Vehicle Speed Measurement Methodology Robust to Playback Speed-Manipulated Video File

Abstract

Concomitant with the virtual ubiquity of dashcams in vehicles, the instantaneous speed of vehicles during accidents can now be measured using dashcam videos to understand the causes of such accidents. In this study, we estimated vehicle speeds using dashcam videos recorded in various road environments and analyzed them by comparing them to ground truth. We also considered various scenarios yielding retaken and re-encoded videos from additional recording devices, depending on the circumstances, wherein the original video can be manipulated in terms of playback speed and/or frames per second. The experimental results revealed that the actual and measured speeds were similar for most user-specific intervals. Moreover, the results suggest that our estimated speed is adequately valid as evidence, regardless of retake and re-encoding states. Furthermore, we adopted a statistical approach (i.e., Pearson's correlation coefficient analysis) to verify the proposed vehicle speed estimation method. The results showed that when playback speed was manipulated in re-encoded or retaken video, the proposed method consistently measured speeds at 99.99 % accuracy. This verified method will play an important role in deriving reliable results from various evidential video sources. INDEX TERMS dashcam, retake •re-encoded video, vehicle speed measurement, video forensic, video manipulation

Detection of Traffic Rule Violations Using Machine Learning: An Analytical Review

“…A similar paper [6] has tried to detect vehicle speed by comparing frames, and it can detect speeds up to 50 km/h with a 120-pixel camera video record capacity. [19] Similar properties are present in the study [20] once again, but in this instance, it can identify a speed of 80 km/h with a 24-fps video camera record. Some systems needed high-quality processing units and equipment.…”

“…In a study, the authors have proposed a speed measurement method to estimate vehicle speeds. [20] The proposed method measures the speed from the previous step and determines whether the playback speed of the video is altered. The authors used dashcam videos recorded in various road environments and analysed them by comparing them to ground-level youth.…”

“…The OCR algorithm recognizes playback speed and extracts time information from videos for measuring vehicle speed. The authors of [20] used OCR to extract temporal data from video input in order to determine vehicle speed.…”

“…To estimate vehicle speeds, in [20] a speed measurement method VESM is applied. The proposed method measures the speed from the previous step and determines whether the playback speed of the video is altered.…”

“…This algorithm can be efficient, as it can be seen that it has a 93% accuracy rate in order to detect the speed of a vehicle. According to the study [20], K.S. Shim et al have given some ideas about how to measure the speed from the previous step and determine whether the playback speed of the video is altered.…”