non-ROI Regions Research Articles

A Multi-Stage Approach to UAV Detection, Identification, and Tracking Using Region-of-Interest Management and Rate-Adaptive Video Coding

The drone industry has opened its market to ordinary people, making drones prevalent in daily life. However, safety and security issues have been raised as the number of accidents rises (e.g., losing control and colliding with people or invading secured properties). For safety and security purposes, observers and surveillance systems must be aware of UAVs invading aerial spaces. This paper introduces a UAV tracking system with ROI-based video coding capabilities that can efficiently encode videos with a dynamic coding rate. The proposed system initially uses deep learning-based UAV detection to locate the UAV and determine the ROI surrounding the detected UAVs. Afterward, the ROI is tracked using optical flow, which is relatively light in computational load. Furthermore, our devised module for effective compression, XROI-DCT, is applied to non-ROI regions, so a different coding rate is applied depending on the region during encoding. The proposed UAV tracking system is implemented and evaluated by utilizing videos from YouTube, Kaggle, and a video of 3DR Solo2 taken by the authors. The evaluation verifies that the proposed system can detect and track UAVs significantly faster than YOLOv7 and efficiently encode a video, compressing 70% of the video based on the ROI. Additionally, it can successfully identify the UAV model with a high accuracy of 0.9869 ROC–AUC score.

Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation

The high prevalence of cardiovascular diseases (CVDs) calls for accessible and cost-effective continuous cardiac monitoring tools. Despite Electrocardiography (ECG) being the gold standard, continuous monitoring remains a challenge, leading to the exploration of Photoplethysmography (PPG), a promising but more basic alternative available in consumer wearables. This notion has recently spurred interest in translating PPG to ECG signals. In this work, we introduce Region-Disentangled Diffusion Model (RDDM), a novel diffusion model designed to capture the complex temporal dynamics of ECG. Traditional Diffusion models like Denoising Diffusion Probabilistic Models (DDPM) face challenges in capturing such nuances due to the indiscriminate noise addition process across the entire signal. Our proposed RDDM overcomes such limitations by incorporating a novel forward process that selectively adds noise to specific regions of interest (ROI) such as QRS complex in ECG signals, and a reverse process that disentangles the denoising of ROI and non-ROI regions. Quantitative experiments demonstrate that RDDM can generate high-fidelity ECG from PPG in as few as 10 diffusion steps, making it highly effective and computationally efficient. Additionally, to rigorously validate the usefulness of the generated ECG signals, we introduce CardioBench, a comprehensive evaluation benchmark for a variety of cardiac-related tasks including heart rate and blood pressure estimation, stress classification, and the detection of atrial fibrillation and diabetes. Our thorough experiments show that RDDM achieves state-of-the-art performance on CardioBench. To the best of our knowledge, RDDM is the first diffusion model for cross-modal signal-to-signal translation in the bio-signal domain.

Black Gram Disease Classification via Deep Ensemble Model with Optimal Training

Black gram crop belongs to the Fabaceae family and its scientific name is Vigna Mungo.It has high nutritional content, improves the fertility of the soil, and provides atmospheric nitrogen fixation in the soil. The quality of the black gram crop is degraded by diseases such as Yellow mosaic, Anthracnose, Powdery Mildew, and Leaf Crinkle which causes economic loss to farmers and degraded production. The agriculture sector needs to classify plant nutrient deficiencies in order to increase crop quality and yield. In order to handle a variety of difficult challenges, computer vision and deep learning technologies play a crucial role in the agricultural and biological sectors. The typical diagnostic procedure involves a pathologist visiting the site and inspecting each plant. However, manually crop disease assessment is limited due to lesser accuracy and limited access of personnel. To address these problems, it is necessary to develop automated methods that can quickly identify and classify a wide range of plant diseases. In this paper, black gram disease classifications are done through a deep ensemble model with optimal training and the procedure of this technique is as follows: Initially, the input dataset is processed to increase its size via data augmentation. Here, the processes like shifting, rotation, and shearing take place. Then, the model starts with the noise removal of images using median filtering. Subsequent to the preprocessing, segmentation takes place via the proposed deep joint segmentation model to determine the ROI and non-ROI regions. The next process is the extraction of the feature set that includes the features like improved multi-texton-based features, shape-based features, color-based features, and local Gabor X-OR pattern features. The model combines the classifiers like Deep Belief Networks, Recurrent Neural Networks, and Convolutional Neural Networks. For tuning the optimal weights of the model, a new algorithm termed swarm intelligence-based Self-Improved Dwarf Mongoose Optimization algorithm (SIDMO) is introduced. Over the past two decades, nature-based metaheuristic algorithms have gained more popularity because of their ability to solve various global optimization problems with optimal solutions. This training model ensures the enhancement of classification accuracy. The accuracy of the SIDMO, which is around 94.82%, is substantially higher than that of the existing models, which are FPA[Formula: see text]88.86%, SSOA[Formula: see text]88.99%, GOA[Formula: see text]85.84%, SMA[Formula: see text]85.11%, SRSR[Formula: see text]85.32%, and DMOA[Formula: see text]88.99%, respectively.

English

The analog signals are changed to digital signals for an instance of time designed as a powerful imaging system. The imaging system produced in the digital form as it evolves the analog imaging devices has the ability to perform digital technology. Therefore, the image expansion is guided by the diagnostic system and surgical systems. The present research work used a hybrid compressive sensing algorithm consisting of an optimized neural network and lossy-lossless compression using Adaptively learned sparsifying based on L1 minimization. The Region of Interest (ROI) is compressed using Integer-based Lifting Wavelet Transform with lossless compression, and the non-ROI using an Optimized neural network. The lossy models are irreversible and achieve a higher compression ratio; therefore, the medical image processing has the visual quality in reconstruction showing compression ratio at the highest. The proposed method overcomes the dimensional reduction problem for optimizing with sparsity to non-ROI regions. Therefore, the medical image is transmitted over the network with limited bandwidth. The proposed work outcomes showed that the developed model attained a PSNR of 35.62 dB and SSIM of 0.984 better when compared to the existing ROI-CS Net model, which obtained a PSNR of 29.55 dB and SSIM of 0.89.

Optimized active contor segmentation model for medical image compression

Nowadays, medical imaging systems tend to have greatest impact on disease identification, diagnosis, and surgical preparation. To save hardware space and transmission bandwidth, it is important to reduce data redundancy in the image. Compressing images is very important for storage and transmitting purposes as it decreases the amount of bits required while retaining the critical information content encapsulated in the image document. This makes the system more peculiar in this field. The proposed paradigm image segmentation is the first step attained by the Optimized Active Contour Model (OACM). Using a new Modified marriage in honey bees optimization model (MMBO), ACM's weighting factor and maximum iteration are fine-tuned. Thereby, the collected inputimage is segmented into N-ROI and ROI. The ROI marked field will indeed be encoded using ISPIHT-based lossy compression model, whereas the non-ROI area is encoded using DCT based lossy compression model. In terms of BSC, the outcomes from both ISPIHT algorithm and DCTmodel are merged and the compressed image is itsoutput. Then, the compressed image will then be subjected to image decompression. This will include bit-stream segregation, which will be processed separately for the ROI and non-ROI regions using ISPIHT decoder and DCT-based decomposition. This process results in the original image. A comparative evaluation is undergone between the proposed and the existing techniques under PSNR, SSIM, and CR. Accordingly, the PSNR of the Proposed model is (∼)0.22, which is 26 %, 50 %, 60 %, and 55 % superior to the conventional methods like the MFO, LA, MBO, and JCF-LA.

An Improved Image Compression Model Enabled by Adaptive Active Contour and Supervised Learning-Based ROI Classification

This paper plans to develop a novel image compression model with four major phases. (i) Segmentation (ii) Feature Extraction (iii) ROI classification (iv) Compression. The image is segmented into two regions by Adaptive ACM. The result of ACM is the production of two regions, this model enables separate ROI classification phase. For performing this, the features corresponding to GLCM are extracted from the segmented parts. Further, they are subjected to classification via NN, in which new training algorithm is adopted. As a main novelty JA and WOA are merged together to form J-WOA with the aim of tuning the ACM (weighting factor and maximum iteration), and training algorithm of NN, where the weights are optimized. This model is referred as J-WOA-NN. This classification model exactly classifies the ROI regions. During the compression process, the ROI regions are handled by JPEG-LS algorithm and the non-ROI region are handled by wavelet-based lossy compression algorithm. Finally, the decompression model is carried out by adopting the same reverse process.

Computational modeling to predict the micromechanical environment in tissue engineering scaffolds

Cell fate in tissue engineering (TE) strategies is paramount to regenerate healthy, functional organs. The mechanical loads experienced by cells play an important role in cell fate. However, in TE scaffolds with a cell-laden hydrogel matrix, it is prohibitively complex to prescribe and measure this cellular micromechanical environment (CME). Accordingly, this study aimed to develop a finite element (FE) model of a TE scaffold unit cell that can be subsequently implemented to predict the CME and cell fates under prescribed loading. The compressible hyperelastic mechanics of a fibrin hydrogel were characterized by fitting unconfined compression and confined compression experimental data. This material model was implemented in a unit cell FE model of a TE scaffold. The FE mesh and boundary conditions were evaluated with respect to the mechanical response of a region of interest (ROI). A compressible second-order reduced polynomial hyperelastic model gave the best fit to the experimental data (C10 = 1.72 × 10−4, C20 = 3.83 × 10−4, D1 = 3.41, D2 = 8.06 × 10−2). A mesh with seed sizes of 40 µm and 60 µm in the ROI and non-ROI regions, respectively, yielded a converged model in 54 min. The in-plane boundary conditions demonstrated minimal influence on ROI mechanics for a 2-by-2 unit cell. However, the out-of-plane boundary conditions did exhibit an appreciable influence on ROI mechanics for a two bilayer unit cell. Overall, the developed unit cell model facilitates the modeling of the mechanical state of a cell-laden hydrogel within a TE scaffold under prescribed loading. This model will be utilized to characterize the CME in future studies, and 3D micromechanical criteria may be applied to predict cell fate in these scaffolds.

Medical Image Compression by Optimal Filter Coefficients Aided Transforms using Modified Rider Optimization Algorithm

Owing to a large amount of images, image compression is requisite for minimizing the redundancies in image, and it offers efficient transmission and archiving of images. This paper presents a novel medical image compression model using intelligent techniques. The adopted medical image compression comprises of three major steps such as, Segmentation, Image compression, and Image decompression. Initially, the Region of Interest (ROI) and Non-ROI regions of the image are split by means of a Segmentation procedure using Modified Region Growing (MRG) algorithm. Moreover, the image compression process begins which is varied for both ROI and Non-ROI regions. On considering the ROI regions, the compression is carried out by Discrete Cosine Transform (DCT) model and SPIHT encoding method, whereas the compression of Non-ROI region is carried out by Discrete Wavelet Transform (DWT) and Merge-based Huffman encoding (MHE) methods. As a main contribution, this paper intends to deploy the optimized filter coefficients in both DCT and DWT techniques. Here, the optimization of both filter coefficients is performed using Modified Rider Optimization Algorithm (ROA) called Improvised Steering angle and Gear-based ROA (ISG-ROA). In the final step, decompression is done by implementing the reverse concept of compression process with similar optimized coefficients. The filter coefficients are tuned in such a way that the Compression Ratio (CR) should be minimum. In addition, the comparative analysis over the state-of-the-art models proves the superior performance of the proposed model.

Region of interest-based adaptive segmentation for image compression using hybrid Jaya–Lion mathematical approach

This paper intends to propose a new image compression technique, which is processed under various sequences of progressions. The initial process is the image segmentation and is handled by Adaptive Active Contour Model (ACM), which divides or segments the image into two regions: ROI (Region of Interest) and non-ROI. In this, the adaptiveness of this ACM is influenced with the concept of optimization. JPEG-LS algorithm is used to handle the ROI regions, and the wavelet-based lossy compression algorithm is used to handle the non-ROI region. The result of both JPEG-LS algorithm and wavelet-based compression model is combined in terms of bit-stream combination and outputs the compressed image. Subsequently, the compressed image is subjected for image decompression, which will be the reverse process of compression. This will include the bit-stream separation, which is then separately processed under both the JPEG-LS decoding and wavelet-based decomposition for attaining the ROI and non-ROI regions. Finally, the original image is attained precisely. Further, the major contribution of this work falls in the adaptiveness under optimization. The weighting factor and maximum iteration in ACM are optimally selected and for this a new hybrid optimization model that hybridizes the concept of Jaya Algorithm and Lion Algorithm is introduced.

Cloud-based Reversible Dynamic Secure Steganography Model for embedding pathological report in medical images

ABSTRACT Over past decades, several research works have been published in the direction of hiding confidential data that includes only the patients personal details in medical images. The medical images and respective pathological reports are stored separately in the storage device. Storing medical images and pathological reports separately occupy more storage compared to storing pathological reports Stego in medical images. This research identified pixel space available in the medical image for storing other relevant secret information. In this technique, a new algorithm is proposed for generating secret keys. The secret keys are utilized to segment the medical image into five regions: (i) one Region of Interest (ROI) sub-image and (ii) four non-Region of Interest sub-images. From the four non-Region of Interest sub-images, a particular non-ROI region sub-image is randomly selected from the secret key matrix. The pathological report is embedded into the preprocessed selected non-ROI region sub-image of the medical image and generated the Stego medical image. The Stego medical image and secret key are communicated using various network communication applications to the user for deStego the original X-ray image and pathological report at the user end. The research work confirmed the quality of the medical image using MSE and PSNR values.

MICCS: A Novel Framework for Medical Image Compression Using Compressive Sensing

The vision of some particular applications such as robot-guided remote surgery where the image of a patient body will need to be captured by the smart visual sensor and to be sent on a real-time basis through a network of high bandwidth but yet limited. The particular problem considered for the study is to develop a mechanism of a hybrid approach of compression where the Region-of-Interest (ROI) should be compressed with lossless compression techniques and Non-ROI should be compressed with Compressive Sensing (CS) techniques. So the challenge is gaining equal image quality for both ROI and Non-ROI while overcoming optimized dimension reduction by sparsity into Non-ROI. It is essential to retain acceptable visual quality to Non-ROI compressed region to obtain a better reconstructed image. This step could bridge the trade-off between image quality and traffic load. The study outcomes were compared with traditional hybrid compression methods to find that proposed method achieves better compression performance as compared to conventional hybrid compression techniques on the performances parameters e.g. PSNR, MSE, and Compression Ratio.

HEMS: Hierarchical Exemplar-Based Matching-Synthesis for Object-Aware Image Reconstruction

Motivated by the attention on salient objects, conventional region-of-interest (ROI)-based image coding approaches attempt to assign more bits to ROIs and fewer bits to other regions. Thus, the perceptual quality of salient object regions is improved by sacrificing the quality of non-ROI regions with unpleasant artifacts. To address this issue, we concentrate on the efficient compression of object-centered images by encoding salient objects and background features separately. To fully recover the object and background, we propose a hierarchical exemplar-based matching-synthesis (HEMS) approach to reconstruct the image from exemplars. In the proposed framework, once the salient object regions are encoded, only the quantized color features and local descriptors of the background are kept, achieving bit-rate reduction. To make it possible and practical to reconstruct background regions, the hierarchical framework is designed in three layers, including relevant image search, patch candidates matching, and distortion optimized image synthesis. In the hierarchical framework, firstly, image search from an external database returns relevant images, limiting the search space to a feasible number of patch candidates. Secondly, patches are matched by color features to select the appropriate candidates. Finally, the distortion optimized image synthesis further makes it possible to automatically choose the most suitable texture sample, and seamlessly reconstruct the image. Compared to the conventional ROI-based image coding schemes, the proposed approach can achieve better visual quality on both ROI and background regions.

INTELLIGENT DETECTION AND CLASSIFICATION OF MICROCALCIFICATION IN COMPRESSED MAMMOGRAM IMAGE

The main contribution of this article is introducing an intelligent classifier to distinguish between benign and malignant areas of micro-calcification in companded mammogram image which is not proved or addressed elsewhere. This method does not require any manual processing technique for classification, thus it can be assimilated for identifying benign and malignant areas in intelligent way. Moreover it gives good classification responses for compressed mammogram image. The goal of the proposed method is twofold: one is to preserve the details in Region of Interest (ROI) at low bit rate without affecting the diagnostic related information and second is to classify and segment the micro-calcification area in reconstructed mammogram image with high accuracy. The prime contribution of this work is that details of ROI and Non-ROI regions extracted using multi-wavelet transform are coded at variable bit rate using proposed Region Based Set Partitioning in Hierarchical Trees (RBSPIHT) before storing or transmitting the image. Image reconstructed during retrieval or at the receiving end is preprocessed to remove the channel noise and to enhance the diagnostic contrast information. Then the preprocessed image is classified as normal or abnormal (benign or malignant) using Probabilistic neural network. Segmentation of cancerous region is done using Fuzzy C-means Clustering (FCC) algorithm and the cancerous area is computed. The experimental result shows that the proposed model performance is good at achieving high sensitivity of 97.27%, specificity of 94.38% at an average compression rate and Peak Signal to Noise Ratio (PSNR) of 0.5bpp and 58dB respectively.

Link-Aware Reconfigurable Point-to-Point Video Streaming for Mobile Devices

Even though people of all social standings use current mobile devices in the wide spectrum of purpose from entertainment tools to communication means, some issues with real-time video streaming in hostile wireless environment still exist. In this article, we introduce CoSA , a link-aware real-time video streaming system for mobile devices. The proposed system utilizes a 3D camera to distinguish the region of importance (ROI) and non-ROI region within the video frame. Based on the link-state feedback from the receiver, the proposed system allocates a higher bandwidth for the region that is classified as ROI and a lower bandwidth for non-ROI in the video stream by reducing the video's bit rate. We implemented CoSA in a real test-bed where the IEEE 802.11 is employed as a medium for wireless networking. Furthermore, we verified the effectiveness of the proposed system by conducting a thorough empirical study. The results indicate that the proposed system enables real-time video streaming while maintaining a consistent visual quality by dynamically reconfiguring video coding parameters according to the link quality.

An improved medical image compression technique with lossless region of interest

Hospitals and medical centers produce an enormous amount of digital medical images every day, which are used for different purposes such as surgical and diagnostic plans. The ease of storing and transmission of digital medical images is a boon to patients and medical professionals. Due to the large volume of images, image compression is required to reduce the redundancies in image and represents it in shorter manner for efficient archiving and transmission of images. However, compressing digital medical images as the region of interest for diagnosis is generally small when compared to the whole image. Lossless compression techniques compress without loss of any information but have low compression rate, and lossy compression techniques can compress at high compression ratio but with a slight loss of data. Using lossless techniques in medical image does not give enough advantage in transmission and storage and lossy techniques may lose crucial data required for diagnosis. In this paper, an improved medical image compression technique based on region of interest (ROI) is proposed to maximize compression. The image is firstly divided into two parts: ROI regions and non-ROI regions. Lossless compression algorithm is then applied to the marked area of ROI, and image restoration technique and the wavelet-based lossy compression algorithm are utilized to the other area of the image. Finally, a set of experiments is designed to assess the effectiveness of the proposed compression method.

An Effective Selection of DCT and DWT Coefficients for an Adaptive Medical Image Compression Technique Using Multiple Kernel FCM

Over the last two decades, great developments have been made in image compression approaches driven by a growing demand for storage and transmission of visual information. However, a number of publications have demonstrated good results of the compressed domain approach to image analysis. Nevertheless, very little work has been carried out on ROI based compression. In this paper, we have proposed an adaptive approach to compress the image without lossless version using selection of DCT and DWT coefficients and MKFCM. Our proposed approach consists of three stages, (i) Region segmentation (ii) Image compression (iii) Image decompression. At first, the input medical image is segmented by ROI, Non-ROI and background using MKFCM. Subsequently, the ROI region compressed by DCT and SPIHT coding and Non-ROI region is compressed by DWT and Huffman coding. The non-relevant regions are directly converted to zero. From the compressed regions like as ROI, Non-ROI and background, finally we obtain compression ratio to evaluate the proposed approach. Then, in decompression stage, the original medical image is extracted using the devised procedure. We can also see that our proposed image compression approach have outperformed by having better compression ratio of 4.6446 when compared existing technique only achieved 4.4326

Region-of-interest determination and bit-rate conversion for H.264 video transcoding

Abstract This paper presents a video bit-rate transcoder for baseline profile in H.264/AVC standard to fit the available channel bandwidth for the client when transmitting video bit-streams via communication channels. To maintain visual quality for low bit-rate video efficiently, this study analyzes the decoded information in the transcoder and proposes a Bayesian theorem-based region-of-interest (ROI) determination algorithm. In addition, a curve fitting scheme is employed to find the models of video bit-rate conversion. The transcoded video will conform to the target bit-rate by re-quantization according to our proposed models. After integrating the ROI detection method and the bit-rate transcoding models, the ROI-based transcoder allocates more coding bits to ROI regions and reduces the complexity of the re-encoding procedure for non-ROI regions. Hence, it not only keeps the coding quality but improves the efficiency of the video transcoding for low target bit-rates and makes the real-time transcoding more practical. Experimental results show that the proposed framework gets significantly better visual quality.

Research on ROI Image Processing Technology of Teleoperation Construction Robot Based on Trinocular Stereo Vision

Digital image has a large quantity of image data and long time for transmitting. It affects the real-time of the teleoperation robot system. According to the basic principle of human eye identifying objects and image blurry processing, a new image processing method of simulating human eye range of interest (ROI) is proposed. The method uses the calibration algorithm of three-dimensional stereo target and the Gauss blurred principle. The non-ROI region is blurred to hierarchy for extracting the feature and measurement to finish the image processing tasks. The experimental results showed that the quality of the images was assured and the transmission time was shorted. The real-time of the teleoperation robot system was also guaranteed.

Interactive region of interest scalability for wavelet based scalable video coder

The current wavelet-based scalable video coder supports quality, spatial and temporal scalabilities required for recent multimedia applications. One of the key scalability required by the Joint Video Team (JVT) is Interactive Region of Interest (IROI) scalability. This paper proposes a technique to interactively extract ROI from scalable sub bit-streams. At the encoder, after sub-band decomposition the 3D wavelet tree is divided into N sub tree, each of these has spatial relevance in the original video, which can be decoded interactively. A generalized model for optimal value of N is proposed, that satisfies minimum requirement of the JVT about IROI support at reduced cost of the encoder. The ROI request from decoder along with resolution and bandwidth are mapped to that in the sub-band domain and respective sub-bit-streams are identified. The extractor assigns more bandwidth to ROI and remaining to non-ROI regions. Hence the decoder reconstructs the video with highest quality at the ROI. The proposed IROI functionality enhances the scalability of video coding by additional dimension.