Obstacle detection and recognition using SSD

TaeJun Moon; Noriyuki Nakamura; Tad Gonsalves

doi:10.1117/12.2514269

Translator Disclaimer

29 October 2018 Obstacle detection and recognition using SSD

TaeJun Moon, Noriyuki Nakamura, Tad Gonsalves

Author Affiliations +

Proceedings Volume 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence; 108360M (2018) https://doi.org/10.1117/12.2514269
Event: 2018 International Conference on Image, Video Processing and Artificial Intelligence, 2018, Shanghai, China

Abstract

Fast obstacle detection is essential for autonomous driving. In this research, we have developed an obstacle detection model using Single Shot Multi Box Detector. SSD is a regression-based object detecting convolutional neural network that takes images as an input to compute localization and classification at once. By using SSD, processing time is dramatically reduced compare to multi shot detector. SSD object detection model was trained using APIs provided by Google in different patterns of number of classes and availability of transfer learning. Increase of the number of classes tended to decrease the detection rate. Training with transfer learning increased the average precision in general. The effectiveness of transfer learning in image recognition can be confirmed. Also there is a difference in average precision depending on the class.

Citation Download Citation

TaeJun Moon, Noriyuki Nakamura, and Tad Gonsalves "Obstacle detection and recognition using SSD", Proc. SPIE 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence, 108360M (29 October 2018); https://doi.org/10.1117/12.2514269

ACCESS THE FULL ARTICLE