© The Institution of Engineering and Technology
Computing the positions of road signs from in-vehicle video log images is one of the most fundamental tasks for intelligent sign inventory. This study analysed vision-based positioning methods from video log images and proposed an analytic model of road sign positioning (AM-RSP) based on error propagation and first-order approximation. Both image noises and camera calibration errors were modelled as two error sources. The AM-RSP model can evaluate and quantify the positioning uncertainties for both single view and stereo vision-based methods. Moreover, it can quantitatively establish the relationship between the positioning uncertainties and the various parameters of the vehicle and the camera,such as camera focal length, view angle, baseline width, height, image acquisition interval, vehicle distance to the road edge etc. Hence, the proposed AM-RSP model can be applied to configure the parameters of the camera and the vehicle to meet some specific computation requirement such as RSP accuracy. The proposed AM-RSP model has been validated with real video log image data collected in the field. These results show that the AM-RSP model is accurate and reliable to compute sign positioning uncertainties.
References
-
-
1)
-
13. Welzel, A., Auerswald, A., Wanielik, G.: ‘Accurate camera-based traffic sign localization’. 17th IEEE Intelligent Transportation Systems Conf. (ITSC), Qingdao, China, 2014, pp. 445–450.
-
2)
-
4. Baro, X., Escalera, S., Vitria, J., et al: ‘Traffic sign recognition using evolutionary Adaboost detection and forest-ECOC classification’, IEEE Trans. Intell. Transp. Syst., 2009, 10, (1), pp. 113–126 (doi: 10.1109/TITS.2008.2011702).
-
3)
-
10. Zhou, L., Deng, Z.: ‘LIDAR and vision-based real-time traffic sign detection and recognition algorithm for intelligent vehicle’. 17th IEEE Intelligent Transportation Systems Conf. (ITSC), Qingdao, China, 2014, pp. 578–583.
-
4)
-
5. Zhang, K., Sheng, Y., Li, J.: ‘Automatic detection of road traffic signs from natural scene images based on pixel vector and central projected shape feature’, IET Intell. Transp. Syst., 2011, 5, (4), pp. 294–301 (doi: 10.1049/iet-its.2011.0060).
-
5)
-
12. Wang, K., Hou, Z., Gong, W.: ‘Automated road sign inventory system based on stereo vision and tracking’, Comput. Aided Civil Infrastruct. Eng., 2010, 25, (6), pp. 468–477 (doi: 10.1111/j.1467-8667.2010.00657.x).
-
6)
-
7. Yang, F., Wang, H., Wei, H., et al: ‘Circular road sign analysis and visual localization approach based on monocular vision’. 2012 Third Global Congress on Intelligent Systems (GCIS), 2012, pp. 334–337.
-
7)
-
18. Tsai, Y., Hu, Z., Wang, Z.: ‘Vision-based roadway geometry computation’, J. Transp. Eng. ASCE, 2010, 136, (3), pp. 223–233 (doi: 10.1061/(ASCE)TE.1943-5436.0000073).
-
8)
-
14. Laflamme, C., Kingston, T., McCuaig, R.: ‘Automated mobile mapping for asset managers’. XXIII Int. FIG Congress, Munich, Germany, 8–13 October 2006, pp. 1–14.
-
9)
-
9. Hu, Z., Tsai, Y.: ‘Generalized image recognition algorithm for sign inventory’, ASCE J. Comput. Civil Eng., 2011, 48, (3), pp. 149–158 (doi: 10.1061/(ASCE)CP.1943-5487.0000076).
-
10)
-
6. Okyere, A., Attoh-Okine, N.: ‘Traffic sign recognition using sparse representations and active contour models’, Transp. Res. Rec., J. Transp. Res. Board, 2014, 2463, (1), pp. 35–45 (doi: 10.3141/2463-05).
-
11)
-
8. Hu, Z.: ‘Intelligent road sign inventory (IRSI) with image recognition and attribute computation from video log’, Comput. Aided Civil Infrastruct. Eng., 2013, 28, (2), pp. 130–145 (doi: 10.1111/j.1467-8667.2012.00768.x).
-
12)
-
11. Hu, Z., Tsai, Y.: ‘Homography-based vision algorithm for traffic sign attribute computation’, Comput. Aided Civil Infrastruct. Eng., 2009, 24, (6), pp. 385–400 (doi: 10.1111/j.1467-8667.2009.00598.x).
-
13)
-
2. Nguyen, K., Le, D., Duong, D.: ‘Efficient traffic sign detection using bag of visual words and multi-scales SIFT’. Proc. of Neural Information Processing, 2013, pp. 433–441.
-
14)
-
15. Chen, X., Kohlmeyer, B., Stroila, M., et al: ‘Next generation map making: geo-referenced ground-level LIDAR point clouds for automatic retro-reflective road feature extraction’. Proc. 17th ACM SIGSPATIAL Int. Conf. on Advances in Geographic Information Systems, NY, USA, 2009, pp. 488–491.
-
15)
-
3. Salti, S., Petrelli, A., Tombari, F., et al: ‘Traffic sign detection via interest region extraction’, Pattern Recognit., 2015, 48, (4), pp. 1039–1049 (doi: 10.1016/j.patcog.2014.05.017).
-
16)
-
6. Zhang, Z.: ‘A flexible new technique for camera calibration’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 22, (11), pp. 1330–1334 (doi: 10.1109/34.888718).
-
17)
-
1. Fleyeh, H., Davami, E.: ‘Eigen-based traffic sign recognition’, IET Intell. Transp. Syst., 2011, 5, (3), pp. 190–196 (doi: 10.1049/iet-its.2010.0159).
-
18)
-
16. Hartley, R., Zisserman, A.: ‘Multi-view geometry in computer vision’ (Cambridge University Press, Cambridge, 2004, 2nd edn.).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2015.0078
Related content
content/journals/10.1049/iet-its.2015.0078
pub_keyword,iet_inspecKeyword,pub_concept
6
6