Abstract
The detection of the vehicle taillights is important for predicting the driving intention of the vehicle in front. The YOLOv4 target detection algorithm has problems such as insufficient detection capabilities for small targets and inaccurate bounding box positioning. In response to this problem, a front vehicle taillight detection algorithm combining high-level semantics and low-level features is proposed. Based on the improved CSPResNeXt model to extract features, the algorithm uses the mask image containing semantic information and the corresponding feature map to fuse and enhance distinguishability of vehicle taillights and background. At the same time, BiFPN model is used for further multi-scale feature fusion to extract more detailed information. The experimental results show that our proposed algorithm can improve the mAP of object detection without affecting the real-time performance of the YOLOv4 algorithm. Our algorithm achieves 90.55% mAP (IoU = 0.5) on the test set, which is 14.42% mAP (IoU [0.5:0.95]) higher than the original YOLOv4 algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhong, G., et al.: Learning to tell brake lights with convolutional features. In: 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), pp. 1558–1563. IEEE (2016)
Vancea, F.I., Costea, A.D., Nedevschi, S.: Vehicle taillight detection and tracking using deep learning and thresholding for candidate generation. In: 2017 13th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP), pp. 267–272. IEEE (2017)
Vancea, F.I., Nedevschi, S.: Semantic information based vehicle relative orientation and taillight detection. In: 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP), pp. 259–264. IEEE (2018)
Nava, D., Panzani, G., Savaresi, S.M.: A collision warning oriented brake lights detection and classification algorithm based on a mono camera sensor. In: 2019 IEEE Intelligent Transportation Systems Conference (ITSC), pp. 319–324. IEEE (2019)
Li, X.: Recognition of the vehicle and rear light videos based on deep learning. Master’s thesis, Guangdong University of Technology (2019)
Hsu, H.K., et al.: Learning to tell brake and turn signals in videos using CNN-LSTM structure. In: 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), pp. 1–6. IEEE (2017)
Lee, K.H., Tagawa, T., Pan, J.E.M., Gaidon, A., Douillard, B.: An attention-based recurrent convolutional network for vehicle taillight recognition. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 2365–2370. IEEE (2019)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132–7141 (2018)
Yu, F., et al.: BDD100K: a diverse driving video database with scalable annotation tooling, vol. 2, no. 5, p. 6. arXiv preprint arXiv http://arxiv.org/abs/1805.04687 (2018)
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781–10790 (2020)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. arXiv preprint arXiv http://arxiv.org/abs/1904.07850 (2019)
Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9627–9636 (2019)
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv http://arxiv.org/abs/2004.10934 (2020)
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Chang, L., Zhang, C. (2021). Vehicle Taillight Detection Based on Semantic Information Fusion. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1517. Springer, Cham. https://doi.org/10.1007/978-3-030-92310-5_61
Download citation
DOI: https://doi.org/10.1007/978-3-030-92310-5_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92309-9
Online ISBN: 978-3-030-92310-5
eBook Packages: Computer ScienceComputer Science (R0)