Abstract

Although there are well established object detection methods based on static images, their application to video data on a frame by frame basis faces two shortcomings: (i) lack of computational efficiency due to redundancy across image frames or by not using a temporal and spatial correlation of features across image frames, and (ii) lack of robustness to real-world conditions such as motion blur and occlusion. Since the introduction of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) in 2015, a growing number of methods have appeared in the literature on video object detection, many of which have utilized deep learning models. The aim of this paper is to provide a review of these papers on video object detection. An overview of the existing datasets for video object detection together with commonly used evaluation metrics is first presented. Video object detection methods are then categorized and a description of each of them is stated. Two comparison tables are provided to see their differences in terms of both accuracy and computational efficiency. Finally, some future trends in video object detection to address the challenges involved are noted.

Highlights

  • Video object detection involves detecting objects using video data as compared to conventional object detection using static images

  • Object detection approaches can be grouped into two major categories: (1) one-stage detectors and (2) two-stage detectors

  • The definition is the mean of the Average Precision of each category

Read more

Summary

Introduction

Video object detection involves detecting objects using video data as compared to conventional object detection using static images. With the help of ILSVRC2015, studies in video object detection have further increased. Earlier attempts in video object detection involved performing object detection on each image frame. Object detection approaches can be grouped into two major categories: (1) one-stage detectors and (2) two-stage detectors. One-stage detectors (e.g., [6,7,8,9,10,11,12]) are often more computationally efficient than two-stage detectors (e.g., [13,14,15,16,17,18,19,20,21]). Two-stage detectors are shown to produce higher accuracies compared to one-stage detectors

Objectives
Methods
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.