gprHOG and the popularity of Histogram of Oriented Gradients (HOG) for Buried Threat Detection in Ground-Penetrating Radar

Substantial research has been devoted to the development of algorithms that automate buried threat detection (BTD) with ground penetrating radar (GPR) data, resulting in a large number of proposed algorithms. One popular algorithm GPR-based BTD, originally applied by Torrione et al., 2012, is the Histogram of Oriented Gradients (HOG) feature. In a recent large-scale comparison among five veteran institutions, a modified version of HOG referred to here as "gprHOG", performed poorly compared to other modern algorithms. In this paper, we provide experimental evidence demonstrating that the modifications to HOG that comprise gprHOG result in a substantially better-performing algorithm. The results here, in conjunction with the large-scale algorithm comparison, suggest that HOG is not competitive with modern GPR-based BTD algorithms. Given HOG's popularity, these results raise some questions about many existing studies, and suggest gprHOG (and especially HOG) should be employed with caution in future studies.

[1]  Jordan M. Malof,et al.  A Large-Scale Multi-Institutional Evaluation of Advanced Discrimination Algorithms for Buried Threat Detection in Ground Penetrating Radar , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  Jordan M. Malof,et al.  Improvements to the Histogram of Oriented Gradient (HOG) prescreener for buried threat detection in ground penetrating radar data , 2017, Defense + Security.

[4]  M. M. Mokji,et al.  Automatic target detection in GPR images using Histogram of Oriented Gradients (HOG) , 2014, 2014 2nd International Conference on Electronic Design (ICED).

[5]  Sébastien Lefèvre,et al.  Buried Object Detection from B-Scan Ground Penetrating Radar Data Using Faster-RCNN , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[6]  Leslie M. Collins,et al.  Texture Features for Antitank Landmine Detection Using Ground Penetrating Radar , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[7]  Arban Uka,et al.  Comparison of histograms of oriented gradients and 3-row Average Subtraction (3RAS) using GprMax , 2017, 2017 6th Mediterranean Conference on Embedded Computing (MECO).

[8]  Hichem Frigui,et al.  A fisher vector representation of GPR data for detecting buried objects , 2016, SPIE Defense + Security.

[9]  Jordan M. Malof,et al.  Discriminative dictionary learning to learn effective features for detecting buried threats in ground penetrating radar data , 2017, Defense + Security.

[10]  Lance E. Besaw,et al.  Detecting buried explosive hazards with handheld GPR and deep learning , 2016, SPIE Defense + Security.

[11]  Jordan M. Malof,et al.  Some good practices for applying convolutional neural networks to buried threat detection in Ground Penetrating Radar , 2017, 2017 9th International Workshop on Advanced Ground Penetrating Radar (IWAGPR).

[12]  N. Aswini,et al.  Detection and classification of ground penetrating radar image using textrual features , 2014, 2014 International Conference on Advances in Electronics Computers and Communications.

[13]  Przemyslaw Klesk,et al.  Fast Analysis of C-Scans From Ground Penetrating Radar via 3-D Haar-Like Features With Application to Landmine Detection , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[14]  Jordan M. Malof,et al.  Learning improved pooling regions for the Histogram of Oriented Gradient (HOG) feature for buried threat detection in ground penetrating radar , 2017, Defense + Security.

[15]  Jordan M. Malof,et al.  On Choosing Training and Testing Data for Supervised Algorithms in Ground-Penetrating Radar Data for Buried Threat Detection , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Jordan M. Malof,et al.  How do we choose the best model? The impact of cross-validation design on model evaluation for buried threat detection in ground penetrating radar , 2018, Defense + Security.

[17]  Umar S. Khan,et al.  Using pattern recognition with HOG to automatically detect reflection hyperbolas in ground penetrating radar data , 2017, 2017 International Conference on Electrical and Computing Technologies and Applications (ICECTA).

[18]  Eyyup Temlioglu,et al.  Comparison of feature extraction methods for landmine detection using Ground Penetrating Radar , 2016, 2016 24th Signal Processing and Communication Application Conference (SIU).

[19]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[20]  Paul D. Gader,et al.  Landmine detection using discrete hidden Markov models with Gabor features , 2007, SPIE Defense + Commercial Sensing.

[21]  Leslie M. Collins,et al.  Histograms of Oriented Gradients for Landmine Detection in Ground-Penetrating Radar Data , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[22]  Joseph N. Wilson,et al.  A Large-Scale Systematic Evaluation of Algorithms Using Ground-Penetrating Radar for Landmine Detection and Discrimination , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[23]  Akara Prayote,et al.  Fast and efficient detection of buried object for GPR image , 2014, The 20th Asia-Pacific Conference on Communication (APCC2014).

[24]  X. Derobert,et al.  Assessment of statistical-based clutter reduction techniques on ground-coupled GPR data for the detection of buried objects in soils , 2014, Proceedings of the 15th International Conference on Ground Penetrating Radar.

[25]  Jordan M. Malof,et al.  How much shape information is enough, or too much? Designing imaging descriptors for threat detection in ground penetrating radar data , 2018, Defense + Security.

[26]  Paul D. Gader,et al.  Detection and Discrimination of Land Mines in Ground-Penetrating Radar Based on Edge Histogram Descriptors and a Possibilistic $K$-Nearest Neighbor Classifier , 2009, IEEE Transactions on Fuzzy Systems.

[27]  Jordan M. Malof,et al.  Algorithm development for deeply buried threat detection in GPR data , 2016, SPIE Defense + Security.

[28]  Jordan M. Malof,et al.  The effect of translational variance in training and testing images on supervised buried threat detection algorithms for ground penetrating radar , 2017, 2017 9th International Workshop on Advanced Ground Penetrating Radar (IWAGPR).

[29]  Eyyup Temlioglu,et al.  Histograms of Dominant Orientations for anti-personnel landmine detection using Ground Penetrating Radar , 2017, 2017 4th International Conference on Electrical and Electronic Engineering (ICEEE).