Aircraft Recognition In Satellite Images using Matlab

SKU: PAN_IPM_011 Categories: ,

Description

The project proposes to recognize an aircraft in satellite image using template matching for accurate detection and tracking. This recognition system involves dimensionality reduction, segmentation and aircraft identification with templates. Here, Histogram probability thresholding is used to detect the desired object from background. Connected component analysis is used here to label the segmented image for grouping similar objects. Correlation measurement is used for measuring similarity between two different object region features. This is used to locate the aircraft region for tracking it and it shows that reliable and compatible method for this process. High resolution multispectral satellite images with multi-angular look capability have tremendous potential applications. Here the system involves an object tracking algorithm with three-step processing that includes moving object estimation, target modeling, and target matching. Potentially moving objects are first identified on the time-series images. The target is then modeled by extracting both spectral and spatial features. In the target matching procedure, template will be used as matching model to recognize with each frame by frame for accurate detection. Final simulated will be demonstrated the capability of object tracking in remote sensing images with help of used approaches.


Introduction

AIRCRAFT recognition is an important issue of target recognition in satellite images and has many important applications in practice such as airfield dynamic surveillance. As the resolution of satellite images gets higher, more abundant color, texture, and spatial information are provided. Such information offers good opportunity to recognize aircraft that has a very complex structure. However, automatic aircraft recognition is not a simple problem. Besides the complex structure, different aircraft differ in size, shape, and color, and even for one kind of aircraft, the texture and intensity are usually dissimilar in different scenarios. Moreover, recognition often suffers from various disturbances such as clutter, different contrasts, and intensity in homogeneity. Thus, the robustness and resistance to disturbance are highly required for the method. We illustrate some typical satellite aircraft images. Here the system involves an object tracking algorithm with three-step processing that includes moving object estimation, target modeling, and target matching. Potentially moving objects are first identified on the time-series images. The target is then modeled by extracting both spectral and spatial features. In the target matching procedure, template will be used as matching model to recognize with each frame by frame for accurate detection. Final simulated will be demonstrated the capability of object tracking in remote sensing images with help of used approaches.

Existing Systems

  • Sensor based tracking
  • Internet protocol based tracking
  • Wireless communication

Drawbacks

  • Visualization is not possible
  • Position of object cannot be found
  • Recognition is not possible

Proposed method

The proposing method has three steps, object detection, target modeling, target tracking.

  • Object detection involves objects extracted frame by frame.
  • Target modeling, we find features and obtain target in the images.
  • Target tracking, we track the object in every images

?Advantages

  • Accurate tracking with position
  • Communication with object to satellite is achieved
  • Low complexity

Block diagram

System Architecture

Aircraft Recognition In Satellite Images using Matlab

Template Matching

Aircraft Recognition In Satellite Images using Matlab 1


Preprocessing

Image recuperation is the operation of taking a corrupted/noisy photograph and estimating the smooth unique photograph. Corruption might probable are also to be had many bureaucracy on the side of motion blur, noise, and digital digital camera misfocus.? Image healing isn’t like photo enhancement in that the latter is designed to emphasize capabilities of the photo that make the photograph extra captivating to the observer, but no longer constantly to supply sensible information from a systematic difficulty of view. Image enhancement techniques (like evaluation stretching or de-blurring by a nearest neighbor approach) supplied thru “Imaging packages” use no a priori version of the manner that created the image.? With photo enhancement noise may be successfully be removed by using sacrificing some choice, but this isn’t suitable in many programs. In a Fluorescence Microscope selection inside the z-route is terrible as it is. More advanced image processing techniques ought to be carried out to get higher the item.? De-Convolution is an example of picture recovery approach. It is able to: Increasing decision, especially within the axial route removing noise developing evaluation.

Template Matching

It is a technique in digital image processing for finding small parts of an image which match a template image. A sliding window over other image sequences is used to indicate the possible presence of the reference target. A regional feature matching operator is applied to find the similarity between the target model and the pixels within the window. The labeled component from segmentation module will be applied to extract the region features to describe its characteristics. Here correlation coefficient will be used to measure the similarity between two different objects for target detection and tracking.

Correlation Coefficient: It is used to find the similarity between two different objects with their region features. It will be described by,

????????? Cor_coef = [sum(sum(u1.*u2))] / [sqrt(sum(sum(u1.*u1))*sum(sum(u2.*u2)))]; ?????????????????? ??????????????????????????????????? ??

Where, u1 = F1 ? mean of F1,? u2 = F2 ? mean of F2

??????????????? F1 ? Feature set1 and F2 ? Features set2

?Target detection

Target?detection?refers to the use of high spectral resolution remotely sensed images to map the locations of a target or feature (often a plant species of interest) with a particular spectral or spatial signature. Here the satellite images are used and their template are matched by using matching template concept after that we are used one of the technique called target detection by this technique , we got more information about the given image simply get some features.

Especially using hyper spectral imaging has evolving various strategic and civilian placations. The existence of a reference dataset for research is scarce, and datasets from multiple platforms are not available so far. Detection algorithms. In order for detection of targets to be automated, a training database needs to be created. This is usually done using experimental data collected when the target is known, and is then stored for use by the ATR algorithm.

Mathematical morphology

A shape (in blue) and its morphological dilation (in green) and erosion (in yellow) by a diamond-shape structuring element. Mathematical morphology (MM) is a theory and technique for the analysis and processing of geometrical structures, based on set theory, lattice theory, topology, and random functions. MM is most commonly applied to digital images, but it can be employed as well on graphs, surface meshes, solids, and many other spatial structures.

Topological and geometrical continuous-space concepts such as size, shape, convexity, connectivity, and geodesic distance, can be characterized by MM on both continuous and discrete spaces. MM is also the foundation of morphological image processing, which consists of a set of operators that transform images according to the above characterizations.

MM was originally developed for binary images, and was later extended to grayscale functions and images. The subsequent generalization to complete lattices is widely accepted today as MM’s theoretical foundation.


Requirement Specifications

Hardware Requirements

  • system
  • 4 GB of RAM
  • 500 GB of Hard disk

SOFTWARE REQUIREMENTS:


References

[1] A. Yilmaz, O. Javed, and M. Shah, ?Object tracking: A survey,? ACM Comput. Surv., vol. 38, Dec. 2006.

[2] S. Hinz, R. Bamler, and U. Stilla, ?Theme issue: Airborne and space borne traffic monitoring,? ISPRS J. Photogramm. Remote Sens., vol. 61, no. 3?4, pp. 135?280, 2006.

[3] I. Szottka and M. Butenuth, ?Tracking multiple vehicles in airborne image sequences of complex urban environments,? in Proc. 2011 Joint Urban Remote Sensing Event (JURSE), Apr. 2011, pp. 13?16.

[4] K. Palaniappan, F. Bunyak, P. Kumar, I. Ersoy, S. Jaeger, K. Ganguli, A. Haridas, J. Fraser, R. Rao, and G. Seetharaman, ?Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video,? in Proc. 13th Conf. Information Fusion (FUSION),Jul. 2010, pp. 1?8

[5] N. Joshi, R. Szeliski, and D. Kriegman, ?Psf estimation using sharp edge prediction,? in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, AL, USA, 2008.


 

Customer Reviews

There are no reviews yet.

Be the first to review “Aircraft Recognition In Satellite Images using Matlab”

Your email address will not be published. Required fields are marked *