Search

Most state-of-the-art instance-level human parsing models adopt two-stage anchor-based detectors and, therefore, cannot avoid the heuristic anchor box design and the lack of analysis on a pixel level. To address these two issues, we have designed an instance-level human parsing network which is anchor-free and solvable on a pixel level. It consists of two simple sub-networks: an anchor-free detection head for bounding box predictions and an edge-guided parsing head for human segmentation. The anchor-free detector head inherits the pixel-like merits and effectively avoids the sensitivity of hyper-parameters as proved in object detection applications. By introducing the part-aware boundary clue, the edge-guided parsing head is capable to distinguish adjacent human parts from among each other up to 58 parts in a single human instance, even overlapping instances. Meanwhile, a refinement head integrating box-level score and part-level parsing quality is exploited to improve the quality of the parsing results. Experiments on two multiple human parsing datasets (i.e., CIHP and LV-MHP-v2.0) and one video instance-level human parsing dataset (i.e., VIP) show that our method achieves the best global-level and instance-level performance over state-of-the-art one-stage top-down alternatives., Comment: Accepted by IEEE Transactions on Image Processing (TIP)

An accelerated class of adaptive scheme of iterative thresholding algorithms is studied analytically and empirically. They are based on the feedback mechanism of the null space tuning techniques (NST+HT+FB). The main contribution of this article is the accelerated convergence analysis and proofs with a variable/adaptive index selection and different feedback principles at each iteration. These convergence analysis require no longer a priori sparsity information $s$ of a signal. %key theory in this paper is the concept that the number of indices selected at each iteration should be considered in order to speed up the convergence. It is shown that uniform recovery of all $s$-sparse signals from given linear measurements can be achieved under reasonable (preconditioned) restricted isometry conditions. Accelerated convergence rate and improved convergence conditions are obtained by selecting an appropriate size of the index support per iteration. The theoretical findings are sufficiently demonstrated and confirmed by extensive numerical experiments. It is also observed that the proposed algorithms have a clearly advantageous balance of efficiency, adaptivity and accuracy compared with all other state-of-the-art greedy iterative algorithms.

Thresholding based iterative algorithms have the trade-off between effectiveness and optimality. Some are effective but involving sub-matrix inversions in every step of iterations. For systems of large sizes, such algorithms can be computationally expensive and/or prohibitive. The null space tuning algorithm with hard thresholding and feedbacks (NST+HT+FB) has a mean to expedite its procedure by a suboptimal feedback, in which sub-matrix inversion is replaced by an eigenvalue-based approximation. The resulting suboptimal feedback scheme becomes exceedingly effective for large system recovery problems. An adaptive algorithm based on thresholding, suboptimal feedback and null space tuning (AdptNST+HT+subOptFB) without a prior knowledge of the sparsity level is also proposed and analyzed. Convergence analysis is the focus of this article. Numerical simulations are also carried out to demonstrate the superior efficiency of the algorithm compared with state-of-the-art iterative thresholding algorithms at the same level of recovery accuracy, particularly for large systems.

Salient object detection is very useful in many computer vision applications such as image segmentation, content-based image editing and object recognition. In this paper, we present a salient object detection algorithm by using color spatial distribution (CSD) and minimum spanning tree weight (MSTW). We first use a segmentation algorithm to decompose an image into superpixel-level elements, then use these elements as nodes to construct a minimum spanning tree (MST), each connected edge weight is the mean color difference between two nodes. CSD of each element can be computed by integrating color, spatial distance and MSTW. Note that if the color of one element is the most widely distributed over the entire image, it should have the biggest CSD value, we regard this element as a background node (BG Node). Then we use the MSTW between other element and BG node to generate a MSTW map. The superpixel-level saliency map can be obtained by combining the CSD map and MSTW map. Finally, we use a guided filter to get the pixel-level saliency map. Experimental results on two databases demonstrate that our proposed method outperforms other previous state-of-the-art approaches.

The development of a singular spectrum analysis-based algorithm and its application to reconstruct the decomposed components and subsequently select the principal components of typical acoustic-emission waveforms determined by laboratory rock-burst tests for a sample of Shuicang limestone from Jiahe coal mine, eastern China are described. The eigenfrequencies of the component waves - the spectral domain precursors - are found to consistently represent the frequency shift. Precursory waves of the first main component were found to give a good representation of the time dynamics of the acoustic-emission signals and the rock responses at different rock-burst stages., The development of a singular spectrum analysis-based algorithm and its application to reconstruct the decomposed components and subsequently select the principal components of typical acoustic-emission waveforms determined by laboratory rock-burst tests for a sample of Shuicang limestone from Jiahe coal mine, eastern China are described. The eigenfrequencies of the component waves - the spectral domain precursors - are found to consistently represent the frequency shift. Precursory waves of the first main component were found to give a good representation of the time dynamics of the acoustic-emission signals and the rock responses at different rock-burst stages.