Abstract
Unmanned aerial vehicles and battleships are equipped with the infrared search and tracking (IRST) systems for its mission to search and detect targets even in low visibility environments. However, infrared sensors are easily affected by diverse types of conditions, therefore most of IRST systems need to apply advanced contrast enhancement (CE) methods to cope with the low dynamic range of sensor output and image saturation. The general histogram equalization for infrared images has unwanted side effects such as low contrast expansion and saturation. Also, the local area processing for saturation reduction has been studied to solve the problems regarding the saturation and non-uniformity. We propose the cross fusion based adaptive contrast enhancement with three counter non-uniformity methods. We evaluate the proposed method and compare it with conventional CE methods using the discrete entropy, PSNR, SSIM, RMSE, and computation time indexes. We present the experimental results for images from various products using several datasets such as infrared, multi-spectral satellite, surveillance, general gray and color images, as well as video sequences. The results are compared using the integrated image quality measurement index and they show that the proposed method maintains its performance on various degraded datasets.
Highlights
Infrared search and tracking (IRST) systems are used on unmanned aerial vehicles (UAV) and surveillance applications such as pan-tilt searching electro-optical systems [1]
EXPERIMENTAL RESULTS we compare the results of methods: contrast limited adaptive histogram equalization (CLAHE), which is widely used for improving the contrast ratio in the regions as well as traditional methods such as general histogram equalization (GHE), brightness preserving bi-histogram equalization (BBHE), dualistic sub-image histogram equalization (DSIHE), brightness preserving dynamic histogram equalization (BPDHE), interlace histogram equalization (IHE), singular value decomposition discrete wavelet transform (SVD-DWT), adaptive gamma correction with weighting distribution (AGCWD), CegaHE, and the proposed method
The experimental results were obtained for images from five image datasets and a real-time video sequence dataset using 10 above-mentioned methods
Summary
Infrared search and tracking (IRST) systems are used on unmanned aerial vehicles (UAV) and surveillance applications such as pan-tilt searching electro-optical systems [1]. In such applications, it is required to process contrast expansion and noise reduction because of the low output characteristics of IR detection sensors and because its image dynamic range is severely degraded by low visibility conditions occurring due to light scattering by microscopic aerosols such as the fog and haze. Several complaints of flight pilots have been reported about the difficulties associated with recognizing summit mountain lines (SML) or detecting targets due to low dynamic and saturated images of IR. The autodetection and object tracking methods are affected by the quality and Homogeneous brightness of training images and are used to derive more information from the images with respect to how well they represent targets and details
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
