Airborne LiDAR (Light Detection And Ranging) remote sensing for individual tree-level forest inventory necessitates proper extraction of individual trees and accurate measurement of tree structural parameters. Due to the inadequate tree finding capability offered by LiDAR technology and the complex patterns of forest canopies, significant omission and commission errors occur frequently in the segmentation results. Aimed at error reduction and accuracy refinement, this paper presents a novel adaptive mean shift-based clustering scheme aided by a tree trunk detection technique to segment individual trees and estimate tree structural parameters based solely on the airborne LiDAR data. Tree trunks are detected by analyzing points' vertical histogram to detach all potential crown points and then clustering the separated trunk points according to their horizontal mutual distances. The detected trunk information is used to adaptively calibrate the kernel bandwidth of the mean shift procedure in the fine segmentation stage by applying an original 2D (two-dimensional) estimation of individual crown diameters. Trunk detection results and LiDAR point clusters generated by the adaptive mean shift procedures serve as mutual references for final detection of individual trees. Experimental results show that a combination of adaptive mean shift clustering and detected tree trunk can provide a significant performance improvement in individual tree-level forest measurement. Compared with conventional clustering techniques, the trunk detection-aided mean shift clustering approach can detect 91.1% of the trees ("recall") with a higher tree positioning accuracy (the mean positioning error is reduced by 33%) in a multi-layered coniferous and broad-leaved mixed forest in South China, and 93.5% of the identified trees are correct ("precision"). The tree detection brings the estimation of structural parameters for individual trees up to an accuracy level: −2.2% mean relative error and 5.8% relative RMSE (Root Mean Square Error) for tree height and 0.6% mean relative error and 21.9% relative RMSE for crown diameter, respectively.
This work focuses on the extremely low-light image enhancement, which aims to improve image brightness and reveal hidden information in darken areas. Recently, image enhancement approaches have yielded impressive progress. However, existing methods still suffer from three main problems: (1) low-light images usually are high-contrast. Existing methods may fail to recover images details in extremely dark or bright areas; (2) current methods cannot precisely correct the color of low-light images; (3) when the object edges are unclear, the pixel-wise loss may treat pixels of different objects equally and produce blurry images. In this paper, we propose a two-stage method called Edge-Enhanced Multi-Exposure Fusion Network (EEMEFN) to enhance extremely low-light images. In the first stage, we employ a multi-exposure fusion module to address the high contrast and color bias issues. We synthesize a set of images with different exposure time from a single image and construct an accurate normal-light image by combining well-exposed areas under different illumination conditions. Thus, it can produce realistic initial images with correct color from extremely noisy and low-light images. Secondly, we introduce an edge enhancement module to refine the initial images with the help of the edge information. Therefore, our method can reconstruct high-quality images with sharp edges when minimizing the pixel-wise loss. Experiments on the See-in-the-Dark dataset indicate that our EEMEFN approach achieves state-of-the-art performance.
Forest fire is a common disturbance factor, especially in boreal forests. The detection of forest disturbance and monitoring of post-fire forest recovery are crucial to both ecological research and forest management. The Greater Hinggan Mountain area of China is rich in forest resources, but also has a high incidence of forest fires. After the most serious forest fire in the history of P. R. China, three restoration modes were adopted for local forest recovery, namely artificial regeneration, natural regeneration and artificial promotion. In this study, based on time series Landsat data, we proposed to detect the disturbance and monitor the post-fire forest recovery under the three restoration modes. Disturbance Index (DI) was proven to be an effective approach for the detection and monitoring. The results indicated that the forest under natural regeneration achieved a totally different recovery process with those under the other two modes. In combination with the field survey data analysis, the availability of different remote sensing indices and applicability of the three restoration modes were evaluated and compared. It could provide significant suggestions for local post-fire forest management.
Influence maximization is the task of finding a set of seed nodes in a social network such that the influence spread of these seed nodes based on certain influence diffusion model is maximized. Topic-aware influence diffusion models have been recently proposed to address the issue that influence between a pair of users are often topic-dependent and information, ideas, innovations etc. being propagated in networks (referred collectively as items in this paper) are typically mixtures of topics. In this paper, we focus on the topic-aware influence maximization task. In particular, we study preprocessing methods for these topics to avoid redoing influence maximization for each item from scratch. We explore two preprocessing algorithms with theoretical justifications. Our empirical results on data obtained in a couple of existing studies demonstrate that one of our algorithms stands out as a strong candidate providing microsecond online response time and competitive influence spread, with reasonable preprocessing effort.
In this paper, we study the problem of online in uence maximization in social networks. In this problem, a learner aims to identify the set of "best in uencers" in a network by interacting with the network, i.e., repeatedly selecting seed nodes and observing activation feedback in the network. We capitalize on an important property of the in uence maximization problem named network assortativity, which is ignored by most existing works in online in uence maximization. To realize network assortativity, we factorize the activation probability on the edges into latent factors on the corresponding nodes, including in uence factor on the giving nodes and susceptibility factor on the receiving nodes. We propose an upper con dence bound based online learning solution to estimate the latent factors, and therefore the activation probabilities. Considerable regret reduction is achieved by our factorization based online in uence maximization algorithm. Extensive empirical evaluations on two real-world networks showed the e ectiveness of our proposed solution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.