Layered double hydroxides (LDHs) have been demonstrated to be promising gas-sensing materials because of their high specific surface area and unique layered structure. However, the general stacking and low conductivity make the LDHs insensitive in most cases towards rarefied gas exposure. In this work, we designed and hydrothermally prepared nanocomposites of LDHs/rGO (layered double hydroxides/reduced graphene oxide) based on electrostatic self-assembly. The as-formed nanocomposite with proper addition of GO shows loose arrangement of LDH nanoflakes on both sides of the highly conductive rGO instead of the stacked flower-like structure of pure LDHs. The unique microstructure, as well as the conductivity modulation by rGO, induces enhanced sensing performance of the LDHs/rGO nanocomposites compared with that of the pure ZnTi-LDHs. At room temperature, the sensor based on LDHs/rGO is responsive to rarefied NO2 low to 50 ppb and 4-fold enhancement in gas response is achieved upon 0.5–50 ppm NO2 exposure in comparison to that of the single ZnTi-LDHs sensor. Meanwhile, the LDHs/rGO sensors show near instantaneous response characteristics and good stability. The satisfactory sensing response of LDHs/rGO is analyzed in terms of the unique guided-assembly microstructure and the synergistic contributions on gas-sensing and conductivity properties of ZnTi-LDHs and rGO.
Vehicle line-pressing identification from a roadside perspective is a challenging task in intelligent transportation systems. Factors such as vehicle pose and environmental lighting significantly affect identification performance, and the high cost of data collection further exacerbates the problem. Existing methods struggle to achieve robust results across different scenarios. To improve the robustness of roadside vehicle line-pressing identification, we propose an efficient method. First, we construct the first large-scale vehicle line-pressing dataset based on roadside cameras (VLPI-RC). Second, we design an end-to-end convolutional neural network that integrates vehicle and lane line mask features, incorporating a mask-guided attention module to focus on key regions relevant to line-pressing events. Finally, we introduce a binary balanced contrastive loss (BBCL) to improve the model’s ability to generate more discriminative features, addressing the class imbalance issue in binary classification tasks. Experimental results demonstrate that our method achieves 98.65% accuracy and 96.34% F1 on the VLPI-RC dataset. Moreover, when integrated into the YOLOv5 object detection framework, it attains an identification speed of 108.29 FPS. These results highlight the effectiveness of our approach in accurately and efficiently detecting vehicle line-pressing behaviors.