Detection and localization of scorebox in long duration broadcast sports videos

Khan, Abdullah; Lin, Haoyang; Tumrani, Saifullah; Wang, Zheng; Shao, Jie

doi:10.1117/12.2575834

Cited by 7 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such networks have achieved higher performance in many Artificial Intelligence (AI) applications. AI based automation has already proven itself in other domains [11][12][13].…”

Section: Proposed Methodsmentioning

confidence: 99%

H3DNN: 3D Deep Learning Based Detection of COVID-19 Virus using Lungs Computed Tomography

Khan

Shafiq

Kumar

et al. 2020

2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)

Self Cite

View full text Add to dashboard Cite

With the rapid spread of the novel COVID-19 virus, there is an increasing demand for screening COVID-19 patients. Typical methods for screening coronavirus patients have a large false detection rate. An effective and reliable screening method for detecting coronavirus is required. For this reason, some other reliable methods such as Computed Tomography (CT) imaging is employed to detect coronavirus accurately. In this paper, we present a 3D-Deep learning based method that automatically screens coronavirus patients using 3D volumetric CT image data. Our proposed system assists medical practitioners to effectively screen out COVID-19 patients. We performed extensive experiments on two datasets i.e., CC-19 and COVID-CT using various state-of-the-art 3D Deep learning based methods including 3D ResNets, C3D, 3D DenseNets, I3D, and LRCN. The results of the experiments show the competitive effectiveness of our proposed approach.

show abstract

“…Such networks have achieved higher performance in many Artificial Intelligence (AI) applications. AI based automation has already proven itself in other domains [11][12][13].…”

Section: Proposed Methodsmentioning

confidence: 99%

H3DNN: 3D Deep Learning Based Detection of COVID-19 Virus using Lungs Computed Tomography

Khan

Shafiq

Kumar

et al. 2020

2020 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Broadcast footage text recognition: In [25] authors describe a method of localizing broadcast text region using traditional vision techniques, while [11] authors showcase an architecture specific to the task of understanding clock text. Event detection for contextual information: Recent works on detecting actions in basketball (NBA) [20], baseball (MLB) [19] and soccer [2] attempt to solve the problem at a coarse-grained level.…”

Section: Related Workmentioning

confidence: 99%

Distantly Supervised Semantic Text Detection and Recognition for Broadcast Sports Videos Understanding

Shah

Biswas

Ramadoss

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Comprehensive understanding of key players and actions in multiplayer sports broadcast videos is a challenging problem. Unlike in news or finance videos, sports videos have limited text. While both action recognition for multiplayer sports and detection of players has seen robust research, understanding contextual text in video frames still remains one of the most impactful avenues of sports video understanding. In this work we study extremely accurate semantic text detection and recognition in sports clocks, and challenges therein. We observe unique properties of sports clocks, which makes it hard to utilize general-purpose pre-trained detectors and recognizers, so that text can be accurately understood to the degree of being used to align to external knowledge. We propose a novel distant supervision technique to automatically build sports clock datasets. Along with suitable data augmentations, combined with any state-of-the-art text detection and recognition model architectures, we extract extremely accurate semantic text. Finally, we share our computational architecture pipeline to scale this system in industrial setting and proposed a robust dataset for the same to validate our results. CCS CONCEPTS• Computing methodologies → Activity recognition and understanding; Visual content-based indexing and retrieval; Scene understanding; Object detection; Object recognition.

show abstract

“…Key methods for analyzing cricket batting are also explored 17 through key event detection and event importance scoring. Similarly, an SVM classifier is employed in a few Khan et al papers 18,19 to detect scoreboxes in the video frames. The extracted features are used as input to the classifier, which learns to distinguish between scoreboxes and non-scorebox regions.…”

mentioning

confidence: 99%

Automated player identification and indexing using two-stage deep learning network

Liu,

Adreon,

Wagnon

et al. 2023

Sci Rep

View full text Add to dashboard Cite

American football games attract significant worldwide attention every year. Identifying players from videos in each play is also essential for the indexing of player participation. Processing football game video presents great challenges such as crowded settings, distorted objects, and imbalanced data for identifying players, especially jersey numbers. In this work, we propose a deep learning-based player tracking system to automatically track players and index their participation per play in American football games. It is a two-stage network design to highlight areas of interest and identify jersey number information with high accuracy. First, we utilize an object detection network, a detection transformer, to tackle the player detection problem in a crowded context. Second, we identify players using jersey number recognition with a secondary convolutional neural network, then synchronize it with a game clock subsystem. Finally, the system outputs a complete log in a database for play indexing. We demonstrate the effectiveness and reliability of player tracking system by analyzing the qualitative and quantitative results on football videos. The proposed system shows great potential for implementation in and analysis of football broadcast video.

show abstract

Detection and localization of scorebox in long duration broadcast sports videos

Cited by 7 publications

References 13 publications

H3DNN: 3D Deep Learning Based Detection of COVID-19 Virus using Lungs Computed Tomography

H3DNN: 3D Deep Learning Based Detection of COVID-19 Virus using Lungs Computed Tomography

Distantly Supervised Semantic Text Detection and Recognition for Broadcast Sports Videos Understanding

Automated player identification and indexing using two-stage deep learning network

Contact Info

Product

Resources

About