In the manufacturing process of industrial robots, the defect detection of raw materials includes two types of tasks, which makes the defect detection guarantee its accuracy. It also makes the defect detection task challenging in practical work. In analyzing the disadvantages of the existing defect detection task methods, such as low precision and low generalization ability, a detection method on the basis of attention mechanism and dilated convolution module is proposed. In order to effectively extract features, a two-stage detection framework is chosen by applying Resnet50 as the pre-training network of our model. With this foundation, the attention mechanism and dilated convolution are utilized. With the attention mechanism, the network can focus on the features of effective regions and suppress the invalid regions during detection. With dilated convolution, the receptive field of the model can be increased without increasing the calculation amount of the model. As a result, it can achieve a larger receptive field, which will obtain more dense data and improve the detection effect of small target defects. Finally, great experiments are conducted on the NEU-DET dataset. Compared with the baseline network, the proposed method in this paper achieves 81.79% mAP, which are better results.

Multi-object tracking (MOT) is a topic of great interest in the field of computer vision, which is essential in smart behavior-analysis systems for healthcare, such as human-flow monitoring, crime analysis, and behavior warnings. Most MOT methods achieve stability by combining object-detection and re-identification networks. However, MOT requires high efficiency and accuracy in complex environments with occlusions and interference. This often increases the algorithm’s complexity, affects the speed of tracking calculations, and reduces real-time performance. In this paper, we present an improved MOT method combining an attention mechanism and occlusion sensing as a solution. A convolutional block attention module (CBAM) calculates the weights of space and channel attention from the feature map. The attention weights are used to fuse the feature maps to extract adaptively robust object representations. An occlusion-sensing module detects an object’s occlusion, and the appearance characteristics of an occluded object are not updated. This can enhance the model’s ability to extract object features and improve appearance feature pollution caused by the short-term occlusion of an object. Experiments on public datasets demonstrate the competitive performance of the proposed method compared with the state-of-the-art MOT methods. The experimental results show that our method has powerful data association capability, e.g., 73.2% MOTA and 73.9% IDF1 on the MOT17 dataset.

Visible-infrared person re-identification aims to match pedestrian images between visible and infrared modalities, and its two main challenges are intra-modality differences and cross-modality differences between visible and infrared images. To address these issues, many advanced methods attempt to design new network structures to extract modality-sharing features, mitigate modality differences, or learn part-level features to overcome background interference. However, they ignore the parameter sharing of the convolutional layers to obtain more modality-sharing features. At the same time, only using part-level features lack discriminative pedestrian representations such as body structure and contours. To handle these problems, a parameter sharing and feature learning network is proposed in this paper to mitigate modality differences and further enhance feature discrimination. Firstly, a new two-stream parameter sharing network is proposed, by sharing the convolutional layers parameters to obtain more modality-sharing features. Secondly, a multi-granularity feature learning module is designed to reduce modality differences at both coarse and fine-grained levels while further enhancing feature discriminability. In addition, a center alignment loss is proposed to learn relationships between identities and to reduce modality differences by clustering features into their centers. For the part-level feature learning, the hetero-center triplet loss is adopted to alleviate the strict constraints of triplet loss. Finally, extensive experiments are conducted to validate our method outperforms state-of-the-art methods on two challenging datasets. In the SYSU-MM01 dataset, the Rank-1 and mAP reach $$74.0\%$$74.0 % and $$70.51\%$$70.51 % in the all-search mode, which is an increase of $$3.4\%$$3.4 % and $$3.61\%$$3.61 % to baseline, respectively.

At present, span-based entity recognition methods are mainly used to accurately identify the span (entity) boundary for entity recognition, in which the relative position information of the span boundary and the information of words in the span region are routinely ignored. This information can be used to improve entity recognition performance. Therefore, a nested entity recognition model, which integrates the relative position information of the span and the region information within the span, is proposed. The span representation is first obtained with a triaffine attention. Then, the relative position of the span boundary and the word information in the span region, as well as the previous span representation, are fused to obtain a new label-level span representation with another triaffine attention. Finally, the span (entity) recognition task is carried out by a cooperative biaffine mechanism. Experiments were conducted on some public datasets, including ACE2004, ACE2005 and GENIA. The results show that the F1-scores achieved using the proposed method were 87.66%, 86.86% and 80.90% on ACE2004, ACE2005 and GENIA, respectively. These experiments show that the method achieved state-of-the-art (SOTA) results. Moreover, the proposed model has fewer parameters and needs fewer resources with a lower time complexity than the existing triaffine mechanism model.

The Breast Imaging Reporting and Data System (BI-RADS) lexicon has been developed by the American College of Radiology (ACR) to address a lack of standardization and uniformity in breast radiology reporting. In China, structured reports are not widely used in breast imaging and BI-RADS features are stored in free-text reports. It is time-consuming and error-prone to manually extract BI-RADS features for further analysis from breast mammography reports in Chinese. To develop natural language processing (NLP) methods to extract those BI-RADS features automatically, we developed four different NLP methods, including two conventional machine learning methods and two deep learning methods to extract BI-RADS features from breast mammography reports in Chinese. Traditional machine learning methods include hidden Markov model (HMM) and conditional random field model (CRF). Deep learning methods include bidirectional long short-term memory (LSTM) with CRF only (BiLSTM-CRF) and bidirectional long short-term memory (LSTM) with both CRF and attention mechanism (BiLSTM-CRF-Attention). We compared the performance of four NLP methods in terms of precision, recall, and F1-score, and found that CRF method achieved the best NLP performance. This is the first study that applies machine learning based NLP methods to extract BI-RADS features from mammography reports in Chinese, demonstrating the potential of using these BI-RADS features to assist routine clinical care, quality improvement, and research for breast cancer.

In highway scenarios, the rapid motion of vehicles can cause deformation and blur in camera footage, significantly affecting the accuracy of vehicle detection and re-identification (ReID) in multitarget multicamera tracking (MTMCT) systems. To address this issue, this article develops the deformable and blur sensing and regression analysis ReID feature fusion MTMCT system (DSRF). First, a deformable and blur sensing detection module (DFB) in DSRF is designed to overcome the limitations of cameras in capturing fast-moving objects, thereby accurately detecting vehicles moving at high speeds on highways. Then, a regression-based ReID feature fusion algorithm (RARF) in DSRF is proposed, which enhances ReID features by modeling the relationship between vehicle motion and its features, thereby better associating the detected vehicles in consecutive frames into trajectories and establishing intertrajectory relationships. Finally, extensive experiments are conducted on the highway surveillance traffic (HST) dataset developed by our team and the public dataset (CityFlow). Promising results are achieved, validating the effectiveness of our proposed method.