Efficient deep steering control method for self-driving cars through feature density metric

In this paper, a low cost method for input size reduction without sacrificing accuracy is proposed, which reduces required computation resources for both training and inference of deep convolutional neural net-work (DCNN) in the steering control of self-driving cars. Efficient processing of DCNNs is becoming prominent challenge due to its huge computation cost, number of parameters and also inadequate com-putation resources on power efficient hardware devices and the proposed method alleviates the problem comparing the state of the art. The proposed method introduces feature density metric (FDM) as criterion to mask and filter out regions of input image that do not contain adequate amount of features. This fil-tering method prevents DCNN from useless calculations belongs to feature-free regions. Compared to PilotNet, the proposed method accelerates overall training and inference phases of end-to-end (ETE) deep steering control of self-driving cars up to 1.3x and 2.0x respectively.(c) 2022 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a low-cost method for reducing the computation resources required for deep convolutional neural networks (DCNN) in the steering control of self-driving cars, without sacrificing accuracy. The method introduces a feature density metric to filter out regions of input images that do not contain sufficient features, preventing unnecessary calculations. Compared to existing techniques, the proposed method significantly accelerates the training and inference phases.