Segmentation for Object-Based Image Analysis (OBIA): A review of algorithms and challenges from remote sensing perspective

Hossain, Mohammad Dalower; Chen, Dongmei

doi:10.1016/j.isprsjprs.2019.02.009

Cited by 466 publications

(274 citation statements)

References 306 publications

Supporting

Mentioning

269

Contrasting

Unclassified

Order By: Relevance

“…Using a simple histogram thresholding analysis as a classification technique, the overall results showed that specific spectral bands or NIR-derived VIs perform better than the others for discriminating shadow, defoliation, and foliated tree species, which was determined by accuracy assessment in a confusion matrix. In contrast to this simple classification approach, we also used a more complex and robust object-based image classification technique with Random Forest, resulting in overall excellent performance as expected from the literature reviews [33][34][35][36][37].…”

Section: Discussionmentioning

confidence: 99%

“…However, no study has applied such a simple classification method, combined with very high spatial resolution UAS imagery, to forestry applications. This is due to the recent trend in research of UAS technology combined with object-based classification methods such as of 23 OBIA and Random Forest which have demonstrated excellent performance for analyzing complex high spatial resolution data including multispectral, geospatial, and textural properties [33][34][35][36][37]. Although, these object-based image classification techniques are generally considered to be more robust and accurate [33][34][35][36][37], it may require extra knowledge and training with software applications to perform such complex analysis correctly.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimating the Threshold of Detection on Tree Crown Defoliation Using Vegetation Indices from UAS Multispectral Imagery

Otsu

Pla

Duane

et al. 2019

Drones

View full text Add to dashboard Cite

Periodical outbreaks of Thaumetopoea pityocampa feeding on pine needles may pose a threat to Mediterranean coniferous forests by causing severe tree defoliation, growth reduction, and eventually mortality. To cost–effectively monitor the temporal and spatial damages in pine–oak mixed stands using unmanned aerial systems (UASs) for multispectral imagery, we aimed at developing a simple thresholding classification tool for forest practitioners as an alternative method to complex classifiers such as Random Forest. The UAS flights were performed during winter 2017–2018 over four study areas in Catalonia, northeastern Spain. To detect defoliation and further distinguish pine species, we conducted nested histogram thresholding analyses with four UAS-derived vegetation indices (VIs) and evaluated classification accuracy. The normalized difference vegetation index (NDVI) and NDVI red edge performed the best for detecting defoliation with an overall accuracy of 95% in the total study area. For discriminating pine species, accuracy results of 93–96% were only achievable with green NDVI in the partial study area, where the Random Forest classification combined for defoliation and tree species resulted in 91–93%. Finally, we achieved to estimate the average thresholds of VIs for detecting defoliation over the total area, which may be applicable across similar Mediterranean pine stands for monitoring regional forest health on a large scale.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimating the Threshold of Detection on Tree Crown Defoliation Using Vegetation Indices from UAS Multispectral Imagery

Otsu

Pla

Duane

et al. 2019

Drones

View full text Add to dashboard Cite

show abstract

“…These methods are exploited to recognize and detect weeds or discriminate different species in the field. A detailed review of algorithms and challenges for OBIA, from a remote sensing perspective, was reported by Hossain and Chen [135].…”

Section: Image Segmentation 2 Feature Extraction and Classificationmentioning

confidence: 99%

A Review on UAV-Based Applications for Precision Agriculture

2019

View full text Add to dashboard Cite

Emerging technologies such as Internet of Things (IoT) can provide significant potential in Smart Farming and Precision Agriculture applications, enabling the acquisition of real-time environmental data. IoT devices such as Unmanned Aerial Vehicles (UAVs) can be exploited in a variety of applications related to crops management, by capturing high spatial and temporal resolution images. These technologies are expected to revolutionize agriculture, enabling decision-making in days instead of weeks, promising significant reduction in cost and increase in the yield. Such decisions enable the effective application of farm inputs, supporting the four pillars of precision agriculture, i.e., apply the right practice, at the right place, at the right time and with the right quantity. However, the actual proliferation and exploitation of UAVs in Smart Farming has not been as robust as expected mainly due to the challenges confronted when selecting and deploying the relevant technologies, including the data acquisition and image processing methods. The main problem is that still there is no standardized workflow for the use of UAVs in such applications, as it is a relatively new area. In this article, we review the most recent applications of UAVs for Precision Agriculture. We discuss the most common applications, the types of UAVs exploited and then we focus on the data acquisition methods and technologies, appointing the benefits and drawbacks of each one. We also point out the most popular processing methods of aerial imagery and discuss the outcomes of each method and the potential applications of each one in the farming operations.

show abstract

“…The former one is based on reliable samples or suitable thresholds via visual inspection [23]. The other provides an effective method for uniting spatial information, texture information, and semantic information in feature detection [24,25], but may complicate the algorithms. Instead of processing the image with individual pixels directly, the object-based method segments the original image into independent objects in which the pixels are addressed as the same land cover in the following processes [26] using different segmentation algorithms [27][28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Object-Based Shadow Index via Illumination Intensity from High Resolution Satellite Images over Urban Areas

Zhou

Sun

2020

Sensors

View full text Add to dashboard Cite

For multi-spectral remote sensing imagery, accurate shadow extraction is of great significance for overcoming the information loss caused by high buildings and the solar incidence angle in urban remote sensing. However, diverse solar illumination conditions, similarities between shadows, and other dark land features bring uncertainties and deviations to shadow extraction processes and results. In this paper, we classify shadows as either strong or weak based on the ratio between ambient light intensity and direct light intensity, and use the fractal net evolution approach (FNEA), which is a multi-scale segmentation method based on spectral and shape heterogeneity, to reduce the interference of salt and pepper noise and relieve the error of misdiagnosing land covers with high reflectivity in shaded regions as unshaded ones. Subsequently, an object-based shadow index (OSI) is presented according to the illumination intensities of different reflectance features, as well as using the normalized difference water index (NDWI) and near infrared (NIR) band to highlight shadows and eliminate water body interference. The data from three high-spatial-resolution satellites—WorldView-2 (WV-2), WorldView-3 (WV-3), and GaoFen-2 (GF-2)—were used to test the methods and verify the robustness of the OSI. The results show that the OSI index performed well regarding both strong and weak shadows with the user accuracy and the producer accuracy both above 90%, while the four other existing indexes that were tested were not effective at diverse solar illumination conditions. In addition, all the disturbances from water body were excluded well when using the OSI, except for the GF-2 data in weak shadows.

show abstract

Segmentation for Object-Based Image Analysis (OBIA): A review of algorithms and challenges from remote sensing perspective

Cited by 466 publications

References 306 publications

Estimating the Threshold of Detection on Tree Crown Defoliation Using Vegetation Indices from UAS Multispectral Imagery

Estimating the Threshold of Detection on Tree Crown Defoliation Using Vegetation Indices from UAS Multispectral Imagery

A Review on UAV-Based Applications for Precision Agriculture

Object-Based Shadow Index via Illumination Intensity from High Resolution Satellite Images over Urban Areas

Contact Info

Product

Resources

About