In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956. 相似文献
With the emerging development of three-dimensional (3D) related technologies, 3D visual saliency modeling is becoming particularly important and challenging. This paper presents a new depth perception and visual comfort guided saliency computational model for stereoscopic 3D images. The prominent advantage of the proposed model is that we incorporate the influence of depth perception and visual comfort on 3D visual saliency computation. The proposed saliency model is composed of three components: 2D image saliency, depth saliency and visual comfort based saliency. In the model, color saliency, texture saliency and spatial compactness are computed respectively and fused to derive 2D image saliency. Global disparity contrast is considered to compute depth saliency. Particularly, we train a visual comfort prediction function to distinguish stereoscopic image pair as high comfortable stereo viewing (HCSV) or low comfortable stereo viewing (LCSV), and devise different computational rules to generate a visual comfort based saliency map. The final 3D saliency map is obtained by using a linear combination and enhanced by a “saliency-center bias” model. Experimental results show that the proposed 3D saliency model outperforms the state-of-the-art models on predicting human eye fixations and visual comfort assessment. 相似文献
Detection and recognition of a stairway as upstairs, downstairs and negative (e.g., ladder, level ground) are the fundamentals of assisting the visually impaired to travel independently in unfamiliar environments. Previous studies have focused on using massive amounts of RGB-D scene data to train traditional machine learning (ML)-based models to detect and recognize stationary stairway and escalator stairway separately. Nevertheless, none of them consider jointly training these two similar but different datasets to achieve better performance. This paper applies an adversarial learning algorithm on the indicated unsupervised domain adaptation scenario to transfer knowledge learned from the labeled RGB-D escalator stairway dataset to the unlabeled RGB-D stationary dataset. By utilizing the developed method, a feedforward convolutional neural network (CNN)-based feature extractor with five convolution layers can achieve 100% classification accuracy on testing the labeled escalator stairway data distributions and 80.6% classification accuracy on testing the unlabeled stationary data distributions. The success of the developed approach is demonstrated for classifying stairway on these two domains with a limited amount of data. To further demonstrate the effectiveness of the proposed method, the same CNN model is evaluated without domain adaptation and the results are compared with those of the presented architecture. 相似文献
The Iterative Closest Point (ICP) scheme has been widely used for the registration of surfaces and point clouds. However, when working on depth image sequences where there are large geometric planes with small (or even without) details, existing ICP algorithms are prone to tangential drifting and erroneous rotational estimations due to input device errors. In this paper, we propose a novel ICP algorithm that aims to overcome such drawbacks, and provides significantly stabler registration estimation for simultaneous localization and mapping (SLAM) tasks on RGB-D camera inputs. In our approach, the tangential drifting and the rotational estimation error are reduced by: 1) updating the conventional Euclidean distance term with the local geometry information, and 2) introducing a new camera stabilization term that prevents improper camera movement in the calculation. Our approach is simple, fast, effective, and is readily integratable with previous ICP algorithms. We test our new method with the TUM RGB-D SLAM dataset on state-of-the-art real-time 3D dense reconstruction platforms, i.e., ElasticFusion and Kintinuous. Experiments show that our new strategy outperforms all previous ones on various RGB-D data sequences under different combinations of registration systems and solutions.