Fusion of visual salience maps for object acquisition

Abstract

The paradigm of visual attention has been widely investigated and applied to many computer vision applications. In this study, the authors propose a new saliency‐based visual attention algorithm applied to object acquisition. The proposed algorithm automatically extracts points of visual attention (PVA) in the scene, based on different feature saliency maps. Each saliency map represents a specific feature domain, such as textural, contrast, and statistical‐based features. A feature selection, based on probability of detection and false alarm rate and repeatability criteria, is proposed to choose the most efficient feature combination for saliency map. Motivated by the assumption that the extracted PVA represents the most visually salient regions in the image, they suggest using the visual attention approach for object acquisition. A comparison with other well‐known algorithms for point of interest detection shows that the proposed algorithm performs better. The proposed algorithm was successfully tested on synthetic, charge‐coupled device (CCD), and infrared (IR) images. Evaluation of the algorithm for object acquisition, based on ground truth, is carried out using synthetic images, which contain multiple examples of objects, with various sizes and brightness levels. A high probability of correct detection (greater than 90%) with a low false alarm rate (about 20 false alarms per image) was achieved.

Medical image fusion and noise suppression with fractional‐order total variation and multi‐scale decomposition

“…Then E ( D1 ) ≤ lim i→∞ infE ( D1 (i )) and D1 (i ) is a minimum of model (21). Finally, the minimum is unique according to Property 1.…”

“…In model (21), the first term ( 22) is called fusion term which serves for image fusion. The second term ( 23) is regularity term which serves for noise suppression.…”

“…The novel model is used to fuse different small-scale detail layers in the pixel-wise. Furthermore, model (21) reduces to fractional-order TV denoising model when the source noisy layer is a single, and the simplified model [42] is described by min…”

“…Specially, the saliency detection which extracts the significant region is often used in the fusion rules to preserve important regions simply [21][22][23]. Durga and Ravindra [24] propose an image fusion method based on two-scale image decomposition, and they fuse images using saliency detection fully.…”

Electric vehicle regional management system based on the BSP model and multi-information fusion

“…The information cycle transmitted by the three conditional detection modules used in the system is out of sync, so multi-sensor information fusion is needed. Previous studies (Bin et al, 2019;Greenberg et al, 2020;Patra et al, 2020;Simjanoska et al, 2020) have adopted the traditional target-level fusion method for multi-sensor information fusion. The three conditional detection modules in the proposed system have different detection information cycles.…”