WGI-Net: A weighted group integration network for RGB-D salient object detection

Abstract

Salient object detection is used as a pre-process in many computer vision tasks (such as salient object segmentation, video salient object detection, etc.). When performing salient object detection, depth information can provide clues to the location of target objects, so effective fusion of RGB and depth feature information is important. In this paper, we propose a new feature information aggregation approach, weighted group integration (WGI), to effectively integrate RGB and depth feature information. We use a dual-branch structure to slice the input RGB image and depth map separately and then merge the results separately by concatenation. As grouped features may lose global information about the target object, we also make use of the idea of residual learning, taking the features captured by the original fusion method as supplementary information to ensure both accuracy and completeness of the fused information. Experiments on five datasets show that our model performs better than typical existing approaches for four evaluation metrics.

Systematic Review of Aggregation Functions Applied to Image Edge Detection

“…After filtering the papers, using the inclusion and exclusion criteria already discussed, 24 papers remained to be reviewed, listed in Table 2. Among them, 19 papers were found that are specifically dedicated to edge detection, either using multiple descriptors extraction and aggregation or based on fuzzy set theory: type-2 fuzzy and neutrosophic sets [44,47,[80][81][82][83][84][85][86][87][88][89][90] or works that use clustering and pre-aggregation functions, which are dedicated to region segmentation, but consider that their characteristics can be extended to the task of edge detection [46,48,51,52,91,92]. The found methods of segmentation or edge detection, based on aggregation and pre-aggregation functions, can be divided into three groups: (i) based on the aggregation of distance functions and FCM, (ii) multiple descriptors extraction and aggregation, and (iii) based on fuzzy set theory: type-2 fuzzy and neutrosophic sets.…”

“…The use of depth information was also explored by [83] for the detection of region boundaries. According to the authors, detecting the border of salient regions of an image in an accurate way and distinguishing between objects is an extremely difficult task, especially when one has complex backgrounds or when the objects in the main plane and in the background have low contrast between each other.…”

“…In both works [83,84], the model was obtained through a convolutional neural network, which, in the case of the latter, was justified by the attempt to simulate the human subjective visual attention guidance. Similarly, in [45], authors used the Choquet integral, embedded in the form of a neural network, to integrate the results of the segmentations generated by multiple deep neural network models that used the same basis, but considering, in the training stage, the manual segmentation of different experts.…”

Detecting Anomaly Event in Video Based on Generative Adversarial Network

“…CUHK Avenue ShanghaiTech VEC [16] 90.2 74.8 Conv-VRNN [17] 85.8 -MNAD-P [18] 88.5 70.5 AMDN [19] 84.6 -Conv2D-AE [6] 70.2 -StackRNN [16] 80.9…”

“…The first ones are based on density estimation and probability models including VEC [ 16 ] and Conv-VRNN [ 17 ]. The second ones are single-class classification-based methods including MNAD-P [ 18 ] and AMDN [ 19 ]. The third ones are reconstruction-based methods including Conv2D-AE [ 6 ] and StackRNN [ 20 ].…”