Search

In this paper, we propose a spatial–spectral feature fusion model with a predictive feature weighting mechanism and demonstrate its applications to the problems of hyperspectral image classification and segmentation. To address these problems, we learn a set of 1-D convolutional local spectral filters and 2-D spatial–spectral filters that feed features into a fusion module, in an end-to-end fashion. We propose a lightweight predictive feature weighting component embedded in the fusion model and consider four design fusion options, i.e., by adding or concatenating features with equal or predicted weights. For the pixel classification task, the training input consists of image patches with labeled central pixels, whereas for the spatial segmentation task, it includes the label maps of image regions. The proposed networks have been evaluated on the Indian Pines, Pavia University, and Houston University for the classification problem and the SpaceNet data set for the spatial segmentation problem. The quantitative results favor the proposed approach over the state-of-the-art methods across all the four data sets. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of interactive object segmentation with an input rectangle. We present a coarse-to-fine method from region-level segmentation to pixel-level segmentation. In the region-level segmentation, the best combination of adjacent refined superpixels is selected as the coarse segmentation result by measuring its global contrast and tightness degree. Subsequently, we use the coarse segmentation result to aid the construction of the energy function in the pixel-level segmentation. The result can be further refined due to the fusion of region-level and pixel-level segmentation. Experimental results demonstrate that our method can achieve better segmentation performance. [ABSTRACT FROM AUTHOR]

In this paper, we present a multiview approach to segment the foreground objects consisting of a group of people into individual human objects and track them across the video sequence. Depth and occlusion information recovered from multiple views of the scene is integrated into the object detection, segmentation, and tracking processes. Adaptive background penalty with occlusion reasoning is proposed to separate the foreground regions from the background in the initial frame. Multiple cues are employed to segment individual human objects from the group. To propagate the segmentation through video, each object region is independently tracked by motion compensation and uncertainty refinement, and the motion occlusion is tackled as layer transition. The experimental results implemented on both our sequences and other's sequence have demonstrated the algorithm's efficiency in terms of subjective performance. Objective comparison with a state-of-the-art algorithm validates the superior performance of our method quantitatively. [ABSTRACT FROM PUBLISHER]

Abstract: The proposed interpolation filter comprises two concatenating filters, adaptive pre-interpolation filter (APIF) and the normative interpolation filter in H.264/AVC. The former is applied only to the integer pixels in the reference frames; the latter generates all the sub-position samples, supported by the output of APIF. The convolution of APIF and the standard filter minimizes the motion prediction error on a frame basis. APIF preserves the merits of the adaptive interpolation filter (AIF) and the adaptive loop filter (ALF) in the key technical area (KTA) software and at the same time overcomes their drawbacks. The experimental results show that APIF outperforms either AIF or ALF. Compared with the joint use of AIF and ALF, APIF provides comparable performance, but has much lower complexity. [Copyright &y& Elsevier]

Because of the outstanding contribution in improving compression efficiency, block-based quantization has been widely accepted in state-of-the-art image/video coding standards. However, false contour artifacts are introduced, which result in reducing the fidelity of the decoded image/video especially in terms of subjective quality. In this paper, a block-based decontouring method is proposed to reduce the false contour artifacts in the decoded image/video by automatically dithering its direct current (DC) value according to a composite model established between gradient smoothness and block-edge smoothness. Feature points on the model with the corresponding criteria in suppressing contour artifacts are compared to show a good consistency between the model and the actual processing effects. Discrete cosine transform (DCT)-based block level contour artifacts detection mechanism ensures the blocks within the texture region are not affected by the DC dithering. Both the implementation method and the algorithm complexity are analyzed to present the feasibility in integrating the proposed method into an existing video decoder on an embedded platform or system-on-chip (SoC). Experimental results demonstrate the effectiveness of the proposed method both in terms of subjective quality and processing complexity in comparison with the previous methods. [ABSTRACT FROM PUBLISHER]

Instance segmentation has made great progress in recent years. However, current mainstream detection-based methods ignore the process of distinguishing different instances in the same detected region, making it hard to segment the correct instance when a detected region contains multiple instances. To address this problem, we propose an Instance-level Context Attention Network (ICANet) to generate more discriminative features for different instances based on the context from their respective instance scopes, called instance-level context. Specifically, given a detected region, we first propose an instance attention module to obtain the specific attention maps that focus on the relationships between pixel pairs from the same instance by learning an embedding space. With this type of attention map, the features from the same instance achieve mutual gains, while the features from different instances become more discriminative. Then, we propose a spatial attention module to incorporate spatial information and enhance feature representations based on both feature and spatial relations. Moreover, to obtain clearer attention maps, we further propose a weight clipping strategy to filter out the noise by cutting off the lower weight. We perform extensive experiments to verify the effectiveness of the proposed method. As reported in the results, our method steadily outperforms the baseline by over 1.5% on the COCO dataset using different backbones and 3.7% on the Cityscapes dataset, which demonstrates the effectiveness of our method. [ABSTRACT FROM AUTHOR]

The generation of object proposals plays an important role in object detection. Most existing methods produce object proposals by using bottom-up cues, such as closed contour or superpixel. In this paper, we propose a novel method to improve the ranking of object proposals by combining bottom-up cues with top-down information of objectivity. Firstly, we utilize the bottom-up method to generate initial object proposals of the given test image. Then we retrieve its top-k similar images from training images set. Considering both appearance and spatial similarity between initial object proposals and the ground truth bounding boxes of these top-k similar images, we obtain the top-down guided scores of initial object proposals. Finally, the refined score of each initial object proposal is modeled as a fusion of the bottom-up score and the top-down score. Experiments show that our method achieves better performance compared with the state-of-art on the Pascal VOC2007 dataset. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a novel method is proposed to detect salient regions in images. To measure pixel-level saliency, joint spatial-color constraint is defined, i.e., spatial constraint (SC), color double-opponent (CD) constraint and similarity distribution (SD) constraint. The SC constraint is designed to produce global contrast with ability to distinguish the difference between “center and surround”. The CD constraint is introduced to extract intensive contrast of red-green and blue-yellow double opponency. The SD constraint is developed to detect the salient object and its background. A two-layer structure is adopted to merge the SC, CD and SD saliency into a saliency map. In order to obtain a consistent saliency map, the region-based saliency detection is performed by incorporating a multi-scale segmentation technique. The proposed method is evaluated on two image datasets. Experimental results show that the proposed method outperforms the state-of-the-art methods on salient region detection as well as human fixation prediction. [Copyright &y& Elsevier]