Automatic Extraction of Damaged Houses by Earthquake Based on Improved YOLOv5: A Case Study in Yangbi

Efficiently and automatically acquiring information on earthquake damage through remote sensing has posed great challenges because the classical methods of detecting houses damaged by destructive earthquakes are often both time consuming and low in accuracy. A series of deep-learning-based techniques have been developed and recent studies have demonstrated their high intelligence for automatic target extraction for natural and remote sensing images. For the detection of small artificial targets, current studies show that You Only Look Once (YOLO) has a good performance in aerial and Unmanned Aerial Vehicle (UAV) images. However, less work has been conducted on the extraction of damaged houses. In this study, we propose a YOLOv5s-ViT-BiFPN-based neural network for the detection of rural houses. Specifically, to enhance the feature information of damaged houses from the global information of the feature map, we introduce the Vision Transformer into the feature extraction network. Furthermore, regarding the scale differences for damaged houses in UAV images due to the changes in flying height, we apply the Bi-Directional Feature Pyramid Network (BiFPN) for multi-scale feature fusion to aggregate features with different resolutions and test the model. We took the 2021 Yangbi earthquake with a surface wave magnitude (Ms) of 6.4 in Yunan, China, as an example; the results show that the proposed model presents a better performance, with the average precision (AP) being increased by 9.31% and 1.23% compared to YOLOv3 and YOLOv5s, respectively, and a detection speed of 80 FPS, which is 2.96 times faster than YOLOv3. In addition, the transferability test for five other areas showed that the average accuracy was 91.23% and the total processing time was 4 min, while 100 min were needed for professional visual interpreters. The experimental results demonstrate that the YOLOv5s-ViT-BiFPN model can automatically detect damaged rural houses due to destructive earthquakes in UAV images with a good performance in terms of accuracy and timeliness, as well as being robust and transferable.

Adaptive Feature Pyramid Network to Predict Crisp Boundaries via NMS Layer and ODS F-Measure Loss Function

Edge detection is one of the fundamental computer vision tasks. Recent methods for edge detection based on a convolutional neural network (CNN) typically employ the weighted cross-entropy loss. Their predicted results being thick and needing post-processing before calculating the optimal dataset scale (ODS) F-measure for evaluation. To achieve end-to-end training, we propose a non-maximum suppression layer (NMS) to obtain sharp boundaries without the need for post-processing. The ODS F-measure can be calculated based on these sharp boundaries. So, the ODS F-measure loss function is proposed to train the network. Besides, we propose an adaptive multi-level feature pyramid network (AFPN) to better fuse different levels of features. Furthermore, to enrich multi-scale features learned by AFPN, we introduce a pyramid context module (PCM) that includes dilated convolution to extract multi-scale features. Experimental results indicate that the proposed AFPN achieves state-of-the-art performance on the BSDS500 dataset (ODS F-score of 0.837) and the NYUDv2 dataset (ODS F-score of 0.780).

Multiscale U-Net with Spatial Positional Attention for Retinal Vessel Segmentation

Retinal vessel segmentation is essential for the detection and diagnosis of eye diseases. However, it is difficult to accurately identify the vessel boundary due to the large variations of scale in the retinal vessels and the low contrast between the vessel and the background. Deep learning has a good effect on retinal vessel segmentation since it can capture representative and distinguishing features for retinal vessels. An improved U-Net algorithm for retinal vessel segmentation is proposed in this paper. To better identify vessel boundaries, the traditional convolutional operation CNN is replaced by a global convolutional network and boundary refinement in the coding part. To better divide the blood vessel and background, the improved position attention module and channel attention module are introduced in the jumping connection part. Multiscale input and multiscale dense feature pyramid cascade modules are used to better obtain feature information. In the decoding part, convolutional long and short memory networks and deep dilated convolution are used to extract features. In public datasets, DRIVE and CHASE_DB1, the accuracy reached 96.99% and 97.51%. The average performance of the proposed algorithm is better than that of existing algorithms.

Detection of Aerobics Action Based on Convolutional Neural Network

To further improve the accuracy of aerobics action detection, a method of aerobics action detection based on improving multiscale characteristics is proposed. In this method, based on faster R-CNN and aiming at the problems existing in faster R-CNN, the feature pyramid network (FPN) is used to extract aerobics action image features. So, the low-level semantic information in the images can be extracted, and it can be converted into high-resolution deep-level semantic information. Finally, the target detector is constructed by the above-extracted anchor points so as to realize the detection of aerobics action. The results show that the loss function of the neural network is reduced to 0.2 by using the proposed method, and the accuracy of the proposed method can reach 96.5% compared with other methods, which proves the feasibility of this study.

A New Multiface Target Detection Algorithm for Students in Class Based on Bayesian Optimized YOLOv3 Model

Deep learning theory is widely used in face recognition. Combined with the needs of classroom attendance and students’ learning status monitoring, this article analyzes the YOLO (You Only Look Once) face recognition algorithms based on regression method. Aiming at the problem of small target missing detection in the YOLOv3 network structure, an improved YOLOv3 algorithm based on Bayesian optimization is proposed. The algorithm uses deep separable convolution instead of conventional convolution to improve the Darknet-53 basic network, and it reduces the amount of calculation and parameters of the network. A multiscale feature pyramid is built, and an attention guidance module is designed to strengthen multiscale fusion, detecting different sizes of targets. The loss function is improved to solve the imbalance of positive and negative sample distribution and the imbalance between simple samples and difficult samples. The Bayesian function is adopted to optimize the classifier and improve the classification efficiency and accuracy, ensuring the accuracy of small target detection. Five groups of comparative experiments are carried out on public COCO and VOC2012 datasets and self-built datasets. The experimental results show that the proposed improved YOLOv3 model can effectively improve the detection accuracy of multiple faces and small targets. Compared with the traditional YOLOv3 model, the mean mAP of the target is improved by more than 1.2%.

Multi scale switchable atrous convolution for target detection based on feature pyramid

Repeated observation mechanism can effectively solve the problem of low efficiency of feature extraction. By extracting features for many times to strengthen target features, this paper proposed a multi-scale switchable atrous convolution based on feature pyramid, SPC. The head of the detector adopted pyramid convolution mode, constructs 3-D convolution in the feature pyramid, and detected the same target in different pyramid levels by using the shared convolution with different stride changes, which realized the repeated observation of target features on multi-scale. The module optimized the convolution layer, extracted the features of the same image by convolution check of different sizes, and then selected and integrated the extracted results by using switch function, which effectively expanded the field of view of convolution kernel. In this paper, we choosed retinanet as the baseline network, and improved the loss function of focal loss proposed by retinanet to further solved the problem of unbalanced number of samples and sample distribution in the network model. The proposed method performed well on MS coco data set, improved the average accuracy of 9.8% on the basis of retinanet to 48.9%, and achieved FPS of 5.1 in 1333 * 800 images.