No abstract

The detection of moving objects in images is a crucial research objective; however, several challenges, such as low accuracy, background fixing or moving, ‘ghost’ issues, and warping, exist in its execution. The majority of approaches operate with a fixed camera. This study proposes a robust feature threshold moving object identification and segmentation method with enhanced optical flow estimation to overcome these challenges. Unlike most optical flow Otsu segmentation for fixed cameras, a background feature threshold segmentation technique based on a combination of the Horn–Schunck (HS) and Lucas–Kanade (LK) optical flow methods is presented in this paper. This approach aims to obtain the segmentation of moving objects. First, the HS and LK optical flows with the image pyramid are integrated to establish the high-precision and anti-interference optical flow estimation equation. Next, the Delaunay triangulation is used to solve the motion occlusion problem. Finally, the proposed robust feature threshold segmentation method is applied to the optical flow field to attract the moving object, which is the. extracted from the Harris feature and the image background affine transformation model. The technique uses morphological image processing to create the final moving target foreground area. Experimental results verified that this method successfully detected and segmented objects with high accuracy when the camera was either fixed or moving.

By providing a scientific foundation for managing regional ecosystem carbon (C) pools, research on the spatial distribution characteristics of regional C stocks can assist in the development of policies on C emissions reduction and sequestration enhancement. Using the GeoSOS-FLUS and InVEST models and explorations of the Bailong River Basin in the past 20 years, the influence of three future scenarios of land use change—natural development (ND), ecological protection (EP) and arable land protection (ALP)—on C storage was modelled. Between 2000 and 2020, there was a gradual increase in C storage in the BRB with a total increase of 5.58 Tg (3.19%), showing notable spatial heterogeneity. The increase in C storage was attributed to land use conversion among woodland, arable land and grassland, with the conversion between woodland and arable land being the primary factor contributing to the increase in C storage. By 2050, C storage under the EP, ALP and NP scenarios was 183.915, 183.108 and 183.228 Tg, respectively. In 2050, C storage under the EP scenario increased by 0.37% compared with that in 2020, and decreased by 0.07% and 0.005% under the ALP and NP scenarios, respectively. In contrast to the other scenarios, the EP scenario prioritised the protection of the woodland and grassland C sinks, which has significant implications for future planning.