Multitemporal Change Detection and Irregular Land Shape Area Measurement from Multispectral Sensor Images through BSO Algorithm

Pixel-based classication and area measurement play a vital role in satellite image processing. e accuracy in classication and area measurement is required for remote monitoring various regions such as water area, cultivation regions, reservoir water spread, and disease spread in cultivation area. Traditionally, Google Earth Pro-based area measurement has error in area measurement due to curvature nature and irregular land surface. Moreover, exact point identication on land surface on Earth pro is dicult due to frequent changes on the land surface. e problem in the land area measurement is mostly aected due to the man-made changes in that particular land area. In this paper, we solve land area measurement error problem through the automated single and multithresholding pixels of dierent iterations on the land surface by the BSO algorithm. e land cover region pixel intensity changes on the curvature region of land surface with respect to spatial and temporal variations which are identied through BSO optimization-based image segmentation for exact area measurement. For the experimentation of accurate measurement, land area images such as urban, semiurban, hill, and coastal region from LANDSAT and SENTINEL images for period 2016 to 2019 are taken for the land area measurement study. BSO enhances and segments the land regions such as road, building, water body, vegetation, bare land, hill, and coastal region of about 32% more than particle swarm optimization (PSO) algorithm. Furthermore, the urban land area measurement accuracy increases to about 97% than the irregular land surface area.


Introduction
e earth surface comprises of manmade developments such as terrains, arti cial water bodies, roads, and buildings. e manmade components refer as land cover. e land cover shape and size vary according to land use. Humans modify land cover according to their use by constructing road, building, and parks. e land cover modi cation has increased in recent times due to population, economic growth, and human needs. e extensive land cover modi cation a ects existing ecosystem and in uence climate at local and global levels. e climate changes and inadequate seasonal rainfall increase global temperature and water drought. e adverse e ects to change in land use and land cover need continuous monitoring of land surface. e land surface area monitors through satellite images such as sentinel-2, Landsat-8, planet scope, and Rapid eye. Satellite optical sensors capture the land cover image changes in land surface detected in temporal and spatial image. e land cover change in terms of vegetation, water body, and urban buildings is classi ed with time series satellite images of land cover. e land cover is classi ed with the supervised and unsupervised classification algorithm. e supervised classification algorithm for land area measurement includes minimum distance, parallelepiped, and maximum likelihood. e unsupervised classification algorithms for land surface area measurement include Kmeans and Supported Vector Machines (SVMs). e supervised algorithm classifies land cover based on land samples for land cover classification. e unsupervised classification performs land cover classification by assigning radiometric pixels values to land cover components. e conventional land classification algorithms fail to delineate land cover in satellite image due to mixed pixels. e historical aerial data in aerial image improve by Rotated CorneR local binary pattern (R-CRLBP). R-CRLBP extracts features from challenging French territory aerial images, which comprises both urban and rural areas. In addition, R-CRLBP filters the images with Local Binary Pattern (LCoLBP) for land cover assessment [1].
Land cover estimation is performed with entropy-based reliability measurement (EBRM). Initially, homogeneous segment of land is performed and then adaptive clustering is done.
e adaptive clustering determines the anomaly features in land image. EBRM provides quantitative measurement of vector-based land cover estimation. Due to the lower complexity of the local-variation calculation, the EBRM technique can dramatically reduce processing time when compared with the Gaussian mixture model, allowing for real-time processing of high-resolution images as well as efficient analysis of large-scale image. Furthermore, the local variation-based approach is stable with larger input data dimensions, which is not always the case with an EBRM type algorithm. [2]. e homogeneous region in Landsat image is detected with the region growing method. e shortcomings of the snapshot model overcome through integration of time and spatial region growing. e segmentation method identifies spatio temporal region in image with the Dynamic Time Wrapping algorithm [3]. e dynamic classifier system (DCS) classifies hyperspectral images. e image is classified based on context and information class characteristics of land cover. DCS overcomes human intervention in supervised image classification [4]. In PolSAR (polar metric synthetic aperture radar) image, a hybrid image segmentation-based algorithm detects land cover with minimal false rate. e method involves region-based image segmentation and followed by polar metric feature selection and binary image object classification [5].
In targeted land cover classification, land cover classes of interest such as agriculture, forestry, disaster management, habitat mapping are effectively classified. Targeted land cover classification (TLCC) has certain drawbacks and limitations, such as time complexity and economic cost. For effective targeted classification, the ground-truth samples are performed for class of interest and avoids the ground truth information. e targeted land cover in images is identified with respect to ground-truth reference. e targeted land cover classification (TLCC) technique combines unlabeled samples in image and targeted land cover samples and identifies targeted land cover. In addition, the land cover with no ground-truth reference is identified by Markov random field and Expectation Maximization algorithm [6]. e SAR image of tropical forest with cloud is classified with algorithms such as AdaBoost, Naive Bayes, random forest, multilayer perceptron, and support vector machine. e SAR image analyzes with respect to pixel and object and evaluates classifier performance in terms of processing speed and accuracy [7]. Instead of directly matching pixels in the image classes by their appearance, the matching is conducted through reference space where the descriptor of land surface class pixel is transformed to texture descriptors to similarity measures between the pixels of land surface pixels class and reference set is created for segmentation. e Reference Descriptor (RD) feature identifies similar intraclass data between sample dataset and reference dataset. RD generates super pixel by comparing feature of super pixel in image and super pixel of disjoint reference set. e reference set comprises super pixel obtained from different land cover types [8].
e spatial content in high-resolution multispectral (MS) image is extracted with the hierarchical segmentation classification system. Hierarchical segmentation tree selects appropriate scale to represent segmentation layer for modeling pixel in image and avoids region of interest under segmentation. e SVM classifier classifies each pixel spatial information at different tree levels. e classifier extracts spatial context from image accurately [9]. e land cover type identifies trend component with phonological feature variability from time series of remote sensing images. e phonological features such as Length of Season (LOS), End of Season (EOS), Rate of Grow-up (ROG), and Amplitude of Season (AOS) are extracted from time series of remote sensed image by BFAST (Breaks For Additive Seasonal Trend) approach. e dynamic time warping and SVM with phonological features train and classify land cover [10]. e LiDAR high-resolution images provide better land cover classification compared with hyperspectral images. e geospatial data from multiple sources fuse with geographic object image analysis. e analysis involves preprocessing, object segmentation, and evaluation of mean, standard deviation, skewness, and kurtosis for evaluation and intensity calculation [11]. e multiscale segmentation with appropriate segmentation scale extracts feature from objects. e simple scale synthesis divides and groups image section with similar segmentation scale. e optimal segmentation of each image section provides suboptimal object scales similar to ground objects [12]. e land cover in SAR and optical fused image classifies by extracting texture and polar metric features from images. e normalization applies at different scales for land cover classification [13].

Problem Statement.
In Google map, online measure distance feature is used for distance and area measurement as in Figure 1(a). e starting and ending point on an area lead to measurements error, and moving the points with slight variation in distance leads to error in measurement. e area measurement of irregular shapes and size of area leads to more error as shown in Figures 1(a) and 1(b).
From online area measurements in maps for curved path measurements especially in on road areas measurement, error is about 5 to 50 m. Curved path measurements need clear boundary regions to fix the points. e more points in curved region lead to compound error in area measurement. Furthermore, area measurement error is more in the longdistances in the multiple earth surfaces areas such as roads, water body, and vegetation.

Contributions.
e classification accuracy of traditional methods such as KNN, SVM, and PSO provide more error in area measurement. Hence, in this paper, the backtracking search optimization (BSO) algorithm is applied to delineate land covers in urban, semiurban, hill, and coastal region. e BSO iteratively classifies mixed pixels in image by producing new population of radiometric pixel values via selection, crossover, and mutation process. e mixed pixel classifies until global optimal solution satisfies for particular classification process.
(i) To obtain multitemporal change detection through accurate area measurement obtained through the BSO segmentation algorithm to exact enhanced boundary end point selections under different earth surfaces. (ii) To obtain more accuracy in the measurement of area for on and off-road condition, implement through the single and multiple thresholding of pixels with more number of iterations in BSO algorithms, and improve enhancement and segmentation algorithm.
(iii) To validate area measurement of the proposed BSO algorithm, different areas such as hill, urban, road, and water body areas are measured form multipleyear period satellite images. (iv) To obtain accurate area measurement in curved path, BSO algorithm is proposed. e BSO algorithm enhances and segments the curvature boundary of different land surfaces such as road, hills, and waterbody. e paper is organized as follows. Section 2 explains the methodology of BSO in land area measurement. Section 3 explains backtracking search optimization (BSO) algorithm for land surface segmentation and area measurement, and finally Section 4 discusses and concludes about the efficiency of the BSO algorithm.

Methodology
e land cover change in a locality over the year is identified by shape and spectral characteristics of land features from satellite images. e shape and land features extractions are never accurate due to irregular shape and size of area. e    nonparametric method classi er such as arti cial neural network (ANN), Decision tree, and Support Vector Machine (SVM) classi es the land cover with deterministic theories. e classi er algorithm further classi es as supervised and unsupervised classi cation algorithm. e supervised classi cation algorithm requires data training. e supervised classi cation trains by sample pixels from land cover image as input.
e unsupervised classi er classi es land components with interpreter. e interpreter assigns class to di erent land components present in image depending on pixel spectral values. e traditional methods provide inaccurate land cover classi cation for complex land cover with mixed pixels and nonspectral land cover region. Hence, the backtracking search optimization (BSO) algorithm is applied, and it classi es land surface of low resolution (LANDSAT) and high-resolution (Sentinel) satellite images. e BSO classi es land surface successively and classi es mixed pixels in the image. e performance of the BSO algorithm is compared with particle swarm optimization for land cover classi cation. Figure 2 shows overview of area measurement methods.
e PSO algorithm works based on social behavior of birds. e synchronized bird ocking with sudden changes in movement, regrouping, and ying in a particular direction is in uenced in the PSO algorithm. In land cover classi cation, PSO algorithms apply to group similar land covers.
e similar land cover in image is identi ed as particles. Initially, the particles distribute randomly over the image solution space. e particles group until the global optimal solution is reached. e particle group with random change in particle coordinates, speed in successive approximation, and nd personal best t are represented by (1) and (2): i 1, 2, 3,. . .. N where "N" is the swarm size. j 1, 2, 3, . . . D where "D" is the problem dimension. k 1, 2, 3, . . . I where I represents iteration number. x ij k represents particle position, dimension, and current iteration. v ij k represents velocity of particle with respect to its coordinates. e "c" represents particle acceleration; p ij k and p gj k are personal best t and neighbor best t of particular particle in solution space. e particle keeps track of the coordinates and personal best t of adjacent particles. All particles work under same principle to reach global optimal solution. e particles move towards global best solution by evaluating tness function for each coordinate to group land with similar aesthetics. e PSO terminates when global t solution is reached or number of iterations has completed. e PSO further classi es as Discrete Particle Swarm Optimization (DPSO) and Fractional Order Darwinian Particle Swarm Optimization (FODPSO).

Study Area.
e study area is Chennai urban and Tirupathi suburban province of INDIA for land cover classication. e study area of Chennai and Tirupathi with latitude and longitude is shown in Table 1  land cover classification. Sentinel satellites acquire highresolution image of land covers with 10-to 60-meter spatial resolution. e image resolution varies because of spectral band usage. e four spectral band and six spectral band provide 10-meter and 20-meter resolution images. Landsat-8 satellite consists of thermal infrared sensor and operational land imager. e sensors provide radiometric output of land cover with the reflected radiation and electromagnetic spectrum from earth surface. Figure 3 shows urban Chennai region land cover classification with PSO algorithm. e PSO and DPSO perform well for high-resolution land cover classification. e DPSO shows discontinued roads and minimal vegetation present in land image and fails to classify vegetation boundary region and water body in Landsat and sentinel images. e vegetation boundary region in urban region in Landsat and sentinel image is never properly visible due to mixed pixel values in vegetation region. Similarly, the road which ranges from 50 to 60 feet identifies and road below 40 feet fails to detect with PSO and DPSO as shown in Figures 3(a) and  3(b). Figure 4 shows low-resolution and high-resolution satellite image classification with PSO family. e PSO family never classifies land cover region accurately around vegetation region due to higher population of mixed pixels around vegetation and barren land components in Landsat and sentinel image. e water body and green land show distinct variation due to distinct pixel variations. Similarly, the hill region and coastal region show minimal land surface classification as in Figures 5 and 6. Figure 6 shows coastal region of kodiyakadu in Tamilnadu, India. e PSO, DPSO, and FODPSO never segment the region such as beach face, land cover, fallow land, barren land, saltpan, saltwater body, and plantation. e high-resolution sentinel image shows more pixel classification around the coastal region due to pixel saturation by PSO family as in Figures 6(a) and 6(b). e pixel saturation and mixed pixels are classified more accurately with the backtracking search optimization (BSO) algorithm.

Backtracking Search Optimization (BSO)
Algorithm for Land Surface Segmentation and Area Measurement e backtracking search optimization algorithm determines global minimum and global maximum of radiometric pixel values in land cover image as described in the following:  Mathematical Problems in Engineering where f (x) is the input image and ∈ ranges from values between (0.01 to 0.1). e different components in land image are randomly assigned with radiometric pixel values as follows: e pixels of land image surface initially randomize for i � 1, 2, 3, ,,N and j � 1, 2, 3, ,, D where N is the pixel intensity range and D is the land surface boundary size. e up j , and low j are upper and lower bound of land surface and rand assign with random number between 0 and 1. e majority of land surface in image select and radiometric pixel values update according to (4).
e pixel values updated with pixel thresholding and old pixel (old p ) values are obtained by (4). e old radiometric pixel values reshuffle randomly up to x iterations determined by mutation process as follows: Similarly, the suburban region shows change in land, water body, and vegetation as in Figure 9. e AVADI Lake shows distinct change in pixel variation by delineating 451.34 m 2 land cover on 321588.37 m 2 lakes (as per AVADI municipality records). Furthermore, land mound with cross section of 10 × 10 meter was constructed on lake for fishing after year 2018 as in Figure 9(b). e BSO delineates land mound from high-resolution satellite image and never delineates land mound from low-resolution satellite images as in Figures 9(c) and 9(d). e hill region and coastal area land classification with BSO is shown in Figures 10and 11, respectively. e algorithm delineates hill pits, vegetation, water body, and barren land as shown in Figures 10(a) and 10(b). e delineation of land cover is performed well for high-resolution satellite images due to pixel thresholding at successive iterations during BSO mutation process in the BSO algorithm. Similarly, BSO classifies coastal area, which comprises saltpan, saltwater, plantation, fallow land, and barren land as shown in Figures 11(a)-11(d). e shoreline inundation and saltpan data were acquired from different sources such as Geological survey of INDIA, IFSAR, and ALOS PALSAR. e saltpan and saltwater in coastal area are classified by successive pixel value thresholding during mutation process of the BSO algorithm. e water body along coastal region has increased by 48% from March 2016 to March 2019 due to water inflow from ocean as in Figures 11(a) and 11(b). e BSO classifies land cover and land surface better compared with particle swarm optimization. e groundtruth verification for BSO land cover estimation is 97% more accurate compared with PSO land cover classification. e comparative analysis of land use, land cover, and change in land cover changes is shown in Tables 2 and 3.

Conclusion
e online area measurement from Google maps is inaccurate in land area measurement due to the different surface areas, curvatures, and sample point problems. Moreover, targeted land cover classification and land-cover classes of interest needs more ground-truth samples to reduce complexity and economic cost. e proposed BSO algorithm never needs the samples to classify the class of interest. Furthermore, the BSO algorithm is compared with SVM and KNN algorithms. e accurate area measurement is obtained through the backtracking search optimization-based automated single and multithresholding pixels from different iterations on the land surface. e backtracking search optimization (BSO) algorithm for area measurement is implemented through pixel intensity change with respect to spatial and temporal changes. Form the experimentation results, accurate land area measurement such as urban, semiurban, hill, and coastal region from LANSAT and SENTINEL images for period 2016 to 2019 shows better accuracy for BSO algorithm-based area measurement than the online area measurement form Google maps, and then  starting and end points can be fixed for high accuracy in land surface area measurement. e BSO algorithm performs better for land use and land cover classification of lowresolution and high-resolution images. e BSO successfully delineated land use and land covers with 97% more accuracy in land area measurement from different regions such as urban, semiurban, hill, and coastal region compared with PSO, DPSO, and FODPSO algorithms. e delineation accuracy improves by threshold in pixel values after successive iterations of BSO mutation process. e BSO shows land use in urban area increased by 12% in urban, 28% in suburban, less than 5% in coastal, and less than 1% in hill region.
e land use change verified with ground-truth verification shows 97% accuracy. Furthermore, the BSO algorithm can be combined with deep learning algorithms for more accuracy and to reduce the ground-truth verification cost [14,15].
Data Availability e data shall be made available on request.

Conflicts of Interest
e authors declare that they have no conflicts of interest.