No abstract

Vehicle detection in aerial images has attracted great attention as an approach to providing the necessary information for transportation road network planning and traffic management. However, because of the low resolution, complex scene, occlusion, shadows, and high requirement for detection efficiency, implementing vehicle detection in aerial images is challenging. Therefore, we propose an efficient and scene-adaptive algorithm for vehicle detection in aerial images using an improved YOLOv3 framework, and it is applied to not only aerial still images but also videos composed of consecutive frame images. First, rather than directly using the traditional YOLOv3 network, we construct a new structure with fewer layers to improve the detection efficiency. Then, since complex scenes in aerial images can cause the partial occlusion of vehicles, we construct a context-aware-based feature map fusion to make full use of the information in the adjacent frames and accurately detect partially occluded vehicles. The traditional YOLOv3 network adopts a horizontal bounding box, which can attain the expected detection effects only for vehicles with small length-width ratio. Moreover, vehicles that are close to each other are liable to cause lower accuracy and a higher detection error rate. Hence, we design a sloping bounding box attached to the angle of the target vehicles. This modification is conducive to predicting not only the position but also the angle. Finally, two data sets were used to perform extensive experiments and comparisons. The results show that the proposed algorithm generates the desired and excellent performance.

No abstract

With the increasing demand for global water resources and general deterioration of the ecological environment of the Qinghai-Tibetan Plateau, changes to the water conservation functions of ecosystems and the impact mechanisms have attracted great attention. Currently, the research on water conservation has mainly focused on a single biome type, in particular, forests. Few studies explore the differences in water conservation functions of different biome types. Research on this topic mostly utilizes field investigations and sample plot settings to explore the differences in water conservation capacity of a small number of tree species, but these methods are limited in time and space. Therefore, this study uses MODIS products to evaluate the water conservation function of different biome types in the Qinghai-Tibetan Plateau. Dynamic monitoring of the vegetation and water conservation capacity in the study area and research on the responses of the water conservation functions of different biome types were conducted. The results indicate that the vegetation of the Qinghai-Tibetan Plateau increased slightly from 2000 to 2015; however, due to the dual influence of climate and topographic factors, the water conservation capacity showed a slight decline. The water conservation service function mainly comes from grassland ecosystems, which are closely related to vegetation density and biome types. Therefore, to greatly improve the water conservation service function of the Qinghai-Tibetan Plateau, the management and planting of vegetation should be conducted according to the optimal vegetation coverage area, vegetation quantities and biome types.

No abstract