TY - GEN

T1 - Video Stream Processing for an Autonomous Tunnel Drainage Rover

AU - Giordano, Alessandro

AU - Zagar, Bernhard

AU - Micic Batka, Vesna

AU - Schachinger, Tobias

PY - 2023

Y1 - 2023

N2 - Drainage pipes in tunnels are very complicated to service but still need rather frequent inspections in order todetect the initiation of deposited scales stemming from carbonate that tends to precipitate when the pH-value of the mountainwater rises with the release of gaseous carbon dioxide CO2 due to a decreasing water pressure. Drainages allow to designtunnels without resistance to ground water pressure. We present a camera-based optical sensor, developed for an autonomousoperating tunnel drainage rover, that is able to detect and quantify deposited calcite constricting more or less severely the freecross section the drainage rover needs to safely navigate the pipe. The pipe's cross section is imaged via an area-scan cameraat a frame rate adopted to the rover's speed so that at least every 50 mm of movement a frame is acquired. The presented imageprocessing software is segmenting and classifying each frame into the pipe's wall, the pipe's free lumen, eventually existingwater, and calcite.

AB - Drainage pipes in tunnels are very complicated to service but still need rather frequent inspections in order todetect the initiation of deposited scales stemming from carbonate that tends to precipitate when the pH-value of the mountainwater rises with the release of gaseous carbon dioxide CO2 due to a decreasing water pressure. Drainages allow to designtunnels without resistance to ground water pressure. We present a camera-based optical sensor, developed for an autonomousoperating tunnel drainage rover, that is able to detect and quantify deposited calcite constricting more or less severely the freecross section the drainage rover needs to safely navigate the pipe. The pipe's cross section is imaged via an area-scan cameraat a frame rate adopted to the rover's speed so that at least every 50 mm of movement a frame is acquired. The presented imageprocessing software is segmenting and classifying each frame into the pipe's wall, the pipe's free lumen, eventually existingwater, and calcite.

KW - Tunnel drainage inspection

KW - autonomous tunnel rover

KW - optical sensor

KW - digital image processing

KW - calcite deposit detection

U2 - 10.13140/RG.2.2.25009.76647

DO - 10.13140/RG.2.2.25009.76647

M3 - Conference contribution

SP - 94

EP - 98

BT - Sensors and Electronic Instrumentation Advances

T2 - 9th International Conference on Sensors Engineering and Electronics Instrumentation Advances

Y2 - 20 September 2023 through 22 September 2023

ER -