In this paper, we consider building extraction from high spatial resolution remote sensing images. At present, most building extraction methods are based on artificial features. However, the diversity and complexity of buildings mean that building extraction methods still face great challenges, so methods based on deep learning have recently been proposed. In this paper, a building extraction framework based on a convolution neural network and edge detection algorithm is proposed. The method is called Mask R-CNN Fusion Sobel. Because of the outstanding achievement of Mask R-CNN in the field of image segmentation, this paper improves it and then applies it in remote sensing image building extraction. Our method consists of three parts. First, the convolutional neural network is used for rough location and pixel level classification, and the problem of false and missed extraction is solved by automatically discovering semantic features. Second, Sobel edge detection algorithm is used to segment building edges accurately so as to solve the problem of edge extraction and the integrity of the object of deep convolutional neural networks in semantic segmentation. Third, buildings are extracted by the fusion algorithm. We utilize the proposed framework to extract the building in high-resolution remote sensing images from Chinese satellite GF-2, and the experiments show that the average value of IOU (intersection over union) of the proposed method was 88.7% and the average value of Kappa was 87.8%, respectively. Therefore, our method can be applied to the recognition and segmentation of complex buildings and is superior to the classical method in accuracy.

In this paper, we consider water surface object detection in natural scenes. Generally, background subtraction and image segmentation are the classical object detection methods. The former is highly susceptible to variable scenes, so its accuracy will be greatly reduced when detecting water surface objects due to the changing of the sunlight and waves. The latter is more sensitive to the selection of object features, which will lead to poor generalization as a result, so it cannot be applied widely. Consequently, methods based on deep learning have recently been proposed. The River Chief System has been implemented in China recently, and one of the important requirements is to detect and deal with the water surface floats in a timely fashion. In response to this case, we propose a real-time water surface object detection method in this paper which is based on the Faster R-CNN. The proposed network model includes two modules and integrates low-level features with high-level features to improve detection accuracy. Moreover, we propose to set the different scales and aspect ratios of anchors by analyzing the distribution of object scales in our dataset, so our method has good robustness and high detection accuracy for multi-scale objects in complex natural scenes. We utilized the proposed method to detect the floats on the water surface via a three-day video surveillance stream of the North Canal in Beijing, and validated its performance. The experiments show that the mean average precision (MAP) of the proposed method was 83.7%, and the detection speed was 13 frames per second. Therefore, our method can be applied in complex natural scenes and mostly meets the requirements of accuracy and speed of water surface object detection online.

Image-based water level measurement is a visual-sensing technique which automatically inspects the reading of the water line via image processing instead of the human eye. It can be realized easily on an existing video surveillance system and has advantages like low cost, non-contact, as well as results that are verifiable. It has the potential to be widely used in flood and waterlogging monitoring, while facing the challenge that water-line detection under complex natural or artificial illumination conditions is quite difficult in field applications. To handle this problem, a method is proposed assuming that the water line is generally located on the row with the largest local change of gray or edge features in the image of the water gauge. The water line is determined by coarse-to-fine detection of the position of the maximum mean difference (MMD) of the horizontal projections of gray and edge images. Image-based flow-level measurement systems were developed at two measurement sites. In situ comparative experiments were conducted with the float-type stage gauge and other image-based methods. The results show that the fusion of gray and edge features can overcome the shortcomings of single feature methods under complex illumination conditions such as dim light, glares, shadows and artificial night lighting. A coarse-to-fine strategy utilizes the periodicity of the surface pattern distribution of the standard bicolor water gauge, which improves the reliability of water-line detection. The resolution and accuracy of water-level measurement are 1 mm and 1 cm, respectively. In particular, the MMD value is efficient at identifying extremely unfavorable conditions and reducing gross errors.

Object detection is widely used in robot navigation, intelligent security and industrial detection, but it is rarely used in water conservancy industry. In the aspect of river and lake health management, it is important to clean out the floating objects in time, which prevents water pollution caused by the accumulation of the floating objects. The early methods of water surface object detection, such as background subtraction and frame difference, are greatly affected by the change of object shape and background, resulting in poor robustness. Therefore, we propose a real-time detection method of surface floating objects based on improved RefineDet model, which includes three modules: the anchor refinement module, the transfer connection block and the object detection module. We improve anchor refinement module by adding convolution layers to obtain higher-level semantic, and fuse high-level features with low-level features to improve detection accuracy. Moreover, we adjust the parameters setting of anchors according to the scale and aspect ratio distribution to match the multi-scale object better. Aiming at the foreground-background class imbalance caused by dense anchors sampling, we introduce focal loss function to solve it and make our model more efficient by adjusting the parameters of the function. We verify the performance of the proposed method on different floating object datasets we constructed. The detection accuracies on these different datasets are 83.8%, 88.0%, and 82.3% respectively, and the detection speed is 28 FPS. This shows that the improved RefineDet realizes high-precision and real-time detection.

A seizure is a neurological disorder caused by abnormal neuronal discharges in the brain, which severely reduces the quality of life of patients and often endangers their lives. Automatic seizure detection is an important research area in the treatment of seizure and is a prerequisite for seizure intervention. Deep learning has been widely used for automatic detection of seizures, and many related research works decomposed the electroencephalogram (EEG) raw signal with a time window to obtain EEG signal slices, then performed feature extraction on the slices, and represented the obtained features as input data for neural networks. There are various methods for EEG signal decomposition, feature extraction, and representation, and most of the studies have been based on fixed hardware resources for the design of the scheme, which reduces the adaptability of the scheme in different application scenarios and makes it difficult to optimize the algorithms in the scheme. To address the above issues, this paper proposes a deep learning-based model for seizure detection, mainly characterized by the two-dimensional representation of EEG features and the scalability of neural networks. The model modularizes the main steps of seizure detection and improves the adaptability of the model to different hardware resource constraints, in order to increase the convenience of the algorithm optimization or the replacement of each module. The proposed model consists of five parts, and the model was tested using two epilepsy datasets separately. The experimental results showed that the proposed model has strong generality and good classification accuracy for seizure detection.

Maritime search and rescue is a crucial component of the national emergency response system, which mainly relies on unmanned aerial vehicles (UAVs) to detect objects. Most traditional object detection methods focus on boosting the detection accuracy while neglecting the detection speed of the heavy model. However, improving the detection speed is essential, which can provide timely maritime search and rescue. To address the issues, we propose a lightweight object detector named Shuffle-GhostNet-based detector (SG-Det). First, we construct a lightweight backbone named Shuffle-GhostNet, which enhances the information flow between channel groups by redesigning the correlation group convolution and introducing the channel shuffle operation. Second, we propose an improved feature pyramid model, namely BiFPN-tiny, which has a lighter structure capable of reinforcing small object features. Furthermore, we incorporate the Atrous Spatial Pyramid Pooling module (ASPP) into the network, which employs atrous convolution with different sampling rates to obtain multi-scale information. Finally, we generate three sets of bounding boxes at different scales—large, medium, and small—to detect objects of different sizes. Compared with other lightweight detectors, SG-Det achieves better tradeoffs across performance metrics and enables real-time detection with an accuracy rate of over 90% for maritime objects, showing that it can better meet the actual requirements of maritime search and rescue.