Integration of high density airborne LiDAR and high spatial resolution image for landcover classification

Rahman, Muhammad Zulkarnain Abdul; Kadir, Wan Hazli Wan; Rasib, Abd Wahid; Ariffin, Azman; Razak, Khamarrul Azahari

doi:10.1109/igarss.2013.6723438

Cited by 5 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They created a canopy height model derived from LiDAR and 126-band spectral data to classify woodland vegetation. Many others have reported kappa coefficients or accuracies above 80% when using LiDAR information in their GEOBIA analysis(Geerling et al, 2007;; Rahman et al, 2013;; Forzieri et al, 2013;; Debes et al, 2014). Juel et al (2015) provided valuable insight into their object based analysis of a coastal area in Denmark using similar data fusion techniques as our study.…”

supporting

confidence: 52%

Inclusion of Gabor textural transformations and hierarchical structures within an object based analysis of a riparian landscape

Kutz¹

View full text Add to dashboard Cite

ability to write this thesis. This includes my parents who have shown me what complete dedication is, my siblings who each, individually, contributed to my personal and professional interests, my wife's family for their unfailing support, Dr. Linderman who pushed me to pursue new skillsets to achieve the following analyses, and the friends I have found who have held me accountable and continue to teach me about life through our experiences together.

show abstract

supporting

confidence: 52%

Inclusion of Gabor textural transformations and hierarchical structures within an object based analysis of a riparian landscape

Kutz¹

View full text Add to dashboard Cite

show abstract

“…For example, ALS point clouds can provide wall-to-wall geospatial measurements and the locations of tree canopies within a stand. It is also possible to use ALS point clouds to estimate additional metrics, such as crown length and height to live crown, for individual trees, as well as total stand biomass [2,[12][13][14][15][16]. Commonly applied methods for determining total tree height from ALS data include the identification of the highest LiDAR returns within a pre-defined area assumed to represent an individual tree crown [16].…”

Section: Stand Characterization With Remote Sensing Datamentioning

confidence: 99%

“…It is also possible to use ALS point clouds to estimate additional metrics, such as crown length and height to live crown, for individual trees, as well as total stand biomass [2,[12][13][14][15][16]. Commonly applied methods for determining total tree height from ALS data include the identification of the highest LiDAR returns within a pre-defined area assumed to represent an individual tree crown [16]. However, total tree height estimation using individual tree crown (ITC) methodologies from ALS data can provide results that are comparable to field measurements [15,[17][18][19].…”

Section: Stand Characterization With Remote Sensing Datamentioning

confidence: 99%

Rethinking Productivity Evaluation in Precision Forestry through Dominant Height and Site Index Measurements Using Aerial Laser Scanning LiDAR Data

Raigosa-García,

Rathbun,

Cook

et al. 2024

Forests

View full text Add to dashboard Cite

Optimizing forest plantation management has become imperative due to increasing forest product demand, higher fertilization and management costs, declining land availability, increased competition for land use, and the growing demands for carbon sequestration. Precision forestry refers to the ability to use data acquired with technology to support the forest management decision-making process. LiDAR can be used to assess forest metrics such as tree height, topographical position, soil surface attributes, and their combined effects on individual tree growth. LiDAR opens the door to precision silviculture applied at the tree level and can inform precise treatments such as fertilization, thinning, and herbicide application for individual trees. This study uses ALS LiDAR and other ancillary data to assess the effect of scale (i.e., stand, soil type, and microtopography) on dominant height and site index measures within loblolly pine plantations across the southeastern United States. This study shows differences in dominant height and site index across soil types, with even greater differences observed when the interactions of microtopography were considered. These results highlight how precision forestry may provide a unique opportunity for assessing soil and microtopographic information to optimize resource allocation and forest management at an individual tree scale in a scarce higher-priced fertilizer scenario.

show abstract

“…Examples include New York City's topobathymetric LiDAR dataset [5], the United States 3D Elevation Program's datasets [6], and the Netherlands' national Li-DAR datasets [7]. However, much higher point densities (e.g., >50 points/m 2 ) can be achieved in a single pass, such as the 3D mapping of Vienna in Austria at 50 points/m 2 [8] and the mapping of Duursche in the Netherlands at 70 points/m 2 [9]. A pair of exceptionally dense examples are the 2007 and 2015 ALS mapping of Dublin, Ireland (i.e., 225 and 335 points/m 2 , respectively) conducted by Laefer et al [10,11].…”

Section: Introductionmentioning

confidence: 99%

Optimizing Urban LiDAR Flight Path Planning Using a Genetic Algorithm and a Dual Parallel Computing Framework

Laefer

Byrne

2021

Remote Sensing

View full text Add to dashboard Cite

This paper introduces a genetic algorithm (GA) and a beam tracing algorithm incorporated within a dual parallel computing framework to optimize urban aerial laser scanning (ALS) missions to maximize vertical façade data capture, as needed for many three-dimensional reconstruction and modeling workflows. The optimization employs a low-density point cloud from the site of interest as a spatial representation of the urban scene. The GA is suitable for LiDAR flight path optimization due to its capability of handling open-ended problems that have many solutions. However, GAs require evaluating a very large number of candidates. The use of an initial point cloud allows realistic modeling of the urban environment in the optimization at the cost of high data input volumes. To cope with the computational and data demands, a dual parallel computing framework was devised. The parallel computing framework consists of two layers of parallelization. In the upper layer, multiple evaluators work in parallel and in conjunction with a main multi-threading GA optimizer to perform GA operations and evaluate the flight paths. In the lower layer, to evaluate assigned flight paths, each evaluator distributes its data and computation to multiple executors, which can reside on multiple physical nodes of a distributed-memory computing cluster. In addition to parallelism, the data partitioning on the lower layer allows out-of-core computation. Namely, data partitions are efficiently transferred between disks and memory so that only relevant subsets of data are kept in the main memory. The objective of the proposed method is threefold: (1) search for flight paths that yield the highest numbers of vertical points, (2) create a means to explicitly consider the detailed spatial configuration of urban environments, and (3) assure that the proposed optimization strategy is fast and can scale to large problem sizes. Multiple experiments were conducted and demonstrated the success of the proposed method. Converged results were achieved after dozens of generations within two hours. Two flight paths identified by the GA as the most and the least optimal candidates were deployed in real flight missions. The optimal flight path captured 16% more vertical points than the least optimal one, slightly higher than the 13% predicted. Both layers of parallelization were efficient: 13.1/16 for the lower layer and 3.2/4 for the upper layer. The two complementary layers of parallelization allowed flexible and efficient use of distributed computing resources to reduce the runtime. The scalability of the proposed approach was successfully demonstrated up to a data size of 460 million points. The optimization results were realistic and aligned well with the test flight results.

show abstract

Integration of high density airborne LiDAR and high spatial resolution image for landcover classification

Cited by 5 publications

References 4 publications

Inclusion of Gabor textural transformations and hierarchical structures within an object based analysis of a riparian landscape

Inclusion of Gabor textural transformations and hierarchical structures within an object based analysis of a riparian landscape

Rethinking Productivity Evaluation in Precision Forestry through Dominant Height and Site Index Measurements Using Aerial Laser Scanning LiDAR Data

Optimizing Urban LiDAR Flight Path Planning Using a Genetic Algorithm and a Dual Parallel Computing Framework

Contact Info

Product

Resources

About