|Lim Soon Eng||College Of Computer Science and Information Technology, University Tenaga Nasional (UNITEN)|
|Rozita Ismail||College Of Computer Science and Information Technology, University Tenaga Nasional (UNITEN)|
|Wahidah Hashim||Institute of Informatics and Computing in Energy, University Tenaga Nasional (UNITEN)|
|Aslina Baharum||Faculty of Computing and Informatics (FKI), University Malaysia Sabah (UMS), Jalan UMS 88400 Kota Kinabalu, Sabah, Malaysia|
Vegetation monitoring is a task that requires much time and human effort, but by using an unmanned aerial vehicle with a system that can store captured data digitally, the task can be more manageable and efficient. Past research has shown many formulas were developed by researchers to capture vegetation data in varying conditions and equipment. This paper discusses an experiment conducted to test three of those formulas using visible band data images. The formulas are the visible atmospherically resistant index, the green leaf index, and the visible atmospherically resistant indices green. The objective of this paper is to report and discuss our findings from experiments conducted using each formula as well as to compare the accuracy of these formulas.
Green leaf index; Vegetation indices; Vegetation monitoring; Visible atmospherically resistant index
Planting vegetation benefits every living being on earth (William et al., 2012; Pauline et al., 2013). According to the book The Benefits of Urban Vegetation, a survey found that green vegetation can directly affect human health by reducing stress, encouraging physical activity and improving the living environment (Pauline et al., 2013). Most importantly, it also helps reduce the environment temperatures of urban areas (William et al., 2012). However, vegetation can be a problem, too. For example, in Bakersfield, CA, a developer had planted 300 redwoods directly under power line cables. As a result, tree trimming caused challenges that may have reduced the benefits of having vegetation (William et al., 2012). Monitoring vegetation is another issue for some agencies. Research found that a power energy provider had spent and allocated around USD2 billion to USD10 billion per year on vegetation management in order to have proper maintenance at their facilities and provide reliable electricity delivery to consumers (Rancea, 2014). Meanwhile, according to a power provider in South Australia known as SA Power Network, they completed vegetation inspections using a four-wheel-drive vehicle to inspect every potential vegetation encroachment (Lewis, 2018). According to research conducted by de Ronde et al. (2007), the main requirement of vegetation monitoring is to do comparability studies on data between different years. Visible atmospherically resistant index (VARI), green leaf index (GLI) and visible atmospherically resistant indices green (VIgreen) have been used to perform vegetation monitoring by just using visible band (RGB) data. We have conducted an experiment to study and understand the behavior of vegetation formulas on the aerial images captured by unmanned aerial vehicles of different environments. The motivation is to familiarize and determine the differences in the results between each formula, which can be used by utilities industries when verifying vegetation encroachment in power transmission corridors. The purpose of conducting this research is to find out the most suitable formula to perform post-processing of the images captured using consumer drones to highlight vegetation objects from other objects. It can reduce the time taken to perform monitoring for encroachment and trimming of large areas of vegetation.
Throughout this experiment, it was found that the GLI formula proved the most suitable technique for highlighting vegetation in both urban areas and forest areas based on its sensitivity in detecting the differences between vegetation and non-vegetation. Overall, the three formulas can show green objects with minimal false detection in single-band pseudocolor. As for future work, we will include machine-learning techniques and deep-learning analysis in the data processing in order to enhance the vegetation detection to a minimal percentage of misinterpretation.
This research was supported by UNITEN internal grant, project code J510050744. We acknowledge the use of facilities and equipment provided by Micro Multi Copter Aero Science & Technology and Kembara Impian Technologies Sdn. Bhd. We would like to thank Tuan Hussin Daud. and Mr. Alan from Kembara Impian as well as Mr. Edison and Mr. Ken from Micro Multi Copter Aero Science & Technology for providing us suggestions based on their expertise and experience throughout the research.
Ahamed, T., Tian, L., Zhang, Y., Ting, K.C., 2011. A Review of Remote Sensing Methods for Biomass Feedstock Production. Biomass and Bioenergy, Volume 35(7), pp. 2455–2469
Berni, J.A.J., Zarco-Tejada, P.J., Suárez, L., González-Dugo, V., Fereres, E., 2009. Remote Sensing of Vegetation from UAV Platforms using Lightweight Multispectral and Thermal Imaging Sensors. Int. Arch. Photogramm. Remote Sens. Spatial Inform. Sci, Volume 38(6), pp. 1–6
Burgan, R.E., Hartford, R.A., 1993. Monitoring Vegetation Greenness with Satellite Data. Gen. Tech. Rep. INT-GTR-297. Ogden, UT: U.S. Department of Agriculture, Forest Service, Intermountain Research Station
Carpenter, A.T., Elzinga, C.L., Salzer, D. W., Willoughby, J.W., 1999. Measuring and Monitoring Plant Populations. Journal of Range Management, Volume 52(5), pp. 544. 10.2307/4003786
Gitelson, A.A., Kaufman, Y.J., Stark, R., Rundquist, D., 2002. Novel Algorithms for Remote Estimation of Vegetation Fraction. Remote Sensing of Environment, Volume 80(1), pp. 76–87
Gunawan, G., Sutjiningsih, D., Soeryantono, H., Sulistioweni, W., 2013. Soil Erosion Estimation based on GIS and Remote Sensing for Supporting Integrated Water Resources Conservation Management. International Journal of Technology, Volume 4(2), pp. 147–156
De Ronde, R., Haveman, R., 2007. Problem in Vegetation Monitoring in Nature Management Practice: Two Case Studies. Annali Di Botanica, Volume VII, pp. 77–84
Kim, S.R., Lee, W.K., Lim, C.H., Kim, M., Kafatos, M.C., Lee, S.H., Lee, S.S., 2018. Hyperspectral Analysis of Pine Wilt Disease to Determine an Optimal Detection Index. Forests, Volume 9(3), pp. 1–12
Lewis, A., 2018. Networks Protocol for Vegetation Management Near Powerlines 2016-2018. Available Online at https://www.sapowernetworks.com.au/public/download.jsp?id=54955
Li, Z., Walker, R., Hayward, R., Mejias, L.. 2010. Advances in Vegetation Management for Power Line Corridor Monitoring using Aerial Remote Sensing Techniques. In: Proceedings of the First International Conference on Applied Robotics for the Power Industry (CARPI), pp. 1–6
Louhaichi, M., Borman, M.M., Johnson, D.E., 2001. Spatially Located Platform and Aerial Photography for Documentation of Grazing Impacts on Wheat. Geocarto International, Volume 16(1), pp. 65–70
Mckinnon, T., Hoff, P., 2017. Comparing RGB-Based Vegetation Indices with NDVI for Drone Based Agricultural Sensing. Agribotix.Com, Volume 21(17), pp. 1–8
Mokarram, M., Boloorani, A.D., Hojati, M., 2016. Relationship between Land Cover and Vegetation Indices. Case Study: Eghlid Plain, Fars Province, Iran. European Journal of Geography, Volume 7(2), pp. 48–60
Mokarram, M., Hojjati, M., Roshan, G., Negahban, S., 2015. Modeling the Behavior of Vegetation Indices in the Salt Dome of Korsia in North-East of Darab, Fars, Iran. Modeling Earth Systems and Environment, Volume 1(27), pp. 1–9
Motohka, T., Nasahara, K.N., Oguma, H., Tsuchida, S., 2010. Applicability of Green-red Vegetation Index for Remote Sensing of Vegetation Phenology. Remote Sensing, Volume 2(10), pp. 2369–2387
Muraoka, H., Noda, H.M., Nagai, S., Motohka, T., Saitoh, T.M., Nasahara, K.N., Saigusa, N., 2013. Spectral Vegetation Indices as the Indicator of Canopy Photosynthetic Productivity in a Deciduous Broadleaf Forest. Journal of Plant Ecology, Volume 6(5), pp. 393–407
Nagai, S., Ishii, R., Suhaili, A. Bin Suhaili, Kobayashi, H., Matsuoka, M., Ichie., Motohka, T., Kendawang, J.J., Suzuki, R., 2014. Usability of Noise-free Daily Satellite-observed Green–red Vegetation Index Values for Monitoring Ecosystem Changes in Borneo. International Journal of Remote Sensing, Volume 35(23), pp. 7910–7926
Pauline, L., Damien, P., François, C., Julien S., 2013. The Benefits of Urban Vegetation. Plante & Cite
Rancea, G.V., 2014. Evaluation of Methods for Control of Vegetation in Utility Corridors. The University of San Francisco. Available Online at https://repository.usfca.edu/capstone/9
Raturi, G.P., Bhatt, A.B., 2004. Vegetation Pattern Analysis in Rudraprayag District using Remote Sensing and GIS. Journal of the Indian Society of Remote Sensing, Volume 32(2), pp. 217–224
Schneider, P., Roberts, D.A., Kyriakidis, P.C., 2008. A VARI-based Relative Greenness from MODIS Data for Computing the Fire Potential Index. Remote Sensing of Environment, Volume 112(3), pp. 1151–1167
Viña, A., Gitelson, A.A., Rundquist, D.C., Keydan, G., Leavitt, B., Schepers, J., 2004. Monitoring Maize ( L.) Phenology with Remote Sensing. Agronomy Journal, Volume 96(4), pp. 1139–1147
William, B., Most, B., Weissman, S., 2012. Trees and Power Lines: Minimizing Conflicts between Electric Power Infrastructure and the Urban Forest. City Streets, Berkeley Law. Available Online at https://www.law.berkeley.edu/files/Trees_and_Power_Lines_March_2012.pdf
Yuliantika, G., Suprayogi, A., Sukmono, A., 2016. Analisis Pengunaan Saluran Visible untuk Estimasi Kandungan Klorofil Daun Pade dengan Citra Hymap. (Studi Kasus: Kabupaten Karawang, Jawa Barat). Jurnal Geodesi Undip, Volume 5(2), pp. 200–207