Search

A flexible or planar eddy current probe with a differential structure can suppress the lift-off noise during the inspection of defects. However, the extent of the lift-off effect on differential probes, including different coil structures, varies. In this study, two planar eddy current probes with differential pickup structures and the same size, Koch and circular probes, were used to compare lift-off effects. The eddy current distributions of the probes perturbed by 0° and 90° cracks were obtained by finite element analysis. The analysis results show that the 90° crack can impede the eddy current induced by the Koch probe even further at relatively low lift-off distance. The peak-to-peak values of the signal output from the two probes were compared at different lift-off distances using finite element analysis and experimental methods. In addition, the effects of different frequencies on the lift-off were studied experimentally. The results show that the signal peak-to-peak value of the Koch probe for the inspection of cracks in 90° orientation is larger than that of the circular probe when the lift-off distance is smaller than 1.2 mm. In addition, the influence of the lift-off distance on the peak-to-peak signal value of the two probes was studied via normalization. This indicates that the influence becomes more evident with an increase in excitation frequency. This research discloses the lift-off effect of differential planar eddy current probes with different coil shapes and proves the detection merit of the Koch probe for 90° cracks at low lift-off distances. [ABSTRACT FROM AUTHOR]

The complexity of urban scenes presents a challenge for semantic segmentation models. Existing models are constrained by factors such as the scale, color, and shape of urban objects, which limit their ability to achieve more accurate segmentation results. To address these limitations, this paper proposes a novel Multi-Scale Feature Shuffle NetWork (MFSNet), which is an improvement upon the existing Deeplabv3+ model. Specifically, MFSNet integrates a novel Pyramid Shuffle Module (PSM) to extract discriminative features and feature correlations, with the objective of improving the accuracy of classifying insignificant objects. Additionally, we propose an efficient feature aggregation module (EFAM) to effectively expand the receptive field and aggregate contextual information, which is integrated as a branch within the network architecture to mitigate the information loss resulting from downsampling operations. Moreover, in order to augment the precision of segmentation boundary delineation and object localization, we employ a progressive upsampling strategy for reinstating spatial information in the feature maps. The experimental results show that the proposed model achieves competitive performance, achieving 80.4% MIoU on the Pascal VOC 2012 dataset, 79.4% MIoU on the Cityscapes dataset, and 40.1% MIoU on the Coco-Stuff dataset. [ABSTRACT FROM AUTHOR]

Object detection methods based on deep learning typically require devices with ample computing capabilities, which limits their deployment in restricted environments such as those with embedded devices. To address this challenge, we propose Mini-YOLOv4, a lightweight real-time object detection network that achieves an excellent trade-off between speed and accuracy. Based on CSPDarknet-Tiny as the backbone network, we enhance the detection performance of the network in three ways. We use a multibranch structure embedded in an attention module for simultaneous spatial and channel attention calibration. We design a group self-attention block with a symmetric structure consisting of a pair of complementary self-attention modules to mine contextual information, thereby ensuring that the detection accuracy is improved without increasing the computational cost. Finally, we introduce a hierarchical feature pyramid network to fully exploit multiscale feature maps and promote the extraction of fine-grained features. The experimental results demonstrate that Mini-YOLOv4 requires only 4.7 M parameters and has a billion floating point operations (BFLOPs) value of 3.1. Compared with YOLOv4-Tiny, our approach achieves a 3.2% improvement in mean accuracy precision (mAP) for the PASCAL VOC dataset and obtains a significant improvement of 3.5% in overall detection accuracy for the MS COCO dataset. In testing with an embedded platform, Mini-YOLOv4 achieves a real-time detection speed of 25.6 FPS on the NVIDIA Jetson Nano, thus meeting the demand for real-time detection in computationally limited devices. [ABSTRACT FROM AUTHOR]