Abstract:In the scenes of object occlusion, lighting changes and shadow interference, the detection of the point instance network (PINet) has high accuracy but with poor real-time performance. A lane detection model combining the recurrent feature-shift aggregator (RESA) algorithm was proposed to ensure the accuracy of the PINet model and improve the inference speed of the network. To eliminate the redundant multi-scale operations and accelerate the inference speed of the model, only one bottle-neck network was used for the prediction network model after the computational power analysis. To compensate the accuracy decreasing by module pruning, the RESA module was proposed to capture the spatial information across rows and columns in the image for enhancing the lane line features. The tests of the improved model were conducted on the Tusimple, CULane and Custom datasets. The results show that the improved network model performs well in various complex scenarios of object occlusion, lighting changes and shadow interference with improved accuracy and real-time processing speed of lane segmentation. The detection and recognition performance is better than that of traditional PINet network algorithms. Except for slight improvement in the F1 indicator, the inference speeds of the improved model are respectively increased by 20.3%, 52.9% and 13.9% in the three datasets.
范英, 石磊, 苏伟伟, 闫浩. 基于PINet+RESA网络的车道线检测算法[J]. 江苏大学学报(自然科学版), 2023, 44(4): 373-378.
FAN Ying, SHI Lei, SU Weiwei, YAN Hao. Lane detection algorithm based on PINet+RESA network[J]. Journal of Jiangsu University(Natural Science Eidtion)
, 2023, 44(4): 373-378.
SUN W, ZHANG X R, TANG H Q, et al. Lane coordination detection based on Hough transformation and least square fitting[J]. Opto-Electronic Engineering, 2011,38(10):13-19.(in Chinese)
[3]
NEVEN D, DE BRABANDERE B, GEORGOULIS S, et al.Towards end-to-end lane detection: an instance segmentation approach[C]∥2018 IEEE Intelligent Vehicles Symposium (IV). Piscataway,USA:IEEE, 2018:286-291.
[4]
PASZKE A, CHAURASIA A, KIM S, et al. ENet: a deep neural network architecture for real-time semantic segmentation[J]. arXiv Preprint arXiv,DOI:10.48550/arXiv.1606.02147.
[5]
PAN X G, SHI J P, LUO P, et al. Spatial as deep: spatial CNN for traffic scene understanding[J]. arXiv Preprint arXiv,DOI: 10.48550/arXiv.1712.06080.
[6]
KO Y, LEE Y, AZAM S, et al. Key points estimation and point instance segmentation approach for lane detection[J]. IEEE Transactions on Intelligent Transportation Systems,2022,23(7):8949-8958.
[7]
HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]∥IEEE Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE Computer Society,2016:770-778.
[8]
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]∥Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE Computer Society,2016:779-788.
[9]
WANG W, YU R, HUANG Q, et al. SGPN: similarity group proposal network for 3D point cloud instance segmentation[C]∥Proceedings of the IEEE Computer Socie-ty Conference on Computer Vision and Pattern Recognition.Washington,USA:IEEE Computer Society, 2018:2569-2578.
[10]
ZHENG T, FANG H, ZHANG Y, et al. RESA: recurrent feature-shift aggregator for lane detection[J]. arXiv Preprint arXiv,DOI:10.48550/arXiv.2008.13719.
CHEN L C, XU X Z, CAO J F, et al. Multi-scenario lane line detection with auxiliary loss[J]. Journal of Image and Graphics, 2020,25(9):1882-1893.(in Chinese)
ZHOU J M, WANG Y, NING H, et al. Lane detection algorithm based on GLNet for multiple scenes[J]. China Journal of Highway and Transport, 2021,34(7):118-127.(in Chinese)
YANG J X, FAN Y, XIE C L. Lane detection algorithm based on row distance and particle filter[J]. Journal of Jiangsu University(Natural Science Edition), 2020,41(2):138-142,198.(in Chinese)