Moving Object Detection from Moving Camera Image Sequences Using an Inertial Measurement Unit Sensor

Sukwoo Jung,Doojun Kim,Minho Chang,Youngmok Cho

doi:10.3390/app10010268

Abstract

This paper describes a new method for the detection of moving objects from moving camera image sequences using an inertial measurement unit (IMU) sensor. Motion detection systems with vision sensors have become a global research subject recently. However, detecting moving objects from a moving camera is a difficult task because of egomotion. In the proposed method, the interesting points are extracted by a Harris detector, and the background and foreground are classified by epipolar geometry. In this procedure, an IMU sensor is used to calculate the initial fundamental matrix. After the feature point classification, a transformation matrix is obtained from matching background feature points. Image registration is then applied to the consecutive images, and a difference map is extracted to find the foreground region. Finally, a minimum bounding box is applied to mark the detected moving object. The proposed method is implemented and tested with numerous real-world driving videos, which show that it outperforms the previous work.

Highlights

Developing automatic driving assistance systems that can detect driving environments and avoid possible collisions has attracted much interest lately
The objective of this paper is to develop a new moving object detection method to overcome the shortfalls of the previous studies
As mentioned earlier, the feature points of moving objects objects be included the corresponding feature points, and these moving object feature points can be can included in the in corresponding feature points, and these moving object feature points can can adversely affect the accuracy of the transformation matrix calculation

Summary

Introduction

Developing automatic driving assistance systems that can detect driving environments and avoid possible collisions has attracted much interest lately. One of the most critical problems in automatic driving assistance systems is detecting moving objects. The most common approach to moving object detection in this field is using active sensors (e.g., radar, lidar) [1]. The visual information from optical sensors is very important in various applications, such as traffic sign recognition, object classification, or lane detection. To detect detectaamoving movingobject object image sequences, a Harris detector, which is mostly. To in in thethe image sequences, a Harris detector, which is mostly used used in image registration [28,29], is applied to obtain the interesting points in the image. As mentioned earlier, the feature points of moving the two consecutive images [31]. As mentioned earlier, the feature points of moving objects objects be included the corresponding feature points, and these moving object feature points can be can included in the in corresponding feature points, and these moving object feature points can can adversely affect the accuracy of the transformation matrix calculation

Objectives

Methods

Results

Conclusion