Low and mid-level features for target detection in satellite images 

Abstract

Reliably detecting objects in broadarea overhead or satellite images has become an increasingly pressing need, as the capabilities for image acquisition are growing rapidly. The problem is particularly difficult in the presence of large intraclass variability. An automatic approach is used to detect and classify targets in high-resolution broad-area satellite images, which relies on detecting statistical signatures of targets, in terms of a set of biologically-inspired low-level visual features. Biologically-inspired feature extraction methods use the “gestalt” information (continuity, symmetry, closure, repetition) to conduct object detection. Gestalt psychology studies how the human visual system organizes the complex visual input into unitary elements. The goal of the visual system, computer or biological, is to transform a visual input into meaningful semantic information. A new methodology to learn relations inferred from Gestalt principles and an application to segment unknown objects, even if objects are stacked or jumbled and tackle also the problem of segmenting partially occluded objects. The relevance of the relations for object segmentation is learned with support vector machines (SVMs). Multispectral imaging is significant technology for the acquisition and display of accurate color information. This study shows that the proposed target search method can reliably and effectively detect highly variable target objects in large image datasets.  

Authors and Affiliations

Rajani. D. C

Keywords

Related Articles

Modelling and Controller Design of Inverted Pendulum 

In this paper modeling of an inverted pendulum has been done and then three different controllers (PID & SFB, LQR) have been used for stabilization of the pendulum. The proposed system extends classical inverted...

Text Extraction From Images 

Images and videos on webs and in databases are increasing. It is a pressing task to develop effective methods to manage and retrieve these multimedia resources by their content. Text, which carries high-level seman...

Percentage Based Trust Model with Bandwidth Reservation Technique for Privacy Preserving Routing in MANETs 

Routing in Mobile Ad-Hoc Networks are vulnerable to malicious traffic analysis, harmful attackers can mitigate paths and malicious intermediate nodes breaks security, ineffective reserve of available resources ( u...

Tool to Detect and Prevent Web Attacks  

A Web Application Firewall (WAF) is a security tool that protects the web application and web application server from various attacks. Application protection is a valuable security layer to add because it can prote...

Zone based routing protocol in WSNs for varying zone size  

In this paper, we propose a zone based routing protocols for varying zone size. We will increase a size of a zone if the routing path is shorter and decrease zone size if the routing path is larger. If the zone s...

Download PDF file
  • EP ID EP130930
  • DOI -
  • Views 86
  • Downloads 0

How To Cite

Rajani. D. C (2013). Low and mid-level features for target detection in satellite images . International Journal of Advanced Research in Computer Engineering & Technology(IJARCET), 2(2), 817-825. https://europub.co.uk/articles/-A-130930