Segmentation-Based Boundary Modeling For Natural Terrain Scenes

1980 ◽  
Author(s):  
Charles A. McNary ◽  
Diane K. Conti ◽  
Wilfried O. Eckhardt
Keyword(s):  
1997 ◽  
Author(s):  
Randall D. Beer ◽  
Roger Quinn ◽  
Roy Ritzmann ◽  
Hillel Chiel

2014 ◽  
Vol 5 (2) ◽  
pp. 1-21 ◽  
Author(s):  
Arpita Sharma ◽  
Samiksha Goel

This paper proposes two novel nature inspired decision level fusion techniques, Cuckoo Search Decision Fusion (CSDF) and Improved Cuckoo Search Decision Fusion (ICSDF) for enhanced and refined extraction of terrain features from remote sensing data. The developed techniques derive their basis from a recently introduced bio-inspired meta-heuristic Cuckoo Search and modify it suitably to be used as a fusion technique. The algorithms are validated on remote sensing satellite images acquired by multispectral sensors namely LISS3 Sensor image of Alwar region in Rajasthan, India and LANDSAT Sensor image of Delhi region, India. Overall accuracies obtained are substantially better than those of the four individual terrain classifiers used for fusion. Results are also compared with majority voting and average weighing policy fusion strategies. A notable achievement of the proposed fusion techniques is that the two difficult to identify terrains namely barren and urban are identified with similar high accuracies as other well identified land cover types, which was not possible by single analyzers.


Author(s):  
M. Lebherz ◽  
W. Wiesbeck ◽  
W. Krank
Keyword(s):  

2018 ◽  
Vol 25 (2) ◽  
pp. 90-101 ◽  
Author(s):  
Julian S H Kwan ◽  
Harris W K Lam ◽  
Charles W W Ng ◽  
Nelson T K Lam ◽  
S L Chan ◽  
...  

2021 ◽  
Author(s):  
Vincent Acary ◽  
Franck Bourrier ◽  
David Toe ◽  
Francois Kneib

<p><br>Block propagation models are routinely used for the quantitative assessment of rockfall hazard. In these models, one of the major difficulties is the development of physically consistent and field applicable approaches to model the interaction between the block and the natural terrain. For most of propagation models, a thorough calibration of the input parameters is not available over the wide range of configurations encountered in practice. Consequently, the parameters choice is strongly depending on expert knowledge. In addition, most of models exhibit substantial sensitivity to some parameters, i.e. small changes of these parameters entail large differences in the simulation results.</p><p>The trajectory analysis platform Platrock, freely available upon request (contact: [email protected]), allows performing 2D and 3D simulations using both material point rebound models and models, based on non-smooth mechanics, that explicitly account for block shape. This platform provides several simulation tools for detailed analyses of block propagation on study sites.</p><p>The possibilities of the predictive capabilities of different block propagation modelling approaches integrated into the Platrock platform have been assessed on a well-documented study site, where a benchmark of propagation models has been done in the context of C2ROP research project. This analysis emphasized the capacities of trajectory analyses to traduce block propagation but also demonstrated their substantial sensitivity to model parameters. The results from these simulations cannot be relevantly interpreted if they are not accompanied with calibration proofs, sensitivity analysis, and detailed interpretation of the results from the expert in charge of the study.</p>


Sign in / Sign up

Export Citation Format

Share Document