End-to-end space object detection method based on event camera

Xiaoli Zhou; Chao Bei

doi:10.1117/12.3011053

1 November 2023 End-to-end space object detection method based on event camera

Xiaoli Zhou, Chao Bei

Proceedings Volume 12917, International Conference on Precision Instruments and Optical Engineering (PIOE 2023); 129170K (2023) https://doi.org/10.1117/12.3011053
Event: 3rd International Conference on Precision Instruments and Optical Engineering (PIOE 2023), 2023, Shanghai, China

Abstract

Event cameras, offering extremely high temporal resolution and high dynamic range, have provided a new solution to the challenges of space object detection, such as high light, low light and motion blur. However, the asynchronous output characteristics of event cameras make it incompatible with traditional object detection algorithms designed for frame images. Therefore, a new deep network architecture is proposed. First, the asynchronous event streams are characterized by event spike tensor (EST), then extract spatial features using a feed-forward feature extraction network, and finally the end-to-end object detection using continuous event streams is realized. The proposed method is compared with the classical object detection algorithms on the synthetic event stream dataset. The results show that in scenes (high light and low light) where traditional optical cameras fail, event cameras still perform well, and the mAP is improved by 4.2%. This study offers new possibilities for using event cameras for object detection under complex lighting environments and motion conditions, and highlights the advantages of event cameras in space object detection.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiaoli Zhou and Chao Bei "End-to-end space object detection method based on event camera", Proc. SPIE 12917, International Conference on Precision Instruments and Optical Engineering (PIOE 2023), 129170K (1 November 2023); https://doi.org/10.1117/12.3011053

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available