Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. To recover such an image, a dehazing algorithm should enhance the feature in...
Presence of haze in images obscures underlying information, which is undesirable in applications requiring accurate environment information. To recover such an image, a dehazing algorithm should enhance the feature information of the background while weakening the feature information of haze. In this paper, we propose an end-to-end attention-based feature enhanced dehazing network (AEDNet), which integrates enhancement strategy and attention mechanism, to achieve haze removal. The network is based on U-Net, which has the advantages of retaining information, obtaining multi-scale features and so on. In the training of the network, pixel loss and perceptual loss are used to preserve feature information and improve the overall quality of results. The extensive evaluation shows that the proposed model performs significantly better than previous dehazing methods on various benchmarks.
The application of the combination of unmanned aerial vehicles (UAVs) and artificial intelligence is a hot topic in the intelligent inspection of substations, and meter reading is a very challenging task. This paper p...
详细信息
The application of the combination of unmanned aerial vehicles (UAVs) and artificial intelligence is a hot topic in the intelligent inspection of substations, and meter reading is a very challenging task. This paper proposes a method based on the combination of YOLOv6n object detection and Deeplabv3 + image segmentation and performs post-processing on the segmented images to obtain meter readings. First, YOLOv6n is used to detect the meter area of the aerial image and classify the meters. Second, the detected meter images are fed into the image segmentation model. The backbone network of the Deeplabv3 + algorithm is improved by using the MobileNetv3 network, which not only effectively extracts pointers and scales, but also makes the model more lightweight. Third, License Plate Recognition Network (LPRNet) is used to recognize digital meter images. In order to solve the problem of inaccurate pointer meter readings, to begin with, the segmented image is corroded; in addition, the circular dial area is flattened into a rectangular area by concentric circle sampling method. Finally, the meter reading is calculated by the position of the pointer, the scale and the total range of the meter. The post-processing part uses numba to optimize the inference speed. The experimental results show that in two datasets, The mean average precision of 50 (mAP50) accuracy of the YOLOv6n model using this method reached 99.71% and 98.60%, respectively, and the inference speed of a single image was 17.1 ms and 13.2 ms, respectively. The mean intersection over union (mIoU) of the image segmentation model reached 82.00%, 74.73%, 73.50%, 82.26% and 73.20%, respectively, and the single segmentation speed reached 33.7 ms. The LPRNet model has a recognition accuracy of 99.17% and a single image inference speed of 14.7 ms. At the same time, several mainstream object detection and semantic segmentation algorithms are compared. The experimental results show that the method in this paper greatly im
Medical image segmentation has always been a challenging task. This paper proposes a new LUneXt medical image segmentation model based on the characteristics analysis of medical image data sets and testing of differen...
详细信息
Medical image segmentation has always been a challenging task. This paper proposes a new LUneXt medical image segmentation model based on the characteristics analysis of medical image data sets and testing of different nonlinear activation units. Both normalized activations for the original negative input image activation have good optimization capabilities for the tokenization module parameters proposed in the original UneXt model. Using different activation coefficients for different foreground and background areas has achieved better results. The experimental results of this paper on the Breast Ultrasound Images (BUSI) data set reached an intersection over union (IoU) value of 62.64%, a Dice value of 76.12%, and a single inference speed of 807.57 ms. The experimental IoU value of the International Skin Imaging Collaboration (ISIC 2018) data set reached 82.95%, and the Dice value reached 90.50%. The single inference speed reached 842.58 ms. The LUneXt model is more robust than other models. While improving model performance, it does not introduce higher computational complexity and does not have a major impact on the processing speed of a single image.
Distraction and overspeed behaviors are acknowledged as two significant contributors to single-vehicle motorcycle crashes, injuries and fatalities resulting from which are severe and critical issues in Pakistan. To ex...
详细信息
Distraction and overspeed behaviors are acknowledged as two significant contributors to single-vehicle motorcycle crashes, injuries and fatalities resulting from which are severe and critical issues in Pakistan. To explore the temporal instability and differences in the factors determining the injury severities between single-vehicle motorcycle crashes caused by distraction and overspeed behaviors, this study estimated two groups of random parameter logit models with heterogeneity in means and variances. Single-vehicle motorcycle crash data in Rawalpindi city between 2017 and 2019 was used for model estimation, and a wide variety of explanatory variables relating to the rider, roadways, environments, and temporal attributes was simulated in the models. The current study considered three possible crash injury severity outcomes: minor injury, severe injury and fatal injury. Likelihood ratio tests were conducted to explore the temporal instability and non-transferability. Marginal effects were also calculated to further reveal temporal instability of the variables. Except for several variables, the most significant factors reported temporal instability and non-transferability, manifested as the effects varied from year to year and across different crashes. Moreover, out-of-sample prediction was also implemented to capture temporal instability and non-transferability between distraction and overspeed crash observations. The non-transferability between motorcycle crashes caused by distraction and overspeed behaviors provides insights into developing differentiated countermeasures and policies targeted at preventing and mitigating single-vehicle motorcycle crashes caused by the two risk-taking behaviors.
暂无评论