Temporal Driver Action Localization using Action Classification Methods

被引:2
|
作者
Alyahya, Munirah [1 ]
Alghannam, Shahad [1 ]
Alhussan, Taghreed [1 ]
机构
[1] Saudi Technol & Secur Comprehens Control Co, Riyadh, Saudi Arabia
关键词
D O I
10.1109/CVPRW56347.2022.00375
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Driver distraction recognition is an essential computer vision task that can play a key role in increasing traffic safety and reducing traffic accidents. In this paper, we propose a temporal driver action localization (TDAL) framework for classifying driver distraction actions, as well as identifying the start and end time of a given driver action. The TDAL framework consists of three stages: preprocessing, 'which takes untrimmed video as input and generates multiple clips; action classification, which classifies the clips; and finally, the classifier output is sent to the temporal action localization to generate the start and end times of the distracted actions. The proposed framework achieves an F1 score of 27.06% on Track 3A2 dataset of NVIDIA AI City 2022 Challenge. The findings show that the TDAL framework contributes to fine-grained driver distraction recognition and paves the way for the development of smart and safe transportation. Code will be available soon.
引用
收藏
页码:3318 / 3325
页数:8
相关论文
共 50 条
  • [1] Learning Disentangled Classification and Localization Representations for Temporal Action Localization
    Zhu, Zixin
    Wang, Le
    Tang, Wei
    Liu, Ziyi
    Zheng, Nanning
    Hua, Gang
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 3644 - 3652
  • [2] Complementary Temporal Classification Activation Maps in Temporal Action Localization
    Wang, Lijuan
    Zhu, Suguo
    Li, Zhihao
    Fang, Zhenying
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2021, PT II, 2021, 13020 : 373 - 384
  • [3] Temporal Action Localization in Untrimmed Videos Using Action Pattern Trees
    Song, Hao
    Wu, Xinxiao
    Zhu, Bing
    Wu, Yuwei
    Chen, Mei
    Jia, Yunde
    IEEE TRANSACTIONS ON MULTIMEDIA, 2019, 21 (03) : 717 - 730
  • [4] Temporal action proposal for online driver action monitoring using Dilated Convolutional Temporal Prediction Network
    Wen, Boge
    Chen, Siyuan
    Shao, Chenhui
    COMPUTERS IN INDUSTRY, 2020, 121 (121)
  • [5] Online temporal classification of human action using action inference graph
    Elahi, G. M. Mashrur E.
    Yang, Yee-Hong
    PATTERN RECOGNITION, 2022, 132
  • [6] Exploring Action Centers for Temporal Action Localization
    Xia, Kun
    Wang, Le
    Shen, Yichao
    Zhou, Sanpin
    Hua, Gang
    Tang, Wei
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 9425 - 9436
  • [7] MEANS OF IMPLICIT TEMPORAL LOCALIZATION OF A FUTURE ACTION: A VARIANT OF CLASSIFICATION
    Larina, Olga V.
    VESTNIK VOLGOGRADSKOGO GOSUDARSTVENNOGO UNIVERSITETA-SERIYA 2-YAZYKOZNANIE, 2016, 15 (04): : 214 - 220
  • [8] Action Sensitivity Learning for Temporal Action Localization
    Shao, Jiayi
    Wang, Xiaohan
    Quan, Ruijie
    Zheng, Junjun
    Yang, Jiang
    Yang, Yi
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 13411 - 13423
  • [9] Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization
    Zhao, Tao
    Han, Junwei
    Yang, Le
    Zhang, Dingwen
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (03) : 3019 - 3031
  • [10] DECOUPLING LOCALIZATION AND CLASSIFICATION IN SINGLE SHOT TEMPORAL ACTION DETECTION
    Huang, Yupan
    Dai, Qi
    Lu, Yutong
    2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME), 2019, : 1288 - 1293