Ship detection is an important but challenging task in the field of computer vision, partially due to the minuscule ship objects in optical remote sensing images and the interference of clouds occlusion and strong waves. Most of the current ship detection methods focus on boosting detection accuracy while they may ignore the detection speed. However, it is also indispensable to increase ship detection speed because it can provide timely ocean rescue and maritime surveillance. To solve the above problems, we propose an improved YOLOv3 (ImYOLOv3) based on attention mechanism, aiming to achieve the best trade-off between detection accuracy and speed. First, to realize high-efficiency ship detection, we adopt the off-the-shelf YOLOv3 as our basic detection framework due to its fast speed. Second, to boost the performance of original YOLOv3 for small ships, we design a novel and lightweight dilated attention module (DAM) to extract discriminative features for ship targets, which can be easily embedded into the basic YOLOv3. The integrated attention mechanism can help our model learn to suppress irrelevant regions while highlighting salient features useful for ship detection task. Furthermore, we introduce a multi-class ship dataset (MSD) and explicitly set supervised subclass according to the scales and moving states of ships. Extensive experiments verify the effectiveness and robustness of ImYOLOv3, and show that our method can accurately detect ships with different scales in different backgrounds, while at a real-time speed.

High-voltage and ultra-high-voltage overhead power lines are important to meet the electricity demand of our daily activities and productions. Due to the overgrowth of trees/vegetation within the corridor area, the distance between the power lines and its surroundings may break through the safety threshold, which could cause potential hazards such as discharge and fire. To ensure the safe and stable operation of the power lines, it is necessary to survey them regularly so that the potential hazards from the surroundings within the power line corridor could be investigated timely. This paper is motivated to quickly and accurately survey the power line corridor with the 3D point clouds. The main contributions of this paper include: (1) the spatial line clustering is proposed to accurately classify and complete the power line points, which can greatly overcome the sparsity and missing of LiDAR points within the complex power line corridor. (2) The contextual relationship between power lines and pylon is well investigated by the grid-based analysis, so that the suspension points of power lines on the pylon are well located. (3) The catenary plane-based simplification of 3D spatial distance calculation between power lines and ground objects facilitates the survey of the power line corridor. Experimental results show that the accuracy of safety distance surveying is 5 cm for power line corridors of all voltage levels. Compared to the ground-truth point-to-point calculation, the speed of surveying is enhanced thousands of times. It is promising to greatly improve both the accuracy and efficiency of surveying the potential hazards of power line corridor.

In recent years, the foreign fibers in cotton lint significantly affect the quality of the final cotton textile products. It remains a challenging task to accurately distinguish foreign fibers from cotton. This article proposes an embedded system based on field programmable gate array (FPGA) + digital signal processor (DSP) to recognize and remove foreign fibers mixed in cotton. With substantial tests of this system, we collect massive samples of foreign fibers and fake foreign fibers. Based on these samples, a convolution neural network mode is developed to validate the classification of the suspected targets from the detection subsystem, to improve the detection reliability. After training several model architectures, we find a model with the best balance between performance and computation. The high success rate (up to 96% in the validation set) demonstrates the effectiveness of the model. Moreover, the computation time (5 ms on a single image based on an eight-core DSP) indicates the efficiency of the detection, which ensures the real-time application of the system.

Automatic ship detection in optical remote sensing images is of great significance due to its broad applications in maritime security and fishery control. Most ship detection algorithms utilize a single-band image to design low-level and hand-crafted features, which are easily influenced by interference like clouds and strong waves and not robust for large-scale variation of ships. In this paper, we propose a novel coarse-to-fine ship detection method based on discrete wavelet transform (DWT) and a deep residual dense network (DRDN) to address these problems. First, multi-spectral images are adopted for sea-land segmentation, and an enhanced DWT is employed to quickly extract ship candidate regions with missing alarms as low as possible. Second, panchromatic images with clear spatial details are used for ship classification. Specifically, we propose the local residual dense block (LRDB) to fully extract semantic feature via local residual connection and densely connected convolutional layers. DRDN mainly consists of four LRDBs and is designed to further remove false alarms. Furthermore, we exploit the multiclass classification strategy, which can overcome the large intra-class difference of targets and identify ships of different sizes. Extensive experiments demonstrate that the proposed method has high robustness in complex image backgrounds and achieves higher detection accuracy than other state-of-the-art methods.

Waterlogging harms winter wheat growth. To enable accurate monitoring of agricultural waterlogging, this paper conducts a winter wheat waterlogging monitoring study using multi-source data in Guzhen County, Anhui Province, China. The hydrological model HYDRUS-1D is coupled with the crop growth model WOFOST, and the Ensemble Kalman Filter is used to assimilate Sentinel-1 inversion soil moisture data. According to the precision and continuity of soil moisture, the damage of winter wheat waterlogging were obtained. The experimental results show that the accuracy of the soil moisture is improved after data assimilation compared with that before data assimilation, and the Nash–Sutcliffe efficiency (NSE) of the simulated soil moisture values at three monitoring sites increased from 0.528, 0.541 and 0.575 to 0.752, 0.692 and 0.731, respectively. A new waterlogging identification criterion has been proposed based on the growth periods and probability distribution of soil moisture. The proportion, calculated from this identification criterion, of the waterlogging wheat farmland in total farmland shows a high correlation with the yield reduction rate. The correlation coefficient of the waterlogging farmland proportion and the yield reduction rate in 11 towns of Guzhen County reaches 0.78. Through the synchronization of geography, agriculture and meteorology, the framework shows great potential in waterlogging monitoring.