Running Event Visualization using Videos from Multiple Cameras

Abstract

Visualizing the trajectory of multiple runners with videos collected at different points in a race could be useful for sports performance analysis. The videos and the trajectories can also aid in athlete health monitoring. While the runners unique ID and their appearance are distinct, the task is not straightforward because the video data does not contain explicit information as to which runners appear in each of the videos. There is no direct supervision of the model in tracking athletes, only filtering steps to remove irrelevant detections. Other factors of concern include occlusion of runners and harsh illumination. To this end, we identify two methods for runner identification at different points of the event, for determining their trajectory. One is scene text detection which recognizes the runners by detecting a unique 'bib number' attached to their clothes and the other is person re-identification which detects the runners based on their appearance. We train our method without ground truth but to evaluate the proposed methods, we create a ground truth database which consists of video and frame interval information where the runners appear. The videos in the dataset was recorded by nine cameras at different locations during the a marathon event. This data is annotated with bib numbers of runners appearing in each video. The bib numbers of runners known to occur in the frame are used to filter irrelevant text and numbers detected. Except for this filtering step, no supervisory signal is used. The experimental evidence shows that the scene text recognition method achieves an F1-score of 74. Combining the two methods, that is -using samples collected by text spotter to train the reidentification model yields a higher F1-score of 85.8. Re-training the person re-identification model with identified inliers yields a slight improvement in performance(F1 score of 87.8). This combination of text recognition and person re-identification can be used in conjunction with video metadata to visualize running events.

The Arm-Swing Is Discriminative in Video Gait Recognition for Athlete Re-Identification

“…We extend the CampusRun dataset [6] with additional annotations, recorded at a long-distance running event for crosscamera video person re-identification. Experimental results using the CampusRun dataset show that runners can be identified based on their running gait.…”

“…CampusRun dataset. The CampusRun [6] was a running event with 257 runners who were captured on video using 9 non-stationary hand-held smartphone cameras across the whole track, where each camera operator was allowed to move along the course. We use multi-object tracking [27] to extract tracklets and bounding boxes for each runner from the videos.…”

“…With increasing prevalence of smartphones/cameras, images and videos from race organizers or spectators provide an additional source of information for runner identification and tracking [1]. Visionbased methods for identifying distance runners include bib number detection [2,3,4,5] and appearance-based person reidentification [6]. Potential issues with these methods arise when the bib number is partially or fully occluded, or when multiple athletes wear similar clothing styles and color.…”

“…Although speed-invariant gait recognition from treadmill sequences has been proposed before [10,11], to the best of our knowledge, no previous research has evaluated running gait recognition with unconstrained running conditions. In this paper, we use the CampusRun dataset [6] of videos captured by hand-held cameras during a running event and evaluate models in a cross-camera setting.…”

“…• We apply cross-camera video person re-identification in the long-distance running domain by extending the Campus-Run video dataset [6] with 2,581 annotated tracklets of 257 recreational runners from 18 cameras.…”