PySceneDetect in Literature

PySceneDetect is a useful tool for statistical analysis of video. Below are links to various research articles/papers which have either used PySceneDetect as a part of their analysis, or propose more accurate detection algorithms using the current implementation as a comparison.

• Online Detection of Action Start via Soft Computing for Smart City by Tian Wang, Yang Chen, Hongqiang Lv, Jing Teng, Hichem Snoussi, Fei Tao (2020)

• Thesis Project: Smart Shades and Cane for The Blind by Muhammad Hashim (2020)

• Movienet: a movie multilayer network model using visual and textual semantic cues by Youssef Mourchid, Benjamin Renoust, Olivier Roupin, Lê Văn, Hocine Cherifi & Mohammed El Hassouni (2019)

• NLP-Enriched Automatic Video Segmentation by Mohannad AlMousa, Rachid Benlamri, Richard Khoury (2018)

• Online Detection of Action Start in Untrimmed, Streaming Videos by Zheng Shou, Junting Pan, Jonathan Chan, Kazuyuki Miyazawa, Hassan Mansour, Anthony Vetro, Xavi Gir-i-Nieto, Shih-Fu Chang (2018)

• Story Understanding in Video Advertisements by Keren Ye, Kyle Buettner, Adriana Kovashka (2018)

• LoL-V2T: Large-Scale Esports Video Description Dataset by Tsunehiko Tanaka, Edgar Simo-Serra (2021)

This list is only provided for academic and research purposes, and is far from an exhaustive source of the uses of PySceneDetect in literature. If you think a particular submission is relevant and should be added to this list, feel free to raise an issue with your suggestion. Publically available material is preferred, although not a requirement.

Scene Detection Methodology

You can find the source code for each scene detector in the scenedetect/detectors folder. Also see Issue #62: Reference of paper for the methods used on Github for a futher discussion on detection methodologies. You are more than welcome to propose any new ideas on the issue tracker, or share a proof of concept using the Python API by creating a pull request.