Material based salient object detection from hyperspectral images

Abstract

To the best of our knowledge, this is the first time that salient objects are detected based on extracting explicit material property embedded in the spectral responses via retrieval of endmembers and estimating their abundance.

CAGNet: Content-Aware Guidance for Salient Object Detection

“…Traditional methods predict the saliency score based on hand-crafted features. Most 5 of these methods utilize heuristic priors such as center prior [10,11], boundary background [24], and color contrast [25]. Aytekin et al [26] propose a probabilistic framework to encode the boundary connectivity saliency cue and smoothness constraints into a global optimization problem.…”

“…For example, the method proposed in [9] uses color feature to detect salient objects. Some other methods use center prior to improve the performance of salient object detection [10,11]. Because of the lack of semantic information, these methods have limited ability to detect the whole structure of salient objects in complex scenes.…”

Salient Object Detection on Hyperspectral Images Using Features Learned from Unsupervised Segmentation Task

“…Evaluation: We selected [7] and [8] for comparison as being the hyperspectral salient object detection models for natural scenes. In work [7], various approaches were tested Fig. 3.…”

“…(a) Sample scenes of the the hyperspectral data rendered in sRGB with its respective (b) ground-truth salient objects, and saliency map results of the compard models: (c) Itti et al [15,7], (d) SAD [7], (e) SED [7], (f) SED-OCM-GS [7], (g) SED-OCM-SAD [7], (h) SGC [8], (i) HS-MR [17], (j) Proposed SUDF HF −Slic on hyperspectral data so we also apply the approaches tested in [7] on HS-SOD dataset [5] for comparison. i) spectral distances between each spatial region for saliency computation by using spectral Euclidean distance (SED) and spectral Angle distances (SAD) [7,5], ii) color opponency method in [15,7] is replaced by spectral grouping rather than Red-Green and Blue-Yellow differences, in which Euclidean distance between spectral group (GS) vectors by dividing spectral bands into four groups (G1,G2,G3,G4) [7,5]. iii) In [5], spectral distance based saliency also combined with orientation based saliency with combinations such as SED-OCM-GS and SED-OCM-SAD.…”

“…Visual attention modeling (saliency detection) [15,16,17,18,19] is a promising research field for practical applications, which may benefit many other applications on hyperspectral data processing stated prior. For instance, a few studies using low-level features on hyperspectral images demonstrated that salient object detection can be achieved [7,8,9,10]. In contrast to these models relying on low-level features or hand-crafted features to obtain saliency maps, higher-level features can be extracted and used in a self-supervised manner for hyper-spectral data, where each spectral bands' contribution to the representation can be learned with unsupervised neural network used for segmentation task [20].…”