Search

The channel attention mechanism is widely used in deep learning. However, the existing channel attention mechanism directly performs the global average pooling and then full connection for all channels, which causes the local information to be ignored and the feature information cannot be reasonably assigned with the proper weights. This paper proposed a local channel attention module, based on the channel attention. This module focuses on the local information of the feature image, obtains the weight of each regional channel through convolution, and then integrates the information, so that the regional information can be fully utilized. Moreover, the local channel attention module is combined with the residual module, and the local channel attention residual network LSERNet is constructed to detect the abnormal state of the blast furnace tuyere image. With sufficient experiments on the collected datasets of the blast furnace tuyere, the results show that the proposed method can efficiently extract the feature information, and the recognition accuracy of the LSERNet model reached 98.59%. Further, our model achieved the highest accuracy, compared with SE-ResNet50, ResNet50, LSE-ResNeXt, SE-ResNeXt, and ResNeXt models. [ABSTRACT FROM AUTHOR]

There are challenges exist in the segmentation of smoke contours on images currently, the requirements for limited processing resources and low-latency operations based on monitoring platform, and the balance between high accuracy and real-time efficiency of the model performance. Also, smoke always shows to be translucency, resulting in a highly complex mixture of the background and itself, sparse or small smoke is not visually obvious, and its borders are often blurred. Therefore, the task of separating smoke from a single image is challengeable. To overcome the challenges, a dual-path real-time smoke segmentation network based on BiSeNet is adopted in this research, and a PPM to expand the receptive field in the spatial path is added to improve the ability to obtain global information. At the same time, a lightweight ECA channel attention module, included in a context path with fast down-sampling strategy, could reduce the complexity while ensuring the effect of the model. Experimental results show that, on all the self-built dataset, the public synthetic smoke dataset and public videos, the proposed method shows excellent performance, and the detection speed reaches real-time segmentation level, showing high practical value. [ABSTRACT FROM AUTHOR]

The role of the stock market across the overall financial market is indispensable. The way to acquire practical trading signals in the transaction process to maximize the benefits is a problem that has been studied for a long time. This paper put forward a theory of deep reinforcement learning in the stock trading decisions and stock price prediction, the reliability and availability of the model are proved by experimental data, and the model is compared with the traditional model to prove its advantages. From the point of view of stock market forecasting and intelligent decision-making mechanism, this paper proves the feasibility of deep reinforcement learning in financial markets and the credibility and advantages of strategic decision-making. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have been successfully applied on no-reference image quality assessment (NR-IQA) with respect to human perception. Most of these methods deal with small image patches and use the average score of the test patches for predicting the whole image quality. We discovered that image patches from homogenous regions are unreliable for both neural network training and final image quality score estimation. In addition, image patches with complex structures have much higher chances of achieving better image quality prediction. Based on these findings, we enhanced the conventional CNN-based NR-IQA algorithm to avoid homogenous patches for the network training and quality score estimation. Moreover, we also use a variance-based weighting average to bias the final image quality score to the patches with complex structure. The experimental results show that this simple approach can achieve state-of-the-art performance compared with well-known NR-IQA algorithms. [ABSTRACT FROM AUTHOR]

Detection transformer (DETR) combines convolutional neural network (CNN) with transformer, providing a more advanced idea. In this paper, an object detection model based on DETR is proposed for fire and smoke detection. Compared with other methods that based on deep learning, the proposed one simplifies the pipeline of detection and builds an end-to-end detector. At the same time, the original DETR model usually requires long training time and large amount of computation, resulting in relatively poor performance in detection speed and accuracy, and it shows to be not friendly for small or early fire detection. Therefore, when designing the proposed network model, a normalization-based attention module is added in the feature extraction stage to highlight the effective features, being beneficial to the process of encoding. A multiscale deformable attention is also used in the encoder–decoder structure, accelerating therefore, the process of convergence during the training of the model, which includes the enhancement of the detection of small objects. Also, considering the cost of computation, the number of layers in the encoder–decoder structure is redefined to reduce the complexity of the model, and that also reduces the requirements of the application equipment. Detailed experiments are conducted on three self-built datasets and two public video sets. The results show that, the proposed method has an excellent performance on all of the datasets considered here. [ABSTRACT FROM AUTHOR]

• Cope with the challenging issue of pedestrian detection at nighttime. • Introduce a dual attention module to acquire more semantic information. • A new loss function is developed for adapting the small objects detection. • MAF-YOLO achieves the state-of-the-art performance on object detection tasks. Achieving the rapid and precise detection of pedestrians in natural environments is crucial for many applications of artificial intelligence systems. However, accurate pedestrian detection at nighttime is challenging due to the low-luminous density and low-resolution of infrared images, and the detection speed is required. In this paper, a real-time pedestrian detection method using a novel multi-modal attention fusion YOLO (MAF-YOLO) was proposed. Firstly, a multi-modal feature extraction module based on the compressed Darknet53 framework was built to adapt the nighttime pedestrian detection and ensure efficiency. The features were extracted from both modalities and then fused by a modal weighted fusion module. Secondly, we defined a loss function and regenerated the size of the anchor box based on the K-means clustering algorithm to improve the detection speed and the robustness of small objects. Finally, a dual attention module was applied to acquire more semantic features from small objects with low-resolution. The experimental results on KAIST and OSU Color-Thermal datasets corroborated the effectiveness of the proposed MAF-YOLO. The proposed methods could also be utilized to facilitate the performance of other pedestrian detection algorithms. [ABSTRACT FROM AUTHOR]