The implementation of autonomous driving technology required high-precision recognition of traffic signs. However, due to their high similarity, small size, and vulnerability to outdoor environmental factors, achieving real-time and accurate detection posed significant challenges. In response to the limitations of traditional neural network design approaches, an algorithm based on self-selecting architecture was proposed to automatically adjust the network structure, thereby enhancing model performance and efficiency. The algorithm adopted a two-stage training approach to optimize the selection of network paths. Moreover, gradient propagation was employed to train the hyperparameters for multiple loss functions, replacing the conventional manual tuning with a dynamic loss network scheme. The results demonstrated that the proposed algorithm achieved an accuracy rate of 95.74% and a detection speed of 146.58 frames per second on the GTSRB dataset, while maintaining a model parameter size of only 0.46Mb, enabling deployment on mobile devices. Compared to the traditional manual design of static networks, the adoption of the self-learning architecture module not only reduced experimental costs but also improved accuracy and performance. Furthermore, it enabled superior detection outcomes in various environments and exhibited a noticeable enhancement in loss convergence speed.
FengRun-ze, JiangKun, YuWei-guang, et al. Chinese traffic sign recognition based on two-stage classification algorithm[J]. Automotive Engineering, 2022, 44(3): 434-441.
[4]
WangM, LiuR, YangJ, et al.Traffic sign three-dimensional reconstruction based on point clouds and panoramic images[J].Photogrammetric Record, 2022, 37(177): 87-110.
[5]
ShenL, YouL, PengB, et al.Group multi-scale attention pyramid network for traffic sign detection[J].Neuro Computing, 2021, 452(6): 1-14.
[6]
LiuY, PengJ, XueJ H, et al. TSingNet: scale-aware and context-rich feature learning for traffic sign detection and recognition in the wild[J].Neurocomputing, 2021, 447(4): 10-22.
[7]
VashishtM, KumarB. Effective implementation of machine learning algorithms using 3D colour texture feature for traffic sign detection for smart cities[J]. Expert Systems, 2021, 39(5): e12781.
[8]
WanH, GaoL, SuM, et al. A novel neural network model for traffic sign detection and recognition under extreme conditions[J]. Journal of Sensors, 2021, 7: 9984787.
[9]
YuL, XiaX, ZhouK. Traffic sign detection based on visual co-saliency in complex scenes [J]. Applied Intelligence, 2019, 49(2): 764-790.
[10]
CoţovanuD, ZetC, FoşalăuC, et al. Detection of traffic signs based on support vector machine classification using HOG features[C]∥Proceedings of the 2018 International Conference and Exposition on Electrical And Power Engineering, Iasi, Romania, 2018: 8559784.
[11]
LecunY, BottouL, BengioY, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[12]
SimonyanK, ZissermanA.Very deep convolutional networks for large-scale image recognition [J/OL].(2015-04-10)[2023-07-30].
[13]
HeK, ZhangX, RenS, et al. Deep residual learning for image recognition[C]∥Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 7780459.
[14]
CholletF. Xception: deep learning with depthwise separable convolutions[C]∥Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 8099678.
[15]
YuF, KoltunV. Multi-scale context aggregation by dilated convolutions[J/OL].(2016-04-30)[2023-07-30].
[16]
LinT Y, GoyalP, GirshickR, et al. Focal loss for dense object detection[C]∥Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 8237586.
[17]
LiuZ, LinY, CaoY, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]∥Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021: 10012-10022.
[18]
RealE, LiangC, SoD R, et al. AutoML-Zero: evolving machine learning algorithms from scratch[C]∥Proceedings of the International Conference on Machine Learning, Vienna, Austria, 2020: 8007-8019.
GaoS H, ChengM M, ZhaoK, et al. Res2Net: A new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 652-662.
[21]
LiuZ, MaoH, WuC Y, et al. A convnet for the 2020s[C]∥Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 9879745.
[22]
PhamH, GuanM Y, ZophB, et al.Efficient neural architecture search via parameter sharing [J/OL].(2018-02-12)[2023-07-30].
[23]
TangY, HanK, GuoJ, et al. GhostNetV2: enhance cheap operation with long-range attention [J/OL].(2022-11-23)[2023-07-30].
[24]
RaoY, ZhaoW, TangY, et al.HorNet: efficient high-order spatial interactions with recursive gated convolutions [J/OL].(2022-10-11)[2023-07-30].
[25]
ChenJ, KaoS H, HeH, et al. Run, don't walk: chasing higher flops for faster neural networks [J/OL].(2023-05-21)[2023-07-30].