Research of improved object detection with image dehazing

  • Authors

    • Hyochang Ahn
    • June Hwan Lee
    • Han Jin Cho
    2018-04-03
    https://doi.org/10.14419/ijet.v7i2.12.11039
  • Object Detection, Feature Descriptor, Feature Matching, Dark Channel, Image Dehazing

  • Background/Objectives: In this paper, we propose an improved object recognition method that can recover visibility by detecting degraded image due to factors such as weather, and to detect objects in the reconstructed image.

    Methods/Statistical analysis: In this paper, we propose improved object detection and recognition method by visibility restoration by improving degraded image. First, fog removal based on a single image is performed and restored using a median filter instead of using the minimum value in the window. We also used adaptive feature point extraction method to extract feature points by removing unnecessary information such as noise from the improved image.

    Findings: The performance of the proposed algorithm was evaluated by measuring the number of feature points before and after the proposed algorithm. Experimental results show that more feature points are extracted and matched than the case of recognition of the region of interest after reconstructing the image by removing the fog using the intermediate value filter in the image of degraded image by the proposed method.

    Improvements/Applications: Applying the proposed method to a variety of vision - based intelligent systems such as smart cars will eliminate the bad conditions such as fog, which will give better performance.

     

     

  • References

    1. [1] He, K., Sun, J., & Tang, X. Single image haze removal using dark channel prior. IEEE transactions on pattern analysis and machine intelligence, 2011, 33(12), pp.2341-2353.

      [2] Gibson, K. B., Vo, D. T., & Nguyen, T. Q. An investigation of dehazing effects on image and video coding. IEEE transactions on image processing, 2012, 21(2), pp.662-673.

      [3] Tan, R. T. Visibility in bad weather from a single image. In Computer Vision and Pattern Recognition, 2008. CVPR 2008. 2008, pp. 1-8.

      [4] Gadnayak, K. K., Panda, P., & Panda, N. Haze Removal: An Approach Based on Saturation Component. In Intelligent Computing, Communication and Devices, 2015, pp.281-287.

      [5] Lee, J. W., & Hong, S. H. Real-time Haze Removal Method using Brightness Transformation based on Atmospheric Scatter Coefficient Rate and Local Histogram Equalization. Journal of Korea Multimedia Society, 2016, 19(1), pp.10-21.

      [6] Ahn, H., & Lee, Y. H. Performance analysis of object recognition and tracking for the use of surveillance system. Journal of Ambient Intelligence and Humanized Computing, . 2016, 7(5), pp.673-679.

      [7] Viola, P., & Jones, M. Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference, 2001, (Vol. 1, pp. I-I).

      [8] Ahn, H. C., & Rhee, S. B. Fast Image Stitching Based on Improved SURF Algorithm using Meaningful Features. The KIPS Transactions: PartB, 2012, 19(2), pp.93-98.

      [9] Gibson, K., Võ, D., & Nguyen, T. An investigation in dehazing compressed images and video. In OCEANS 2010 IEEE. 2010, September, pp. 1-8.

      [10] Fattal, R. Single image dehazing. ACM transactions on graphics (TOG), 2008, 27(3), 72.

      [11] Lowe, D. G. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 2004. 60(2), pp.91-110.

      [12] Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. Speeded-up robust features (SURF). Computer vision and image understanding, 2008, 110(3), pp.346-359.

      [13] Brown, M., & Lowe, D. G. Invariant Features from Interest Point Groups. In BMVC. 2002, September, Vol. 4.

      [14] Stommel, M., & Herzog, O. Binarising SIFT-descriptors to reduce the curse of dimensionality in histogram-based object recognition. Signal Processing, Image Processing and Pattern Recognition, 2009, pp.320-327.

      [15] Mandle, P., & Pahadiya, B. An Advanced Technique of Image Matching Using SIFT and SURF. International Journal of Advanced Research in Computer and Communication Engineering, 2016, 5(5).nurses in korea. Diabetes Research and Clinical Practice 77, 199–204.

      [16] McMahon GT, Gomes HE, Hohne SH, Hu TM, Levine BA & Conlin PR (2005), Web-based care management in patients with poorly controlled diabetes. Diabetes Care 28, 1624–1629.

      [17] Thakurdesai PA, Kole PL & Pareek RP (2004), Evaluation of the quality and contents of diabetes mellitus patient education on Internet. Patient Education and Counseling 53, 309–313.

  • Downloads

  • How to Cite

    Ahn, H., Hwan Lee, J., & Jin Cho, H. (2018). Research of improved object detection with image dehazing. International Journal of Engineering & Technology, 7(2.12), 76-79. https://doi.org/10.14419/ijet.v7i2.12.11039