Although widely used in many applications, accurate and efficient human action recognition remains a challenging area of research in the field of computer vision. Most recent surveys have focused on narrow problems such as human action recognition methods using depth data, 3D-skeleton data, still image data, spatiotemporal interest point-based methods, and human walking motion recognition. However, there has been no systematic survey of human action recognition. To this end, we present a thorough review of human action recognition methods and provide a comprehensive overview of recent approaches in human action recognition research, including progress in hand-designed action features in RGB and depth data, current deep learning-based action feature representation methods, advances in human⁻object interaction recognition methods, and the current prominent research topic of action detection methods. Finally, we present several analysis recommendations for researchers. This survey paper provides an essential reference for those interested in further research on human action recognition.

A Comprehensive Survey of Vision-Based Human Action Recognition Methods.

To solve the problems of convergence speed in the ant colony algorithm, an improved ant colony optimization algorithm is proposed for path planning of mobile robots in the environment that is expressed using the grid method. The pheromone diffusion and geometric local optimization are combined in the process of searching for the globally optimal path. The current path pheromone diffuses in the direction of the potential field force during the ant searching process, so ants tend to search for a higher fitness subspace, and the search space of the test pattern becomes smaller. The path that is first optimized using the ant colony algorithm is optimized using the geometric algorithm. The pheromones of the first optimal path and the second optimal path are simultaneously updated. The simulation results show that the improved ant colony optimization algorithm is notably effective.

An improved ant colony algorithm for robot path planning

Image denoising review: From classical to state-of-the-art approaches

An overview on spectral and spatial information fusion for hyperspectral image classification: Current trends and challenges

Multi-focus image fusion: A Survey of the state of the art

Compressed sensing has shown great potential and power in image representation, especially in image reconstruction by sparse representation. Due to complementary information and unavoidable noise existing in synthetic aperture radar (SAR) and other source images, joint sparse representation (JSR) is developed to separate redundancy and complementary information with different properties in source images and obtain a fused image, where image de-noising is done simultaneously owing to that noise is not sparse and cannot be represented by sparse representation. As a result, one noisy remote sensing image fusion method based on JSR is presented in this paper. After obtaining redundant and complementary sub-images by JSR, an improved fusion rule based on pulse coupled neural network (PCNN) is employed to fuse complementary sparse coefficients together. At the same time, because the types of noise in SAR and other source images are different, they can be treated as the complementary information in source images and suppressed at this step. Finally, a fused image can be reconstructed by adding the redundant and fused complementary sub-images. Quantitative and qualitative experimental results show that the proposed method outperforms most of other fusion methods and it is more robust to noise, having better visual effects and values of objective evaluation metrics.

/pdf/noisy-remote-sensing-image-fusion-based-on-jsr-325r5mcjjq.pdf

Noisy Remote Sensing Image Fusion Based on JSR

Non-subsampled Shearlet transform (NSST) has good properties such as multi-scale, multi-direction and shift invariance, but limits the signal analysis to the time frequency domain. Fractional Fourier transform (FRFT) extend the signal analysis to fractional domain, but it is unable to analysis the partial characteristic of signal. Combine the advantages of NSST and FRFT, a novel image fusion algorithm is proposed. Firstly, NSST is applied to the two source images. Secondly, the FRFT is applied to the low-frequency sub-bands coefficients of NSST to acquire image description in fractional domain. Thirdly, fusion rule selecting maximizes of sum-modified-Laplacian is applied to fuse high-frequency sub-bands coefficients and fusion rule of the simple averaging operation is applied to fuse low-frequency coefficients. Finally, the fused image is obtained by the inverse FRFT and inverse NSST. Experimental results show that the proposed method can not only obtain good visual effect, but also improve its objective evaluation criteria.

A novel multi-focus image fusion algorithm based on NSST-FRFT

Finding a way to effectively suppress speckle in SAR images has great significance. K-means singular value decomposition (K-SVD) has shown great potential in SAR image de-noising. However, the traditional K-SVD is sensitive to the position and phase of the characteristics in the image, and the de-noised image by K-SVD has lost some detailed information of the original image. In this paper, we present one new SAR image de-noising method based on shift invariant K-SVD and guided filter. The whole method consists of two steps. The first deals mainly with the noisy image with shift invariant K-SVD and obtaining the initial de-noised image. In the second step, we do the guided filtering for the initial de-noised image. Finally, we can recover the final de-noised image. Experimental results show that our method not only has better visual effects and objective evaluation, but can also save more detailed information such as image edge and texture when de-noising SAR images. The presented shift invariant K-SVD can be widely used in image processing, such as image fusion, edge detection and super-resolution reconstruction.

https://www.mdpi.com/2072-4292/9/12/1311/pdf

SAR Image De-Noising Based on Shift Invariant K-SVD and Guided Filter

SAR images have been widely used in many fields such as military and remote sensing. So the suppression of the speckle has been an important research issues. To improve the visual effect of non-local means, generalized non-local (GNL) means with optimized pixel-wise weighting is applied to shrink the coefficients of non-subsample Shearlet transform (NSST) of SAR image. The new method can optimize the weight of GNL, which not only improve the PSNR of de-noised image, but also can significantly enhance the visual effect of de-noising image.

/pdf/sar-image-de-noising-based-on-gnl-means-with-optimized-pixel-2at01wun9e.pdf

SAR Image De-Noising based on GNL-Means with Optimized Pixel-Wise Weighting in Non-Subsample Shearlet Domain

Synthetic aperture radar (SAR) is one of the most widely used remote sensing monitoring methods for large-scale marine activities. Due to the influence of speckle noise, sea clutter and complex environment, ship detection of SAR images is still a challenging task. Based on the multi-layer selective cognition characteristics of the human visual system, we propose a ship target detection algorithm based on region growing and multi-scale saliency. First, the layered rough-fine land-sea segmentation is used to remove the effect of land scattering. Second, the non-subsampled Laplacian pyramid (NSLP) filter is applied to decompose the image at different scales. Then, the saliency region of the transformed coefficients is extracted by spectral residual (SR). And the constant false alarm rate (CFAR) algorithm is used to further filter the false alarm and extract target more accurately. Finally, saliency sub-images of different scales are fused to get the final detection results. Experimental results show that the algorithm not only effectively suppresses the influence of land and sea clutter, but also can improve the detection rate.

Shuaiqi Liu

Papers

Noisy Remote Sensing Image Fusion Based on JSR

A novel multi-focus image fusion algorithm based on NSST-FRFT

SAR Image De-Noising Based on Shift Invariant K-SVD and Guided Filter

SAR Image De-Noising based on GNL-Means with Optimized Pixel-Wise Weighting in Non-Subsample Shearlet Domain

Ship Detection in SAR Images Based on Region Growing and Multi-scale Saliency