Exploring the Contributions of Low-Light Image Enhancement to Network-Based Object Detection

Citation

Loh, Yuen Peng (2021) Exploring the Contributions of Low-Light Image Enhancement to Network-Based Object Detection. In: 25th International Conference on Pattern Recognition Workshops, ICPR 2020, 10-15 January 2021, Virtual Event.

Full text not available from this repository.

Abstract

Low-light is a challenging environment for both human and computer vision to perform tasks such as object classification and detection. Recent works have shown potential in employing enhancements algorithms to support and improve such tasks in low-light, however there has not been any focused analysis to understand the direct effects that low-light enhancement have on an object detector. This work aims to quantify and visualize such effects on the multi-level abstractions involved in network-based object detection. First, low-light image enhancement algorithms are employed to enhance real low-light images, and then followed by deploying an object detection network on the low-light as well as the enhanced counterparts. A comparison of the activations in different layers, representing the detection features, are used to generate statistics in order to quantify the enhancements’ contribution to detection. Finally, this framework was used to analyze several low-light image enhancement algorithms and identify their impact on the detection model and task. This framework can also be easily generalized to any convolutional neural network-based models for the analysis of different enhancements algorithms and tasks.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Image processing
Subjects: T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 08 May 2021 18:23
Last Modified: 08 May 2021 18:23
URII: http://shdl.mmu.edu.my/id/eprint/8695

Downloads

Downloads per month over past year

View ItemEdit (login required)