Earticle

초록

영어

A safe and robust autonomous driving system relies on accurate perception of the environment for application-oriented scenarios. This paper proposes deployment of the three most crucial tasks (i.e., object detection, drivable area segmentation and lane detection tasks) on embedded system for self-driving operations. To achieve this research objective, multi-tasking network is utilized with a simple encoder-decoder architecture. Comprehensive and extensive comparisons for two models based on different backbone networks are performed. All training experiments are performed on server while Nvidia Jetson Xavier NX is chosen as deployment device.

목차

Abstract
I. INTRODUCTION
II. METHOD
A. Network architecture
B. Implementation details
III. EXPERIMENTS AND RESULTS
A. Model size and running efficiency
B. Qualitative Results
IV. CONCLUSION
REFERENCES

저자

• Shokhrukh Miraliev [ Department of Electrical and Computer Engineering Inha University ]
• Shakhboz Abdigapporov [ Department of Electrical and Computer Engineering Inha University ]
• Jumabek Alikhanov [ Department of Electrical and Computer Engineering Inha University ]
• Vijay Kakani [ Department of Integrated System Engineering Inha University ]
• Hakil Kim [ Department of Electrical and Computer Engineering Inha University ] Corresponding Author

참고문헌