skip to main content

Pengukuran jarak objek pejalan kaki terhadap kamera menggunakan kamera stereo terkalibrasi dengan segmentasi objek histogram of oriented gradient

*Tutur Urip  -  Departemen Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro, Semarang, Indonesia
Kusworo Adi  -  Departemen Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro, Semarang, Indonesia
Catur Edi Widodo  -  Departemen Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro, Semarang, Indonesia

Citation Format:
Abstract

The distance measurement of pedestrian object to camera using a calibrated stereo camera has been investigated. The study was conducted by comparing Data-A and Data-B with different conditions and environment data interpretation. The stereo vision methods include camera calibration, image rectification, disparity counting, three-dimensional reconstruction and object segmentation. The object segmentation is performed using the Histogram of Oriented Gradient  feature to segment pedestrian object. Meanwhile, to determine the distance value is based on the information of the centroid of the bounding box segmented object.The calculations were performed using the Euclidian Distance calculation method to find the shortest distance between the centroid of the bounding box with both cameras. From the research results, the best accuracy was obtained  with measurement error of 4%.

Keywords: Measurement object, pedestrian, calibrated stereo camera, Histogram of Oriented Gradient, Euclidian Distance.

Fulltext View|Download
Keywords: Measurement object, pedestrian, calibrated stereo camera, Histogram of Oriented Gradient, Euclidian Distance

Last update:

No citation recorded.

Last update:

No citation recorded.