Object Detection and Movement Tracking Using Tubelets and Faster RCNN Algorithm with Anchor Generation

Prabu Mohandas,Rajkumar Thanasekaran,Khairunnisa Hasikin,Muhammad Mokhzaini Azizan,Jerline Sheebha Anni,Yuanpeng Zhang

doi:10.1155/2021/8665891

Abstract

Object detection in images and videos has become an important task in computer vision. It has been a challenging task due to misclassification and localization errors. The proposed approach explored the feasibility of automated detection and tracking of elephant intrusion along forest border areas. Due to an alarming increase in crop damages resulted from movements of elephant herds, combined with high risk of elephant extinction due to human activities, this paper looked into an efficient solution through elephant’s tracking. The convolutional neural network with transfer learning is used as the model for object classification and feature extraction. A new tracking system using automated tubelet generation and anchor generation methods in combination with faster RCNN was developed and tested on 5,482 video sequences. Real-time video taken for analysis consisted of heavily occluded objects such as trees and animals. Tubelet generated from each video sequence with intersection over union (IoU) thresholds have been effective in tracking the elephant object movement in the forest areas. The proposed work has been compared with other state-of-the-art techniques, namely, faster RCNN, YOLO v3, and HyperNet. Experimental results on the real-time dataset show that the proposed work achieves an improved performance of 73.9% in detecting and tracking of objects, which outperformed the existing approaches.

Highlights

Elephants are pachyderms that live in the forest and move as groups in the search of food and water
The final tubelet generated will be based on an average of the tubelet mean average precision (mAP) with different tubelet intersection over union (IoU) thresholds
The video object detection analysis is made through the machine learning approach

Summary

Introduction

Elephants are pachyderms that live in the forest and move as groups in the search of food and water. Due to deforestation and climatic factors, elephant’s movement in and around the forest areas has been increasing These movements of elephants have led to problems such as elephants moving into human residing areas, elephants crossing roads nearby forest border areas, and crop raiding. There have been several measures proposed such as electric fencing, elephant proof trench, acoustic detection, and image detection methods. These methods have certain disadvantages in tracking the elephant movement [1]. Through the video object detection methodology, the movement of elephant herds can be observed effectively. These herds, moving in between different groups, become a factor in choosing

Methods

Results

Conclusion