19 March 2019 in IEEE Access
The technology used to locate the sources of shallow underground seismic activity is mainly used to assess underground damage, the positioning of bombs in ordnance test fields, and the positioning of charges in engineering blasting. Due to sensor acquisition clock errors and the lack of generalizability of vibration data, the current sourced location methods cannot easily meet the requirements of precise positioning and system reaction time in assessing near-field microseismic activity. Based on the seismic wave analysis technique and the deep reinforcement learning method, this paper proposes a dynamic model for locating shallow underground seismic sources. The model allows the generalization of low-dimensional vibration waves information to high dimensions through spatial scanning. The process of source detection is treated as a Markov process. The correspondence between the center of a source and a high-dimensional energy distribution is established, and training is then gradually performed using the deep reinforcement learning method. The optimization of the center of the source to accurately determine the position of the focal center is provisionally called the reinforcement learning source scanning algorithm (RL-SSA). In addition, a small site-based static explosion test shows that the positioning method can greatly improve the positioning accuracy (<;1 m) in the location of near-field microseismic sources.
22 October 2025 in Optics Express
Multi-view X-ray imaging systems extend the imaging field of view by integrating multiple imaging modules. Nevertheless, inter-module performance variations in detector arrays, gain drift, and angle-dependent effects cause cross-view grayscale inconsistencies, which degrade overall imaging quality. While existing X-ray imaging approaches primarily rely on single-view flat-field correction or per-projection normalization, these strategies remain inadequate for achieving global consistency across views. To overcome this limitation, this study proposes a physics-constrained multi-view image correction (PCMIC) method. By constructing a globally shared attenuation field to model view-specific nonlinear responses and incorporating boundary anchoring together with monotonicity constraints, the method ensures strong physical fidelity. Experiments conducted on a self-developed large-field, high-resolution micro-CT system demonstrate that PCMIC effectively suppresses stitching artifacts and improves grayscale consistency, structural fidelity, and quantitative stability.
18 February 2022 in Applied Optics
Convolutional neural networks have achieved remarkable results in the detection of X-ray luggage contraband. However, with an increase in contraband classes and substantial artificial transformation, the offline network training method has been unable to accurately detect the rapidly growing new classes of contraband. The current model cannot incrementally learn the newly appearing classes in real time without retraining the model. When the quantity of different types of contraband is not evenly distributed in the real-time detection process, the convolution neural network that is optimized by the gradient descent method will produce catastrophic forgetting, which means learning new knowledge and forgetting old knowledge, and the detection effect on the old classes will suddenly decline. To overcome this problem, this paper proposes an incremental learning method for online continuous learning of models and incrementally learns and detects new classes in the absence of old classes in the new classes. First, we perform parameter compression on the original network by distillation to ensure stable identification of the old classes. Second, the area proposal subnetwork and object detection subnetwork are incrementally learned to obtain the recognition ability of the new classes. In addition, this paper designs a new loss function, which causes the network to avoid catastrophic forgetting and stably detect the object of the new contraband classes. To reliably verify the model, this paper produces a multi-angle dataset for security perspective images. A total of 10 classes of contraband are tested, and the interference between two object detections is analyzed by model parameters. The experimental results show that the model can stably perform new contraband object learning even when there is an uneven distribution of data types.
13 November 2019 in IEEE Access
As supervised person re-identification (Re-Id) requires massive labeled pedestrian data and it is very difficult to collect sufficient labeled data in reality, unsupervised Re-Id approaches attract much more attention than the former. Existing unsupervised person Re-Id models learn global features of pedestrian from whole images or several constant patches. These models ignore the difference of each region in the whole pedestrian images for feature representation, such as occluded and pose invariant regions, and thus reduce the robustness of models for cross-view feature learning. To solve these issues, we propose an Unsupervised Region Attention Network (URAN) that can learn the cross-view region attention features from the cropped pedestrian images, fixed by region importance weights on images. The proposed URAN designs a Pedestrian Region Biased Enhance (PRBE) loss to produce high attention weights for most important regions in pedestrian images. Furthermore, the URAN employs a first neighbor relation grouping algorithm and a First Neighbor Relation Constraint (FNRC) loss to provide the training direction of the unsupervised region attention network, such that the region attention features are discriminant enough for unsupervised person Re-Id task. In experiments, we consider two popular datasets, Market1501 and DukeMTMC-reID, as evaluation of PRBE and FNRC loss, and their balance parameter to demonstrate the effectiveness and efficiency of the proposed URAN, and the experimental results show that the URAN provides better performance than the-state-of-the-arts (higher than existing methods at least 1.1%).