Abstract
Aiming at solving the problem of incomplete saliency detection and unclear boundaries in infrared multi-target images with different target sizes and low signal-to-noise ratio under sky background conditions, this paper proposes a saliency detection method for multiple targets based on multi-saliency detection. The multiple target areas of the infrared image are mainly bright and the background areas are dark. Combining with the multi-scale top hat (Top-hat) transformation, the image is firstly corroded and expanded to extract the subtraction of light and shade parts and reconstruct the image to reduce the interference of sky blurred background noise. Then the image obtained by a multi-scale Top-hat transformation is transformed from the time domain to the frequency domain, and the spectral residuals and phase spectrum are extracted directly to obtain two kinds of image saliency maps by multi-scale Gauss filtering reconstruction, respectively. On the other hand, the quaternion features are extracted directly to transform the phase spectrum, and then the phase spectrum is reconstructed to obtain one kind of image saliency map by the Gauss filtering. Finally, the above three saliency maps are fused to complete the saliency detection of infrared images. The test results show that after the experimental analysis of infrared video photographs and the comparative analysis of Receiver Operating Characteristic (ROC) curve and Area Under the Curve (AUC) index, the infrared image saliency map generated by this method has clear target details and good background suppression effect, and the AUC index performance is good, reaching over 99%. It effectively improves the multi-target saliency detection effect of the infrared image under the sky background and is beneficial to subsequent detection and tracking of image targets.
Highlights
In recent years, with the development of infrared technology and computer processing technology, infrared image processing has been widely used in military and civil fields [1]
Image target saliency detection mainly focuses on a single type of target [4], and normally a complex situation of multiple types of targets exists in the sky, so detection methods for multiple targets in infrared images need to be studied
The principle of the algorithm is that the multi-scale top hat (Top-hat) transformed gray image is first transformed into the phase spectrum in the frequency domain by Fourier transform, the phase spectrum of the image is inversely transformed by Fourier transform, and the saliency map is obtained by Gauss filtering, calculated as follows: (14)
Summary
With the development of infrared technology and computer processing technology, infrared image processing has been widely used in military and civil fields [1]. Different saliency maps were obtained by using color space distribution, super-pixel segmentation and block scale to get the final saliency map by CRF fusion This method has a good effect, but it needs a lot of training to obtain the model and training is excessive. The Top-hat transform improved by the multi-scale is used to preprocess the original infrared image, enhance the target in the original image, suppress the interference of background noise, and obtain the image with multiple targets highlighted. According to the parameters in the frequency domain of the acquired image pixels, three improved salient maps, namely, spectrum residual, phase spectrum and Fourier transform, are fused to generate the salient maps of the final infrared target. After a series of real infrared image experiments and comparison with various classic salience models, the algorithm can detect multiple types of targets simultaneously, the saliency detection of the targets is better, the targets are complete and the edges of the targets are clear
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
