Aravind Harikumar

Dr. Aravind Harikumar

University of Toronto, Toronto, Ontario, Canada
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 February 2017 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Aravind HarikumarAravind Harikumar
Aravind Harikumar
Francesca BovoloFrancesca Bovolo
Francesca Bovolo
LBLorenzo Bruzzone
Lorenzo Bruzzone
The knowledge of the tree species is a crucial information that governs the success of precision forest management practice. High-density small footprint multireturn airborne light detection and ranging (LiDAR) scanning can collect a huge amount of point samples containing structural details of the forest vertical profile, which can reveal important structural information of the forest components. LiDAR data have been successfully used to distinguish between coniferous and deciduous/broadleaved tree species. However, species classification within a class (e.g., the conifer class) using LiDAR data is a challenging problem when considering the tree external crown characteristics only. This paper presents a novel method for conifer species classification based on the use of geometric features describing both the internal and external structures of the crown. The internal crown geometric features (IGFs) are defined based on a novel internal branch structure model, which uses 3-D region growing and principal component analysis to delineate the branch structure of a conifer tree accurately. IGFs are used together with external crown geometric features to perform conifer species classification. Three different support vector machines have been considered for classification performance evaluation. The experimental analysis conducted on high-density LiDAR data acquired over a portion of the Trentino region in Italy proves the effectiveness of the proposed method.

10 August 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
Aravind HarikumarAravind Harikumar
Aravind Harikumar
Claudia ParisClaudia Paris
Claudia Paris
Francesca BovoloFrancesca Bovolo
Francesca Bovolo
LBLorenzo Bruzzone
Lorenzo Bruzzone
Crown features derived from high-density airborne laser scanning (ALS) data have proven to be effective for forest species classification at the individual tree level. Most of the general state-of-the-art (SoA) techniques rely on coarse-level crown features extracted from ALS data and under-utilize both the spatial and the spectral information available in the point clouds, Moreover, they are designed on the expected properties of the specific analyzed forest. We present a novel species classification approach, based on quantization of the entire 3-D tree crown into smaller elementary crown volumes (ECVs) that effectively captures the spatial distribution of filled (i.e., stem, branch, and foliage) and empty volumes of crowns. In the first step, a data-driven process dynamically tests and compares three quantization strategies to tailor the definition of the ECV to the forest type (e.g., conifer and deciduous forest). In the second step, for each ECV, a histogram vector is made up of features representing the light detection and ranging (LiDAR) point distribution and intensity to model the internal and the external local crown characteristics. Then, tree histogram feature vectors are obtained by stacking all the ECV histogram feature vectors. Finally, classification is performed by a support vector machine (SVM) classifier using the histogram intersection kernel. All experiments were performed on three high-density (50-200 points/m²) ALS data sets of deciduous, conifer, and mixed (i.e., both deciduous and conifer) trees. The higher classification accuracy of the proposed method over the SoA one proves its ability to better capture the crown characteristics of individual trees, including species-specific traits.

30 March 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
Aravind HarikumarAravind Harikumar
Aravind Harikumar
XLXinlian Liang
Xinlian Liang
Francesca BovoloFrancesca Bovolo
Francesca Bovolo
LBLorenzo Bruzzone
Lorenzo Bruzzone
A comprehensive three-dimensional (3D) structural mapping of stem is essential for an accurate 3D crown modelling and tree parameter estimation. Terrestrial Laser Scanning (TLS) is an effective technology for comprehensive collection of individual tree level data, compared to destructive and costly field measurements. The performance of 3D stem modelling techniques is adversely affected by laser shadowing and point density variations in TLS data. In addition, most of the state-of-the-art techniques perform stem modelling using regular geometric shapes such as circle, ellipse and cylinder, which cannot accurately capture the complex 3D stem geometric shapes. This results in stem modelling errors. In this paper, we propose a 3D stem modelling approach for both singlescan and multiscan TLS data that: a) does not make any prior assumption on the stem geometry, and b) is minimally affected by undesirable stem shadowing and point density variations. The proposed approach accurately models 3D stem and localizes branch-knots for both coniferous and deciduous trees by mapping the void-volume formed within the stem due to opaqueness of tree stem to laser. The modelling performance was evaluated on both singlescan and multiscan data obtained for pine, spruce and birch species. The low estimation errors associated with the stem Diameter at Breast Height (DBH) and branch-knot location, compared to the reference methods, prove the ability of the proposed method to both accurately model 3D stem and localize branch-knots.

21 May 2015 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
Aravind HarikumarAravind Harikumar
Aravind Harikumar
AKAnil Kumar
Anil Kumar
ASAlfred Stein
Alfred Stein
PRP.L.N. Raju
P.L.N. Raju
YMY.V.N. Krishna Murthy
Y.V.N. Krishna Murthy
This article presents a hybrid fuzzy classifier for effective land-use/land-cover (LULC) mapping. It discusses a Bayesian method of incorporating spatial contextual information into the fuzzy noise classifier (FNC). The FNC was chosen as it detects noise using spectral information more efficiently than its fuzzy counterparts. The spatial information at the level of the second-order pixel neighbourhood was modelled using Markov random fields (MRFs). Spatial contextual information was added to the MRF using different adaptive interaction functions. These help to avoid over-smoothing at the class boundaries. The hybrid classifier was applied to advanced wide-field sensor (AWiFS) and linear imaging self-scanning sensor-III (LISS-III) images from a rural area in India. Validation was done with a LISS-IV image from the same area. The highest increase in accuracy among the adaptive functions was 4.1% and 2.1% for AWiFS and LISS-III images, respectively. The paper concludes that incorporation of spatial contextual information into the fuzzy noise classifier helps in achieving a more realistic and accurate classification of satellite images.

26 September 2020
Verified
Conference Paper
Closed access
Aravind HarikumarAravind Harikumar
Aravind Harikumar
PDPetra D'ODorico
Petra D'ODorico
IEIngo Ensminger
Ingo Ensminger
Multispectral remote sensing from Unmanned Aerial Vehicle (UAV) platforms is fast becoming an economical approach to gather Very High Resolution (VHR) spatial data at the individual tree level. However, detecting and delineating tree crowns are challenging due to the intrinsic intra-class spectral variability, shadow and noise in VHR images. In addition to the unrealistic assumption that tree crowns do not overlap in forests, most state-of-the-art algorithms using photogrammetric multispectral data rely maximally on the spectral information to delineate tree crowns, resulting in crown delineation errors. The joint use of both the spectral and the spatial contextual information in multispectral data in classification mitigates the effects of intra-class spectral variance and noise, and hence has the potential to accurately delineate crowns. Thus, we proposed an approach to detect and delineate individual tree crowns by performing a Markov Random Field (MRF) based spatial-contextual modelling on a fuzzy classification framework, to achieve accurate crown delineation. The results obtained prove the proposed method to be effective.

24 April 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Aravind HarikumarAravind Harikumar
Aravind Harikumar
PDPetra D’odorico
Petra D’odorico
IEIngo Ensminger
Ingo Ensminger
Precise delineation of individual tree crowns is critical for accurate forest biophysical parameter estimation, species classification, and ecosystem modelling. Multispectral optical remote sensors mounted on low-flying unmanned aerial vehicles (UAVs) can rapidly collect very-high-resolution (VHR) photogrammetric optical data that contain the spectral, spatial, and structural information of trees. State-of-the-art tree crown delineation approaches rely mostly on spectral information and underexploit the spatial-contextual and structural information in VHR photogrammetric multispectral data, resulting in crown delineation errors. Here, we propose the spectral, spatial-contextual, and structural information-based individual tree crown delineation (S3-ITD) method, which accurately delineates individual spruce crowns by minimizing the undesirable effects due to intracrown spectral variance and nonuniform illumination/shadowing in VHR multispectral data. We evaluate the performance of the S3-ITD crown delineation method over a white spruce forest in Quebec, Canada. The highest mean intersection over union (IoU) index of 0.83, and the lowest mean crown-area difference (CAD) of 0.14 m2, proves the superior crown delineation performance of the S3-ITD method over state-of-the-art methods. The reduction in error by 2.4 cm and 1.0 cm for the allometrically derived diameter at breast height (DBH) estimates compared with those from the WS-ITD and the BF-ITD approaches, respectively, demonstrates the effectiveness of the S3-ITD method to accurately estimate biophysical parameters.