在移动终端进行商标识别时，使用图像处理技术的传统方法已不再适用.针对这一问题，提出基于计算迁移的智能终端商标识别方法.首先通过分析商标识别应用的组织架构来划分商标识别应用的任务节点；然后构建基于任务节点的应用成本图，设计计算迁移的约束条件；最后制定计算迁移的目标函数，以实现应用能耗与应用时长的均衡.实验结果表明，该方法可以提升移动终端商标识别应用的性能，降低本地能耗，增强用户体验.
Trademark is the mark that distinguishes enterprise brand or service, and plays an important role in spreading enterprise culture. Trademark recognition application on intelligent terminal is a computationally intensive application. The application performance is limited by the resource bottlenecks of intelligent terminal. Address to the problem, this paper presents a computation offloading method for trademark recognition application on intelligent terminal. In this method, the entire application is firstly divided into many task nodes by categorizing their usage. Then the energy consumption and execution time of each single task node are monitored and calculated, and an application cost graph can be built up. Finally, the objective functions based on minimum energy consumption, minimum executed time, and the balance between energy consumption and executed time can be derived. In the paper, offloading experiments based on these objective functions are carried out, and the experimental results show that the proposed method can improve the performance of trademark recognition application on intelligent terminal, reduce the energy consumption, and enhance user experience.
[1] Zhang W L, Guo B, Shen Y, Wang Y, Xiong W, Duan L T. Computation offloading on intelligent mobile terminal[J]. Chinese Journal of Computers, 2016, 39(5):1022-1037.
[2] Sun L, Wu X L, Zhou L, Ye J, Fu L R. Application of affine invariant SIFT matching for automatic logo recognition[J]. Computer Engineering and Design, 2011, 32(4):1406-1410.
[3] Lowe D. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 28(6):23-27.
[4] Matas J, Chum O, Urban M, Pajdla T. Robust wide-baseline stereo from maximally stable extremal regions[J]. Image and Vision Computing, 2004, 22(10):384-393.
[5] Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schaffalitzky F, Kadir T, Van L. A comparison of affine region detectors[J]. International Journal of Computer Vision, 2005, 65:65-72.
[6] Lin C, Zhan Y M. Trademark retrieval algorithm based on SIFT feature[J]. Computer Engineering, 2008, 34(23):275-277.
[7] Zhao T P. Task partition in computation offloading for mobile devices[J]. Chinese Journal of Computers, 2013, 36(5):652-659.
[8] Cui Y, Xiao S, Wang X, Li M. Performance-aware energy optimization on mobile devices in cellular network[C]//Proceedings of the IEEE International Conference on Computer Communications(INFOCOM). Toronto, Canada, 2014:1123-1131.
[9] Cuervo E, Balasubramanian A, Cho D, Bahl P. MAUI:making smartphones last longer with code offload[C]//Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services. San Francisco, USA, 2010:49-62.
[10] Kosta S, Aucinas A, Hui P, Mortier R, Zhang X. Thinkair:dynamic resource allocation and parallel execution in the cloud for mobile code offloading[C]//Proceedings of the IEEE INFOCOM. Orlando, USA, 2012:945-953.
[11] Rahimi M R, Ren J, Liu C H, Athanasios V, Nalini V. Mobile cloud computing:a survey, state of art and future directions[J]. Mobile Networks and Applications, 2014, 19(2):133-143.
[12] Gu X, Nahrstedt K, Messer A, Greenberg I, Milojicic D. Adaptive offloading inference for delivering applications in pervasive computting environments[C]//Proceedings of the 1st IEEE International Conference on Pervasive Computing and Communications. Fort Worth, USA, 2003:107-114.
[13] Wolski R. Experiences with predicting resource performance on-line in computational grid settings[J]. ACM SIGMETRICS Performance Evaluation Review, 2003, 30(4):41-49.
[14] Xiong J, Jamieson K. ArrayTrack:a fine-grained indoor location system[C]//Proceedings of USENIX Symposium on Networked Systems Design and Implementation(NSDI). Lombard, Israel, 2013:71-84.
[15] Chun B G, Ihm S, Maniatis P, Naik M, Patti A. Clonecloud:elastic execution between mobile device and cloud[C]//Proceedings of the 6th ACM EuroSys Conference on Computer Systems. New York, USA, 2011:301-314.
[16] Shu Y, Shin K G, He T, Chen J. Last mile navigation using smartphones[C]//Proceedings of the ACM Annual International Conference on Mobile Computing and Networking (Mobicom). Paris, France, 2015:512-524.
[17] Zhang C, Zhang X, Chandra R. Energy efficient WiFi display[C]//Proceedings of the ACM 13th Annual International Conference on Mobile Systems, Applications, and Services (Mobisys). Florence, Italy, 2015:405-418.
[18] Satyanarayanan M, Bahl P, Caceres R, Davies N. The case for VM-based cloudlets in mobile computing[J]. IEEE Pervasive Computing, 2009, 8(4):14-23.
[19] Balan R K, Satyanarayanan M, Park S Y, Okoshi T. Tactics based remote execution for mobile computing[C]//Proceedings of the 1st International Conference on Mobile Systems, Applications and Services. San Francisco, USA, 2003:273-286.
[20] Balan R K, Gergle D, Satyanarayanan M, Herbsleb J. Simplifying cyber foraging for mobile devices[C]//Proceedings of the 5th International Conference on Mobile Systems, Applications and Services. New York, USA, 2007:272-285.
[21] Basri R, Jacobs D W. Recognition using region correspondence[J]. International Journal of Computer Vision, 1997, 25(2):145-166.
