Real-time analysis of parameters of multiple object detection systems
V.I. Protsenko, N.L. Kazanskiy, P.G. Serafimovich

 

Image Processing Systems Institute, Russian Academy of Sciences,

Samara State Aerospace University

Full text of article: Russian language.

 PDF

Abstract:
Analysis of two streaming frameworks: Apache Storm and IBM InfoSphere Streams was performed in solving a multiple object detection task. The analysis focused on two parameters: throughput and 95th percentile of image processing delay. Faces were chosen as the objects to be detected. Profiling was held under CentOS operating systems running on a five node cluster. Face detection was performed using an OpenCV cascade classifier. First architectures and the experiment description were covered. Final suggestions on the applicability of the two systems were made in the concluding section of the article. Apache Storm demonstrated a scalability advantage over IBM InfoSphere Streams in the experiment conducted. It was confirmed that the system based on Apache Storm was able to operate on FullHD video in real-time, achieving throughput of 24 images per second on the hardware used.

Keywords:
big data, stream processing, a set of images, a sliding window, used computer memory, image processing, real time system.

Citation:
Protsenko VI, Kazanskiy NL, Serafimovich PG. Real-time analysis of parameters of multiple object detection systems. Computer Optics 2015; 39(4): 582-91. DOI: 10.18287/0134-2452-2015-39-4-582-591.

References:

  1. Cisco C.V.N.I. Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, 2014–2019 White Paper. Source: <http://www.cisco.com/c/en/us/soluti­ons/collateral/service-provider/visual-networking-in­dex-vni/white_paper_c11-520862.html>.
  2. Kazanskiy NL, Protsenko VI, Serafimovich PG. Comparison of system performance for streaming data analysis in image processing tasks by sliding window. Computer Optics 2014; 38(4): 804-10.
  3. Kazanskiy NL, Popov SB. The distributed vision system of the registration of the railway train. Computer Optics 2012; 36(3): 419-28.
  4. Kazanskiy NL, Popov SB. Machine Vision System for Singularity Detection in Monitoring the Long Process. Optical Memory and Neural Networks (Information Optics) 2010; 19(1): 23-30.
  5. Zimichev EA, Kazanskiy NL. Spectral-spatial classification with k-means++ particional clustering. Computer Optics 2014; 38(2): 281-86.
  6. Popov SB. The concept of distributed storage and parallel processing of large-format images [In Russian]. Computer Optics 2007; 31(4): 77-85.
  7. Gashnikov MV, Glumov NI, Ilyasova NYu, Myasnikov VV, Popov SB, Sergeev VV, Soifer VA, Khramov AG, Chernov AV, Chernov VM, Chicheva MA, Fursov VA. Methods for computer image processing [In Russian]. Ed. Soifer VA. Moscow: "Fizmatlit" Publisher; 2003. 784 p.
  8. Gall J, Lempitsky V. Class-specific hough forests for object detection. Decision forests for computer vision and medical image analysis. Springer London 2013; 143-57.
  9. Cheriyadat AM, Bhaduri BL, Radke RJ. Detecting multiple moving objects in crowded environments with coherent motion regions. Computer Vision and Pattern Recognition Workshops, 2008. CVPRW'08. IEEE Computer Society Conference on. IEEE, 2008; 1-8. DOI: 10.1109/CVPRW.2008.4562983.
  10. Felzenszwalb PF, Girshick RB, Allester D, Ramanan D. Object detection with discriminatively trained part-based models. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2010; 32(9): 1627-45.
  11. Barinova O, Lempitsky V, Kholi P. On detection of multiple object instances using hough transforms. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2012; 34(9): 1773-84.
  12. Kim SH, Shi J, Alfarrarjeh Ab, Xu D, Tan Yu, Shahabi C. Real-Time Traffic Video Analysis Using Intel Viewmont Coprocessor. Databases in Networked Information Systems. Springer Berlin Heidelberg; 2013. 150-60.
  13. Bramberger M, Brunner J, Rinner B. Real-time video analysis on an embedded smart camera for traffic surveillance. Real-Time and Embedded Technology and Applications Symposium, 2004. Proceedings. RTAS 2004. 10th IEEE. IEEE; 2004. 174-81.
  14. Wójcikowski M, Zaglewski R, Pankiewicz B. FPGA-based real-time implementation of detection algorithm for automatic traffic surveillance sensor network. Journal of Signal Processing Systems. 2012; 68(1): 1-18.
  15. Coifman B, Beymer D, McLauchlan Ph, Malik J, Malik J. B A real-time computer vision system for vehicle tracking and traffic surveillance. Transportation Research Part C: Emerging Technologies. 1998; 6(4): 271-88.
  16. Koller D et al. Towards robust automatic traffic scene analysis in real-time. Pattern Recognition, 1994. Vol. 1 –Conference A: Computer Vision & Image Processing., Proceedings of the 12th IAPR International Conference on. IEEE, 1994; 1: 126-31.
  17. Bradski GR. Computer vision face tracking for use in a perceptual user interface. Applications of Computer Vision, 1998, WACV '98, Proceedings, Fourth IEEE Work-shop on 1998: 214-19.
  18. Guan P, Weiss Al, Balan AlO, Black MJ Estimating human shape and pose from a single image. Computer Vision, 2009 IEEE 12th International Conference on. IEEE; 2009. 1381-88.
  19. Pentland A, Moghaddam B, Starner T. View-based and modular eigenspaces for face recognition. Computer Vision and Pattern Recognition, 1994. Proceedings CVPR'94., 1994 IEEE Computer Society Conference on. IEEE; 1994. 84-91.
  20. Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to face recognition. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 2006; 28(12): 2037-41.
  21. de Araújo SA, Pessota JH, Kim HY. Beans quality inspection using correlation-based granulometry. Engineering Applications of Artificial Intelligence 2015; 40: 84-94.
  22. Polder G, Van der Heijden G, Young IT. Spectral image analysis for measuring ripeness of tomatoes. Transactions-American Society of Agricultural Engineers 2002; 45(4): 1155-62.
  23. Ponsa D, Benavente R, Lumbreras F, Mart?´nez J, Roca X. Quality control of safety belts by machine vision inspection for real-time production. Optical Engineering 2003; 42(4): 1114-20.
  24. Xie X. A review of recent advances in surface defect detection using texture analysis techniques. Electronic Letters on Computer Vision and Image Analysis 2008; 7(3).
  25. Xu J, Chen G, Xie M. Vision-guided automatic parking for smart car. Proceedings of the IEEE Intelligent Vehicles Symposium 2000; 725-30.
  26. Gavrila DM, Philomin V. Real-time object detection for “smart” vehicles. Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on. IEEE, 1999; 1: 87-93.
  27. OpenCV Cascade Classification. Source: <http://docs.opencv.org/modules/objdetect/doc/cascade_classification.html>.
  28. Viola P, Jones M. Rapid object detection using a boosted cascade of simple features. Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on. IEEE, 2001; 1: I-511-8. DOI: 10.1109/CVPR.2001.990517.
  29. Lienhart R, Maydt J. An extended set of haar-like features for rapid object detection. Image Processing. 2002. Proceedings. 2002 International Conference on. IEEE, 2002; 1: I-900-3.
  30. OpenCV. Haar Cascades. Source: <http://alereimondo.no-ip.org/OpenCV/34>.
  31. Daniels M, Muldawer K, Schlessman J, Ozer B, Wolf W. Real-time human motion detection with distributed smart cameras. Distributed Smart Cameras, 2007. ICDSC'07. First ACM/IEEE International Conference on. IEEE, 2007; 187-94.
  32. Sinha D, Sanyal G. Application of MPI for Efficient Detection and Extraction of Features in Video Surveillance. International Journal of Computer Technology and Applications. 2011; 2(5).
  33. Herout A, Jošth R, Jur<nek R, Havel J, Hradiš M, Zemcík P. Real-time object detection on CUDA. Journal of Real-Time Image Processing. 2011; 6(3): 159-70.
  34.  Jia H, Zhang Yu, Wang W, Xu J. Accelerating viola-jones facce detection algorithm on gpus. High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), 2012 IEEE 14th International Conference on. IEEE. 2012; 396-403.
  35. Norouznezhad Eh, Bigdeli Ab, Postula Ad, Lovell Br.C. Object tracking on FPGA-based smart cameras using local oriented energy and phase features. Proceedings of the Fourth ACM/IEEE International Conference on Distributed Smart Cameras. ACM, 2010; 33-40.
  36. Neoh HS, Hazanchuk A. Adaptive edge detection for real-time video processing using FPGAs. Global Signal Processing 2004; 7(3): 2-3.
  37. Message passing framework Netty. Source: <http://zeromq.org/>.
  38. Zookeeper. Source: <http://zookeeper.apache.org/>.
  39. Hirzel M, Andrade H, Gedik B, Jacques-Silva G, Khandekar R, Kumar V, Mendell M, Nasgaard H, Schneider S, Soule´ R, Wu K.-L. IBM Streams Processing Language: Analyzing Big Data in motion. IBM Journal of Research and Development. 2013; 57(3-4): 7:1-11. DOI: 10.1147/JRD.2013.2243535.
  40. Gabriela JS. Processing tuples at-least-once in InfoSphere Streams v4 with consistent regions. Source: <https://developer.ibm.com/streamsdev/2015/02/20/processing-tuples-least-infosphere-streams-consistent-regions/>.
  41. Chandy KM, Lamport L. Distributed snapshots: determining global states of distributed systems. ACM Transactions on Computer Systems (TOCS) 1985; 3(1): 63-75.
  42. Valles A. Performance Insights to Intel® Hyper-Threading Technology. Source: <https://software.intel.com/en-us/articles/performance-insights-to-intel-hyper-threading-technology?language=es>.
  43. CUDA platform. Source: <http://opencv.org/plat­forms/cuda.html>.
© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail:journal@computeroptics.ru; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20