Search

The use of depth information, acquired by depth sensors, for salient object detection (SOD) is being explored. Despite the remarkable results from recent deep learning approaches for RGB-D SOD, they fail to fully incorporate original and accurate information to express details of RGB-D images in salient objects. Here, we propose an RGB-D SOD model using a three-input multilevel fusion network (TMFNet), which differs from existing methods based on double-stream networks. In addition to RGB input (first input) and depth input (second input), the RGB image and depth map are combined into a four-channel representation (RGBD input) that constitutes the third input to the TMFNet. The RGBD input generates multilevel features that reflect details of the RGB-D image. In addition, the proposed TMFNet aggregates diverse region-based contextual information without discarding RGB and depth features. Thus, we introduce a cross-fusion module, and benefiting from rich low- and high-level information from salient features, feature fusion enables the improvement of localization of salient objects. The proposed TMFNet achieves state-of-the-art performance on six benchmark datasets for SOD.

Compared with traditional handcrafted features, deep learning has greatly improved the performance of scene parsing. However, it remains challenging under various environmental conditions caused by imaging limitations. Thermal imaging cameras have several advantages over cameras for the visible spectrum, such as operation in total darkness, robustness to shadow effects, insensitivity to illumination variations, and strong ability to penetrate smog and haze. These advantages of thermal imaging cameras make them ideal for the scene parsing of semantic objects in daytime and nighttime. In this paper, we propose a novel multiscale feature fusion and enhancement network (MFFENet) for accurate parsing of RGBthermal urban road scenes even when the quality of the available RGB data is compromised. The proposed MFFENet consists of two encoders, a feature fusion layer, and a multi-labelsupervision layer. We concatenate the multi-scale features with the features that contain global semantic information. Furthermore, we explore the cross-modal fusion of RGB and thermal features at multiple stages, rather than fusing them once at the low or high stage. Then, we propose a spatial attention mechanism module that provides a higher weight to (focuses more on) the foreground area, allowing MFFENet to emphasize foreground objects. Finally, multi-labelsupervision is introduced to optimize parameters of the proposed MFFENet. Experimental results confirm that the proposed MFFENet outperforms similar high-performing methods.

Owing to the widespread adoption of depth sensors, salient object detection (SOD) supported by depth maps for reliable complementary information is being increasingly investigated. Existing SOD models mainly exploit the relation between an RGB image and its corresponding depth information across three fusion domains: input RGB-D images, extracted feature maps, and output salient object. However, these models do not leverage the crossflows between high- and low-level information well. Moreover, the decoder in these models uses conventional convolution that involves several calculations. To further improve RGB-D SOD, we propose a crossflow and cross-scale adaptive fusion network (CCAFNet) to detect salient objects in RGB-D images. First, a channel fusion module allows for effective fusing depth and high-level RGB features. This module extracts accurate semantic information features from high-level RGB features. Meanwhile, a spatial fusion module combines low-level RGB and depth features with accurate boundaries and subsequently extracts detailed spatial information from low-level depth features. Finally, a purification loss is proposed to precisely learn the boundaries of salient objects and obtain additional details of the objects. The results of comprehensive experiments on seven common RGB-D SOD datasets indicate that the performance of the proposed CCAFNet is comparable to those of state-of-the-art RGB-D SOD models.

Scene parsing of high spatial resolution (HSR) remote sensing images has achieved notable progress in recent years by the adoption of convolutional neural networks. However, for scene parsing of multimodal remote sensing images, effectively integrating complementary information remains challenging. For instance, the decrease in feature map resolution through a neural network causes loss of spatial information, likely leading to blurred object boundaries and misclassification of small objects. In addition, object scales on a remote sensing image vary substantially, undermining the parsing performance. To solve these problems, we propose an end-to-end common extraction and gate fusion network (CEGFNet) to capture both high-level semantic features and low-level spatial details for scene parsing of remote sensing images. Specifically, we introduce a gate fusion module to extract complementary features from spectral data and digital surface model data. A gate mechanism removes redundant features in the data stream and extracts complementary features that improve multimodal feature fusion. In addition, a global context module and a multilayer aggregation decoder handle scale variations between objects and the loss of spatial details due to downsampling, respectively. The proposed CEGFNet was quantitatively evaluated on benchmark scene parsing datasets containing HSR remote sensing images, and it achieved state-of-the-art performance.

Compared with monocular images, scene discrepancies between the left- and right-view images impose additional challenges on visual quality predictions in binocular images. Herein, we propose a hierarchical feature fusion network (HFFNet) for blind binocular image quality prediction that handles scene discrepancies and uses multilevel fusion features from the left- and right-view images to reflect distortions in binocular images. Specifically, a feature extraction network based on MobileNetV2 is used to determine the feature layers from distorted binocular images; then, low-level binocular fusion features (or middle-level and high-level binocular fusion features) are obtained by fusing the left and right low-level monocular features (or middle-level and high-level monocular features) using the feature gate module; further, three feature enhancement modules are used to enrich the information of the extracted features at different levels. Finally, the total feature maps obtained from the high-, middle-, and low-level fusion features are applied to a three-input feature fusion module for feature merging. Thus, the proposed HFFNet provides better results, to the best of our knowledge, than existing methods on two benchmark datasets.

This article proposes a three-stream self-attention network (TSNet) for indoor semantic segmentation comprising two asymmetric input streams (asymmetric encoder structure) and a cross-modal distillation stream with a self-attention module. The two asymmetric input streams are ResNet34 for the red-green-blue (RGB) stream and VGGNet16 for the depth stream. Accompanying the RGB and depth streams, a cross-modal distillation stream with a self-attention module extracts new RGB plus depth features in each level in the bottom-up path. In addition, while using bilinear upsampling to recover the spatial resolution of the feature map, we incorporated the feature information of both the RGB flow and the depth flow through the self-attention module. We constructed the NYU Depth V2 dataset to evaluate the TSNet and achieved results comparable to those of current state-of-the-art methods.

Many RGB-D visual attention models have been proposed with diverse fusion models; thus, the main challenge lies in the differences in the results between the different models. To address this challenge, we propose a local-global fusion model for fixation prediction on an RGB-D image; this method combines global and local information through a content-aware fusion module (CAFM) structure. First, it comprises a channel-based upsampling block for exploiting global contextual information and scaling up this information to the same resolution as the input. Second, our Deconv block contains a contrast feature module to utilize multilevel local features stage-by-stage for superior local feature representation. The experimental results demonstrate that the proposed model exhibits competitive performance on two databases.

In recent years, the prediction of salient regions in RGB-D images has become a focus of research. Compared to its RGB counterpart, the saliency prediction of RGB-D images is more challenging. In this study, we propose a novel deep multimodal fusion autoencoder for the saliency prediction of RGB-D images. The core trainable autoencoder of the RGB-D saliency prediction model employs two raw modalities (RGB and depth/disparity information) as inputs and their corresponding eye-fixation attributes as labels. The autoencoder comprises four main networks: color channel network, disparity channel network, feature concatenated network, and feature learning network. The autoencoder can mine the complex relationship and make the utmost of the complementary characteristics between both color and disparity cues. Finally, the saliency map is predicted via a feature combination subnetwork, which combines the deep features extracted from a prior learning and convolutional feature learning subnetworks. We compare the proposed autoencoder with other saliency prediction models on two publicly available benchmark datasets. The results demonstrate that the proposed autoencoder outperforms these models by a significant margin.

The use of RGB-D information for salient object detection (SOD) is being increasingly explored. Traditional multilevel models handle both low- and high-level features similarly, as they use the same number of features for blending. Unlike these models, in this paper, we propose multilevel reverse-context interactive-fusion (MRI) network (MRINet) for RGB-D SOD. Specifically, first, we extract and reuse different numbers of features depending on their level; the deeper the information, the more times do we perform the extraction. Deeper information contains more semantic cues, which are important for locating salient regions. Thereafter, we use an RGB MRI block (MRIB) to merge RGB information at different levels; furthermore, we use depth features as auxiliary information and an RGB-D MRIB for full merging with RGB information. RGB and RGB-D MRIBs can reconstruct the high-level feature map in high resolution and integrate the low-level feature map to enhance boundary details. Extensive experiments demonstrate the effectiveness of the proposed MRINet and its state-of-the-art performance in RGB-D SOD.

In recent years, the detection of distinctive objects in stereoscopic 3D images has drawn increasing attention. Unlike 2D salient object detection, salient object detection in stereoscopic 3D images is highly challenging. Hence, we propose a novel Deep Convolutional Residual Autoencoder (DCRA) for end-to-end salient object detection in stereoscopic 3D images. The core trainable architecture of the salient object detection model employs raw stereoscopic 3D images as the inputs and their corresponding ground truth saliency masks as the labels. A convolutional residual module is applied to both the encoder and the decoder as a basic building block in the DCRA, and long-range skip connections are employed to bypass the equal-sized feature maps between the encoder and the decoder. To explore the complex relationships and exploit the complementarity between RGB (photometric) and depth (geometric) information, multiple feature map fusion modules are constructed. These modules integrate texture and structure information between the RGB and depth branches of the encoder and fuse their features over several multiscale layers. Finally, to efficiently optimize DCRA parameters, a supervision pyramid based on boundary loss and background prior loss is adopted, which employs supervised learning over the multiscale layers in the decoder to prevent vanishing gradients and accelerate the training at the fusion stage. We compare the proposed DCRA with state-of-the-art methods on two challenging benchmark datasets. The results of these experiments demonstrate that our proposed DCRA performs favorably against the comparison models.

Salient object detection (SOD) has received extensive attention in recent years, and many models have been developed. However, most SOD models only consider monocular images and not binocular images, which resemble the human vision and can better reflect human perception for distinguishing salient objects. To leverage the information in binocular images, we propose herein a first-of-its-kind parallax-estimation-enhanced network (PEENet) for binocular SOD. More specifically, we use a weighted binocular fusion module and a parallax correlation fusion module to explore the complementary and different information in binocular images. In addition, a parallax enhancing module and interweave consistency fusion use complementary saliency information and parallax information to enhance saliency and parallax representations. Finally, a transformation module avoids global and local information loss during decoding. Experiments were performed to validate the effectiveness and robustness of the proposed PEENet, which outperforms 10-RGB/RGB-D SOD methods on two binocular SOD datasets.