Roadway Interface Analysis with A Support Vector Regression Based Linear Prediction Method Using Stepped-Frequency Radar

Cédric Le Bastard (1) , J. Pan (2) , Yide Wang (2) , S. Todkar (1) , Amine Ihamouten (1) , Xavier Derobert (3) , David Guilbert (1) , M. Sun (4)

1 ENDSUM - Evaluation non destructive des structures et des matériaux
2 IETR - Institut d'Électronique et des Technologies du numéRique
3 IFSTTAR/GERS/GeoEND - Laboratoire Géophysique et évaluation non destructive
4 Shanghai Maritime University

Ground Penetrating Radar (GPR) is a widely used tool in the management and monitoring of pavement structures. In this paper, we focus on the detection of thin inter-layer debondings between the hot mix asphalt layers of pavement structures. A Stepped-Frequency Radar (SFR) associated with a Support Vector Regression based Linear Prediction (LP-SVR) method is used to detect thin debondings. The performance of SFR with the LP-SVR method is analyzed according to various used frequency bandwidths on the experimental data.

Mots clés: STEPPED-FREQUENCY RADAR (SFR); DETECTION; ROADWAY; LINEAR PREDICTION (LP); SUPPORT VECTOR REGRESSION (SVR)

Mots clés: DECOLLEMENT; CHAUSSEE (CORPS DE); ALTERATION (GEN); RADAR; CONFERENCE; JAPON; DETECTION; ROUTE; MODELE PREDICTIF; RADAR PENETRANT; STRUCTURE DE CHAUSSEE

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Sciences de l'ingénieur [physics]; Electromagnétisme; Traitement du signal et de l'image [eess.SP]

Cédric Le Bastard, J. Pan, Yide Wang, S. Todkar, Amine Ihamouten, et al.. Roadway Interface Analysis with A Support Vector Regression Based Linear Prediction Method Using Stepped-Frequency Radar. IGARSS 2019, IEEE International Geoscience and Remote Sensing Symposium, Jul 2019, Yokohama, Japan. pp. 3598-3601, ⟨10.1109/IGARSS.2019.8899302⟩. ⟨hal-02993052⟩