HOG-based multi-scale motion detection

被引:0
|
作者
He, Li [1 ]
Wang, Guijin [1 ]
Liao, Qingmin [1 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
关键词
histogram of gradient HOG; Multi-scale; Linear fusion; Adaptive weights; Integral image; HISTOGRAMS;
D O I
10.1117/12.2037512
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
Real-time accurate motion detection is a key step for many visual applications, such as object detection, smart video surveillance and so on. Although lots of considerable research efforts have been devoted to it, it is still a challenging task due to illumination variation, etc. In order to enhance the robustness to illumination changes, many block-based motion detection algorithms are proposed. However, these methods usually neglect the influences of different block sizes. Furthermore, they cannot choose background-modeling scale automatically as environment changes. These weaknesses limit algorithm's flexibility and their application scenes. In the paper, we propose a multi-scale motion detection algorithm to benefit from different block sizes. Moreover, an adaptive linear fusion strategy is designed through analyzing the accurateness and robustness of background models at different scales. At detecting, the ratios of different scales would be adjusted as the scene changes. In addition, to reduce the computation cost at each scale, we design an integral image structure for HOG feature of different scales. As a result, all features only need to be computed once. Different out-of-door experiments are tested and demonstrate the performance of proposed model.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Energy-Efficient HOG-based Object Detection at 1080HD 60 fps with Multi-Scale Support
    Suleiman, Amr
    Sze, Vivienne
    [J]. PROCEEDINGS OF THE 2014 IEEE WORKSHOP ON SIGNAL PROCESSING SYSTEMS (SIPS 2014), 2014, : 256 - 261
  • [2] A HOG-based Real-time and Multi-scale Pedestrian Detector Demonstration System on FPGA
    Duerre, Jan
    Paradzik, Dario
    Blume, Holger
    [J]. PROCEEDINGS OF THE 2018 ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE GATE ARRAYS (FPGA'18), 2018, : 163 - 172
  • [3] FPGA Implementation of HOG based Multi-Scale Pedestrian Detection
    Wang, Ming-Shi
    Zhang, Zhe-Rong
    [J]. PROCEEDINGS OF 4TH IEEE INTERNATIONAL CONFERENCE ON APPLIED SYSTEM INNOVATION 2018 ( IEEE ICASI 2018 ), 2018, : 1099 - 1102
  • [4] An Energy-Efficient Hardware Implementation of HOG-Based Object Detection at 1080HD 60 fps with Multi-Scale Support
    Amr Suleiman
    Vivienne Sze
    [J]. Journal of Signal Processing Systems, 2016, 84 : 325 - 337
  • [5] An Energy-Efficient Hardware Implementation of HOG-Based Object Detection at 1080HD 60 fps with Multi-Scale Support
    Suleiman, Amr
    Sze, Vivienne
    [J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2016, 84 (03): : 325 - 337
  • [6] Pedestrian detection based on multi-scale HOG features and integral images
    Huang, Yankun
    Chen, Junrui
    Liu, Xiaoxiang
    Wang, Yichun
    Huang, Yuting
    [J]. Journal of Information and Computational Science, 2015, 12 (18): : 6737 - 6749
  • [7] Multi-scale HOG Feature Used in Object Detection
    Li, Jin
    Zhang, Hong
    Zhang, Lei
    Li, Yawei
    Kang, Qiaochu
    Luo, Zhaohui
    Wu, Yujie
    [J]. TENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2018), 2019, 11069
  • [8] HOGG: Gabor and HOG-based Human Detection
    Fan Guojuan
    Mu Wanquan
    Li Bo
    Liu Xuqing
    [J]. 2016 8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY IN MEDICINE AND EDUCATION (ITME), 2016, : 562 - 566
  • [9] HOG-Based Descriptors on Rotation Invariant Human Detection
    Kittipanya-ngam, Panachit
    Lung, Eng How
    [J]. COMPUTER VISION - ACCV 2010 WORKSHOPS, PT I, 2011, 6468 : 143 - 152
  • [10] Parameter Selection for Efficient HOG-based car detection
    Ilas, Mariana-Eugenia
    [J]. 2017 IEEE 26TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2017, : 1439 - 1444