios from a public UAVCAN dataset. The best-performing configuration achieves average accuracy, precision, and recall of 99.89%, 99.96%, and 99.88%, respectively. Ablation results show that transfer-rule features are particularly effective for replay-attack detection, while combining payload and transfer features provides the most consistent performance across attack types. The proposed approach also outperforms the evaluated automotive CAN IDS baselines and achieves competitive performance compared with existing UAVCAN-specific IDS methods. These findings support the value of protocol-aware feature extraction for UAVCAN intrusion detection.

Millimeter-wave (mmWave) radar enables non-contact human identification by exploiting gait micro-Doppler signatures without capturing visual imagery. Nevertheless, practical deployment encounters several critical challenges: strong torso echoes that obscure faint limb-motion features, channel-dependent responses caused by unconstrained walking styles, and computational limitations on edge hardware. This paper proposes a lightweight gait-based human identification method for multiple-input multiple-output (MIMO) radar systems, which integrates adaptive Gamma correction, multi-transmit-channel differential encoding, and an asymmetric-pooling convolutional recurrent neural network (Asym-CRNN). Specifically, the differences across the three transmit-channel responses of the three-transmit four-receive (3T4R) radar are encoded into a three-channel spatiotemporal representation, and the compact network retains temporal resolution to facilitate efficient gait discrimination. Evaluated on a self-collected five-subject dataset with acquisition-sequence-level train-test separation, the proposed method achieves closed-set accuracies of 89.62% and 99.52% under 1 s and 6 s observation windows, respectively. For open-set scenarios, the method attains a registered-versus-unregistered area under the receiver operating characteristic curve (AUROC) of 0.9869. With a maximum softmax probability (MSP) threshold of 0.85, the method rejects 91.88% of unregistered human samples and all tested pet-interference samples. Furthermore, the model achieves an accuracy of 86.98% using only single-channel IDRad inputs. The exported model requires merely 4.32 MB of storage. Deployed on a Raspberry Pi 5 platform, the acquisition-processing pipeline runs using only two CPU cores with CPU-only execution: one core continuously receives and buffers raw radar data, whereas the other processes previously acquired observation windows. The per-window processing latency reaches 715.7 ms for the 1 s window and 4366.2 ms for the 6 s window, including network inference times of 6.7 ms and 15.2 ms, respectively. The non-causal bidirectional long short-term memory (Bi-LSTM) generates one identity decision once each observation window is fully collected. These results verify the feasibility of the proposed method for privacy-preserving indoor monitoring at small scales on resource-constrained edge devices.

Semantic segmentation of high-resolution remote sensing images faces three major challenges in frequency-spatial feature fusion: background clutter mixed into high-frequency components, semantic discontinuities within large homogeneous regions, and loss of fine rigid boundaries caused by convolutional downsampling. Traditional dual-stream networks rely on complex attention mechanisms and directly concatenate heterogeneous features, which often leads to representation conflicts, information loss, and excessive edge smoothing. To address these issues, we propose FSOD-Net, a Frequency-Spatial Feature Decoupling Network built upon the SFFNet architecture. The feature mapping stage is reconstructed to incorporate physical edge priors and frequency-domain attention-based denoising. Specifically, a Spatial Attention Wavelet Transform Feature Decomposer (SA-WTFD) is introduced in the frequency branch to adaptively suppress high-frequency background clutter and enhance discriminative features. In the spatial global branch, a lightweight pyramid pooling module (L-PPM) captures macro-contextual information to fill semantic gaps within areal objects. In the local branch, a fixed Laplacian operator is embedded as an explicit physical edge prior to preserving micro-scale rigid boundaries during downsampling. These three modules operate along independent paths, enabling decoupled yet collaborative multi-domain feature learning. Extensive experiments on the ISPRS Vaihingen and Potsdam datasets demonstrate that FSOD-Net achieves mean Intersection over Union (mIoU) scores of $84.24\pm 0.11\%$ and $86.79\pm 0.09\%$, respectively, indicating its potential in segmentation accuracy and generalization.