Dr. Kasper Johansen Profile

Dr. Kasper Johansen

Postdoctoral Research Fellow at Univ of Queensland

SPIE Involvement:

Author

Publications (3)

Proceedings Article | 5 October 2017 Paper

Explicit area-based accuracy assessment for mangrove tree crown delineation using Geographic Object-Based Image Analysis (GEOBIA)

Muhammad Kamal, Kasper Johansen

Proceedings Volume 10428, 104280I (2017) https://doi.org/10.1117/12.2278179

KEYWORDS: Accuracy assessment, Image analysis, Image segmentation, Ecosystems, Associative arrays, Shape analysis, Visualization, Image resolution, Photography, Environmental monitoring

Read Abstract +

Effective mangrove management requires spatially explicit information of mangrove tree crown map as a basis for ecosystem diversity study and health assessment. Accuracy assessment is an integral part of any mapping activities to measure the effectiveness of the classification approach. In geographic object-based image analysis (GEOBIA) the assessment of the geometric accuracy (shape, symmetry and location) of the created image objects from image segmentation is required. In this study we used an explicit area-based accuracy assessment to measure the degree of similarity between the results of the classification and reference data from different aspects, including overall quality (OQ), user’s accuracy (UA), producer’s accuracy (PA) and overall accuracy (OA). We developed a rule set to delineate the mangrove tree crown using WorldView-2 pan-sharpened image. The reference map was obtained by visual delineation of the mangrove tree crowns boundaries form a very high-spatial resolution aerial photograph (7.5cm pixel size). Ten random points with a 10 m radius circular buffer were created to calculate the area-based accuracy assessment. The resulting circular polygons were used to clip both the classified image objects and reference map for area comparisons. In this case, the area-based accuracy assessment resulted 64% and 68% for the OQ and OA, respectively. The overall quality of the calculation results shows the class-related area accuracy; which is the area of correctly classified as tree crowns was 64% out of the total area of tree crowns. On the other hand, the overall accuracy of 68% was calculated as the percentage of all correctly classified classes (tree crowns and canopy gaps) in comparison to the total class area (an entire image). Overall, the area-based accuracy assessment was simple to implement and easy to interpret. It also shows explicitly the omission and commission error variations of object boundary delineation with colour coded polygons.

SPIE Journal Paper | 21 August 2014

Object-based classification of semi-arid vegetation to support mine rehabilitation and monitoring

Nisha Bao, Alex Lechner, Kasper Johansen, Baoying Ye

JARS, Vol. 8, Issue 01, 083564, (August 2014) https://doi.org/10.1117/12.10.1117/1.JRS.8.083564

KEYWORDS: Vegetation, Mining, Image classification, Image segmentation, Accuracy assessment, Land mines, Remote sensing, Image resolution, Spatial resolution, Fuzzy logic

Read Abstract +

Mining activities result in significantly modified landscapes that require rehabilitation to mitigate the negative environmental impacts and restore ecological function. The aim of this study was to develop a remote sensing method suitable for monitoring the vegetation cover at mine rehabilitation sites. We used object-based image analysis (OBIA) methods and high-spatial resolution SPOT-5 imagery to identify discrete land-cover patterns that occur at fine spatial scales. These patterns relate to spatial processes that are important drivers of successful restoration of mine sites. SPOT-5 imagery of the Kidston Gold mine tailing dam in semi-arid tropical north Queensland was acquired in July 2005, comprising four 10-m spectral bands and a 2.5-m panchromatic (PAN) band. The classification scheme used in this study was adapted to the spatial scale of SPOT-5 imagery from mine closure criteria cover requirements, according to a mine rehabilitation plan. Four land-cover classes were identified: tree cover, dense grass, sparse grass, and bare ground. First, textural layers (contrast, dissimilarity, and homogeneity) were derived for each vegetation class except for bare ground from the PAN and multispectral bands. Of all textural layer combinations, homogeneity and contrast in the PAN band were identified using a Z-test as the most useful for differentiating between multiple land-cover classes. Next, an optimal segmentation scale parameter of 15 was identified using an analysis of spatial autocorrelation. Finally, the SPOT-5 image bands, derived textural layers, and normalized difference vegetation index (NDVI) were used in an OBIA fuzzy membership classification approach to map vegetation land-cover classes. The classification results were assessed with the traditional error matrix approach and the object-based accuracy assessment method. The overall classification accuracy using the error matrix was 92.5% and 81% using the object-based method. The relatively high-classification accuracy demonstrates the potential of SPOT-5 imagery for monitoring mine rehabilitation. The complete spatial coverage associated with remote sensing data at fine spatial scales has the potential to complement field-based approaches commonly used in rehabilitation monitoring. Furthermore, SPOT-5 data along with OBIA can characterize vegetation spatial patterns at spatial scales appropriate for monitoring rehabilitated landscapes, providing an important tool for landscape function analysis.

SPIE Journal Paper | 28 October 2013

Assessing stream bank condition using airborne LiDAR and high spatial resolution image data in temperate semirural areas in Victoria, Australia

Kasper Johansen, James Grove, Robert Denham, Stuart Phinn

JARS, Vol. 7, Issue 01, 073492, (October 2013) https://doi.org/10.1117/12.10.1117/1.JRS.7.073492

KEYWORDS: Vegetation, LIDAR, Data modeling, Associative arrays, Spatial resolution, Image resolution, Visualization, Optical resolution, Image processing, Statistical modeling

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years