Jiawei Wang
ABSTRACT
In order to identify dashboard fault indicators timely and help drivers take countermeasures, we design and implement a mobile platform-based dashboard fault indicator recognition algorithm. First we collect dashboard fault indicator images through mobile phone shooting and network download, and then use image augmentation to expand our dataset. This paper improves the SSD algorithm by increasing the number of feature maps in the feature pyramid and changing the specifications of the default box. These changes made the algorithm better detect fault indicators. Aiming at the excessive volume in model compression and transplantation, we select a better compression algorithm by comparing three different compression methods. Finally, the compressed model is transplanted to the mobile terminal.
- Lecun Y, Bottou L, Bengio Y, et al. 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11): 2278--2324.Google Scholar
- Liu W, Anguelov D, Erhan D, et al. 2016. SSD: single shot multibox detecto. Proceedings of the 2016 European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Cham: Springer, 2016: 21--37.Google Scholar
- Dai J, Li Y, He K, et al. 2016. R-fcn: Object detection via region-based fully convolutional networks. Advances in neural information processing systems, 2016: 379--387.Google Scholar
- He K, Gkioxari G, Dollar P, et al. 2017. Mask r-cnn. Proceeding of the IEEE international conference on computer vision, 2017: 2961--2969.Google Scholar
- Zhao M C, Xiu S W, et al. 2019. Multi-Label Image Recognition with Graph Convolutional Networks. Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 5177--5186.Google Scholar
- LeCun Y, Denker J S, Solla S A, et al. 1989. Optimal brain damage. Advances in neural information processing systems. Denver, 1989: 598.Google Scholar
- Srinivas S, Subramanya A, Venkatesh Babu R. 2017. Training Sparse Neural Networks. Proceeding of IEEE Conference on Computer Vision and Pattern Recognition Workshops. Hawaii, 2017: 138.Google ScholarCross Ref
- Lin S H, Ji R R, Li Y C, et al. 2019. Toward compact ConvNets via structure-sparsity regularized filter pruning. IEEE Trans Neural Networks Learn Syst, 2019: 1.Google Scholar
- Savala R, Dey P, Gupta N. 2018. Artificial neural network model to distinguish follicular adenoma from follicular carcinoma on fine needle aspiration of thyroid. Diagnostic Cytopathology, 2018, 46(3): 244--249.Google Scholar
- Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012: 1097--1105.Google ScholarDigital Library
- Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. Conference and Workshop on Neural Information Processing Systems. 2015.Google Scholar
Index Terms
- Research of Automobile Fault Lamp Recognition Algorithm Based on Mobile Platform
Recommendations
Graceful Degradation in Algorithm-Based Fault Tolerant Multiprocessor Systems
Algorithm-based fault tolerance (ABFT) is a technique which improves the reliability of a multiprocessor system by providing concurrent error detection and fault location capability to it. It encodes data at the system level and modifies the algorithm ...
Algorithm-Based Fault Tolerance for FFT Networks
Algorithm-based fault tolerance (ABFT) is a low-overhead system-level fault tolerance technique. Many ABFT schemes have been proposed in the past for fast Fourier transform (FFT) networks. In this paper, a new ABFT scheme for FFT networks is proposed. ...
Research on Fault-Tolerant Controller for Mobile Robot Based on Artificial Immune Principle
ICNC '07: Proceedings of the Third International Conference on Natural Computation - Volume 03Imitating such biological immune system mechanisms as self-learning, memory-storing and immune- response, combined with fault tolerance design approach of redundancy and reconfiguration, an immune fault tolerance controller (IFTC) is designed and ...
Comments