Fuzzy logic detection of landmines with ground penetrating radar

نویسندگان

  • Paul D. Gader
  • Bruce N. Nelson
  • Hichem Frigui
  • Gary Vaillette
  • James M. Keller
چکیده

An automatic landmine detection algorithm using Ground Penetrating Radar is described. The algorithm combines outputs of multiple detection and feature extraction algorithms to generate a single confidence that a landmine is present at a location. The combination is performed using a fuzzy inference system. Results are provided for real data obtained in real-time with the Geo-Centers Vehicle Mounted Mine Detection System (VMMDS). Detection and removal of landmines is a serious problem affecting civilians and soldiers worldwide. It is estimated that there are up to 100 million active buried million landmines in the world and that every 20 minutes someone is either killed or maimed by a landmine [1]. Ground Penetrating Radar (GPR) sensors are currently under investigation for landmine detection. A signal processing research question is “How well can GPR signatures of landmines can be detected and discriminated from signatures generated by non-mine clutter or system artifacts?”. We describe an experimental signal processing approach todetecting landmines with GPR that uses multiple algorithms to generate a confidence value that a landmine is present at a location. The confidence values from the multiple algorithms, or information sources, are combined to generate a single value using a Mamdani fuzzy inference system. Results are presented for real data collected in real-time from the Geo-Centers VMMDS at a variety of locations in the United States. The GPR data is first described. An overview of the detection algorithm is then given. The individual information sources are described. Some information sources have been tested in the field and results are provided for those. The fuzzy inference system is discussed. The experimental results show that fusing information sources based on the same sensor with fuzzy logic can dramatically reduce false alarms while not reducing detection rates. The GEO-CENTERS’ VMMDS uses a patented Energy Focusing GPR (EFGPR)[2,3] specifically designed for use in vehicle mounted mine detection applications. The EFGPR incorporates 15 transmitter/receiver pairs. Each transmitter is sequentially pulsed with time delays that result in the simultaneous arrival of the radar wavefronts at a unique point in space. The reflected energy from that point is then detected by the receivers that are individually gated with time delays to receive signals from this point. Individual transmitter/receiver time delays are then modified to move the focus point and to create a two-dimensional “raster scan” or scan of the subsurface. Figure 1 illustrates the operation of the system with 4 transmitter/receiver pairs.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multi-feature Based Detection of Landmines Using Ground Penetrating Radar

In this paper, we present a method for detecting antitank or anti-personnel landmines buried in the ground. A set of data generated by a ground penetrating radar is processed to remove the surface reflection and clutter, yielding signals for possible landmines. In order to detect landmines in the signals, features are computed and compared against a database, which contains those of various lan...

متن کامل

Fuzzy Clustering for Land Mine Detection

Fuzzy Clustering is applied to the problem of detecting landmines. Sensor data generated by a Ground Penetrating Radar (GPR) is processed to detect the mines. The GPR produces a three-dimensional array of intensity values, representing a volume below the surface of the ground. Features are computed from this array and clustered using a fuzzy Competitive Agglom-erative (CA) algorithm. Prototypes...

متن کامل

Application of Advanced Background Subtraction Techniques for the Detection of Buried Plastic Landmines

Landmine problem is enormous and worldwide. Impulse ground penetrating radar (ImGPR) is one of the technologies that have been extensively researched as a means of improving landmine detection efficiency. We propose two methods to detect buried landmines. Both methods are based on background subtraction techniques to detect buried plastic landmines. The first method uses adaptive background est...

متن کامل

Multi-Feature Based Multiple Landmine Detection Using Ground Penetration Radar

This paper presents a novel method for detection of multiple landmines using a ground penetrating radar (GPR). Conventional algorithms mainly focus on detection of a single landmine, which cannot linearly extend to the multiple landmine case. The proposed algorithm is composed of four steps; estimation of the number of multiple objects buried in the ground, isolation of each object, feature ext...

متن کامل

Signal Processing Techniques for Landmine Detection Using Impulse Ground Penetrating Radar

Landmines are affecting the lives and livelihoods of millions of people around the world. A number of detection techniques, developed for use with impulse ground penetrating radar, are described, with emphasis on a Kalman filter based approach. Comparison of results from real data show that the Kalman filter algorithm provides the best detection performance, although its computational burden is...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Signal Processing

دوره 80  شماره 

صفحات  -

تاریخ انتشار 2000