Object Tracking System by Pan-Tilt Cameras and Arm Robot Using Particle Filter

2010 ◽  
Vol 36 ◽  
pp. 442-450
Author(s):  
Hiroyuki Ukida ◽  
Yasuyuki Yamanaka ◽  
Masahiro Inoue ◽  
Masayuki Kawanami
Keyword(s):  
Object Detection ◽  
Particle Filter ◽  
Object Tracking ◽  
High Speed ◽  
Tracking System ◽  
Object Location ◽  
Tracking Method ◽  
Wide Range

In this paper, we propose an object tracking system using an arm robot and two pan-tilt cameras. By combining these devices, we realize the high speed and wide range object tracking method. In order to trace an object, we must find the pattern of object in camera images. To perform fast object detection, we employ a method of the particle filter which describes object location probabilistically. In experiments, our tracking system can trace objects which move surround of the system, and we can confirm effectiveness of proposed method.

scholarly journals OBJECT TRACKING SYSTEM BY TWO PAN-TILT MOVING CAMERAS AND ARM ROBOT

2014 ◽  
pp. 60-67
Author(s):  
Hiroyuki Ukida ◽  
Yoshio Tanimoto ◽  
Hideki Yamamoto
Keyword(s):  
Object Tracking ◽  
High Speed ◽  
Robot Control ◽  
Tracking System ◽  
Search Method ◽  
Object Location ◽  
Camera Control ◽  
Object Locations ◽  
Speed Performance ◽  
Binocular Stereo

We propose an object tracking system using an arm robot and two pan-tilt cameras. In this study, we use the active search method to detect the object location in images of cameras. Moreover, we estimate the 3D coordinates of this object from detected locations in images using the binocular stereo method. By using 3D object locations, the robot and cameras are rotated toward to the object. To realize the high speed performance, we use the parallel processing by the thread function for the processes of the object detection, the 3D coordinate estimation, the camera control and the robot control. We perform the object tracking experiments and confirm the efficiency of the proposed method.

scholarly journals Fast and Economical Object Tracking using Raspberry Pi 3.0

2019 ◽  
Vol 8 (6S) ◽  
pp. 336-338
Keyword(s):  
Computer Vision ◽  
Power Consumption ◽  
Low Power ◽  
Object Detection ◽  
Object Tracking ◽  
Tracking System ◽  
Low Power Consumption ◽  
Raspberry Pi ◽  
Multiple Object Detection ◽  
Vision Application

This paper proposes a way to construct a financially cheap and fast object tracking using Raspberry Pi3. Multiple object detection is an important step in any computer vision application. Since the number of cameras included is more these gadgets are compelled by expense per hub, control utilization and handling power. We propose a tracking system with low power consumption. The framework is completely designed with python and OpenCV. The tracking quality and accuracy is measured using publicly available datasets.

Multi-object tracking using deformable convolution networks with tracklets updating

2019 ◽  
Vol 17 (06) ◽  
pp. 1950042 ◽  
Author(s):  
Yuanping Zhang ◽  
Yuanyan Tang ◽  
Bin Fang ◽  
Zhaowei Shang
Keyword(s):  
Object Tracking ◽  
Tracking System ◽  
Sampling Strategy ◽  
Geometric Transformation ◽  
Histogram Of Oriented Gradient ◽  
Tracking Method ◽  
Sampling Locations ◽  
Deep Networks ◽  
Background Clutter ◽  
Appearance Changes

Many multi-object tracking methods have been proposed to solve the computer vision problem which has been attracting significant attentions because of the significant appearance changes caused by deformation, abrupt motion, background clutter and occlusion. In this paper, hybrid deformable convolution neural networks with frame-pair input and deformable layers for multi-object tracking are presented. The object tracking method trained using two successive frames can predict the centers of searching windows as the locations of tracked targets to improve the accuracy and robustness of object tracking. Histogram of Oriented Gradient and CNN features are extracted as appearance features to measure similarities between objects. Kalman filter and Hungarian algorithm are used to create tracklets association which indicates the location and the trajectories of tracked targets. To solve the problem of object transformation, we construct a novel sampling strategy for off-line training with the idea of augmenting the special sampling locations in the convolution layers and pooling layers with additional offsets. Experiments on the popular challenging datasets show that the proposed tracking system performs on par with recently developed generic multi-object tracking methods, but effective for dense geometric transformation objects and with much less memory. In addition, the proposed tracking system can run in a speed of over 75 (24) fps with a GPU (CPU), much faster than most deep networks-based trackers.

Sign in / Sign up

Export Citation Format

Share Document