A Dual-Polarimetric SAR Ship Detection Dataset and a Memory-Augmented Autoencoder-Based Detection Method

With the development of imaging and space-borne satellite technology, a growing number of multipolarized SAR imageries have been implemented for object detection. However, most of the existing public SAR ship datasets are grayscale images under single polarization mode. To make full use of the polarization characteristics of multipolarized SAR, a dual-polarimetric SAR dataset specifically used for ship detection is presented in this paper (DSSDD). For construction, 50 dual-polarimetric Sentinel-1 SAR images were cropped into 1236 image slices with the size of 256 × 256 pixels. The variances and covariance of both VV and VH polarization were fused into R,G,B channels of the pseudo-color image. Each ship was labeled with both a rotatable bounding box (RBox) and a horizontal bounding box (BBox). Apart from 8-bit pseudo-color images, DSSDD also provides 16-bit complex data for readers. Two prevalent object detectors R3Det and Yolo-v4 were implemented on DSSDD to establish the baselines of the detectors with the RBox and BBox respectively. Furthermore, we proposed a weakly supervised ship detection method based on anomaly detection via advanced memory-augmented autoencoder (MemAE), which can significantly remove false alarms generated by the two-parameter CFAR algorithm applied upon our dual-polarimetric dataset. The proposed advanced MemAE method has the advantages of a lower annotation workload, high efficiency, good performance even compared with supervised methods, making it a promising direction for ship detection in dual-polarimetric SAR images. The dataset is available on github.

Recent very severe tropical cyclones over the Bay of Bengal : Analysis with satellite data

lkj & bl 'kks/k&i= esa caxky dh [kkM+h ds m".kdfVca/kh; pØokrksa dh rhozrk dk vkdyu vkSj pØokr ds ekxZ dk iwokZuqeku yxkus esa mixzg ds vk¡dM+ksa ls cus izHkko dks n’kkZ;k x;k gSA bl 'kks/k&i= esa ys[kdksa us pØokrh rwQkuksa ds ekxZ dk] pØokr ds cuus dk vkSj pØokr dh xfrfof/k;ksa dk irk yxkus esa mixzg ds vk¡dM+ksa ds mi;ksx dks vuqdwy cukus esa lqnwj laosnh rduhdksa dh gky gh esa feyh lQyrk vkSj mlds mi;ksx dh izxfr ij fo’ks"k :Ik ls /;ku dsfUnzr fd;k gSA nks pØokrksa dk fo’ys"k.k fd;k x;k gS & 16 ls 19 ebZ 2004 esa E;kaekj esa vk;k izpaM pØokrh rwQku vkSj nwljk 26 ls 31 vDrwcj 1999 esa mM+hlk esa vk;k pØokrA pØokrh rwQkuksa ds cuus vkSj muds vkxs c<+us ds iwokZuqeku esa vfr mPp foHksnu jsfM;ksehVj ¼oh- ,p- vkj- vkj-½ vk¡dM+ksa] LdsVªksehVj iouksa vkSj cfgxkZeh nh?kZrjax fofdj.k ¼vks- ,y- vkj-½ ds pØokrksa ds vkl&ikl Ñf=e o.kZ esa n’kkZ, x, vk¡dM+ksa dk mi;ksx djrh gqbZ mixzg ij vk/kkfjr rduhd cgqr vf/kd mi;ksxh ikbZ xbZ gSA bl v/;;u esa caxky dh [kkM+h esa vk, nks pØokrksa ds cuus vkSj muds vkxs c<+us dh vlekurk dks fo’ks"k :Ik ls crk;k x;k gSA This paper shows the impact made by the satellite data in the intensity estimation and track prediction of tropical cyclones of Bay of Bengal. The authors in this paper have focused on the recent accomplishment and advances in the remote sensing techniques to optimize the use of satellite data in tracking, formation and movement of cyclonic storms. Two cyclones - firstly the Myanmar severe cyclonic storm of 16 to 19 May 2004 and secondly the 26 – 31 October 1999 Orissa cyclone have been analysed. Satellite based technique using Very High Resolution Radiometer (VHRR) data, scatterometer winds and outgoing long wave radiation (OLR) data in pseudo color around the cyclones have been found to be more useful in predicting formation and movement of cyclonic storms. The present study has significantly brought out the difference in formation and movement of the two cyclones formed over the Bay of Bengal.

Seam welds quality control improvement using method of pseudo-color coding images

The method of seam welds quality control using X-ray is considered. The X-ray methods of control are based on the capability of gamma radiation to penetrate through a metal including welded areas. Regions having defects - pores, faulty welds, cracks, scale inclusions - look darker on images. Appearance, linear dimensions and depths of the defects usually are determined by a visual examination comparing the X-ray image with standard defects images. It is known that a human eye can distinguish not more than 12-15 shades on a black and white image but more than a hundred on a colored image. The paper considers possibilities of the developed method by the author and based on the optical mixing of two or three complementary colors - red, blue and green. The method can use only one pair of the colors at a time, i.e. it is possible to have three various pairs for a pseudo-color image. The obtained pseudo-color image has the same informational capacity as the original black and white image. But the greater fraction of the saved information becomes available for visual examination of the X-ray image. In the end the efficiency of the seam weld quality control increases.

Value of Cardiac Cine MRI in Comparison to Contrast Transcranial Doppler Sonography for Patent Foramen Ovale Assessment in Patients with Cerebral Disorders

Purpose: To investigate the clinical feasibility of diagnosing and classifying patent foramen ovale (PFO) in patients with cerebral disorders by cardiac cine MRI (CCMRI) without contrast.Materials and Methods: Forty-four patients (24 males and 20 females; mean age, 41.3 years; range, 21–64 years) with cerebral disorders underwent contrast transcranial Doppler sonography (cTCD) and non-enhanced CCMRI examinations between October 2019 and March 2020. CCMRI was performed with a 3.0T magnetic resonance (MR) scanner using the OBL FIESTA CINE 4CH sequence. The scanning direction was perpendicular to the interatrial septum (IAS). The obtained MR images were analyzed by AW station 4.4. Pseudo-color coding was performed based on the different phases. The blood shunt condition was observed and recorded, noting the PFO length and width and whether it was complicated by IAS aneurysm or secondary septum thickening.Results: Thirty-nine of the 44 patients with cerebral disorders were confirmed to have right-to-left shunt by cTCD, and 37 of them were diagnosed with PFO by CCMRI. Two of the five remaining patients were also diagnosed with PFO by CCMRI. Compared with cTCD as a standard, CCMRI assessment resulted in the following: sensitivity, 94.9%; specificity, 60.0%; accuracy, 90.9%; positive predictive value, 94.9%; negative predictive value, 60.0%; area under the curve, 0.774. Using pseudo-color coding, a right-to-left color jet was observed in 34 patients, and a two-way shunt was found in five. IAS aneurysm and secondary septum thickening were found in five and three patients (11.4% and 6.8%), respectively. The maximum PFO diameters ranged from 1.7 to 16.8 mm, and the mean diameter was 5.4 ± 3.4 mm.Conclusion: The noninvasive CCMRI without contrast proved an excellent method for PFO identification, evaluation, and classification, with high sensibility (92.85%) and concordance (90.9%) compared to cTCD.

Study on Data Partition for Delimitation of Masses in Mammography

Mammography is the primary medical imaging method used for routine screening and early detection of breast cancer in women. However, the process of manually inspecting, detecting, and delimiting the tumoral massess in 2D images is a very time-consuming task, subject to human errors due to fatigue. Therefore, integrated computer-aided detection systems have been proposed, based on modern computer vision and machine learning methods. In the present work, mammogram images from the publicly available Inbreast dataset are first converted to pseudo-color and then used to train and test a Mask R-CNN deep neural network. The most common approach is to start with a dataset and split the images into train and test set randomly. However, since there are often two or more images of the same case in the dataset, the way the dataset is split may have an impact on the results. Our experiments show that random partition of the data can produce unreliable training, so the dataset must be split using case-wise partition for more stable results. In experimental results, the method achieves an average true positive rate of 0.936 with 0.063 standard deviation using random partition and 0.908 with 0.002 standard deviation using case-wise partition, showing that case-wise partition must be used for more reliable results.

A Study on Radiation Imaging Mechanism and Characteristics in Different Inspection Systems

Radiation imaging, as a key issue in nuclear technology, has received considerable attention in the industry. It is widely used in nuclear medicine, Customs supervision, and many other areas. The objective of this investigation is to get insight into the principle, operation characteristics and image characteristics of radiation imaging. In this paper, an investigation on radiation imaging is conducted on three main inspection systems for Customs supervision, including small X-ray inspection machine, CT baggage inspection system, and large container inspection system. The principle, operation characteristics, evaluation indexes, pseudo-color processing and image characteristics are discussed in detail. The results indicate that the spatial resolution of small X-ray inspection machine is much higher than that of CT baggage/goods inspection system and large container/vehicle inspection system. It is a challenge to identify substances and specific shapes in the case of overlapping for small X-ray inspection system. Moreover, the mechanism of X-ray images is discussed as well. The radiation images are divided into three types, including two-dimensional, pseudo-color, high spatial resolution; two-dimensional, gray, high spatial resolution; three-dimensional, pseudo-color, high density resolution. The further investigation on machine inspection images is suggested to focus on the application environment. For some objects with specific characteristics, such as amorphous, explosive, the CT baggage inspection has much better performance than other systems. The research in this paper reveals the mechanism, parametric effect and imaging characteristics. It could provide a necessary foundation for the follow-up intelligent processing, detection, identification and annotation for radiation imaging in nuclear area. The research on inspection devices could lend strong experience to medical treatment, industry and many other fields.

Interactive System Based on Leap Motion for 3D Medical Model

An interactive visualization of the patients’ 3D medical anatomical model as guide is often helpful for doctors during complex surgery. However, there are certain limitations according to the actual requirements of building sterile operating environment. Traditional human–computer interaction tools (mouse and keyboard) must be disinfected regularly and cannot be used in the process. A noncontact gesture control medical model based on Leap Motion is proposed in this study. The gesture is recognized and localized without using mouse and keyboards through a binocular camera assembled on Leap Motion. Hence, the model is directly controlled by the gesture to complete the operation of rotation, zoom, and other functions. In this study, a 3D heart model is combined with pseudo-color processing technology to enhance the observability of its 3D structure. Gesture recognition technology is then utilized to control the rendered model as rotation and zoom. Experimental results show that our system has an absolute accuracy in recognizing circle, swipe, and other actions. Thus, rotation is proposed as a new motion that can be identified steadily. Rotation plays an essential role in usability, intuition, and interactive efficiency of future system design. The system is applicable to sterile operating environments due to its stable recognition process and small space occupation.

Restoration method of sootiness mural images based on dark channel prior and Retinex by bilateral filter

Environmental changes and human activities can cause serious degradation of murals, where sootiness is one of the most common problems of ancient Chinese indoor murals. In order to improve the visual quality of the murals, a restoration method is proposed for sootiness murals based on dark channel prior and Retinex by bilateral filter using hyperspectral imaging technology. First, radiometric correction and denoising through band clipping and minimum noise fraction rotation forward and inverse transform were applied to the hyperspectral data of the sootiness mural to produce its denoised reflectance image. Second, a near-infrared band was selected from the reflectance image and combined with the green and blue visible bands to produce a pseudo color image for the subsequent sootiness removal processing. The near-infrared band is selected because it is better penetrating the sootiness layer to a certain extent comparing to other bands. Third, the sootiness covered on the pseudo color image was preliminarily removed by using the method of dark channel prior and by adjusting the brightness of the image. Finally, the Retinex by bilateral filter was performed on the image to get the final restored image, where the sootiness was removed. The results show that the images restored by the proposed method are superior in variance, average gradient, information entropy and gray scale contrast comparing to the results from the traditional methods of homomorphic filtering and Gaussian stretching. The results also show the highest score in comprehensive evaluation of edges, hue and structure; thus, the method proposed can support more potential studies or sootiness removal in real mural paintings with more detailed information. The method proposed shows strong evidence that it can effectively reduce the influence of sootiness on the moral images with more details that can reveal the original appearance of the mural and improve its visual quality.