中国邮电高校学报(英文) ›› 2021, Vol. 28 ›› Issue (5): 68-81.doi: 10.19682/j.cnki.1005-8885.2021.0023

• Artificial Intelligence • 上一篇    下一篇

Exploring the usefulness of light field super-resolution for object detection

张文喆1,石凡1,2,赵萌1,2,陈胜勇1,2   

  1. 1. 天津理工大学
    2.
  • 收稿日期:2020-09-17 修回日期:2020-12-22 出版日期:2021-10-31 发布日期:2021-10-29
  • 通讯作者: 石凡 E-mail:shifan@email.tjut.edu.cn
  • 基金资助:
    国家自然科学基金;国家重点研发计划

Exploring the usefulness of light field super-resolution for object detection

  • Received:2020-09-17 Revised:2020-12-22 Online:2021-10-31 Published:2021-10-29
  • Contact: fan .shi E-mail:shifan@email.tjut.edu.cn
  • Supported by:
    National Natural Science Foundation of China;National Key R&D Program of China

摘要:

In order to solve the impact of image degradation on object detection, an object detection method based on light field super-resolution ( LFSR) is proposed. This method takes LFSR as an image enhancement step to provide high- quality images for object detection without using expensive imaging equipment. To evaluate this method, three types of objects: person, bicycle, and car, are chosen and the results are compared from 5 parts: detected object quantity, mean confidence score, detection results in different scenes, error detection, and detection results from different images sizes and detection speed. Experimental results based on the common object in context ( COCO) dataset show that the method incorporated LFSR improves performance of object detection models.


关键词:

light-field ( LF), super-resolution ( SR), object detection, RetinaNet, YOLOv3, TinyYOLOv3


Abstract:

In order to solve the impact of image degradation on object detection, an object detection method based on light field super-resolution ( LFSR) is proposed. This method takes LFSR as an image enhancement step to provide high- quality images for object detection without using expensive imaging equipment. To evaluate this method, three types of objects: person, bicycle, and car, are chosen and the results are compared from 5 parts: detected object quantity, mean confidence score, detection results in different scenes, error detection, and detection results from different images sizes and detection speed. Experimental results based on the common object in context ( COCO) dataset show that the method incorporated LFSR improves performance of object detection models.

Key words:

light-field ( LF), super-resolution ( SR), object detection, RetinaNet, YOLOv3, TinyYOLOv3