This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Generation and Usage of Virtual Data for the Development of Perception Algorithms Using Vision
Technical Paper
2016-01-0170
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
Camera data generated in a 3D virtual environment has been used to train object detection and identification algorithms. 40 common US road traffic signs were used as the objects of interest during the investigation of these methods. Traffic signs were placed randomly alongside the road in front of a camera in a virtual driving environment, after the camera itself was randomly placed along the road at an appropriate height for a camera located on a vehicle’s rear view mirror. In order to best represent the real world, effects such as shadows, occlusions, washout/fade, skew, rotations, reflections, fog, rain, snow and varied illumination were randomly included in the generated data. Images were generated at a rate of approximately one thousand per minute, and the image data was automatically annotated with the true location of each sign within each image, to facilitate supervised learning as well as testing of the trained algorithms. A deep convolutional neural network was built using 8 hidden layers, 1.5 million free parameters, and 250,000 neurons, with unique configurations optimal for traffic sign classification. This network was then trained using the above mentioned dataset. A high cross-validation accuracy of 98% with stable k-fold validation energy was achieved. This network, trained using virtual images, was then tested on real-world images with promising results, and the network was able to consistently classify signs that appear much smaller and farther away than those in the images it was trained on. The algorithm also attempted to classify signs for which it had not been trained, and predictably classified such signs using the most similar label.
Recommended Content
Authors
Topic
Citation
Nariyambut Murali, V., Micks, A., Goh, M., and Liu, D., "Generation and Usage of Virtual Data for the Development of Perception Algorithms Using Vision," SAE Technical Paper 2016-01-0170, 2016, https://doi.org/10.4271/2016-01-0170.Also In
References
- Deng , Jia et al. Imagenet: A large-scale hierarchical image database Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on IEEE 2009
- Cireşan , Dan et al. Multi-column deep neural network for traffic sign classification Neural Networks 32 2012 333 338
- Haltakov , Vladimir , Unger Christian , and Ilic Slobodan Framework for generation of synthetic ground truth data for driver assistance applications Pattern Recognition 323 332 Springer Berlin Heidelberg 2013
- Marin , Javier , Vázquez David , Gerónimo David , and López Antonio M. Learning appearance in virtual scenarios for pedestrian detection Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on 137 144 IEEE 2010 Texas 2006
- Stallkamp , Johannes et al. The German traffic sign recognition benchmark: a multi-class classification competition Neural Networks (IJCNN), The 2011 International Joint Conference on IEEE 2011
- Mogelmose , Andreas , Liu Dongran , and Trivedi Mohan Manubhai Traffic sign detection for US roads: Remaining challenges and a case for tracking Intelligent Transportation Systems (ITSC), 2014 IEEE 17th International Conference on IEEE 2014
- Møgelmose , Andreas , Trivedi Mohan Manubhai , and Moeslund Thomas B. Vision-based traffic sign detection and analysis for intelligent driver assistance systems: Perspectives and survey Intelligent Transportation Systems, IEEE Transactions on 13 4 2012 1484 1497
- Dollár , Piotr Piotr's Computer Vision Matlab Toolbox (PMT)
- Matas , Jiri et al. Robust wide-baseline stereo from maximally stable extremal regions Image and vision computing 22 10 2004 761 767