On­road object detection is a critical component in an autonomous driving system. The safety of the vehicle is just as good as the reliability of
the on­road object detection system. Thus, developing a fast and robust
object detection algorithm has been the main goal of many automotive industries and institutes. In this paper, we focus on developing a novel object
proposal algorithm to improve object detection speed. It does so by reducing the number of proposals that has to be evaluated by the classification
network. The proposed method uses cues from edge­map to obtain scores
from each candidate proposals and rank them. To improve detection quality and speed, efficient complementary methods using entropy and road
segmentation are also employed. Finally, in the experimental test using
KITTI, the proposed method achieves an average of 72.1% recall rate on 4
classes (pedestrian, cyclist, car, and truck) and 15 milliseconds of run time,
surpassing other object proposal algorithms.

[1] Z. Sun, G. Bebis, and R. Miller, “On­road vehicle detection: a review,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, pp. 694–711, May 2006.
[2] M. Ryan, “The Future of Transportation: Ethical, Legal, Social and
Economic Impacts of Self­driving Vehicles in the Year 2025,” Science
and Engineering Ethics, Sept. 2019.
[3] J. Cheng, Z. Xiang, T. Cao, and J. Liu, “Robust vehicle detection using 3D Lidar under complex urban environment,” in 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 691–
696, May 2014. ISSN: 1050­4729.
[4] S. Sivaraman and M. M. Trivedi, “Looking at Vehicles on the Road:
A Survey of Vision­Based Vehicle Detection, Tracking, and Behavior
Analysis,” IEEE Transactions on Intelligent Transportation Systems,
vol. 14, pp. 1773–1795, Dec. 2013.
[5] A. Mukhtar, L. Xia, and T. B. Tang, “Vehicle Detection Techniques
for Collision Avoidance Systems: A Review,” IEEE Transactions
on Intelligent Transportation Systems, vol. 16, pp. 2318–2338, Oct.
2015.
[6] S. Sivaraman and M. M. Trivedi, “A review of recent developments
in vision­based vehicle detection,” in 2013 IEEE Intelligent Vehicles
Symposium (IV), pp. 310–315, June 2013. ISSN: 1931­0587.
45
[7] Y. Kang, H. Yin, and C. Berger, “Test Your Self­Driving Algorithm:
An Overview of Publicly Available Driving Datasets and Virtual Testing Environments,” IEEE Transactions on Intelligent Vehicles, vol. 4,
pp. 171–185, June 2019.
[8] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan,
“Object Detection with Discriminatively Trained Part­Based Models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, pp. 1627–1645, Sept. 2010.
[9] J. Hosang, R. Benenson, P. Dollár, and B. Schiele, “What Makes for
Effective Detection Proposals?,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, pp. 814–830, Apr. 2016.
[10] S. Ren, K. He, R. Girshick, and J. Sun, “Faster R­CNN: Towards
Real­Time Object Detection with Region Proposal Networks,” in Advances in Neural Information Processing Systems 28 (C. Cortes, N. D.
Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, eds.), pp. 91–99,
Curran Associates, Inc., 2015.
[11] T.­Y. Lin, P. Dollar, R. Girshick, K. He, B. Hariharan, and S. Belongie,
“Feature Pyramid Networks for Object Detection,” pp. 2117–2125,
2017.
[12] J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” in
2017 IEEE Conference on Computer Vision and Pattern Recognition
(CVPR), pp. 6517–6525, July 2017. ISSN: 1063­6919.
[13] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.­Y. Fu, and
A. C. Berg, “SSD: Single Shot MultiBox Detector,” in Computer Vi46
sion–ECCV 2016 (B. Leibe, J. Matas, N. Sebe, and M. Welling, eds.),
(Cham), pp. 21–37, Springer International Publishing, 2016.
[14] M.­M. Cheng, Y. Liu, W.­Y. Lin, Z. Zhang, P. L. Rosin, and P. H. S.
Torr, “BING: Binarized normed gradients for objectness estimation
at 300fps,” Computational Visual Media, vol. 5, pp. 3–20, Mar. 2019.
[15] J. Carreira and C. Sminchisescu, “CPMC: Automatic Object Segmentation Using Constrained Parametric Min­Cuts,” IEEE Transactions
on Pattern Analysis and Machine Intelligence, vol. 34, pp. 1312–
1328, July 2012.
[16] J. R. R. Uijlings, K. E. A. van de Sande, T. Gevers, and A. W. M.
Smeulders, “Selective Search for Object Recognition,” International
Journal of Computer Vision, vol. 104, pp. 154–171, Sept. 2013.
[17] J. Pont­Tuset, P. Arbeláez, J. T. Barron, F. Marques, and J. Malik, “Multiscale Combinatorial Grouping for Image Segmentation and
Object Proposal Generation,” IEEE Transactions on Pattern Analysis
and Machine Intelligence, vol. 39, pp. 128–140, Jan. 2017.
[18] X. Yuan, S. Su, and H. Chen, “A Graph­Based Vehicle Proposal Location and Detection Algorithm,” IEEE Transactions on Intelligent
Transportation Systems, vol. 18, pp. 3282–3289, Dec. 2017.
[19] B. Alexe, T. Deselaers, and V. Ferrari, “Measuring the Objectness of
Image Windows,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, pp. 2189–2202, Nov. 2012.
[20] C. L. Zitnick and P. Dollár, “Edge Boxes: Locating Object Proposals
from Edges,” in Computer Vision –ECCV 2014 (D. Fleet, T. Pajdla,
47
B. Schiele, and T. Tuytelaars, eds.), vol. 8693, pp. 391–405, Cham:
Springer International Publishing, 2014.
[21] Q. Wu, H. Li, F. Meng, and K. N. Ngan, “Generic Proposal Evaluator: A Lazy Learning Strategy Toward Blind Proposal Quality Assessment,” IEEE Transactions on Intelligent Transportation Systems,
vol. 19, pp. 306–319, Jan. 2018.
[22] H. Kuang, L. Chen, L. L. H. Chan, R. C. C. Cheung, and H. Yan, “Feature Selection Based on Tensor Decomposition and Object Proposal
for Night­Time Multiclass Vehicle Detection,” IEEE Transactions on
Systems, Man, and Cybernetics: Systems, vol. 49, pp. 71–80, Jan.
2019.
[23] X. Yuan, X. Cao, X. Hao, H. Chen, and X. Wei, “Vehicle Detection by
a Context­Aware Multichannel Feature Pyramid,” IEEE Transactions
on Systems, Man, and Cybernetics: Systems, vol. 47, pp. 1348–1357,
July 2017. Conference Name: IEEE Transactions on Systems, Man,
and Cybernetics: Systems.
[24] Y. Xu, X. Cao, and H. Qiao, “An Efficient Tree Classifier Ensemble­Based Approach for Pedestrian Detection,” IEEE Transactions
on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 41,
pp. 107–117, Feb. 2011. Conference Name: IEEE Transactions on
Systems, Man, and Cybernetics, Part B (Cybernetics).
[25] P. Dollár and C. L. Zitnick, “Structured Forests for Fast Edge Detection,” in 2013 IEEE International Conference on Computer Vision,
pp. 1841–1848, Dec. 2013. ISSN: 2380­7504.
48
[26] Y. Song, Y. Ju, K. Du, W. Liu, and J. Song, “Online Road Detection
under a Shadowy Traffic Image Using a Learning­Based Illumination­Independent Image,” Symmetry, vol. 10, p. 707, Dec. 2018.
[27] F. Hermosillo­Reynoso, D. Torres­Roman, J. Santiago­Paz, and
J. Ramirez­Pacheco, “A Novel Algorithm Based on the Pixel­Entropy
for Automatic Detection of Number of Lanes, Lane Centers, and Lane
Division Lines Formation,” Entropy, vol. 20, p. 725, Oct. 2018.