نوع مقاله: مقاله پژوهشی

نویسندگان

1 استاد دانشکده مهندسی برق دانشگاه علم و صنعت ایران

2 دانشجوی کارشناسی ارشد - دانشکده مهندسی برق، دانشگاه علم و صنعت ایران

3 استادیار - دانشکده فناوری اطلاعات و ارتباطات، دانشگاه جامع امام حسین (ع)

چکیده

در این مقاله، Raspberry Pi 2 به عنوان سخت‌افزاری کم هزینه، کم وزن و کم توان برای پیاده‌سازی روش‎های آشکارسازی اهداف در تصویر مادون قرمز مورد بررسی و تحلیل قرار می‌گیرد. پیاده‌سازی مناسب این روش‌ها و انجام عملیات بصورت بلادرنگ برای سامانه‌های دفاعی از اهمیت ویژه‌ای برخوردار است. نتایج نشان می‌دهند که Raspberry Pi 2 دارای قدرت محاسباتی کافی برای پیاده‌سازی الگوریتم‌ آشکارسازی هدف در تصاویر مادون قرمز می‌باشد. قدرت پردازش سخت‌افزار پیشنهادی با استفاده از الگوریتم آشکارسازی هدف تصاویر مادون قرمز روی محیط توسعه نرم‌افزاری Qt و توابع کتابخانه پردازش تصویر OpenCV با PC روی محیط توسعه نرم‌افزاری Qt و توابع کتابخانه OpenCV و همچنین با نرم‌افزار سطح بالای MATLAB مقایسه می‌شود. نتایج به دست آمده نشان می‌دهند که پیاده‌سازی روی Raspberry Pi 2 نسبت به MATLAB سرعت اجرای الگوریتم را 6.5 برابر افزایش می‌دهد. همچنین زمان اجرای پیاده‌سازی الگوریتم آشکارسازی هدف در تصاویر مادون قرمز (به زبان C++) با استفاده از کتابخانه OpenCV روی PC تقریبا 8 برابر اجرای آن با Raspberry Pi 2 است. همچنین با مقایسه Raspberry Pi 2 و PC از نظر توان مصرفی، وزن و هزینه مشاهده می‌شود که Raspberry Pi 2 کارآیی بسیار بهتری را از نظر توان مصرفی، وزن و هزینه نسبت به PC دارد. نتایج نشان می‌دهند که هر چند استفاده از نرم‌افزارهای سطح بالا مثل MATLAB دارای شاخص‌های ارزیابی ضرایب تضعیف پس‌زمینه ((SCR و نسبت سیگنال به نویز ((BSF بالاتری نسبت به استفاده از کتابخانه OpenCV است، اما نتایج زمان اجرا نشان می‌دهد که سخت‌افزار پیشنهادی زمان اجرا را نسبت به نرم‌افزارهای سطح بالا مثل MATLAB بهبود می‌دهد. برای بهینه‌سازی و کاهش زمان اجرا از برنامه‌نویسی چندریسه‌ای روی Raspberry Pi 2 (که شامل پردازنده 4 هسته‌ای ARM Cortex-A7 است) و خاصیت افزایش ‌فرکانس (برای افزایش سرعت سخت‌افزار Raspberry Pi 2) استفاده می‌شود.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Implementation of Image Processing Algorithm on Efficient Embedded Systems with Open Source Development Tools

نویسندگان [English]

  • M.R Mousavi 1
  • B. Mohammadi 2
  • M. Nasiri 3

2 دانشجوی کارشناسی ارشد - دانشکده مهندسی برق، دانشگاه علم و صنعت ایران

3 استادیار - دانشکده فناوری اطلاعات و ارتباطات، دانشگاه جامع امام حسین (ع)

چکیده [English]

In many practical applications, implementation of algorithms is required into low-cost and low-power hardware, proper processing power, simplicity in algorithm development and maximum flexibility. Proper implementation of these methods and real-time operations for defense systems has particular importance. Studies have shown that Raspberry Pi 2 has sufficient computational power to implement an infrared target detection algorithm. Therefore, in this paper, Raspberry Pi 2 is considered as low-cost, low-weight, and low-power hardware for optimum implementing infrared target detection methods and to optimize and reduce runtime, it with the overclocking technique is used. Finally, their performance is compared with other hardware with different software development environment. These comparisons include the Qt software development environment based on the OpenCV image processing library in the Raspberry Pi 2 hardware with Qt software development environment based on the OpenCV library functions in the PC hardware, as well as the high-level MATLAB software. The results show that implementation on the Raspberry Pi 2 in comparison with MATLAB speeds up implementation of the algorithm 6.5 times. As well as, implementation time of the infrared target detection algorithm (C ++) using the OpenCV library on the PC is approximately eight times that of Raspberry Pi 2. Also, comparing Raspberry Pi 2 and PC in terms of power consumption, weight and cost is observed that Raspberry Pi 2 has a much better performance in terms of power consumption, weight and cost than PCs. The results show that although the use of high-level software such as MATLAB has background suppression factor (SCR) and signal to clutter ratio (BSF) higher than use of the OpenCV library, the results of runtime indicate that the proposed hardware improves the runtime of high-level software like MATLAB. The results of optimization on the Raspberry Pi 2 show that speed of the algorithm is improved by more than 40%.

کلیدواژه‌ها [English]

  • Target detection
  • Raspberry Pi 2
  • OpenCV
  • low-power
  • low-cost
  • low-weight

[1]     H. Deng, X. Sun, M. Liu, C. Ye and X. Zhou, "Entropy-Based Window Selection for Detecting Dim and Small Infrared Targets", Pattern Recognition, Vol.61, pp.66-71, 2017.

[2]     X. Wang, G. Lv and L. Xu, “Infrared Dim Target Detection Based on Visual Attention”, Infrared Physics & Technology, Vol.55, No.6, pp.513-521, 2012.

[3]     H. Sugano and R. Miyamoto, “Highly Optimized Implementation of OpenCV for the Cell Broadband Engine”, Computer Vision and Image Understanding, Vol.114, No.11, pp.1273-1281, 2010.

[4]     R. Laganière, “OpenCV 2 Computer Vision Application Programming Cookbook”, Packt Publishing Ltd, 2011.

[5]     H. Jina, “Review Paper on Industrial Automation based on OpenCV”, International Journal of Emerging Trends in Electrical and Electronics, Vol.2, Issue.1, pp.92-95, 2013.

[6]     S. Matuska, R. Hudec and M. Benco, “The Comparison of CPU Time Consumption for Image Processing Algorithm in Matlab and OpenCV”, In ELEKTRO, pp.75-78, 2012.

[7]     M. Marengoni and D. Stringhini, “High Level Computer Vision using OpenCV”, 24th SIBGRAPI Conference on In Graphics, Patterns and Images Tutorials (SIBGRAPI-T), ‎pp.11-24, ‎2011.

[8]     P. N. Druzhkov, V. L. Erukhimov, N. Y. Zolotykh, E. A. Kozinov, V. D. Kustikova, I. B. Meerov and A. N. Polovinkin, “New Object Detection Features in the OpenCV Library”, Pattern Recognition and Image Analysis, Vol.21, No.3, pp.384-386, 2011.

[9]     G. B. García, O. D. Suarez, J. L. E. Aranda, J. S. Tercero, I. S. Gracia and N. V. Enano, “Learning Image Processing with OpenCV”, Packt Publishing Ltd, 2015.

[10]  A. Kaehler and G. Bradski, “Learning OpenCV”, O'Reilly Media, 2014.

[11]  Q. Yu, H. H. Cheng, W. W. Cheng and X. Zhou, “Ch OpenCV for Interactive Open Architecture Computer Vision”, Advances in Engineering Software, Vol.35, No.8, pp.527-536, 2004.

[12]  X. Yuanfang and S. Xia, “System Design for Real-Time Image Processing Based on Multi-Core DSP”, Journal of ‎Networks, Vol.9, No.11, pp.3143-3150, November 2014.‎

[13]  W. Wasfy and H. Zheng, “General Structure Design for Fast Image Processing Algorithms Based upon FPGA DSP Slice”, International Conference on Medical Physics and Biomedical Engineering, pp.690-697, 2012.

[14]  ‎ M. S. Kumar and D. Nedumaran, “Development of Image Enhancement Algorithm for ‎Fingerprint Images in ‎TMS320C6416 DSK”, IEEE Conference on Computational ‎Intelligence in Biometrics and Identity ‎Management (CIBIM), pp.1-6, 16-19 April 2013.‎

[15]  D. Jinghong, D. Yaling and L. Kun, “Development of Image Processing System Based on DSP and FPGA”, The ‎Eight International Conference on Measurement and Instruments, pp.791-794, 2007.‎

[16]  M. Ali, E. Stotzer, F. D. Igual and R. A. Geijn, “Level-3 BLAS on the TI C6678 Multi-Core DSP”, IEEE Conference on Computer Architecture and High Performance Computing, pp.179-186, 24-28 ‎October‎ 2012. ‎

[17]  L. Yan, T. Zhang and S. Zhong, “A DSP/FPGA-Based Parallel Architecture for Real-Time Image Processing”, The ‎Sixth World Congress on Intelligent Control and Automation, pp.10022-10025, 21-23 June 2006.‎

[18]  B. Ramesh, A. Bhardwaj, J. Richardson, A. D. George and H. Lam, “Optimization and Evaluation of Image and Signal Processing Kernels on the TI C6678 Multi-Core DSP”, 2014 IEEE High Performance Extreme ‎Computing Conference, pp.1-6, 9-11 September 2014.‎

[19]  S. K. Teoh, V. V. Yap, C. S. Soh and P. Sebastian, “Implementation and Optimization of Human Tracking System ‎using ARM Embedded Platform”, 4th International Conference on Intelligent and Advanced Systems, ‎pp.353-356, 12-14 June 2012.

[20]  L. Yang, J. Yang and K. Yang, “Adaptive Detection for Infrared Small Target under Sea-Sky Complex Background”, Electron Letters, Vol.40, No.17, pp.1083-1085, 2004.

[21]  F. A. Sadjadi, “Infrared Target Detection with Probability Density Functions of Wavelet Transform Sub-bands”, Applied Optics, Vol.43, No.2, pp.315-323, 2004.

[22]   X. Wang and Z. M. Tang, “Combining Wavelet Packets with Higher-Order Statistics for Infrared Small Targets Detection, Infrared Laser Eng, Vol.38, No.5, pp.915-920, 2009.

[23]  J. F. Khan, M. S. Alam and S. M. Bhuiyan, “Automatic Target Detection in Forward-Looking Infrared Imagery via Probabilistic Neural Networks”, Applied Optics, Vol.48, No.3, pp.464-476, 2009.

[24]  P. Zhang and J. Li, “Neural-Network-Based Single-Frame Detection of Dim Spot Target in Infrared Images”, Optical Engineering, Vol.46, No.7, pp.076401-076401, 2007.

[25]  J. F. Khan and M. S. Alam, “Target Detection in Cluttered Forward-Looking Infrared Imagery”, Optical Engineering, Vol.44, No.7, pp.076404-076404, 2005.

[26]   M. Zeng, J. X. Li and Z. Peng, “The Design of Top-Hat Morphological Filter and Application to Infrared Target Detection”, Infrared Physics & Technology, Vol.48, No.1, pp.67-76, 2006.

[27]   Y. Q. Sun, J. W. Tian and J. Liu, “Novel Method on Dual-Band Infrared Image Fusion for Dim Small Target Detection”, Optical Engineering, Vol.46, No.11, pp.116402-116402, 2007.

[28]   X. Wang, L. Liu and Z. M. Tang, “Infrared Dim Target Detection Based on Fractal Dimension and Third-Order Characterization”, Chinese Optics Letters, Vol.7, No.10, pp.931-933, 2009.

[29]   L. Itti, C. Koch and E. Niebur, “A Model of Saliency-Based Visual Attention for Rapid Scene Analysis”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.20, No.11, pp.1254-1259, 1998.

[30]   B. C. Ko and J. Nam, “Object-of-Interest Image Segmentation Based on Human Attention and Semantic Region Clustering”, Journal of the Optical Society of America A, Vol.23, No.10, pp.2462-2470, 2006.

[31]   Y. Xu, Y. Zhao, C. Jin, Z. Qu, L. Liu and X. Sun, “Salient Target Detection Based on Pseudo-Wigner-Ville Distribution and Rényi Entropy”, Optics letters, Vol.35, No.4, pp.475-477, 2010.

[32]   W. Li, C. Pan and L. X. Liu, “Saliency-Based Automatic Target Detection in Forward Looking Infrared Images”, IEEE International Conference on Image Processing (ICIP), pp. 957-960, 2009.

[33]  L. Zhao, K. Wu, X. Chai and C. Gu, “Image Processor for Visual Prosthesis based on ARM”, 7th ‎International ‎Conference on Biomedical Engineering and Information (BMEI 2014), pp.592-596, 2014.‎

[34]  D. F. Vera, D. M. Cadena and J. M. Ramírez, "Iris Recognition Algorithm on Beagle Bone Black", In Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Vol.1, pp.282-286, 2015.

[35]  P. Poudel and M. Shirvaikar, "Optimization of Computer Vision Algorithms for Real Time Platforms", 42nd South Eastern Symposium on System Theory (SSST), pp.51-55, 2010.

[36]  K. S. Shilpashree, H. Lokesha and H. Shivkumar, “Implementation of Image Processing on Raspberry Pi”, International Journal of Advanced Research in Computer and Communication Engineering, Vol.4, No.5, pp.199-202, 2015.

[37]  B. E. Gamal, A. N. Ouda, Y. Z. Elhalwagy and G. A. Elnashar, "Embedded Target Detection System Based on Raspberry Pi System", International Conference on Computer Engineering, pp.154-157, 2016.

[38]  G. Arva and T. Fryza, "Embedded Video Processing on Raspberry Pi", International Conference on Radioelektronika, pp.1-4, 2017.

[39]  R. Dudas, C. VandenBussche, A. Baras, S. Z. Ali and M. T. Olson, “Inexpensive Telecytology Solutions That Use the Raspberry Pi and the iPhone”, Journal of the American Society of Cytopathology, Vol.3, No.1, pp.49-55, 2014.

[40]  V. Vujovic and M. Maksimovic, “Raspberry Pi as a Sensor Web Node for Home Automation”, Computers & Electrical Engineering, Vol.44, pp.153-71, 2015.

[41]  D. S. Bölsche and A. M. Schön, “A Raspberry in Sub-Saharan Africa? Chances and Challenges of Raspberry Pi and Sensor Networking in Humanitarian Logistics”, Procedia Engineering, Vol.107, pp.263-272, 2015.

[42]  A. D. Deshmukh and U. B. Shinde, "A Low Cost Environment Monitoring System using Raspberry Pi and Arduino with Zigbee", International Conference on Inventive Computation Technologies, Vol.3, pp.1-6, 2016.

[43]  V. S. Tomar and V. Bhatia, “Low Cost and Power Software Defined Radio using Raspberry Pi for Disaster Effected Regions”, Procedia Computer Science, Vol.58, pp.401-407, 2015.

[44]  J. Bermúdez-Ortega, E. Besada-Portas, J. A. López-Orozco, J. A. Bonache-Seco and J. M. Cruz, “Remote Web-Based Control Laboratory for Mobile Devices Based on EJS, Raspberry Pi and Node.Js”, International Federation of Accountants, pp.158-163, 2015.

[45]   B. Qureshi, Y. Javed, A. Koubâa, M. F. Sriti and M. Alajlan, “Performance of a Low Cost Hadoop Cluster for Image Analysis in Cloud Robotics Environment”, Symposium on Data Mining Applications, pp.90-98, 2016.

[46]  N. Hossain, M. T. Kabir, T. R. Rahman, M. S. Hossen and F. Salauddin, "A Real-Time Surveillance Mini-Rover Based on OpenCV-Python-Java using Raspberry Pi 2", International Conference on Control System, Computing and Engineering, pp.476-481, 2015.

[47]  Q. He, B. Segee and V. Weaver, "Raspberry Pi 2 B+ GPU Power, Performance and Energy Implications", International Conference on Computational Science and Computational Intelligence, pp.163-167, 2016.

C. I. Hilliard, “Selection of a Clutter Rejection Algorithm for Real Time Target Detection from an Airborne Platform”, International Society for Optics and Photonics, Vol.4048, pp.74-84, 2000.