Direction-Oriented Topic Modeling with Applications in Traffic Scene Analysis

被引:0
作者
Ahmadi, Parvin [1 ]
Gholampour, Iman [2 ]
机构
[1] ICT Res Inst, IT Res Fac, Tehran, Iran
[2] Sharif Univ Technol, Elect Res Inst, Tehran, Iran
关键词
Motion patterns; Topic model; Traffic scene; Abnormal event detection; Traffic phase detection; VIDEO;
D O I
10.1007/s13177-023-00373-1
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
Unlike text analysis for which topic models are historically developed, traffic video analysis is dealing with much simpler topics, made of restricted motion patterns. In this paper, we propose a dual-layer direction-oriented framework for more efficient traffic motion patterns description based on topic models through considering the simplicity of traffic topics. The aforesaid framework compels the involved topic models to learn the foreknown visually meaningful motion patterns that exist in traffic scenes, as developed theoretically in this paper. Experimental results produced by common datasets show that the proposed method provides more intuitive topics for traffic flow description. Based on experimental results, our framework outperforms other topic-model based methods by 4% to more than 11% in detecting abnormal events, in terms of the area under the Receiver Operating Characteristic curve. In addition to that, in a scene analysis evaluation at intersections equipped with traffic signals, our method reaches 4% higher traffic phase detection accuracy, compared to conventional topic models.
引用
收藏
页码:18 / 33
页数:16
相关论文
共 27 条
  • [21] Neural Networks with Emotion Associations, Topic Modeling and Supervised Term Weighting for Sentiment Analysis
    Hajek, Petr
    Barushka, Aliaksandr
    Munk, Michal
    INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2021, 31 (10)
  • [22] Exploring Issues in a Networked Public Sphere: Combining Hyperlink Network Analysis and Topic Modeling
    Maier, Daniel
    Waldherr, Annie
    Miltner, Peter
    Jaehnichen, Patrick
    Pfetsch, Barbara
    SOCIAL SCIENCE COMPUTER REVIEW, 2018, 36 (01) : 3 - 20
  • [23] YouTube Dataset on Mobile Streaming for Internet Traffic Modeling and Streaming Analysis
    Loh, Frank
    Wamser, Florian
    Poignee, Fabian
    Geissler, Stefan
    Hossfeld, Tobias
    SCIENTIFIC DATA, 2022, 9 (01)
  • [24] BAHA:A Novel Approach to Automatic Bug Report Assignment with Topic Modeling and Heterogeneous Network Analysis
    ZHANG Wen
    WANG Song
    WANG Qing
    Chinese Journal of Electronics, 2016, 25 (06) : 1011 - 1018
  • [25] BAHA: A Novel Approach to Automatic Bug Report Assignment with Topic Modeling and Heterogeneous Network Analysis
    Zhang Wen
    Wang Song
    Wang Qing
    CHINESE JOURNAL OF ELECTRONICS, 2016, 25 (06) : 1011 - 1018
  • [26] Customers' experience of purchasing event tickets: mining online reviews based on topic modeling and sentiment analysis
    Celuch, Krzysztof
    INTERNATIONAL JOURNAL OF EVENT AND FESTIVAL MANAGEMENT, 2021, 12 (01) : 36 - 50
  • [27] Toward Cloud-Based Distributed Interactive Applications: Measurement, Modeling, and Analysis
    Wang, Haiyang
    Li, Tong
    Shea, Ryan
    Ma, Xiaoqiang
    Wang, Feng
    Liu, Jiangchuan
    Xu, Ke
    IEEE-ACM TRANSACTIONS ON NETWORKING, 2018, 26 (01) : 3 - 16