As an essential task in computer vision, video anomaly detection technology is used in video surveillance, scene understanding, road traffic analysis and other fields. However, the definition of anomaly, scene change and complex background present great challenges for video anomaly detection tasks. The insight that motivates this study is that the reconstruction error for normal samples would be lower since they are closer to the training data, while the anomalies could not be reconstructed well. In this paper, we proposed a Convolutional Recurrent AutoEncoder (CR-AE), which combines an attention-based Convolutional Long–Short-Term Memory (ConvLSTM) network and a Convolutional AutoEncoder. The ConvLSTM network and the Convolutional AutoEncoder could capture the irregularity of the temporal pattern and spatial irregularity, respectively. The attention mechanism was used to obtain the current output characteristics from the hidden state of each Covn-LSTM layer. Then, a convolutional decoder was utilized to reconstruct the input video clip and the testing video clip with higher reconstruction error, which were further judged to be anomalies. The proposed method was tested on two popular benchmarks (UCSD ped2 Dataset and Avenue Dataset), and the experimental results demonstrated that CR-AE achieved 95.6% and 73.1% frame-level AUC on two public datasets, respectively.

The feasibility of modified tabia (MT) with composite-activated coal gangue (CACG) as the subgrade material of low-grade highways was experimentally investigated. A composite activation method was employed to improve the pozzolanic activity of coal gangue. The effect of CACG content on the mechanical properties of MT was investigated through a series of experiments. It was found that the pozzolanic reactivity of coal gangue was remarkably enhanced by the composite activation method. Compared with traditional tabia (TT), the unconfined compressive strength, splitting strength, and flexural tensile strength of the MT with 50% of CACG content increased by 5.03 times, 9.71 times, and 1.50 times, respectively. The impermeability of specimens with CACG significantly improved. Furthermore, the mass loss rate of MT was less than 2.83%, while it reached up to 34.20% in TT after being conditioned to 40 freeze–thaw cycles. Finally, the microstructure change and hydration mechanism of MT are discussed and revealed.