Does depth estimation help object detection?


Cetinkaya B., Kalkan S., Akbaş E.

Image and Vision Computing, vol.122, 2022 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 122
  • Publication Date: 2022
  • Doi Number: 10.1016/j.imavis.2022.104427
  • Journal Name: Image and Vision Computing
  • Journal Indexes: Science Citation Index Expanded, Scopus, Academic Search Premier, Applied Science & Technology Source, Biotechnology Research Abstracts, Compendex, Computer & Applied Sciences, INSPEC
  • Keywords: Object detection, Depth estimation, RGB-D

Abstract

Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color. However, estimated depth does not always yield improvements. Many factors affect the performance of object detection when estimated depth is used. In this paper, we comprehensively investigate these factors with detailed experiments, such as using ground-truth vs. estimated depth, effects of different state-of-the-art depth estimation networks, effects of using different indoor and outdoor RGB-D datasets as training data for depth estimation, and different architectural choices for integrating depth to the base object detector network. We propose an early concatenation strategy of depth, which yields higher mAP than previous works' while using significantly fewer parameters.