To solve the problem that the existing semantic segmentation method is challenging to balance the two indicators of reasoning speed and accuracy under low-light conditions, a lightweight real-time semantic segmentation method that can run on embedded vehicle terminals under low-light conditions, namely, LCG-BiSeNetV2 is proposed. Firstly, the Zero-DCE++ method is introduced to preprocess the low-light video frames; Secondly, by improving the module of the BiSeNetV2 method and optimizing the downsampling convolution in the encoder structure, the semantic feature extraction ability of the BiSeNetV2 method has been significantly improved; Finally, the self-made road scene semantic segmentation dataset and the CAMVID dataset were used for training and testing, the mIoU coefficient reaches 72.37% and 76.73%, and the reasoning speed reaches 148.91 Frames Per Second (FPS) and 136.75 FPS, which shows that the LCG-BiSeNetV2 method has achieved fast reasoning and precise semantic segmentation.
GaoX. and BianX., Autonomous driving of vehicles based on artificial intelligence, Journal of Intelligent & Fuzzy Systems41(4) (2021), 4955–4964.
2.
HuangD., ZhouZ., DengM. and LiZ., Night time vehicle detection based on direction attention network and bayes corner localization, Journal of Intelligent & Fuzzy Systems41(1) (2021), 783–801.
3.
XiaoY., HeX., YangC., LiuH. and LiuY., Dynamic graph computing: A method of finding companion vehicles from traffic streaming data, Information Sciences591 (2022), 128–141.
4.
DengL., YangM., LiH., LiT., HuB. and WangC., Restricted deformable convolution-based road scene semantic segmentation using surround view cameras, IEEE Transactions on Intelligent Transportation Systems21(10) (2019), 4350–4362.
5.
YuC., GaoC., WangJ., YuG., ShenC. and SangN., Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation, International Journal of Computer Vision129(11) (2021), 3051–3068.
6.
YangZ., YuH., FengM., SunW., LinX., SunM., MaoZ.-H. and MianA., Small object augmentation of urban scenes for real-time semantic segmentation, IEEE Transactions on Image Processing29 (2020), 5175–5190.
7.
PengC., TianT., ChenC., GuoX. and MaJ., Bilateral attention decoder: A lightweight decoder for real-time semantic segmentation, Neural Networks137 (2021), 188–199.
8.
UrmsonC., AnhaltJ., BagnellD., BakerC., BittnerR., ClarkM., DolanJ., DugginsD., GalataliT., GeyerC., et al., Autonomous driving in urban environments: Boss and the urban challenge, Journal of field Robotics25(8) (2008), 425–466.
9.
PadenB., CápM., YongS.Z., YershovD. and FrazzoliE., A survey of motion planning and control techniques for self-driving urban vehicles, IEEE Transactions on Intelligent Vehicles1(1) (2016), 33–55.
10.
KendallA., HawkeJ., JanzD., MazurP., RedaD., AllenJ.-M., LamV.-D., BewleyA. and ShahA., Learning to drive in a day, in: 2019 International Conference on Robotics and Automation (ICRA), IEEE, 2019, pp. 8248–8254.
11.
CaiP., SunY., WangH. and LiuM., Vtgnet: A vision-based trajectory generation network for autonomous vehicles in urban environments, IEEE Transactions on Intelligent Vehicles6(3) (2020), 419–429.
12.
FalaschettiL., ManoniL. and TurchettiC., A low-rank cnn architecture for real-time semantic segmentation in visual slam applications, IEEE Open Journal of Circuits and Systems3 (2022), 115–133.
13.
PaszkeA., ChaurasiaA., KimS. and CulurcielloE., Enet: A deep neural network architecture for real-time semantic segmentation, arXiv preprint arXiv:1606.02147 (2016).
14.
LiG., YunI., KimJ. and KimJ., Dabnet: Depth-wise asymmetric bottleneck for real-time semantic segmentation, arXiv preprint arXiv:1907.11357 (2019).
15.
ZhangY., QiuZ., LiuJ., YaoT., LiuD. and MeiT., Customizable architecture search for semantic segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11641–11650.
16.
LiuH., MaS., XiaD. and LiS., Sfanet: A spectrum-aware feature augmentation network for visible-infrared person reidentification, IEEE Transactions on Neural Networks and Learning Systems (2021).
17.
YuC., WangJ., PengC., GaoC., YuG. and SangN., Bisenet: Bilateral segmentation network for real-time semantic segmentation, in: Proceedings of the European conference on computer vision (ECCV), 2018, pp. 325–341.
18.
CordtsM., OmranM., RamosS., RehfeldT., EnzweilerM., BenensonR., FrankeU., RothS. and SchieleB., The cityscapes dataset for semantic urban scene understanding, in: Proceedings of the IEEE conference on computer vision and Pattern Recognition, 2016, pp. 3213–3223.
19.
BrostowG.J., ShottonJ., FauqueurJ. and CipollaR., Segmentation and recognition using structure from motion point clouds, in: Computer Vision–ECCV 2008:10th European Conference on Computer Vision, Marseille, France, October 12–18, 2008, Proceedings, Part I 10, Springer, 2008, pp. 44–57.
20.
LiC., GuoC. and LoyC.C., Learning to enhance low-light image via zero-reference deep curve estimation, arXiv preprint arXiv:2103.00860 (2021).
21.
ZhuA., ZhangL., ShenY., MaY., ZhaoS. and ZhouY., Zero-shot restoration of underexposed images via robust retinex decomposition, in: 2020 IEEE International Conference on Multimedia and Expo (ICME), IEEE, 2020, pp. 1–6.
22.
LoreK.G., AkintayoA. and SarkarS., Llnet: A deep autoencoder approach to natural low-light image enhancement, Pattern Recognition61 (2017), 650–662.
23.
ShenL., YueZ., FengF., ChenQ., LiuS. and MaJ., Msr-net: Low-light image enhancement using deep convolutional network, arXiv preprint arXiv:1711.02488 (2017).
24.
LanY., HuangK., YangC., LeiL., YeJ., ZhangJ., ZengW., ZhangY. and DengJ., Real-time identification of rice weeds by uav low-altitude based on improved semantic segmentation model, Remote Sensing13(21) (2021), 4370.
25.
ZhaoH., QiX., ShenX., ShiJ. and JiaJ., Icnet for realtime semantic segmentation on high-resolution images, in: Proceedings of the European conference on computer vision (ECCV), 2018, pp. 405–420.
26.
LinP., SunP., ChengG., XieS., LiX. and ShiJ., Graph-guided architecture search for real-time semantic segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 4203–4212.
27.
YanG., YuM., ShiS. and FengC., The recognition of traffic speed limit sign in hazy weather, Journal of Intelligent & Fuzzy Systems33(2) (2017), 873–883.
28.
LiuZ., LinY., CaoY., HuH., WeiY., ZhangZ., LinS. and GuoB., Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 10012–10022.
29.
HuJ., ShenL. and SunG., Squeeze-and-excitation networks, in: Proceedings of the IEEE conference on computer vision and Pattern Recognition, 2018, pp. 7132–7141.
30.
LiJ., WeiY., LiangX., DongJ., XuT., FengJ. and YanS., Attentive contexts for object detection, IEEE Transactions on Multimedia19(5) (2016), 944–954.
31.
ChenL.-C., PapandreouG., KokkinosI., MurphyK. and YuilleA.L., Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs, IEEE Transactions on Pattern Analysis and Machine Intelligence40(4) (2017), 834–848.
32.
ChenL.-C., ZhuY., PapandreouG., SchroffF. and AdamH., Encoder-decoder with atrous separable convolution for semantic image segmentation, in: Proceedings of the European conference on computer vision (ECCV), 2018, pp. 801–818.
33.
YuF. and KoltunV., Multi-scale context aggregation by dilated convolutions, arXiv preprint arXiv:1511.07122 (2015).
34.
MaN., ZhangX., ZhengH.-T. and SunJ., Shufflenet v2: Practical guidelines for efficient cnn architecture design, in: Proceedings of the European conference on computer vision (ECCV), 2018, pp. 116–131.
35.
ChangJ. and GuanS., Class highlight generative adversarial networks for strip steel defect classification, International Journal of Pattern Recognition and Artificial Intelligence36(02) (2022), 2252004.
