A Deep Learning-Based Fragment Detection Approach for the Arena Fragmentation Test

The arena fragmentation test (AFT) is one of the tests used to design an effective warhead. Conventionally, complex and expensive measuring equipment is used for testing a warhead and measuring important factors such as the size, velocity, and the spatial distribution of fragments where the fragments penetrate steel target plates. In this paper, instead of using specific sensors and equipment, we proposed the use of a deep learning-based object detection algorithm to detect fragments in the AFT. To this end, we acquired many high-speed videos and built an AFT image dataset with bounding boxes of warhead fragments. Our method fine-tuned an existing object detection network named the Faster R-convolutional neural network (CNN) on this dataset with modification of the network’s anchor boxes. We also employed a novel temporal filtering method, which was demonstrated as an effective non-fragment filtering scheme in our recent previous image processing-based fragment detection approach, to capture only the first penetrating fragments from all detected fragments. We showed that the performance of the proposed method was comparable to that of a sensor-based system under the same experimental conditions. We also demonstrated that the use of deep learning technologies in the task of AFT significantly enhanced the performance via a quantitative comparison between our proposed method and our recent previous image processing-based method. In other words, our proposed method outperformed the previous image processing-based method. The proposed method produced outstanding results in terms of finding the exact fragment positions.

[1]  Md. Saiful Islam,et al.  End-to-End Deep Learning Fusion of Fingerprint and Electrocardiogram Signals for Presentation Attack Detection , 2020, Sensors.

[2]  Insung Hwang,et al.  Real-Time Weld Quality Prediction Using a Laser Vision Sensor in a Lap Fillet Joint during Gas Metal Arc Welding , 2020, Sensors.

[3]  Byeongkeun Kang,et al.  High-Resolution Neural Network for Driver Visual Attention Prediction , 2020, Sensors.

[4]  Wei Li,et al.  Fragment Velocity Distribution of Cylindrical Rings Under Eccentric Point Initiation , 2015 .

[5]  Zhou Hanchang,et al.  Optoelectronic System for Measuring Warhead Fragments Velocity , 2011 .

[6]  Fariborz Baghaei Naeini,et al.  A Novel Dynamic-Vision-Based Approach for Tactile Sensing Applications , 2020, IEEE Transactions on Instrumentation and Measurement.

[7]  Robert X. Gao,et al.  Composite-Graph-Based Sparse Subspace Clustering for Machine Fault Diagnosis , 2020, IEEE Transactions on Instrumentation and Measurement.

[8]  Jesus Bermudez-Cameo,et al.  OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision , 2020, Sensors.

[9]  Guoliang Lu,et al.  Planar Motion Measurement of a Compliant Micro Stage: An Enhanced Microscopic Vision Approach , 2020, IEEE Transactions on Instrumentation and Measurement.

[10]  Marcia Muller,et al.  Sparse Force Mapping System Based on Compressive Sensing , 2017, IEEE Transactions on Instrumentation and Measurement.

[11]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Shibin Gao,et al.  A Robust Pantograph–Catenary Interaction Condition Monitoring Method Based on Deep Convolutional Network , 2020, IEEE Transactions on Instrumentation and Measurement.

[13]  M. Held,et al.  Consideration to the Mass Distribution of Fragments by natural‐fragmentation in combination with preformed fragments , 1976 .

[14]  Seung-Hyun Lee,et al.  Deep learning-based small object detection , 2018 .

[15]  Mohan M. Trivedi,et al.  Are all objects equal? Deep spatio-temporal importance prediction in driving videos , 2017, Pattern Recognit..

[16]  N. Mott,et al.  Fragmentation of shell cases , 1947, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[17]  B. R. Nayana,et al.  Improved Identification of Various Conditions of Induction Motor Bearing Faults , 2020, IEEE Transactions on Instrumentation and Measurement.

[18]  손원일,et al.  Deep Learning based Object Detection and Distance Estimation using Mono Camera , 2018, Journal of Korean Institute of Intelligent Systems.

[19]  Jooyoung Park,et al.  Prediction of Driver’s Intention of Lane Change by Augmenting Sensor Information Using Machine Learning Techniques , 2017, Sensors.