Abstract

Video retrieval is one of the emerging areas in video capturing that gained various technical advances, increasing the availability of a huge mass of videos. For the text or the image query given, retrieving the relevant videos and the objects from the videos is not always an easy task. A hybrid model was developed in the previous work using the Nearest Search Algorithm (NSA) and exponential weighted moving average (EWMA), for the video object retrieval. In NSA + EWMA, the object trajectories are retrieved based on the query specific distance. This work extends the previous work by developing a novel path equalization scheme for equalizing the path length of the query and the tracked object. Initially, a hybrid model based on Support Vector Regression and NSA tracks the position of the object in the video. The proposed density measure scheme equalizes the path length of the query and the object. Then, the identified path length related to the query is given to extended nearest neighbor classifier for retrieving the video. From the simulation results, it is evident that the proposed video retrieval scheme achieved high values of 0.901, 0.860, 0.849, and 0.922 for precision, recall, F-measure, and multiple object tracking precision, respectively.

Highlights

  • In recent years, video surveillance has seen a progressive development in various fields, such as driving assistance, human–computer interaction, augmented reality, and so on [1]

  • Video retrieval strategy has gained more interest in recent years as the technique can be applied in various applications

  • Video retrieval is done in three phases, (1) object detection, (2) path length equalization, and (3) video retrieval

Read more

Summary

Introduction

Video surveillance has seen a progressive development in various fields, such as driving assistance, human–computer interaction, augmented reality, and so on [1]. Visual tracking scheme [1] finds the position of the target object in consecutive frames of the object and finds it trajectory or moving path. During the video processing schemes, the video may lose quality due to the rotation, and geometric deformation [1] Techniques, such as region-based [11], feature-based [12], model-based [13], and active contour-based techniques [14] achieved significant results in visual object tracking [1]. The major contribution of this paper is the development of a novel path equalization scheme based on the density measure. 2. Section 3 deals with the proposed path length equalization scheme and the ENN based retrieval strategy.

Literature survey
Challenges
Tracking the position of the object based on the NSA model
Tracking the position of the object based on Support vector regression
Hybrid model for object tracking
Path length equalization using the proposed SSDM technique
Video retrieval related to user query
Results and discussion
Experimental setup
Database description
Evaluation metrics
Comparative techniques
Experimental results
Comparative analysis
Comparative analysis using video 2
Comparative analysis using video 3
Comparative analysis using video 4
Comparative analysis using video 5
Comparative discussion
Conclusion
Full Text
Published version (Free)

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