Keep Your Eye on the Puck: Automatic Hockey Videography

Pidaparthy, Hemanth; Elder, James H.

doi:10.1109/wacv.2019.00179

Cited by 18 publications

(15 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike most sport videos, they were fi lmed with a static camera and thus avoid any potential artifacts based on camera movement. Furthermore, we went through the time-consuming process of handlabelling the positions of the puck throughout the videos 8 . We selected a subset of 18 different 10 s clips from these hockey videos and presented them to 15 naïve participants with no expertise in ice hockey while tracking their eye movements.…”

Section: Ice Hockey Spectators Use Contextual Cues To Guide Predictive Eye Movementsmentioning

confidence: 99%

Ice hockey spectators use contextual cues to guide predictive eye movements

et al. 2021

Self Cite

View full text Add to dashboard Cite

Section: Ice Hockey Spectators Use Contextual Cues To Guide Predictive Eye Movementsmentioning

confidence: 99%

Ice hockey spectators use contextual cues to guide predictive eye movements

et al. 2021

Self Cite

View full text Add to dashboard Cite

“…Computer vision is currently being applied in many sports analytics problems. Problems such as sports event detection [12,23,30], player action recognition [4,31], sports field registration [16,27] and sports ball tracking [24,33] are being solved with the help of computer vision. McNally et al [23] use a hybrid CNN-LSTM network for golf swing sequencing and also introduce a new dataset for the same.…”

Section: Computer Vision Based Sports Analyticsmentioning

confidence: 99%

“…Giancola et al [12] introduce a new task of action spotting in soccer for finding anchors of game events in broadcast video. Pidaparthy et al [24] use AlexNet [18] to track the hockey puck in video by minimizing the mean-squared error (MSE) loss between the ground truth and predicted puck coordinates. Sharma et al [27] perform field registration in soccer by computing the transformation between a broadcast image and static field model through nearest neighbour search.…”

Section: Computer Vision Based Sports Analyticsmentioning

confidence: 99%

Ice hockey player identification via transformers and weakly supervised learning

Vats¹,

McNally²,

Walters³

et al. 2021

Preprint

View full text Add to dashboard Cite

Identifying players in video is a foundational step in computer vision-based sports analytics. Obtaining player identities is essential for analyzing the game and is used in downstream tasks such as game event recognition. Transformers are the existing standard in Natural Language Processing (NLP) and are swiftly gaining traction in computer vision. Motivated by the increasing success of transformers in computer vision, in this paper, we introduce a transformer network for recognizing players through their jersey numbers in broadcast National Hockey League (NHL) videos. The transformer takes temporal sequences of player frames (also called player tracklets) as input and outputs the probabilities of jersey numbers present in the frames. The proposed network performs better than the previous benchmark on the dataset used. We implement a weaklysupervised training approach by generating approximate frame-level labels for jersey number presence and use the frame-level labels for faster training. We also utilize player shifts available in the NHL play-by-play data by reading the game time using optical character recognition (OCR) to get the players on the ice rink at a certain game time. Using player-shifts improved the player identification accuracy by 6%.

show abstract

“…These cameras provide detailed views of dynamic scenes and are widely used in sports broadcasting. A robust pan-tilt-zoom SLAM system is beneficial for object tracking and autonomous broadcasting [5,19,28,41]. These real applications motivate our work.…”

Section: Introductionmentioning

confidence: 95%

Pan-tilt-zoom SLAM for Sports Videos

Lu,

Chen,

Little

2019

Preprint

View full text Add to dashboard Cite

We present an online SLAM system specifically designed to track pan-tilt-zoom (PTZ) cameras in highly dynamic sports such as basketball and soccer games. In these games, PTZ cameras rotate very fast and players cover large image areas. To overcome these challenges, we propose to use a novel camera model for tracking and to use rays as landmarks in mapping. Rays overcome the missing depth in pure-rotation cameras. We also develop an online pan-tilt forest for mapping and introduce moving objects (players) detection to mitigate negative impacts from foreground objects. We test our method on both synthetic and real datasets. The experimental results show the superior performance of our method over previous methods for online PTZ camera pose estimation.

show abstract

Keep Your Eye on the Puck: Automatic Hockey Videography

Cited by 18 publications

References 22 publications

Ice hockey spectators use contextual cues to guide predictive eye movements

Ice hockey spectators use contextual cues to guide predictive eye movements

Ice hockey player identification via transformers and weakly supervised learning

Pan-tilt-zoom SLAM for Sports Videos

Contact Info

Product

Resources

About