Abstract
For crowd analytics and surveillance systems, motion estimation is an essential first step. Lots of crowd motion estimation algorithms have been presented in the last years comprising pedestrian motion. However, algorithms based on optical flow and background subtraction have numerous limitations such as the complexity of the computation in the presence of high dense crowd and sudden motion changes. Therefore, a novel estimation algorithm is proposed to measure the motion of crowd with less computational complexity and satisfy the real time requirements. The proposed algorithm is based on block-based matching, particle advection, and social force model. By the block-based matching, the motion is estimated in each frame, and the corresponding motion field is created. The particle advection process provides more information about the behavior of pedestrians groups, their tracked trajectories and the boundary of each group segment. Relying on the social force model, a predicted direction of the motion vectors (MV) could be measured significantly. Subsequently, the block-based technique is combined with the social force model to obtain the accurate motion vector with the less possible number of search points. The experimental results indicate that the proposed method achieves high performance by reducing the search points, particularly when many collision situations or obstacles exist in the scenes. Considering the reduction in the computational complexity, the quality of degradation is very low. In all cases, average PSNR degradation of the proposed algorithm is only 0.09.
Similar content being viewed by others
References
Ali S, Shah M (2007) A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis. 2007 I.E. Conference on Computer Vision and Pattern Recognition. pp 1–6
Basset A, Bouthemy P, Kervrann C (2014) Recovery of motion patterns and dominant paths in videos of crowded scenes. 2014 I.E. International Conference on Image Processing (ICIP). pp 184–188
BenAbdelkader C, Cutler R, Davis L (2002) Motion-based recognition of people in EigenGait space. Proceedings - 5th IEEE International Conference on Automatic Face Gesture Recognition, FGR 2002 267–272. doi: 10.1109/AFGR.2002.1004165
Chaker R, Junejo IN, Al Aghbari Z (2015) Crowd modeling using social networks. Image Processing (ICIP), 2015 I.E. International Conference on. pp 1280–1284
Chang X, Nie F, Yang Y, Huang H (2014) A convex sparse PCA for feature analysis. arXiv preprint arXiv:1411.6233
Chang X, Nie F, Wang S, et al. (2015) Compound rank-k projections for bilinear analysis
Chang X, Yu Y-L, Yang Y, Xing EP (2016) Semantic pooling for complex event analysis in untrimmed videos. IEEE Transactions on Pattern Analysis and Machine Intelligence
Chen T, Lu S (2016) Object-level motion detection from moving cameras
Cong Y, Gong H, Tang Y et al (2015) Real-time one-dimensional motion estimation and its application in computer vision. Mach Vis Appl 26:633–648
Crivelli T, Piriou G, Bouthemy P, et al. (2008) Simultaneous motion detection and background reconstruction with a mixed-state conditional Markov random field. European Conference on Computer Vision 113–126
Daamen W (2002) SimPed: a pedestrian simulation tool for large pedestrian areas. Conference Proceedings EuroSIW. pp 24–26
Duives DC, Daamen W, Hoogendoorn SP (2013) State-of-the-art crowd motion simulation models. Transportation research part C: emerging technologies 37:193–209
Ferryman J, Shahrokni A (2009) An overview of the pets 2009 challenge
Helbing D, Molnar P (1995) Social force model for pedestrian dynamics. Phys Rev E 51:4282
Helbing D, Farkas I, Vicsek T (2000) Simulating dynamical features of escape panic. Nature 407:487–490
Huang S-Y, Cho C-Y, Wang J-S (2005) Adaptive fast block-matching algorithm by switching search patterns for sequences with wide-range motion content. IEEE Transactions on Circuits and Systems for Video Technology 15:1373–1384
Jain J, Jain A (1981) Displacement measurement and its application in interframe image coding. IEEE Trans Commun 29:1799–1808
Jou S-Y, Chang S-J, Chang T-S (2015) Fast motion estimation algorithm and Design for Real Time QFHD high efficiency video coding. IEEE Transactions on Circuits and Systems for Video Technology 25:1533–1544
Kajo I, Malik AS, Kamel N (2015) Motion estimation of crowd flow using optical flow techniques: A review. Signal Processing and Communication Systems (ICSPCS), 2015 9th International Conference on. pp 1–9
Lam THW, Lee RST, Zhang D (2007) Human gait recognition by the fusion of motion and static spatio-temporal templates. Pattern Recogn 40:2563–2573. doi:10.1016/j.patcog.2006.11.014
Lam THW, Cheung KH, Liu JNK (2011) Gait flow image: a silhouette-based gait representation for human identification. Pattern Recogn 44:973–987. doi:10.1016/j.patcog.2010.10.011
Li R, Zeng B, Liou ML (1994) A new three-step search algorithm for block motion estimation. IEEE transactions on circuits and systems for video technology 4:438–442
Li B, Li W, Tu Y (2003) A fast block-matching algorithm using smooth motion vector field adaptive search technique. J Comput Sci Technol 18:14–21
Li W, Ye Z, Xin M, Jin Q (2015) Social recommendation based on trust and influence in SNS environments. Multimedia Tools and Applications 1–18
Lin L, Wey I-C, Ding J-H (2016) Fast predictive motion estimation algorithm with adaptive search mode based on motion type classification. SIViP 10:171–180
Liu L-K, Feig E (1996) A block-based gradient descent search algorithm for block motion estimation in video coding. IEEE Transactions on circuits and systems for Video Technology 6:419–422
Love NS, Kamath C (2006) An empirical study of block matching techniques for the detection of moving objects. Center for Applied Scientific Computing. Lawrence Livermore National Laboratory, Livermore
Luo J, Yang X, Liu L (2015) A fast motion estimation algorithm based on adaptive pattern and search priority. Multimedia Tools and Applications 74:11821–11836
Mehran R, Oyama A, Shah M (2009) Abnormal crowd behavior detection using social force model. Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. pp 935–942
Paul A (2015) Adaptive search window for high efficiency video coding. Journal of Signal Processing Systems 79:257–262
Po L-M, Ma W-C (1996) A novel four-step search algorithm for fast block motion estimation. IEEE transactions on circuits and systems for video technology 6:313–317
Richardson IE (2011) The H. 264 advanced video compression standard. Wiley, New York
Salmane H, Khoudour L, Ruichek Y (2015) A video-analysis-based railway-road safety system for detecting hazard situations at level crossings. IEEE Trans Intell Transp Syst 16:596–609
Schadschneider A (2001) Cellular automaton approach to pedestrian dynamics-theory. arXiv preprint cond-mat/0112117
Shi Z, Fernando W, Kondoz A (2011) Adaptive direction search algorithms based on motion correlation for block motion estimation. IEEE Trans Consum Electron 57:1354–1361
Sobral A, Vacavant A (2014) A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos. Comput Vis Image Underst 122:4–21
Tourapis AM (2002) Enhanced predictive zonal search for single and multiple frame motion estimation. Electronic Imaging 2002:1069–1079
Treuille A, Cooper S, Popovi’c Z (2006) Continuum crowds. ACM Transactions on Graphics (TOG). pp 1160–1168
Xin Y, Hou J, Dong L, Ding L (2014) A self-adaptive optical flow method for the moving object detection in the video sequences. Optik-International Journal for Light and Electron Optics 125:5690–5694
Xiong M, Cai W, Zhou S, et al. (2009) A case study of multi-resolution modeling for crowd simulation. Proceedings of the 2009 Spring Simulation Multiconference. p 17
Yang J-F, Chang S-C, Chen C-Y (2002) Computation reduction for motion search in low rate video coders. IEEE Transactions on Circuits and Systems for Video Technology 12:948–951
Yang L, Yu K, Li J, Li S (2005) An effective variable block-size early termination algorithm for H. 264 video coding. IEEE Transactions on Circuits and Systems for Video Technology 15:784–788
Zhu S, Ma K-K (2000) A new diamond search algorithm for fast block-matching motion estimation. IEEE Trans Image Process 9:287–290
Zhu C, Lin X, Chau L-P (2002) Hexagon-based search pattern for fast block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology 12:349–355
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kajo, I., Kamel, N. & Malik, A.S. An adaptive block-based matching algorithm for crowd motion sequences. Multimed Tools Appl 77, 1783–1809 (2018). https://doi.org/10.1007/s11042-016-4327-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-4327-9