Vision-IMU Based Obstacle Detection Method

  • Yi Xu
  • Song GaoEmail author
  • Shiwu Li
  • Derong Tan
  • Dong Guo
  • Yuqiong Wang
  • Qiang Chen
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 503)


Obstacles’ accurate classification is the first step in traditional obstacle detection methods, and the step causes the problem of high time and space complexity. In this paper, an obstacle detection method based on the principle of pinhole imaging is proposed to solve the problem. The monocular camera and inertial measurement unit are used as the basic sensing units in proposed method. The obstacle detection steps and indoor experiments are shown to expound the detection process of the Vision-IMU based obstacle detection method. The Vision-IMU based obstacle detection method and Adaboost cascade detection method are used to detect obstacles in indoor experiments, and the Producer’s Accuracy, the User’s Accuracy, the Overall Accuracy, and κ are used as evaluating indicators to compare test results, and the results show that the Vision-IMU based obstacle detection method has higher accuracy. The processing time of the Vision-IMU based obstacle detection method and Adaboost cascade detection method are compared, and it is shown that the Vision-IMU based obstacle detection method has faster processing speed.


Monocular vision Inertial measurement unit Obstacle detection Pinhole imaging 



Research was supported by Key Projects of National Key R & D Plan (2016YFD0701101), China Postdoctoral Science Foundation (2018M632696), Changbai Mountain Scholars Program (440020031167), National Natural Science Foundation of China (51508315), Natural Science Foundation of Shandong Province (ZR2016EL19, ZR2018PEE016, ZR2018LF009).


  1. 1.
    Liu T, Zheng N, Zhao L, et al (2005) Learning based symmetric features selection for vehicle detection. In: Proceedings of intelligent vehicles symposium, IEEE. IEEE, pp 124–129Google Scholar
  2. 2.
    Tsai LW, Hsieh JW, Fan KC (2007) Vehicle detection using normalized color and edge map. IEEE Trans Image Process 16(3):850–864MathSciNetCrossRefGoogle Scholar
  3. 3.
    Mori H, Charkari NM (1993) Shadow and rhythm as sign patterns of obstacle detection. In: IEEE international symposium on industrial electronics, 1993. Conference Proceedings, ISIE’93-Budapest. IEEE, pp 271–277Google Scholar
  4. 4.
    Ravindran V, Viswanathan L, Rangaswamy S (2016) A novel approach to automatic road-accident detection using machine vision techniques. Int J Adv Comput Sci Appl 7(11):235–242Google Scholar
  5. 5.
    Yousef KMA, Al-Tabanjah M, Hudaib E et al (2015) SIFT based automatic number plate recognition. In: International conference on information and communication systems. IEEE, 36–39Google Scholar
  6. 6.
    Elkerdawi SM, Sayed R, Elhelw M (2014) Real-time vehicle detection and tracking using haar-like features and compressive tracking. ROBOT2013: First Iberian robotics conference. Springer, Berlin, pp 381–390CrossRefGoogle Scholar
  7. 7.
    Elkerdawy S, Salaheldin A, Elhelw M (2015) Vision-based scale-adaptive vehicle detection and tracking for intelligent traffic monitoring. In: IEEE international conference on robotics and biomimetics. IEEE, pp 1044–1049Google Scholar
  8. 8.
    Miller N, Thomas MA, Eichel JA, et al (2015) A hidden Markov model for vehicle detection and counting. In: Computer and robot vision. IEEE, pp 269–276Google Scholar
  9. 9.
    Momin BF, Mujawar TM (2015) Vehicle detection and attribute based search of vehicles in video surveillance system. In: International conference on circuit, power and computing technologies. IEEEGoogle Scholar
  10. 10.
    Pepikj B, Stark M, Gehler P et al (2013) Occlusion patterns for object class detection. In: IEEE conference on computer vision and pattern recognition. IEEE, pp 3286–3293Google Scholar
  11. 11.
    Hu Q, Paisitkriangkrai S, Shen C et al (2015) Fast detection of multiple objects in traffic scenes with a common detection framework. IEEE Trans Intell Transp Syst 17(4):1002–1014CrossRefGoogle Scholar
  12. 12.
    Pomerleau DA (1993) Knowledge-based training of artificial neural networks for autonomous robot driving. Robot learning. Springer, Berlin, pp 88–97Google Scholar
  13. 13.
    Xiao L, Dai B, Liu D et al (2016) Monocular road detection using structured random forest. Int J Adv Rob Syst 13(3):101CrossRefGoogle Scholar
  14. 14.
    Sivaraman S, Trivedi MM (2010) A general active-learning framework for on-road vehicle recognition and tracking. IEEE Trans Intell Transp Syst 11(2):267–276CrossRefGoogle Scholar
  15. 15.
    Song X, Rui T, Zha Z et al (2015) The AdaBoost algorithm for vehicle detection based on CNN features. In: The, international conference, pp 1–5Google Scholar
  16. 16.
    Goodfellow I, Pouget-Abadie J, Mirza M et al (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680Google Scholar
  17. 17.
    Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder-decoder architecture for scene segmentation. IEEE Trans Pattern Anal Mach Intell 2017:1–14Google Scholar
  18. 18.
    Tang SJW, Ng KY, Khoo BH et al (2015) Real-time lane detection and rear-end collision warning system on a mobile computing platform. In: IEEE, computer software and applications conference. IEEE Computer Society, pp 563–568Google Scholar
  19. 19.
    Trivedi MM, Moeslund TB (2015) Trajectory analysis and prediction for improved pedestrian safety: integrated framework and evaluations. In: Intelligent Vehicles Symposium (IV), 2015 IEEE. IEEE, pp 330–335Google Scholar
  20. 20.
    Yao J, Ramalingam S, Taguchi Y et al (2015) Estimating drivable collision-free space from monocular video. In; 2015 IEEE Winter Conference on Applications of computer vision (WACV). IEEE, pp 420–427Google Scholar
  21. 21.
    Wang H, Yuan C, Cai Y (2015) Smart road vehicle sensing system based on monocular vision. Optik-Int J Light Electron Opt 126(4):386–390CrossRefGoogle Scholar
  22. 22.
    Park KY, Hwang SY (2014) Robust range estimation with a monocular camera for vision-based forward collision warning system. Sci World J 2014Google Scholar
  23. 23.
    Viola P, Jones MJ (2001) Robust real-time object detection. Int J Comput Vision 57(2):87Google Scholar
  24. 24.
    Schapire RE (1990) The strength of weak learn ability. Mach Learn 5(2):28–33Google Scholar
  25. 25.
    Schapire RE (1999) A brief introduction to boosting. In: Sixteenth international joint conference on artificial intelligence. Morgan Kaufmann Publishers Inc., pp 1401–1406Google Scholar
  26. 26.
    Freund Y, Schapire RE (1999) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139MathSciNetCrossRefGoogle Scholar
  27. 27.
    Patel AK, Chatterjee S, Gorai AK (2017) Development of machine vision-based ore classification model using support vector machine (SVM) algorithm. Arab J Geosci 10(5):107CrossRefGoogle Scholar
  28. 28.
    Perea-Moreno AJ, Aguilera-Ureña MJ, Meroño-De Larriva JE et al (2016) Assessment of the potential of UAV video image analysis for planning irrigation needs of golf courses. Water 8(12):584CrossRefGoogle Scholar
  29. 29.
    Khehra BS, Pharwaha APS (2016) Classification of clustered microcalcifications using MLFFBP-ANN and SVM. Egypt Inform J 17(1):11–20CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Yi Xu
    • 1
  • Song Gao
    • 1
    • 3
    Email author
  • Shiwu Li
    • 2
  • Derong Tan
    • 1
  • Dong Guo
    • 1
  • Yuqiong Wang
    • 1
  • Qiang Chen
    • 2
    • 4
  1. 1.School of Transportation and Vehicle EngineeringShandong University of TechnologyZiboChina
  2. 2.School of TransportationJilin UniversityChangchunChina
  3. 3.Collaborative Innovation Center for New Energy Vehicle of Shandong UniversitiesZiboChina
  4. 4.School of Automotive and TransportationTianjin University of Technology and EducationTianjinChina

Personalised recommendations