Multimodal false information detection method based on Text-CNN and SE module.

False information detection can detect false information in social media and reduce its negative impact on society. With the development of multimedia, the multimodal content contained in false information is increasing, so it is important to use multimodal features to detect false information. This paper mainly uses information from two modalities, text and image. The features extracted by the backbone network are not further processed in the previous work, and the problems of noise and information loss in the process of fusing multimodal features are ignored. This paper proposes a false information detection method based on Text-CNN and SE modules. We use Text-CNN to process the text and image features extracted by BERT and Swin-transformer to enhance the quality of the features. In addition, we use the modified SE module to fuse text and image features and reduce the noise in the fusion process. Meanwhile, we draw on the idea of residual networks to reduce information loss in the fusion process by concatenating the original features with the fused features. Our model improves accuracy by 6.5% and 2.0% on the Weibo dataset and Twitter dataset compared to the attention based multimodal factorized bilinear pooling. The comparative experimental results show that the proposed model can improve the accuracy of false information detection. The results of ablation experiments further demonstrate the effectiveness of each module in our model.

Scene Text Detection Based on Two-Branch Feature Extraction.

Scene text detection refers to locating text regions in a scene image and marking them out with text boxes. With the rapid development of the mobile Internet and the increasing popularity of mobile terminal devices such as smartphones, the research on scene text detection technology has been highly valued and widely applied. In recent years, with the rise of deep learning represented by convolutional neural networks, research on scene text detection has made new developments. However, scene text detection is still a very challenging task due to the following two factors. Firstly, images in natural scenes often have complex backgrounds, which can easily interfere with the detection process. Secondly, the text in natural scenes is very diverse, with horizontal, skewed, straight, and curved text, all of which may be present in the same scene. As convolutional neural networks extract features, the convolutional layer with limited perceptual field cannot model the global semantic information well. Therefore, this paper further proposes a scene text detection algorithm based on dual-branch feature extraction. This paper enlarges the receptive field by means of a residual correction branch (RCB), to obtain contextual information with a larger receptive field. At the same time, in order to improve the efficiency of using the features, a two-branch attentional feature fusion (TB-AFF) module is proposed based on FPN, to combine global and local attention to pinpoint text regions, enhance the sensitivity of the network to text regions, and accurately detect the text location in natural scenes. In this paper, several sets of comparative experiments were conducted and compared with the current mainstream text detection methods, all of which achieved better results, thus verifying the effectiveness of the improved proposed method.

AAF-Net: Scene text detection based on attention aggregation features.

With the advent of the era of artificial intelligence, text detection is widely used in the real world. In text detection, due to the limitation of the receptive field of the neural network, most existing scene text detection methods cannot accurately detect small target text instances in any direction, and the detection rate of mutually adhering text instances is low, which is prone to false detection. To tackle such difficulties, in this paper, we propose a new feature pyramid network for scene text detection, Cross-Scale Attention Aggregation Feature Pyramid Network (CSAA-FPN). Specifically, we use a Attention Aggregation Feature Module (AAFM) to enhance features, which not only solves the problem of weak features and small receptive fields extracted by lightweight networks but also better handles multi-scale information and accurately separate adjacent text instances. An attention module CBAM is introduced to focus on effective information so that the output feature layer has richer and more accurate information. Furthermore, we design an Adaptive Fusion Module (AFM), which weights the output features and pays attention to the pixel information to further refine the features. Experiments conducted on CTW1500, Total-Text, ICDAR2015, and MSRA-TD500 have demonstrated the superiority of this model.

ARDformer: Agroforestry Road Detection for Autonomous Driving Using Hierarchical Transformer.

Road detection is a crucial part of the autonomous driving system, and semantic segmentation is used as the default method for this kind of task. However, the descriptive categories of agroforestry are not directly definable and constrain the semantic segmentation-based method for road detection. This paper proposes a novel road detection approach to overcome the problem mentioned above. Specifically, a novel two-stage method for road detection in an agroforestry environment, namely ARDformer. First, a transformer-based hierarchical feature aggregation network is used for semantic segmentation. After the segmentation network generates the scene mask, the edge extraction algorithm extracts the trail's edge. It then calculates the periphery of the trail to surround the area where the trail and grass are located. The proposed method is tested on the public agroforestry dataset, and experimental results show that the intersection over union is approximately 0.82, which significantly outperforms the baseline. Moreover, ARDformer is also effective in a real agroforestry environment.

Detection of Pine Wilt Nematode from Drone Images Using UAV.

Pine wilt nematode disease is a devastating forest disease that spreads rapidly. Using drone remote sensing to monitor pine wilt nematode trees promptly is an effective way to control the spread of pine wilt nematode disease. In this study, the YOLOv4 algorithm was used to automatically identify abnormally discolored wilt from pine wilt nematode disease on UAV remote sensing images. Because the network structure of YOLOv4 is too complex, although the detection accuracy is high, the detection speed is relatively low. To solve this problem, the lightweight deep learning network MobileNetv2 is used to optimize the backbone feature extraction network. Furthermore, the YOLOv4 algorithm was improved by improving the backbone network part, adding CBAM attention, and adding the Inceptionv2 structure to reduce the number of model parameters and improve the accuracy and efficiency of identification. The speed and accuracy of the Faster R-CNN, YOLOv4, SSD, YOLOv5, and the improved MobileNetv2-YOLOv4 algorithm were compared, and the detection effects of the Faster R-CNN, YOLOv4, SSD, YOLOv5 and the improved MobileNetv2-YOLOv4 algorithm on trees with pine wilt nematode were analyzed. The experimental results show that the average precision of the improved MobileNetv2-YOLOv4 algorithm is 86.85%, the training time of each iteration cycle is 156 s, the parameter size is 39.23 MB, and the test time of a single image is 15 ms, which is better than Faster R-CNN, YOLOv4, and SSD, but comparable to YOLOv5. Compared with the advantages and disadvantages, comprehensively comparing these four indicators, the improved algorithm has a more balanced performance in the detection speed, the parameter size, and the average precision. The F1 score of the improved algorithm (95.60%) was higher than that of Faster R-CNN (90.80%), YOLOv4 (94.56%), and SSD (92.14%), which met the monitoring requirements of pine wilt nematode trees. Faster R-CNN and SSD pine-wilt-nematode tree detection models are not ideal in practical applications. Compared with the YOLOv4 pine-wilt-nematode tree detection model, the improved MobileNetv2-YOLOv4 algorithm satisfies the condition of maintaining a lower model parameter quantity to obtain higher detection accuracy; therefore, it is more suitable for practical application scenarios of embedded devices. It can be used for the rapid detection of pine wilt nematode diseased trees.

Infrared Small Target Detection Using Regional Feature Difference of Patch Image.

Aiming at a thorny issue, that conventional small target detection algorithm using local contrast method is not sensitive for residual background clutter, robustness of algorithms is not strong. A Gaussian fusion algorithm using multi-scale regional patch structure difference and Regional Brightness Level Measurement is proposed. Firstly, Regional Energy Cosine (REC) is constructed to measure the structural discrepancy among a small target with neighboring cells. At the same time, Regional Brightness Level Measurement (RBLM) is constructed utilizing the brightness difference characteristics between small target and background areas. Then, a brand new Gaussian fusion algorithm is proposed for the generated saliency map in multi-scale space to characterize the overall heterogeneity in original infrared small target and local neighborhood. Finally, a self-adapting separation algorithm is adopted with the objective to obtain a small target from background interference. This method is able to utmostly restrain background interference and enhance the target. Extensive qualitative and quantitative testing results display that the desired algorithm has remarkable performance in strengthening target region and restraining background interference compared with current algorithms.

MR-FPN: Multi-Level Residual Feature Pyramid Text Detection Network Based on Self-Attention Environment.

With humanity entering the age of intelligence, text detection technology has been gradually applied in the industry. However, text detection in a complex background is still a challenging problem for researchers to overcome. Most of the current algorithms are not robust enough to locate text regions, and the problem of the misdetection of adjacent text instances still exists. In order to solve the above problems, this paper proposes a multi-level residual feature pyramid network (MR-FPN) based on a self-attention environment, which can accurately separate adjacent text instances. Specifically, the framework uses ResNet50 as the backbone network, which is improved on the feature pyramid network (FPN). A self-attention module (SAM) is introduced to capture pixel-level relations, increase context connection, and obtain efficient features. At the same time, the multi-scale enhancement module (MEM) improves the expression ability of text information, extracting strong semantic information and integrating the multi-scale features generated by the feature pyramid. In addition, information regarding the upper features will cause loss when the feature pyramid is passed down step by step, and multi-level residuals can effectively solve this problem. The proposed model can effectively improve the fusion ability of the feature pyramid, provide more refined features for text detection, and improve the robustness of text detection. This model was evaluated on CTW1500, Total-Text, ICDAR2015, and MSRA-TD500 datasets of different kinds and achieved varying degrees of improvement. It is worth mentioning that the F-measure of 83.31% obtained by this paper on the Total-Text dataset exceeds that of the baseline system by 5%.

Multi-Feature Single Target Robust Tracking Fused with Particle Filter.

Aiming at the problems of target model drift or loss of target tracking caused by serious deformation, occlusion, fast motion, and out of view of the target in long-term moving target tracking in complex scenes, this paper presents a robust multi-feature single-target tracking algorithm based on a particle filter. The algorithm is based on the correlation filtering framework. First, to extract more accurate target appearance features, in addition to the manual features histogram of oriented gradient features and color histogram features, the depth features from the conv3-4, conv4-4 and conv5-4 convolutional layer outputs in VGGNet-19 are also fused. Secondly, this paper designs a re-detection module of a fusion particle filter for the problem of how to return to accurate tracking after the target tracking fails, so that the algorithm in this paper can maintain high robustness during long-term tracking. Finally, in the adaptive model update stage, the adaptive learning rate update and adaptive filter update are performed to improve the accuracy of target tracking. Extensive experiments are conducted on dataset OTB-2015, dataset OTB-2013, and dataset UAV123. The experimental results show that the proposed multi-feature single-target robust tracking algorithm with fused particle filtering can effectively solve the long-time target tracking problem in complex scenes, while showing more stable and accurate tracking performance.