Refined UNet V4: End-to-End Patch-Wise Network for Cloud and Shadow Segmentation with Bilateral Grid

Remote sensing images are usually contaminated by cloud and corresponding shadow regions, making cloud and shadow detection one of the essential prerequisites for processing and translation of remote sensing images. Edge-precise cloud and shadow segmentation remains challenging due to the inherent high-level semantic acquisition of current neural segmentation fashions. We, therefore, introduce the Refined UNet series to partially achieve edge-precise cloud and shadow detection, including two-stage Refined UNet, v2 with a potentially efficient gray-scale guided Gaussian filter-based CRF, and v3 with an efficient multi-channel guided Gaussian filter-based CRF. However, it is visually demonstrated that the locally linear kernel used in v2 and v3 is not sufficiently sensitive to potential edges in comparison with Refined UNet. Accordingly, we turn back to the investigation of an end-to-end UNet-CRF architecture with a Gaussian-form bilateral kernel and its relatively efficient approximation. In this paper, we present Refined UNet v4, an end-to-end edge-precise segmentation network for cloud and shadow detection, which is capable of retrieving regions of interest with relatively tight edges and potential shadow regions with ambiguous edges. Specifically, we inherit the UNet-CRF architecture exploited in the Refined UNet series, which concatenates a UNet backbone of coarsely locating cloud and shadow regions and an embedded CRF layer of refining edges. In particular, the bilateral grid-based approximation to the Gaussian-form bilateral kernel is applied to the bilateral message-passing step, in order to ensure the delineation of sufficiently tight edges and the retrieval of shadow regions with ambiguous edges. Our TensorFlow implementation of the bilateral approximation is relatively computationally efficient in comparison with Refined UNet, attributed to the straightforward GPU acceleration. Extensive experiments on Landsat 8 OLI dataset illustrate that our v4 can achieve edge-precise cloud and shadow segmentation and improve the retrieval of shadow regions, and also confirm its computational efficiency.

A two-step computer vision-based framework for bolt loosening detection and its implementation on a smartphone application

Bolt loosening detection is a labor-intensive and time-consuming process for field engineers. This paper develops a two-step computer vision-based framework to quickly identify bolt loosening angle from field images captured by unmanned aerial vehicle (UAV). In step one, a total of 1200 image samples of bolted structures were used to train faster region based convolutional neural network (Faster R-CNN) for bolt detection from UAV captured images. In step two, computer vision-based technologies, including Gaussian filter, perspective transform, and Hough transform (HT), were performed to quantify bolt loosening angle. The developed framework was then integrated into web server and an iOS application (app) was designed to enable fast data communication between field workplace (UAV captured images) and web server (bolt loosening angle quantification), so that field engineers can quickly view the inspection results on their phone screens. The proposed framework and designed smartphone app greatly help field engineers to improve the accuracy and efficiency for onsite inspection and maintenance of bolted structures.

An efficient look up table based approximate adder for field programmable gate array

The approximate computing is an alternative computing approach which can lead to high-performance implementation of audio and image processing as well as deep learning applications. However, most of the available approximate adders have been designed using application specific integrated circuits (ASICs), and they would not result in an efficient implementation on field programmable gate arrays (FPGAs). In this paper, we have designed a new approximate adder customized for efficient implementation on FPGAs, and then it has been used to build the Gaussian filter. The experimental results of the implementation of Gaussian filter based on the proposed approximate adder on a Virtex-7 FPGA, indicated that the resource utilization has decreased by 20-51%, and the designed filter delay based on the modified design methodology for building approximate adders for FPGA-based systems (MDeMAS) adder has improved 10-35%, due to the obtained output quality.

Enhanced Image Compression and Processing Scheme

Image compression refers to the process of encoding image using fewer number of bits. The major aim of lossless image compression is to reduce the redundancy and irreverence of image data for better storage and transmission of data in the better form. The lossy compression scheme leads to high compression ratio while the image experiences lost in quality. However, there are many cases where the loss of image quality or information due to compression needs to be avoided, such as medical, artistic and scientific images. Efficient lossless compression become paramount, although the lossy compressed images are usually satisfactory in divers’ cases. This paper titled Enhanced Lossless Image Compression Scheme is aimed at providing an enhanced lossless image compression scheme based on Bose, Chaudhuri Hocquenghem- Lempel Ziv Welch (BCH-LZW) lossless image compression scheme using Gaussian filter for image enhancement and noise reduction. In this paper, an efficient and effective lossless image compression technique based on LZW- BCH lossless image compression to reduce redundancies in the image was presented and image enhancement using Gaussian filter algorithm was demonstrated. Secondary method of data collection was used to collect the data. Standard research images were used to validate the new scheme. To achieve these, an object approach using Java net beans was used to develop the compression scheme. From the findings, it was revealed that the average compression ratio of the enhanced lossless image compression scheme was 1.6489 and the average bit per pixel was 5.416667. Gaussian filter image enhancement was used for noise reduction and the image was enhanced eight times the original.

Skin Lesion Extraction Using Multiscale Morphological Local Variance Reconstruction Based Watershed Transform and Fast Fuzzy C-Means Clustering

Early identification of melanocytic skin lesions increases the survival rate for skin cancer patients. Automated melanocytic skin lesion extraction from dermoscopic images using the computer vision approach is a challenging task as the lesions present in the image can be of different colors, there may be a variation of contrast near the lesion boundaries, lesions may have different sizes and shapes, etc. Therefore, lesion extraction from dermoscopic images is a fundamental step for automated melanoma identification. In this article, a watershed transform based on the fast fuzzy c-means (FCM) clustering algorithm is proposed for the extraction of melanocytic skin lesion from dermoscopic images. Initially, the proposed method removes the artifacts from the dermoscopic images and enhances the texture regions. Further, it is filtered using a Gaussian filter and a local variance filter to enhance the lesion boundary regions. Later, the watershed transform based on MMLVR (multiscale morphological local variance reconstruction) is introduced to acquire the superpixels of the image with accurate boundary regions. Finally, the fast FCM clustering technique is implemented in the superpixels of the image to attain the final lesion extraction result. The proposed method is tested in the three publicly available skin lesion image datasets, i.e., ISIC 2016, ISIC 2017 and ISIC 2018. Experimental evaluation shows that the proposed method achieves a good result.

Texture Feature Extraction of Lumbar Spine Trabecular Bone Radiograph Image using Laplacian of Gaussian Filter with KNN Classification to Diagnose Osteoporosis

The human bones are categorized based on elemental micro architecture and porosity. The porosity of the inner trabecular bone is high that is 40-95% and the nature of the bone is soft and spongy whereas the cortical bone is harder and is less porous that is 5 to 15%. Osteoporosis is a disease that normally affects women usually after their menopause. It largely causes mild bone fractures and further stages lead to the demise of an individual. The detection of Osteoporosis in Lumbar Spine has been widely recognized as a promising way to frequent fractures. Therefore, premature analysis of osteoporosis will estimate the risk of the bone fracture which prevents life threats. The paper is systematized in two different sections to classify normal (non-osteoporosis) and abnormal(osteoporosis)Lumbar spine trabecular bone. In this method, the first section is based on discriminating the lumbar spine trabecular bone micro-architecture predisposing by means of first and second order directional derivative of Laplacian of Gaussian filter with different standard deviation to acquire the minimum and maximum responses. The dimension reduction of texture features, quantization and adjacent scale coding with weighted multipliers are used to lessen the intensity variations of texture features. The second section is based on the reduction of histogram features as a training data set for classification of normal and osteoporotic images of lumbar spine (L1-L4) using K-Nearest Neighborhood (KNN) classifier. The tested dataset result gives effective classification accuracy of 97.22% with lesser texture feature dimension. The usage of weight multiplier as well as quantization technique plays a major role for the improvement of accuracy to diagnose osteoporosis for an input noisy and noiseless image.

A Study on Weak Edge Detection of COVID-19’s CT Images Based on Histogram Equalization and Improved Canny Algorithm

The coronavirus disease 2019 (COVID-19) is a substantial threat to people’s lives and health due to its high infectivity and rapid spread. Computed tomography (CT) scan is one of the important auxiliary methods for the clinical diagnosis of COVID-19. However, CT image lesion edge is normally affected by pixels with uneven grayscale and isolated noise, which makes weak edge detection of the COVID-19 lesion more complicated. In order to solve this problem, an edge detection method is proposed, which combines the histogram equalization and the improved Canny algorithm. Specifically, the histogram equalization is applied to enhance image contrast. In the improved Canny algorithm, the median filter, instead of the Gaussian filter, is used to remove the isolated noise points. The K -means algorithm is applied to separate the image background and edge. And the Canny algorithm is improved continuously by combining the mathematical morphology and the maximum between class variance method (OTSU). On selecting four types of lesion images from COVID-CT date set, MSE, MAE, SNR, and the running time are applied to evaluate the performance of the proposed method. The average values of these evaluation indicators are 1.7322, 7.9010, 57.1241, and 5.4887, respectively. Compared with other three methods, these values indicate that the proposed method achieves better result. The experimental results prove that the proposed algorithm can effectively detect the weak edge of the lesion, which is helpful for the diagnosis of COVID-19.

An Efficient Method for Capturing the High Peak Concentrations of PM2.5 Using Gaussian-Filtered Deep Learning

This paper proposes a deep learning model that integrates a convolutional neural network with a gate circulation unit that captures patterns of high-peak PM2.5 concentrations. The purpose is to accurately predict high-peak PM2.5 concentration data that cannot be trained in general deep learning models. For the training of the proposed model, we used all available weather and air quality data for three years from 2015 to 2017 from 25 stations of the National Institute of Environmental Research (NIER) and the Korea Meteorological Administration (KMA) observatory in Seoul, South Korea. Our model trained three years of data and predicted high-peak PM2.5 concentrations for the year 2018. In addition, we propose a Gaussian filter algorithm as a preprocessing method for capturing high concentrations of PM2.5 in the Seoul area and predicting them more accurately. This model overcomes the limitations of conventional deep learning approaches that are unable to predict high peak PM2.5 concentrations. Comparing model measurements at each of the 25 monitoring sites in 2018, we found that the deep learning model with a Gaussian filter achieved an index of agreement of 0.73–0.89 and a proportion of correctness of 0.89–0.96, and compared to the conventional deep learning method (average POC = 0.85), the Gaussian filter algorithm (average POC = 0.94) improved the accuracy of high-concentration PM2.5 prediction by an average of about 9%. Applying this algorithm in the preprocessing stage could be updated to predict the risk of high PM2.5 concentrations in real time.