Uneingeschränkter Zugang

A novel approach to label road defects in video data: semi-automated video analysis

Jakob Thumm
Jakob Thumm
, 
Johannes Masino
Johannes Masino
, 
Martin Knoche
Martin Knoche
, 
Frank Gauterin
Frank Gauterin
 und 
Markus Reischl
Markus Reischl
   | 30. Apr. 2020
International Journal on Smart Sensing and Intelligent Systems's Cover Image
Über diesen Artikel
Vorheriger Artikel
Nächster Artikel
Zitieren
Article Category: Research-Article
Online veröffentlicht: 30. Apr. 2020
Seitenbereich: 1 - 9
Eingereicht: 05. Dez. 2019
DOI: https://doi.org/10.21307/ijssis-2020-007
Schlüsselwörter
© 2020 Jakob Thumm et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1:

Overview of the program workflow.
Overview of the program workflow.

Figure 2:

Algorithm to compress the data and extract information about oscillation.
Algorithm to compress the data and extract information about oscillation.

Figure 3:

Algorithm to calculate the score comparison table.
Algorithm to calculate the score comparison table.

Figure 4:

Algorithm to calculate the final score for each window.
Algorithm to calculate the final score for each window.

Figure 5:

Arrangement of speed sections.
Arrangement of speed sections.

Figure 6:

Score table entries for the minimum and maximum standard deviation of z-acceleration.
Score table entries for the minimum and maximum standard deviation of z-acceleration.

Figure 7:

Image annotation using ‘labelImg’.
Image annotation using ‘labelImg’.

Figure 8:

Comparison between our approach, Maeda, Angulo, and manual labeling. The higher number of events per shown image leads to a lower evaluation time and a less tiring workflow. The significantly higher percentage of severe damages in the labeled set is important for a ground truth with a balanced number of events per class.
Comparison between our approach, Maeda, Angulo, and manual labeling. The higher number of events per shown image leads to a lower evaluation time and a less tiring workflow. The significantly higher percentage of severe damages in the labeled set is important for a ground truth with a balanced number of events per class.

Comparison of evaluations with different thresholds.

Threshold 0.28 0.3 0.35 Manual
Total distance (km) 73.95 73.95 73.95 8.34
Total video time (min) 162.88 162.88 162.88 18.62
Evaluation time (min) 40 30 17 35
Images shown 119 89 50 1,117
Cracks 10 5 3 20
Patches 6 3 2 5
Potholes 14 9 6 1
Railroad tracks 1 1 0 0
Speedbump 4 4 0 1
Sunken manholes 12 9 5 4
Sum of events 47 31 16 31
Images containing events (%) 39.5 34.8 32 2.8
Time per true event (s) 51 58 64 68
Event every × m 1,573 2,385 4,622 269

Comparison between our approach, Maeda, Angulo, and manual labeling.

Proposed method Maeda Angulu Manual (video)
Presented images 119 163,664 180,345 1,117 sec
Containing event (%) 39.5 9.4 25.2 2.8
Severe damages (%) 29.8 2.65 2.64 3.22
Light damages (%) 59.6 67.9 Unknown 93.5
Other (%) 10.6 29.45 Unknown 3.28
Event every × m 1,573 97 36 269
eISSN:
1178-5608
Sprache:
Englisch
Zeitrahmen der Veröffentlichung:
Volume Open
Fachgebiete der Zeitschrift:
Technik, Einführungen und Gesamtdarstellungen, andere
Zeitschrift RSS Feed