Real-time tracking of multiple moving objects in moving camera image sequences using robust statistics

Author(s):  
S. Araki ◽  
T. Matsuoka ◽  
H. Takemura ◽  
N. Yokoya
2019 ◽  
Vol 10 (1) ◽  
pp. 268
Author(s):  
Sukwoo Jung ◽  
Youngmok Cho ◽  
Doojun Kim ◽  
Minho Chang

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.


Sensors ◽  
2019 ◽  
Vol 19 (15) ◽  
pp. 3371 ◽  
Author(s):  
Hossain ◽  
Lee

In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-the-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one was designed using a Jetson TX or AGX Xavier, and the other was based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-the-art deep learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates, as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep learning-based association metric approach with simple online and real-time tracking (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.


1998 ◽  
Vol 4 (1) ◽  
pp. 3-20 ◽  
Author(s):  
K. Daniilidis ◽  
C. Krauss ◽  
M. Hansen ◽  
G. Sommer

1997 ◽  
Vol 43 (5) ◽  
pp. 359-369 ◽  
Author(s):  
A K Rastogi ◽  
B N Chatterji ◽  
A K Ray

Sign in / Sign up

Export Citation Format

Share Document