USING REDUNDANT INFORMATION FROM MULTIPLE AERIAL IMAGES FOR THE DETECTION OF BOMB CRATERS BASED ON MARKED POINT PROCESSES

Abstract. Many countries were the target of air strikes during World War II. Numerous unexploded bombs still exist in the ground. These duds can be tracked down with the help of bomb craters, indicating areas where unexploded bombs may be located. Such areas are documented in so-called impact maps based on detected bomb craters. In this paper, a stochastic approach based on marked point processes (MPPs) for the automatic detection of bomb craters in aerial images taken during World War II is presented. As most areas are covered by multiple images, the influence of redundant image information on the object detection result is investigated: we compare the results generated based on single images with those obtained by our new approach that combines the individual detection results of multiple images covering the same location. The object model for the bomb craters is represented by circles. Our MPP approach determines the most likely configuration of objects within the scene. The goal is reached by minimizing an energy function that describes the conformity with a predefined model by Reversible Jump Markov Chain Monte Carlo sampling in combination with simulated annealing. Afterwards, a probability map is generated from the automatic detections via kernel density estimation. By setting a threshold, areas around the detections are classified as contaminated or uncontaminated sites, respectively, which results in an impact map. Our results show a significant improvement with respect to its quality when redundant image information is used.

[1]  Florent Lafarge,et al.  Geometric Feature Extraction by a Multimarked Point Process , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  W. Förstner,et al.  COMBINE MARKOV RANDOM FIELDS AND MARKED POINT PROCESSES TO EXTRACT BUILDING FROM REMOTELY SENSED IMAGES , 2012 .

[3]  Sanjiv Kumar,et al.  Discriminative Random Fields , 2006, International Journal of Computer Vision.

[4]  Xavier Descombes,et al.  Multiple objects detection in biological images using a marked point process framework. , 2017, Methods.

[5]  Christian Heipke,et al.  Marked Point Processes for the Automatic Detection of Bomb Craters in Aerial Wartime Images , 2019 .

[6]  Jon Atli Benediktsson,et al.  Crater detection based on marked point processes , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[7]  Tingting Lv,et al.  Crater Detection via Convolutional Neural Networks , 2016, ArXiv.

[8]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[9]  Ding Meng,et al.  Method of Passive Image Based Crater Autonomous Detection , 2009 .

[10]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[11]  Xavier Descombes,et al.  Cells detection using segmentation competition , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[12]  Josiane Zerubia,et al.  Unsupervised marked point process model for boat extraction in harbors from high resolution optical remotely sensed images , 2013, 2013 IEEE International Conference on Image Processing.

[13]  Adrien Bousseau,et al.  Extracting Geometric Structures in Images with Delaunay Point Processes , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  O. Tournaire,et al.  Extracting polygonal building footprints from digital surface models: A fully-automatic global optimization framework , 2013 .

[15]  Bo Wu,et al.  Active Machine Learning Approach for Crater Detection From Planetary Imagery and Digital Elevation Models , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Csaba Benedek,et al.  An Embedded Marked Point Process Framework for Three-Level Object Population Analysis , 2017, IEEE Transactions on Image Processing.

[17]  Ulrike Goldschmidt,et al.  An Introduction To The Theory Of Point Processes , 2016 .

[18]  Christian Heipke,et al.  SUPERVISED DETECTION OF BOMB CRATERS IN HISTORICAL AERIAL IMAGES USING CONVOLUTIONAL NEURAL NETWORKS , 2019 .

[19]  S. Sheather.  Density Estimation , 2004 .

[20]  Wolfgang Förstner,et al.  FACADE INTERPRETATION USING A MARKED POINT PROCESS , 2016 .

[21]  Alfredo Petrosino,et al.  Image Analysis and Processing , 2016, Springer US.

[22]  Cesare Furlanello,et al.  Machine Learning on Historic Air Photographs for Mapping Risk of Unexploded Bombs , 2005, ICIAP.

[24]  Nicolas Cedilnik,et al.  SPADE: A Small Particle Detection Method Using A Dictionary Of Shapes Within The Marked Point Process Framework , 2018 .

[25]  Hubert Konik,et al.  Automatic Method for Visual Grading of Seed Food Products , 2014, ICIAR.

[26]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[27]  Josiane Zerubia,et al.  Marked point process in image analysis , 2002, IEEE Signal Process. Mag..

[28]  Emile H. L. Aarts,et al.  Simulated Annealing: Theory and Applications , 1987, Mathematics and Its Applications.

[30]  Tomasz F. Stepinski,et al.  Automatic detection of sub-km craters in high resolution planetary images , 2009 .

[31]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[32]  F. Rottensteiner,et al.  GENERATING IMPACT MAPS FROM AUTOMATICALLY DETECTED BOMB CRATERS IN AERIAL WARTIME IMAGES USING MARKED POINT PROCESSES , 2018 .

[33]  Josiane Zerubia,et al.  Automatic Flamingo detection using a multiple birth and death process , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[34]  Gabriele Moser,et al.  Planetary crater detection and registration using marked point processes, multiple birth and death algorithms, and region-based analysis , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[35]  Rie Honda,et al.  Learning to Detect Small Impact Craters , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[36]  Qingxian Wu,et al.  Novel approach of crater detection by crater candidate region selection and matrix-pattern-oriented least squares support vector machine , 2013 .

[37]  Touqeer Ahmad,et al.  Crater Detection Using Unsupervised Algorithms and Convolutional Neural Networks , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[38]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[39]  Ming Cheng,et al.  A marked point process for automated tree detection from mobile laser scanning point cloud data , 2012, 2012 International Conference on Computer Vision in Remote Sensing.

[40]  G. Sohn,et al.  SINGLE TREE DETECTION FROM AIRBORNE LASER SCANNING DATA USING A MARKED POINT PROCESS BASED METHOD , 2013 .

[41]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[42]  D. W. Scott.  Kernel Density Estimators , 2008 .