Moving Object Detection for a Moving Camera Based on Global Motion Compensation and Adaptive Background Model

다국어 초록 (Multilingual Abstract)

A fast and effective moving object detection method for a moving camera is proposed in this paper.
The global motion is estimated through tracking the grid-based key points using optical flow. After the motioncompensation, the background model, candidate background model and candidate age are used for the background modelling. Then the local pixel difference and the consistency of local changes between the current frame and thebackground model are used for the background subtraction. The lighting influence threshold and the local pixeldifference between the current frame and two previous aligned frames are used to reduce the lighting influences.
Finally, Gaussian filter, connected-components analysis, erosion and dilation are used to refine the results. Theperformance evaluation shows that this proposed method works very fast in real time and has competitive resultscompared with others in the public dataset.

참고문헌 (Reference)

1 "http://jacarini.dinf.usherbrooke.ca/dataset2014/"

2 M. D. Gregorio, "WiSARDRP for change detection in video sequences" 453-458, 2017

3 김은태, "Wet Area and Puddle Detection for Advanced Driver Assistance Systems (ADAS) Using a Stereo Camera" 제어·로봇·시스템학회 14 (14): 263-271, 2016

4 Y. Lin, "Visualattention-based background modeling for detecting infrequently moving objects" 27 (27): 1208-1221, 2017

5 H. Sajid, "Universal multimode background subtraction" 26 (26): 3249-3260, 2017

6 C. H. Yeh, "Three-pronged compensation and hysteresis thresholding for moving object detection in real-Time video surveillance" 64 (64): 4945-4955, 2017

7 L. Maddalena, "The SOBS algorithm : what are the limits?" 21-26, 2012

8 S. M. Smith, "Susana new approach to low level image processing" 23 (23): 45-78, 1997

9 P. L. St-Charles, "Subsense : a universal change detection method with local adaptive sensitivity" 24 (24): 359-373, 2015

10 S. Varadarajan, "Spatial mixture of gaussians for dynamic background modelling" 63-68, 2013

11 K. Yun, "Scene conditional background update for moving object detection in a moving camera" 88 (88): 57-63, 2017

12 H. Bay, "SURF: Speeded up robust features" 3951 : 404-417, 2006

13 M. A. Fischler, "Random sample consensus : a paradigm for model fitting with applications to image analysis and automated cartography" 24 (24): 381-395, 1981

14 J. Y. Bouguet, "Pyramidal implementation of the afne Lucas Kanade feature tracker description of the algorithm" 5 (5): 1-10, 2001

15 L. Kurnianggoro, "Online background-subtraction with motion compensation for freely moving Camera" 9772 : 569-578, 2016

16 T. Chen, "Object-level motion detection from moving cameras" 27 (27): 2333-2343, 2017

17 D. G. Lowe, "Object recognition from local scale-invariant features" 2 : 1150-1157, 1999

18 김홍현, "Multi-task Convolutional Neural Network System for License Plate Recognition" 제어·로봇·시스템학회 15 (15): 2942-2949, 2017

19 Y. Wu, "Moving object detection with a freely moving camera via background motion subtraction" 27 (27): 236-248, 2017

20 D. Zhou, "Moving object detection and segmentation in urban environments from a moving platform" 68 : 76-87, 2017

21 E. Rosten, "Machine learning for high-speed corner detection" 3951 : 430-443, 2006

22 A. Zheng, "Local-to-global background modeling for moving object detection from non-static cameras" 76 (76): 11003-11019, 2017

23 Y. Chen, "Learning sharable models for robust background subtraction" 1-6, 2015

24 Hongying Zhao, "Lane Detection and Tracking based on Annealed Particle Filter" 제어·로봇·시스템학회 12 (12): 1303-1312, 2014

25 Y. Wang, "Interactive deep learning method for segmenting moving objects" 96 : 66-75, 2017

26 Bin Chen, "Hierarchical Saliency: A New Salient Target Detection Framework" 제어·로봇·시스템학회 14 (14): 301-311, 2016

27 홍금식, "Extraction of Sparse Features of Color Images in Recognizing Objects" 제어·로봇·시스템학회 14 (14): 616-627, 2016

28 S. Minaeian, "Effective and efficient detection of moving targets from a UAV’s camera" 19 (19): 497-506, 2018

29 최광남, "Effective Pedestrian Detection using Deformable Part Model based on Human Model" 제어·로봇·시스템학회 14 (14): 1618-1625, 2016

30 G. Allebosch, "EFIC: edge based foreground background segmentation and interior classification for dynamic camera viewpoints" 9386 : 130-141, 2015

31 S. Bianco, "Combination of video change detection algorithms by genetic programming" 21 (21): 914-928, 2017

32 Suryo Adhi Wibowo, "Collaborative Learning based on Convolutional Features and Correlation Filter for Visual Tracking" 제어·로봇·시스템학회 16 (16): 335-349, 2018

33 M. Gregorio, "Change detection with weightless neural networks" 403-407, 2014

34 H. Sajid, "Background subtraction for static & moving camera" 4530-4534, 2015

35 M. Calonder, "BRIEF:Binary robust independent elementary features" 6314 : 778-792, 2010

36 T. Minematsu, "Adaptive background model registration for moving cameras" 96 : 86-95, 2017

37 P. L. St-Charles, "A self-adjusting approach to change detection based on background word consensus" 990-997, 2015

38 D. Avola, "A keypoint-based method for background modeling and foreground detection using a PTZ camera" 96 : 96-105, 2017

39 S. Kim, "A disparitybased adaptive multihomography method for moving target detection based on global motion compensation" 26 (26): 1407-1420, 2016

40 C. Harris, "A combined corner and edge detector" 15 : 147-151, 1988