In this research wok, three different techniques of change detection were used to detect changes in forest areas. One of the techniques used a local similarity measure approach to detect changes. This new approach of change detection technique, which used mutual information to measure the similarity between two multi-temporal images, was developed based on correspondence of the pixel values, rather than the difference in their intensity. Pixels suffering any changes will be maximally dissimilar. The study was conducted using multi-temporal SPOT 5 satellite images, with the resolution of 10 m x10 m on 5th August 2005 and 13th June 2007. The experimental results show that local mutual information provides more reliable results in detecting changes of the multitemporal images containing different lighting condition compared to the image differencing and NDVI technique, specifically in areas with less plant growth. In addition, it can also overcome the problem on selecting the threshold value. Besides, the findings of this study have also shown that band 3, which is sensitive to vegetation biomass, gave the best result in detecting area of changes compared to the others.
Basal stem rot (BSR), caused by the Ganoderma fungus, is an infectious disease that affects oil palm (Elaeis guineensis) plantations. BSR leads to a significant economic loss and reductions in yields of up to Malaysian Ringgit (RM) 1.5 billion (US$400 million) yearly. By 2020, the disease may affect ∼1.7 million tonnes of fresh fruit bunches. The plants appear symptomless in the early stages of infection, although most plants die after they are infected. Thus, early, accurate, and nondestructive disease detection is crucial to control the impact of the disease on yields. Terrestrial laser scanning (TLS) is an active remote-sensing, noncontact, cost-effective, precise, and user-friendly method. Through high-resolution scanning of a tree's dimension and morphology, TLS offers an accurate indicator for health and development. This study proposes an efficient image processing technique using point clouds obtained from TLS ground input data. A total of 40 samples (10 samples for each severity level) of oil palm trees were collected from 9-year-old trees using a ground-based laser scanner. Each tree was scanned four times at a distance of 1.5 m. The recorded laser scans were synched and merged to create a cluster of point clouds. An overhead two-dimensional image of the oil palm tree canopy was used to analyze three canopy architectures in terms of the number of pixels inside the crown (crown pixel), the degree of angle between fronds (frond angle), and the number of fronds (frond number). The results show that the crown pixel, frond angle, and frond number are significantly related and that the BSR severity levels are highly correlated (R2 = 0.76, P < 0.0001; R2 = 0.96, P < 0.0001; and R2 = 0.97, P < 0.0001, respectively). Analysis of variance followed post hoc tests by Student-Newman-Keuls (Newman-Keuls) and Dunnett for frond number presented the best results and showed that all levels were significantly different at a 5% significance level. Therefore, the earliest stage that a Ganoderma infection could be detected was mildly infected (T1). For frond angle, all post hoc tests showed consistent results, and all levels were significantly separated except for T0 and T1. By using the crown pixel parameter, healthy trees (T0) were separated from unhealthy trees (moderate infection [T2] and severe infection [T3]), although there was still some overlap with T1. Thus, Ganoderma infection could be detected as early as the T2 level by using the crown pixel and the frond angle parameters. It is hard to differentiate between T0 and T1, because during mild infection, the symptoms are highly similar. Meanwhile, T2 and T3 were placed in the same group, because they showed the same trend. This study demonstrates that the TLS is useful for detecting low-level infection as early as T1 (mild severity). TLS proved beneficial in managing oil palm plantation disease.
Ground-based LiDAR also known as Terrestrial Laser Scanning (TLS) technology is an active remote sensing imaging method said to be one of the latest advances and innovations for plant phenotyping. Basal Stem Rot (BSR) is the most destructive disease of oil palm in Malaysia that is caused by white-rot fungus Ganoderma boninense, the symptoms of which include flattening and hanging-down of the canopy, shorter leaves, wilting green fronds and smaller crown size. Therefore, until now there is no critical investigation on the characterisation of canopy architecture related to this disease using TLS method was carried out. This study proposed a novel technique of BSR classification at the oil palm canopy analysis using the point clouds data taken from the TLS. A total of 40 samples of oil palm trees at the age of nine-years-old were selected and 10 trees for each health level were randomly taken from the same plot. The trees were categorised into four health levels - T0, T1, T2 and T3, which represents the healthy, mildly infected, moderately infected and severely infected, respectively. The TLS scanner was mounted at a height of 1 m and each palm was scanned at four scan positions around the tree to get a full 3D image. Five parameters were analysed: S200 (canopy strata at 200 cm from the top), S850 (canopy strata at 850 cm from the top), crown pixel (number of pixels inside the crown), frond angle (degree of angle between fronds) and frond number. The results taken from statistical analysis revealed that frond number was the best single parameter to detect BSR disease as early as T1. In classification models, a linear model with a combination of parameters, ABD - A (frond number), B (frond angle) and D (S200), delivered the highest average accuracy for classification of healthy-unhealthy trees with an accuracy of 86.67 per cent. It also can classify the four severity levels of infection with an accuracy of 80 per cent. This model performed better when compared to the severity classification using frond number. The novelty of this research is therefore on the development of new approach to detect and classify BSR using point clouds data of TLS.