ali jahed saravani

In this article, a contrast enhancement algorithm using wavelet transform is proposed to create natural enhancement in images with various brightness ranges. In the proposed method, the input image is first decomposed into 4 sub-bands by discrete wavelet transformation. Then, in the LL sub band image, the histogram cutting process is performed by the cutting threshold level equal to the average intensities. Next, the cut histogram based on entropy is divided into three parts with approximately equal number of pixels, and before equalization process, each sub-histogram is mapped to the new dynamic range. Finally, we use the inverse discrete wavelet transform to create an improved image. By controlling the enhancement ratio, the proposed method produces an image with maximum details and natural enhancement in the output image. Comparing the performance of the proposed method with previously presented methods, in terms of entropy as well as visual quality based on the mean opinion score, shows the superiority of the proposed algorithm.

Automatic tracking systems of flying targets play a key role in the battle field. Nowadays, vision sensors have attracted wide attention due to their outstanding features such as being cheap, passive, and their resistant to jamming in comparison to expensive radar-based tracking system which prone to jamming. In this paper, a system is considered and designed for automatic tracking of flying targets using segmentation and digital image processing. In the first section, images of flying targets are proceed using color image segmentation algorithm through Kmeans and FCM clustering techniques and then desired target is detected. In following, edges of images are detected using Prewitt algorithm and then desired object is identified and tracked. Visual results of developed techniques are similar and have sufficient accuracy but, speed of automatic tracking using edge detection is higher in comparison to color image segmentation and so its performance in battle field and online tracking of flying targets is preferred.

Template matching techniques are widely used today in image-based tracking systems to identify and track military targets. Due to their passivity, these systems are resistant to common electronic warfare techniques. One of the problems with using template matching algorithms is that they are slow, especially when rotation and scaling occur in targets relative to a predetermined pattern. In this paper, we perform an optimized algorithm for grayscale template-matching based on correlation coefficients which is invariant to scale and angle. The ‘brute force’ algorithm performs template-matching between the image to analyze and the template query shape rotated by specific angle, translated to specific scale. This takes too long and thus is no practical. The optimized algorithm includes three cascaded filters for scale, angle and template matching which results in probability of scaling, rotated angle for each pixel and point of template-matching, respectively. This algorithm accelerates searching and is 400 times faster than ‘Brute Force’ algorithm. By implementing hardware on the FPGA, it is possible to identify and track military targets at a speed of 10 frames per second.