High-definition (HD) maps are key components that provide rich topologic and semantic information for decision-making in vehicle autonomous driving systems. A complete ground orthophoto is usually used as the base image to construct the HD map. The ground orthophoto is obtained through inverse perspective transformation and image mosaicing. During the image mosaicing, multiple consecutive orthophotos are stitched together using pose information and image registration. In this study, wavelet transform is introduced to the image mosaicing process to alleviate the information loss caused by image overlapping. In the orthophoto wavelet transform, high-frequency and low-frequency components are fused using different strategies to form a complete base image with clearer local details. Experimental results show that the accuracy of the orthophotos generated using this method is improved.
ZHUANG Hanyang (庄瀚洋), ZHOU Xuejun (周学军), WANG Chunxiang (王春香), QIAN Yuhan (钱宇晗)
. Wavelet Transform-Based High-Definition Map Construction From a Panoramic Camera[J]. Journal of Shanghai Jiaotong University(Science), 2021
, 26(5)
: 569
-576
.
DOI: 10.1007/s12204-021-2346-9
[1] HA¨ NE C, HENG L, LEE G H, et al. 3D visual per-ception for self-driving cars using a multi-camera sys-tem: Calibration, mapping, localization, and obstacle detection [J]. Image and Vision Computing, 2017, 68:
14- 27.
[2] GUO L D, YANG M, WANG B, et al. Occupancy grid based urban localization using weighted point cloud [C]//2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC ). Rio de Janeiro: IEEE, 2016: 60-65.
[3] LI L, YANG M, WANG B, et al. An overview on sensor map based localization for automated driv-ing [C]//2017 Joint Urban Remote Sensing Event (JURSE). Dubai: IEEE, 2017: 1-4.
[4] HEY,LUH,WANGC X,et al. Generation ofprecise lane-level maps based on multi-sensors [J]. Journal of Chang’an University (Natural Science Edition), 2015, 35(S1): 274-278 (in Chinese).
[5] BENDER P, ZIEGLER J, STILLER C. Lanelets: E?cient map representation for autonomous driving [C]//2014 IEEE Intelligent Vehicles Symposium Pro-ceedings. Dearborn, MI: IEEE, 2014: 420-425.
[6] SAHU D K, PARSAI M P. Di?erent image fusion tech-niques — A critical review [J]. International Journal of Modern Engineering Research (IJMER), 2012, 2(5): 4298-4301.
[7] SONG H H, LU Z. Image fusion scheme based on non-subsampled contourlet and block-based cosine trans-form [J]. Journal of Shanghai Jiaotong University (Sci-ence), 2012, 17(1): 8-12. [8] YANG B, JING Z L, ZHAO H T. Review of pixel-level image fusion [J]. Journal of Shanghai Jiaotong University (Science), 2010, 15(1): 6-12.
[9] BURT P J, KOLCZYNSKI R J. Enhanced image capture through fusion [C]//1993 (4th) International Conference on Computer Vision. Berlin: IEEE, 1993:
173- 182.
[10] AMOLINS K, ZHANG Y, DARE P. Wavelet based im-age fusion techniques — An introduction, review and comparison [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007, 62(4): 249-263.
[11] RANI K, SHARMA R. Study of di?erent image fusion algorithm [J]. International journal of Emerging Tech-nology and Advanced Engineering, 2013, 3(5): 288-291.
[12] TOET A, VAN RUYVEN L J, VALETON J M. Merg-ing thermal and visual images by a contrast pyramid [J]. Optical Engineering, 1989, 28(7): 287789.
[13] TOET A. A morphological pyramidal image decom-position [J]. Pattern Recognition Letters, 1989, 9(4):
255- 261.
[14] LI M J, DONG Y B, WANG X L. Image fusion algo-rithm based on gradient pyramid and its performance evaluation [J]. Applied Mechanics and Materials, 2014, 525: 715-718.
[15] GAO J M, LIU Z H, REN T. A new image fusion scheme based on wavelet transform [C]//2008 3rd In-ternational Conference on Innovative Computing In-formation and Control. Dalian: IEEE, 2008: 441.
[16] RUAN J X, XIE L Y, RUAN Y Y, et al. Imageorm [C]//2018 7th International Conference on Digi-tal Home (ICDH ). Guilin: IEEE, 2018: 9-13. [17] ADEL E, ELMOGY M, ELBAKRY H. Image stitching based on feature extraction techniques: A survey [J]. International Journal of Computer Applications, 2014, 99(6): 1-8.
[18] ZHANG J, ZHANG Q. Image fusion algorithm based on wavelet transform [C]//2015 4th International Con-ference on Advanced Information Technology and Sen-sor Application (AITS ). Harbin: IEEE, 2015: 47-50.
[19] LLOYD C D, ATKINSON P M, APLIN P. Char-acterising local spatial variation in land cover us-ing geostatistical functions and the discrete wavelet transform [M]//Geostatistics for environmental appli-cations. Berlin: Springer, 2005: 391-402.
[20] SONG H H, YU S Y, SONG L, et al. Fusion of multi-spectral and panchromatic satellite images based on contourlet transform and local average gradient [J]. Optical Engineering, 2007, 46(2): 020502.
[21] YANG M, WANG C X, CHEN F, et al. A new approach to high-accuracy road orthophoto mapping based on wavelet transform [J]. International Jour-nal of Computational Intelligence Systems, 2011, 4(6): 1367-1374.
[22] ZHUANG H Y, WANG C X, QIAN Y H, et al. Semantic-based road segmentation for high-de?nition map construction [M]//Communications in computer and information science. Singapore: Springer, 2021:
527- 537.