Many accidents happen under shunting mode when the speed of a train is below 45 km/h. In this mode, train attendants observe the railway condition ahead using the traditional manual method and tell the observation results to the driver in order to avoid danger. To address this problem, an automatic object detection system based on convolutional neural network (CNN) is proposed to detect objects ahead in shunting mode, which is called Feature Fusion Refine neural network (FR-Net). It consists of three connected modules, i.e., the depthwise-pointwise convolution, the coarse detection module, and the object detection module. Depth-wise-pointwise convolutions are used to improve the detection in real time. The coarse detection module coarsely refine the locations and sizes of prior anchors to provide better initialization for the subsequent module and also reduces search space for the classification, whereas the object detection module aims to regress accurate object locations and predict the class labels for the prior anchors. The experimental results on the railway traffic dataset show that FR-Net achieves 0.8953 mAP with 72.3 FPS performance on a machine with a GeForce GTX1080Ti with the input size of 320 × 320 pixels. The results imply that FR-Net takes a good tradeoff both on effectiveness and real time performance. The proposed method can meet the needs of practical application in shunting mode.

No abstract

Pneumonia has become one of the main causes of human death. However, it is a tall order to efficiently and accurately diagnose pneumonia for clinicians.Therefore, A novel method based on anchor-free detection framework is proposed to automatically locate lung opacities on chest radiographs in this study.We conducted extensive sets of experiments on the dataset of the Radiological Society of North America (RSNA) pneumonia detection challenge from the Kaggle competition. The results show superior performances for our method compared with previous studies. The best method achieved 52.9% in average precision (AP) and 97.5% in average recall (AR). For better interpretability of the results, visualization techniques are applied to provide visual explanations for our method. The visualization of these randomly selected samples shows that the method has excellent performance for lung opacity detection. Our method achieves better discriminative results and is suitable for the pneumonia diagnosis.