Pedestrian trajectory prediction is vital for transportation systems. Generally we can divide pedestrian behavior modeling into two categories, i.e., knowledge-driven and data-driven. The former might bring expert bias, and it sometimes generates unrealistic pedestrian movement due to unnecessary repulsive forces. The latter approach is popular nowadays but most existing neural networks, including fully connected long short-term memory (LSTM) networks, use a 1D vector to model their input and state. The shortcoming is that these works cannot learn spatial information about pedestrians, especially in a dense crowd. To tackle this, we propose to use tensors to represent essential environment features of pedestrians. Accordingly, a convolutional LSTM is designed and deepened to predict spatiotemporal trajectory sequences. As the tensor and convolution can learn better spatiotemporal interactions among pedestrians and environments, experimental results show that the proposed network can estimate more realistic trajectories for a dense crowd in evacuation and counterflow.

High-voltage direct-current (HVdc) transmission lines have been implemented in many countries, including Australia, Brazil, China, and Sweden, and the safety concerns as the result of the high electromagnetic-radiation underneath the HVdc lines have garnered increased public attentions. Here, we report on the model, design, and testing of field-mill electric field sensors to measure the electric field at the ground level under the HVdc transmission lines. This study utilized a finite-element analysis method to establish numerical simulation results based on the electrical and mechanical parameters to achieve optimal designs with experimental calibrations. Afterward, these sensors were successfully tested and utilized at the national high-voltage test base.

Anomaly detection has become one of the crucial tasks in hyperspectral images (HSIs) processing. However, most deep learning-based anomaly detection methods often suffer from the incapability of utilizing spatial-spectral information, which decreases the detection accuracy. To address this problem, we propose a novel hyperspectral anomaly detection method with spatial-spectral dual-window mask transformer, termed as S2DWMTrans, which can fully extract features from global and local perspectives, and suppress the reconstruction of anomaly targets adaptively. Specifically, the dual-window mask transformer (DWMTrans) aggregates background information of the entire image from a global perspective to neutralize anomalies, and uses neighboring pixels in a dual-window to suppress anomaly reconstruction. An adaptive-weighted loss function (AWLF) is designed to further suppress anomaly reconstruction adaptively during network training process. According to our investigation, this is the first work to apply Transformer to hyperspectral anomaly detection. Comparative experiments and ablation studies demonstrate that the proposed S2DWMTrans achieves competitive performance.

Recently, convolutional neural networks (CNN) have been widely used in image denoising. But with most CNN denoising methods, all the channels are treated equally and the relationship between spatial locations are neglected. In the letter, we propose a novel channel and space attention neural network (CSANN) for image denoising. In CSANN, we concatenate the noise level with the average and maximum values of each channel as the input and propose a convolutional network to learn the relationship between channels. Meanwhile, we combine the noise level map with the average and maximum values of each spatial locations as the input and use a convolutional network to learn the relationship between spatial locations. Moreover, we combine them as an attention network and introduce it into the main CNN and symmetric skip connections, which makes channels related to attention network play different roles in the subsequent convolution and offsets the performance degradation caused by using a single convolution kernel in spatial locations. In addition, the use of symmetric skip connections and resnet blocks avoid the vanishing gradient problem and the loss of shallow features. Experimental results show that, compared with some state-of-the-art denoising algorithms, the experimental results of CSANN have better visual effects and higher peak signal-to-noise ratio (PSNR) values.

Recently, deep neural networks (DNNs) have been widely used in hyperspectral image change detection (HSI-CD). Generally, training such a DNNs-based HSI-CD network often requires a large number of labeled training samples. However, it is time-consuming, labor-intensive, or even infeasible to label training samples in practice. In this paper, we propose a feature mutual representation based graph domain adaptive network (FGDANet) for unsupervised HSI-CD. This method constructs a pseudo-siamese backbone consisting of two customized unsupervised learning domains, which can make full use of the information from different domains through the graph domain adaptation strategy to improve the feature expression capability and generalization. There are three key characteristics: (i) In each customized unsupervised learning domain, a graph convolutional network (GCN) based difference feature extraction architecture is designed to model the local and global dependency among the features of multi-temporal HSIs; (ii) A progressive graph-to-pixel joint constraints strategy (PJCS) is proposed to provide the high-confidence training sample labels for the unsupervised learning of the network in each domain; (iii) The homogeneous mutual representation joint graph feature alignment (HJGFA) module of the graph domain adaptation strategy can make full use of the difference features from the two domains through the information interaction to facilitate the model to capture the changed and unchanged essential characteristics. The experimental results on four HSI datasets demonstrate the superiority of the proposed FGDANet. Code is available at https://github.com/Jiahuiqu/FGDANet.