To aid the diagnosis of chronic obstructive pulmonary disease (COPD), a local-to-global deep framework with group attentions and slice-aware loss is designed in this paper, which utilizes the chest CT sequences of the patients as the network input. To fully mine the medical hints submerged in the CT slices, two types of group attentions are designed to extract local–global features of the grouped slices. Specifically, in each group, a group local attention block (GLAB) and a group global attention block (GGAB) are designed to extract local features in the CT slices and long-range dependencies among the grouped slices. To alleviate the influence of different numbers of CT slices in the chest CT sequences for different patients, a slice-aware loss is proposed by incorporating a normalized coefficient into the cross-entropy loss. Experimental results indicate that the designed deep model performs a good COPD identification on a real COPD dataset with 96.08% accuracy, 94.12% sensitivity, 97.06% specificity, and 95.32% AUC, which is superior to some existing deep learning methods.

To automatically measure the surface profile of a cylindrical workpiece, a high-precision multi-beam optical method is proposed in this paper. First, some successive images for the cylindrical workpiece’s surface are acquired by a multi-beam angle sensor under different light directions. Then, the light directions are estimated based on the feature regions in the images to calculate surface normal vectors. Finally, according to the relationship of the surface normal vector and the vertical section of the workpiece’s surface, a depth map is reconstructed to achieve the curvature surface, which can be employed to measure the curvature radius of the cylindrical workpiece’s surface. Experimental results indicate that the proposed measurement method can achieve good measurement precision with a mean error of the curvature radius of a workpiece’s surface of 0.89% at a reasonable speed of 10.226 s, which is superior to some existing methods.

Infrared tiny target detection is faced with difficulty that tiny-sized targets are easily drowned out in complex backgrounds. To address this problem, this paper presents an end-to-end deep learning framework, which consists of an anchor-free U-shaped backbone for extracting image features and a detection head block for target attributes regression. To capture fine-grained details and semantic information, a multi-hop and multiscale fusion block is designed in the backbone for effective progressive feature fusion. Moreover, to adaptively adjust the constraints for the localization and shape description of the targets, a tolerance-adjustable measure is proposed in the detection head to provide a reliable means for determining the authenticity of targets. Extensive experiments indicate that our trained model can simultaneously detect infrared targets with various sizes, especially achieve an excellent detection performance for point targets with 98.2% F1-score, 3.1% error rate and 0.5% omission rate. Comparative experiments indicate that the proposed method is superior to SOTA deep learning based methods, especially for tiny targets.