浏览全部资源
扫码关注微信
Received：29 March 2019，
Revised：2019-8-19，
Accepted：26 August 2019，
Published：16 February 2020
移动端阅览
目的
2
传统的轨道检测算法受环境干扰因素大导致检测效率低，基于卷积神经网络（CNN）算法的轨道检测结果缺乏对于对象的细腻、独特刻画且过多依赖可视化后处理技术，因此本文提出一种结合多尺度信息的条件生成对抗网络（CGAN）轨道线检测算法。
方法
2
在生成器网络中采用多粒度结构将生成器分解为全局和局部两个部分；在判别器网络中采用多尺度共享卷积结构，进一步监督生成器的训练；引入蒙特卡罗搜索技术通过对生成器的中间状态进行搜索，并将结果再送入到判别器中进行对比。
结果
2
在井下巷道场景测试集中，本文方法取得了82.43%像素精度和0.621 8的平均交并比，并且对轨道的检测可以达到95.01%的准确率；与现有的语义分割的算法相比，表现出了优越性。
结论
2
本文方法能够有效应用于井下复杂环境，一定程度上解决了传统的图像处理算法和卷积神经网络算法存在的问题，从而有效服务于井下自动驾驶。
Objective
2
In recent years
the frequent occurrence of large-scale mine accidents has led to many casualties and property losses. The mines' production and transportation should be promoted in the way of intelligence. When moving under the mine
the controller of a locomotive needs track information to detect the presence of pedestrians or obstacles in front of it. Then
the locomotive slows down or stops as soon as an emergency condition appears. Track detection
which uses image processing technology to identify the track area in a video or image and displays the specific position of the track
is a key technology for computer vision to achieve automatic driving downhole. Track detection algorithms based on traditional image processing can be classified into two categories. The first is a feature-based approach
which uses the difference between the edge and surrounding environment to extract the track region and obtains the specific track location in the image. However
this method relies heavily on the underlying features of the image and is easily interfered by the surrounding environment
which brings great challenges to the subsequent work and affects the final detection effect of the track. The second is a model-based strategy
which converts the track detection into a problem of solving the track model parameters and achieves the fitting of the track based on its shape in the local range. The track model often cannot adapt to multiple scenarios
and the approach lacks robustness and flexibility. Track detection results based on the convolutional neural network algorithm lack a detailed
unique characterization of the object and rely heavily on visual post-processing techniques. Therefore
we propose conditional generative adversarial net
a track detection algorithm combining multiscale information.
Method
2
First
the multigranularity structure is used to decompose it into global and local parts in the generator network. The global part is responsible for low-resolution image generation
and the local part will combine with the global part to generate high-resolution images. Second
the multiscale shared convolution structure is adopted in the discriminator network. The primary features of the real and synthesized samples are extracted by sharing the convolution layer
the corresponding feature map is obtained
and different samples are sent to the multiscale discriminator to supervise the training of the generator further. Finally
the Monte Carlo search technique is introduced to search the intermediate state of the generator
and the result is sent to the discriminator for comparison.
Result
2
The proposed algorithm achieves an average pixel accuracy of 82.43% and a mean intersection over-union of 0.621 8. Moreover
the accuracy of detecting the track can reach 95.01%. For many different underground scenes
the track test results show good performance and superiority compared with the existing semantic segmentation algorithms.
Conclusion
2
The proposed algorithm can be effectively applied to the complex underground environment and resolves the dilemma of algorithms existing in traditional image processing and convolutional neural network
thus effectively serving underground automatic driving. The algorithm has the following virtues. First
it generates high-resolution images by generative adversarial nets and addresses unstable training in generating edge features of high-resolution images. Second
the multitask learning mechanism is further conducive to discriminator identification
thereby effectively monitoring the results generated by the generator. Finally
the Monte Carlo search strategy is used to search the intermediate state of the generator
which is then feed it into the discriminator
thereby strengthening the constraints of the generator and enhancing the quality of the generated image. Experimental results show that our algorithm can achieve satisfactory results. In the future
we will focus on overcoming the issue of track line prediction under occlusion
expanding the datasets
and strengthening the speed
robustness
and practicality of the algorithm.
Bente T F, Szeghalmy S and Fazekas A. 2018. Detection of lanes and traffic signs painted on road using on-board camera//Proceedings of the IEEE International Conference on Future IoT Technologies. Eger, Hungary: IEEE: 1-7[ DOI: 10.1109/FIOT.2018.8325600 http://dx.doi.org/10.1109/FIOT.2018.8325600 ]
Cao Y J, Jia L L, Chen Y X, Lin N and Li X X. 2018. Review of computer vision based on generative adversarial networks. Journal of Image and Graphics, 23(10):1433-1449
曹仰杰, 贾丽丽, 陈永霞, 林楠, 李学相. 2018.生成式对抗网络及其计算机视觉应用研究综述.中国图象图形学报, 23(10):1433-1449)[DOI:10.11834/jig.180103]
Chen Q F and Koltun V. 2017. Photographic image synthesis with cascaded refinement networks//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice: IEEE: 1520-1529[ DOI: 10.1109/ICCV.2017.168 http://dx.doi.org/10.1109/ICCV.2017.168 ]
Denton E, Chintala S, Szlam A and Fergus R. 2015. Deep generative image models using a Laplacian pyramid of adversarial networks//Proceedings of the 28th International Conference on Neural Information Processing Systems-Volume 1. Montreal, Canada: MIT Press: 1486-1494
Dosovitskiy A and Brox T. 2016. Generating images with perceptual similarity metrics based on deep networks//Proceedings of the 30th Conference on Neural Information Processing Systems. Barcelona, Spain: Curran Associates, Inc.: 658-666
Gatys L A, Ecker A S and Bethge T. 2016. Image style transfer using convolutional neural networks//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV: IEEE: 2414-2423[ DOI: 10.1109/CVPR.2016.265 http://dx.doi.org/10.1109/CVPR.2016.265 ]
Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A and Bengio Y. 2014. Generative adversarial nets//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press: 2672-2680
Guo B and Dong Y. 2017. Railway track detection algorithm based on piecewise curve model. Journal of Railway Science and Engineering, 14(2):355-363
郭碧, 董昱. 2017.基于分段曲线模型的铁路轨道检测算法.铁道科学与工程学报, 14(2):355-363)[DOI:10.3969/j.issn.1672-7029.2017.02.022]
Isola P, Zhu J Y, Zhu T H and Efros A A. 2017. Image-to-image translation with conditional adversarial networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE: 5967-5976[ DOI: 10.1109/CVPR.2017.632 http://dx.doi.org/10.1109/CVPR.2017.632 ]
Johnson J, Alahi A and Li F F. 2016. Perceptual losses for real-time style transfer and super-resolution//Proceedings of the 14th European Conference on Computer Vision. Amsterdam, The Netherlands: Springer: 694-711[ DOI: 10.1007/978-3-319-46475-6_43 http://dx.doi.org/10.1007/978-3-319-46475-6_43 ]
Li J Y, Jin L Z, Fei S M and Ma J Y. 2014. Urban road detection based on multi-scale feature representation. Journal of Electronics and Information Technology, 36(11):2578-2585
李骏扬, 金立左, 费树岷, 马军勇. 2014.基于多尺度特征表示的城市道路检测.电子与信息学报, 36(11):2578-2585)[DOI:10.3724/SP.J.1146.2014.00271]
Lin Y L, Dai X Y, Li L, Wang X and Wang F Y. 2018. The new frontier of AI research:generative adversarial networks. Acta Automatica Sinica, 44(5):775-792
林懿伦, 戴星原, 李力, 王晓, 王飞跃. 2018.人工智能研究的新前线:生成式对抗网络.自动化学报, 44(5):775-792)[DOI:10.16383/j.aas.2018.y000002]
Mirza M and Osindero S. 2014. Conditional generative adversarial nets[EB/OL]2014-11-06[2019-08-16] . https://arxiv.org/pdf/1411.1784.pdf https://arxiv.org/pdf/1411.1784.pdf
Neven D, De Brabandere B, Georgoulis S, Proesmans M and Van Gool L. 2018. Towards end-to-end lane detection: an instance segmentation approach//Proceedings of 2018 IEEE Intelligent Vehicles Symposium (Ⅳ). Changshu: IEEE: 286-291[ DOI: 10.1109/IVS.2018.8500547 http://dx.doi.org/10.1109/IVS.2018.8500547 ]
Pan X P, Shi J P, Luo P, Wang X G and Tang X O. 2018. Spatial as deep: spatial CNN for traffic scene understanding//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. New Orleans: AAAI: 7276-7283
Quach C H, Tran V L, Nguyen D H, Nguyen V H, Pham M T and Phung M D. 2018. Real-time lane marker detection using template matching with RGB-D camera//Proceedings of the 2nd IEEE International Conference on Recent Advances in Signal Processing, Telecommunications and Computing (SigTelCom). Ho Chi Minh, Vietnam: IEEE: 152-157[ DOI: 10.1109/SIGTELCOM.2018.8325781 http://dx.doi.org/10.1109/SIGTELCOM.2018.8325781 ]
Ulyanov D, Vedaldi A and Lempitsky V. 2017. Instance normalization: the missing ingredient for fast stylization[EB/OL]2017-11-06[2019-08-16] . https://arxiv.org/pdf/1607.08022.pdf https://arxiv.org/pdf/1607.08022.pdf
Wang K and Wan X J. 2018. SentiGAN: generating sentimental texts via mixture adversarial networks//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: IJCAI: 4446-4452[ DOI: 10.24963/ijcai.2018/618 http://dx.doi.org/10.24963/ijcai.2018/618 ]
Yang Y, Zhang H Y, Zhu Y and Zhang Y N. 2018. Class-information generative adversarial network for single image super-resolution. Journal of Image and Graphics, 23(12):1777-1788
杨云, 张海宇, 朱宇, 张艳宁. 2018.类别信息生成式对抗网络的单图超分辨重建.中国图象图形学报, 23(12):1777-1788)[DOI:10.11834/jig.180331]
Yu L T, Zhang W N, Wang J and Yu Y. 2017. SeqGAN: sequence generative adversarial nets with policy gradient//Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco: AAAI: 2852-5858
Zhang Y and Yang Q. 2018. A survey on multi-task learning[EB/OL]2018-07-27[2019-08-16] . https://arxiv.org/pdf/1707.08114.pdf https://arxiv.org/pdf/1707.08114.pdf
相关作者
相关机构
京公网安备11010802024621
