Abstract
Considering importance of the autonomous driving applications for mobile devices, it is imperative to develop both fast and accurate semantic segmentation models. Thanks to emergence of Deep Learning (DL) techniques, the segmentation models enhanced their accuracy. However, this improved performance of currently popular DL models for self-driving car applications come at the cost of time and computational efficiency. Moreover, networks with efficient model architecture experience lack of accuracy. Therefore, in this study, we propose robust, efficient, and fast network (REF-Net) that combines carefully formulated encoding and decoding paths. Specifically, the contraction path uses mixture of dilated and asymmetric convolution layers with skip connections and bottleneck layers, while the decoding path benefits from nearest neighbor interpolation method that demands no trainable parameters to restore original image size. This model architecture considerably reduces the number of trainable parameters, required memory space, training, and inference time. In fact, the proposed model required nearly 90 times fewer trainable parameters and approximately 4 times less memory space that allowed 3-fold faster training runtime and 2-fold inference speedup in the conducted experiments using Cambridge-driving Labeled Video Database (CamVid) and Cityscapes datasets. Moreover, despite its notable efficiency in terms of memory and time, the REF-Net attained superior results in several segmentation evaluation metrics that showed roughly 2%, 4%, and 3% increase in pixel accuracy, Dice coefficient, and Jaccard Index, respectively.
Highlights
Being one of the most popular members of computer vision tasks, semantic segmentation has been widely used in numerous applications in various domains
Traditional methods for semantic segmentation mainly depended on domain expert intervention, heavy use of high level engineering skills for feature choice [1], emergence of Deep Learning (DL) techniques entailed unprecedentedly notable progress in a number of semantic segmenta
An autonomous driving vehicle is a means of transport that possesses ability to recognize its surroundings and move safely with little or no human intervention [17], [18]
Summary
Being one of the most popular members of computer vision tasks, semantic segmentation has been widely used in numerous applications in various domains. Traditional methods for semantic segmentation mainly depended on domain expert intervention, heavy use of high level engineering skills for feature choice [1], emergence of DL techniques entailed unprecedentedly notable progress in a number of semantic segmenta-. An autonomous driving (driverless) vehicle is a means of transport that possesses ability to recognize its surroundings and move safely with little or no human intervention [17], [18]. Depending on the human intervention in driving process, autonomous vehicles are categorized into five levels. Level 0 vehicles are under full control of a driver and Level 5 vehicles are totally independent from human activity [19]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.