Evaluation of Synthetic Video Data in Machine Learning Approaches for Parking Space Classification

Horn, Daniela; Houben, Sebastian

doi:10.1109/ivs.2018.8500453

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tschentscher et al [24] created a synthetic dataset of a car park in Unreal Engine 4 where camera angles and weather conditions can be changed at will. Through the use of this dataset, Horn and Houben [25] improved a k-NN based parking space detection algorithm by six percentage points while simultaneously reducing the time for generating the dataset.…”

Section: Introductionmentioning

confidence: 99%

“…As this paper focuses on the improvement of the detection and tracking of construction workers, a few particularities have to be taken into consideration. Construction sites depict more complex and harder to model environments than the well structured car park scenarios in [25]. Sites are essentially less structured and subject to greater changes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Synthetic Data to Improve and Evaluate the Tracking Performance of Construction Workers on Site

2020

View full text Add to dashboard Cite

Vision-based tracking systems enable the optimization of the productivity and safety management on construction sites by monitoring the workers’ movements. However, training and evaluation of such a system requires a vast amount of data. Sufficient datasets rarely exist for this purpose. We investigate the use of synthetic data to overcome this issue. Using 3D computer graphics software, we model virtual construction site scenarios. These are rendered for the use as a synthetic dataset which augments a self-recorded real world dataset. Our approach is verified by means of a tracking system. For this, we train a YOLOv3 detector identifying pedestrian workers. Kalman filtering is applied to the detections to track them over consecutive video frames. First, the detector’s performance is examined when using synthetic data of various environmental conditions for training. Second, we compare the evaluation results of our tracking system on real world and synthetic scenarios. With an increase of about 7.5 percentage points in mean average precision, our findings show that a synthetic extension is beneficial for otherwise small datasets. The similarity of synthetic and real world results allow for the conclusion that 3D scenes are an alternative to evaluate vision-based tracking systems on hazardous scenes without exposing workers to risks.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%