scholarly journals An improved method for object detection in astronomical images

2015 ◽  
Vol 451 (4) ◽  
pp. 4445-4459 ◽  
Author(s):  
Caixia Zheng ◽  
Jesus Pulido ◽  
Paul Thorman ◽  
Bernd Hamann
Keyword(s):  
Object Detection ◽  
Improved Method ◽  
Astronomical Images

scholarly journals FA-YOLO: An Improved YOLO Model for Infrared Occlusion Object Detection under Confusing Background

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Shuangjiang Du ◽  
Baofu Zhang ◽  
Pin Zhang ◽  
Peng Xiang ◽  
Hong Xue
Keyword(s):  
Object Detection ◽  
Background Information ◽  
Detection Accuracy ◽  
Infrared Images ◽  
Improved Method ◽  
Negative Sample ◽  
Remote Sensing Images ◽  
Complex Background ◽  
Small Targets ◽  
The Impact

Infrared target detection is a popular applied field in object detection as well as a challenge. This paper proposes the focus and attention mechanism-based YOLO (FA-YOLO), which is an improved method to detect the infrared occluded vehicles in the complex background of remote sensing images. Firstly, we use GAN to create infrared images from the visible datasets to make sufficient datasets for training as well as using transfer learning. Then, to mitigate the impact of the useless and complex background information, we propose the negative sample focusing mechanism to focus on the confusing negative sample training to depress the false positives and increase the detection precision. Finally, to enhance the features of the infrared small targets, we add the dilated convolutional block attention module (dilated CBAM) to the CSPdarknet53 in the YOLOv4 backbone. To verify the superiority of our model, we carefully select 318 infrared occluded vehicle images from the VIVID-infrared dataset for testing. The detection accuracy-mAP improves from 79.24% to 92.95%, and the F1 score improves from 77.92% to 88.13%, which demonstrates a significant improvement in infrared small occluded vehicle detection.

Moving Object Detection Based on Edge Difference and Contour Matching

2012 ◽  
Vol 182-183 ◽  
pp. 1863-1867
Author(s):  
Wei Liu ◽  
Xue Jun Xu ◽  
Bi Tao Fu ◽  
Xi Zhu
Keyword(s):  
Object Detection ◽  
Moving Object Detection ◽  
Moving Object ◽  
Improved Method ◽  
Contour Matching ◽  
Continuous Frames ◽  
Good Detection

This paper presents an improved method to detect moving object and obtain the relative accurate location. First we detect the edge difference of continuous frames. Then we utilize the contour matching to find the edge pairs in order to reach a good detection of the moving object and location. The extensive experiments show that our method is robust and efficient to the moving object detection.

scholarly journals Stellar Object Detection Using the Wavelet Transform

10.14311/1462 ◽  
2011 ◽  
Vol 51 (6) ◽  
Author(s):  
E. Anisimova ◽  
P. Páta ◽  
M. Blažek
Keyword(s):  
Wavelet Transform ◽  
Object Detection ◽  
Globular Clusters ◽  
Detection Algorithm ◽  
Stellar Object ◽  
Stellar Objects ◽  
Astronomical Images ◽  
Source Extraction

Several algorithms are used nowadays for detecting stellar objects in astronomical images, for example in the DAOPHOTprogram package and in SExtractor (Software for source extraction). Our team has become acquainted with the wavelet transform and its good localization properties. After studying the manual for DAOPHOT and SExtractor, and becoming familiar with the  trous algorithm used for calculating the wavelet transform, we set ourselves the task to implement an algorithm for star detection on the basis of the wavelet transform. We focused on detecting stellar objects in complex fields, such as globular clusters and galaxies. This paper describes a stellar object detection algorithm with the help ofthe wavelet transform, and presents our results. 

Moving Object Detection Based on Edge Pair Difference

2011 ◽  
Vol 204-210 ◽  
pp. 1407-1410 ◽  
Author(s):  
Yu Yong Cui ◽  
Zhi Yuan Zeng ◽  
Wei Hong Cui ◽  
Bi Tao Fu ◽  
Wei Liu
Keyword(s):  
Object Detection ◽  
Moving Object Detection ◽  
Moving Object ◽  
Improved Method ◽  
Continuous Frames ◽  
Good Detection

We present an improved method to detect moving object and obtain the relative accurate location in this paper. The Canny detector is applied to detect the edge of image, which is the edge difference of continuous frames. Then we utilize the pair of moving object information to reach a good detection of the moving object and location. The extensive experiments show that our method is efficient to the moving object detection.

Automated object detection for astronomical images

2005 ◽  
Author(s):  
Sonny Orellana ◽  
Lei Zhao ◽  
Helen Boussalis ◽  
Charles Liu ◽  
Khosrow Rad ◽  
...  
Keyword(s):  
Object Detection ◽  
Astronomical Images ◽  
Automated Object Detection

scholarly journals Object Detection with Component-Graphs in Multi-band Images: Application to Source Detection in Astronomical Images

IEEE Access ◽  
2021 ◽  
pp. 1-1
Author(s):  
T. X. Nguyen ◽  
G. Chierchia ◽  
O. Razim ◽  
R. Peletier ◽  
L. Najman ◽  
...  
Keyword(s):  
Object Detection ◽  
Source Detection ◽  
Astronomical Images ◽  
Multi Band
Sign in / Sign up

Export Citation Format

Share Document