Computer Vision in Remote Sensing

Lab 5 Computer Vision in Remote Sensing Literature Review

Chioce of Topic: OBIA using UAV Imagery

Source 1: (Article) Mapping and Classification of Ecologically Sensitive Marine Habitats Using Unmanned Aerial Vehicle (UAV) Imagery and Object-Based Image Analysis (OBIA)

In this study, researchers utilized OBIA classification of high resolution UAV imagery to map three different ecologically sensitive marine habitatas in Italy. The authors concluded that OBIA classification of UAV imagery is an effiecient method for high resolution, low-cost, time saving classification mapping of sensitive marine environments and monitoring and management of natural resources. They also state that there is extreme benefit to using UAV imagery as it opens the door for ecologists to use OBIA for environmental modeling and allows researchers the powerful ability to control the temporal resolution of their data.

Source 2: (Blog) Boats, drones and Great Mapping Results

This blog discusses the use of OBIA with UAV imagery to map traditionally difficult-to-access coastal marshlands. The case study discussed utilized eCognition software to classify UAV imagery in Lousiana, USA. The blog emphasizes the importance of being able to accurately map and classify habitats without physically disturbing them, and use of a UAV is able to do just that. Additionally, it covers the topic of more detailed and accurate land cover maps being produced by OBIA.

Source 3: (Article) Comparison of pixel-based and object-based image classification techniques in extracting information from UAV imagery data

This study explored the classification of high resolution aerial imagery acquired via UAV in Perak, Malaysia to determine if supervised OBIA or pixel-based classification would produce more accurate results. Confusion matrices were computed for both methods and it was found that OBIA produced more accurate classifcation results. The authors emphasized that the pixelpbased technique created more mis-classified pixels and the OBIA method did a better job at classifying because it considered shape and texture of features instead of only considering spectral characteristics.

References

Source 1: Ventura, D., Bonifazi, A., Gravina, M. F., Belluscio, A., & Ardizzone, G. (2018). Mapping and classification of ecologically sensitive marine habitats using unmanned aerial vehicle (UAV) imagery and object-based image analysis (OBIA). Remote Sensing, 10(9), 1331.

Source 2: Stängel, M. (2020, January 20). Boats, drones and Great Mapping Results. eCognition Blog. Retrieved May 1, 2023, from https://ecognition.blog/boats-drones-and-great-mapping-results/

Source 3: Sibaruddin, H. I., Shafri, H. Z. M., Pradhan, B., & Haron, N. A. (2018, June). Comparison of pixel-based and object-based image classification techniques in extracting information from UAV imagery data. In IOP conference series: earth and environmental science (Vol. 169, No. 1, p. 012098). IOP Publishing.