Image-stitching (or) mosaicing is considered an active research-topic with numerous use-cases in computer-vision, AR/VR, computer-graphics domains, but maintaining homogeneity among the input image sequences during th...
详细信息
Image-stitching (or) mosaicing is considered an active research-topic with numerous use-cases in computer-vision, AR/VR, computer-graphics domains, but maintaining homogeneity among the input image sequences during the stitching/mosaicing process is considered as a primary-limitation & major-disadvantage. To tackle these limitations, this article has introduced a robust and reliable image stitching methodology (l,r-Stitch Unit), which considers multiple non-homogeneous image sequences as input to generate a reliable panoramically stitched wide view as the final output. The l,r-Stitch Unit further consists of a pre-processing, post-processing sub-modules & a l,r-PanoED-network, where each sub-module is a robust ensemble of several deep-learning, computer-vision & image-handling techniques. This article has also introduced a novel convolutional-encoder-decoder deep-neural-network (l,r-PanoED-network) with a unique split-encoding-network methodology, to stitch non-coherent input left, right stereo image pairs. The encoder-network of the proposed l,r-PanoED extracts semantically rich deep-feature-maps from the input to stitch/map them into a wide-panoramic domain, the feature-extraction & feature-mapping operations are performed simultaneously in the l,r-PanoED's encoder-network based on the split-encoding-network methodology. The decoder-network of l,r-PanoED adaptively reconstructs the output panoramic-view from the encoder networks' bottle-neck feature-maps. The proposed l,r-Stitch Unit has been rigorously benchmarked with alternative image-stitching methodologies on our custom-built traffic dataset and several other public-datasets. Multiple evaluation metrics (SSIM, PSNR, MSE, L-alpha,L-beta,L-gamma,L- FM-rate, Average-latency-time) & wild-Conditions (rotational/color/intensity variances, noise, etc) were considered during the benchmarking analysis, and based on the results, our proposed method has outperformed among other image-stitching methodologies and has prov
Background: Acute ischemic stroke is one of the leading death causes. Delineating stoke infarct core in medical images plays a critical role in optimal stroke treatment selection. However, accurate estimation of infar...
详细信息
Background: Acute ischemic stroke is one of the leading death causes. Delineating stoke infarct core in medical images plays a critical role in optimal stroke treatment selection. However, accurate estimation of infarct core still remains challenging because of 1) the large shape and location variation of infarct cores;2) the complex relationships between perfusion parameters and final tissue outcome. Methods: We develop an encoder-decoder based semantic model, i.e., Ischemic Stroke Prediction Network (ISP-Net), to predict infarct core after thrombolysis treatment on CT perfusion (CTP) maps. Features of native CTP, CBF (Cerebral Blood Flow), CBV (Cerebral Blood Volume), MTT (Mean Transit Time), Tmax are generated and fused with five-path convolutions for comprehensive analysis. A multi-scale atrous convolution (MSAC) block is firstly put forward as the enriched high-level feature extractor in ISP-Net to improve prediction accuracy. A retrospective dataset which is collected from multiple stroke centers is used to evaluate the performance of ISP-Net. The gold standard infarct cores are delineated on the follow-up scans, i.e., non-contrast CT (NCCT) or MRI diffusion-weighted image (DWI). Results: In clinical dataset crossvalidation, we achieve mean Dice Similarity Coefficient (DSC) of 0.801, precision of 81.3%, sensitivity of 79.5%, specificity of 99.5%, Area Under Curve (AUC) of 0.721. Our approach yields better outcomes than several advanced deep learning methods, i.e., Deeplab V3, U-Net++, CE-Net, X-Net and Non-local U-Net, demonstrating the promising performance in infarct core prediction. No significant difference of the prediction error is shown for the patients with follow-up NCCT and follow-up DWI (P>0.05). Conclusion: This study provides an approach for fast and accurate stroke infarct core estimation. We anticipate the prediction results of ISP-Net could offer assistance to the physicians in the thrombolysis or thrombectomy therapy selection. (C) 2022 Publis
In Korea, strawberry producers lack efficient and precise yield forecasts, which would allow them to deploy optimal manpower, equipment, and other resources for harvesting, shipping, and marketing. Reliable estimation...
详细信息
ISBN:
(纸本)9788993215212
In Korea, strawberry producers lack efficient and precise yield forecasts, which would allow them to deploy optimal manpower, equipment, and other resources for harvesting, shipping, and marketing. Reliable estimation of the quantity of strawberry fruit with respect to their ripeness level is critical for forecasting the upcoming strawberry production. Typically, the quantity and ripeness of fruits are estimated manually, which is labor-intensive and time-consuming. In this case, automated yield prediction based on robotic agriculture is a realistic option. We provide in this study an automated strawberry fruit recognition and counting system for accurate and reliable yield prediction. This paper proposes a unique neural network training approach for strawberry fruit counting and ripeness detection that combines semantic graphics for data annotation with a fully convolutional neural network (FCN). Semantic graphics, the suggested data annotation approach, is straightforward to apply, and the desired targets can be quickly tagged with little effort. Moreover, the proposed FCN is an enhanced encoder-decoder network designed specifically for efficient learning of semantic graphics. Quantitative analysis of proposed algorithm showed 4.47% increase in detection accuracy over prior techniques while running at higher frames per second.
MRI reconstruction is one of the critical processes of MRI machines, along with the acquisition. Due to a slow processing time of signal acquiring, parallel imaging and reconstruction techniques are applied for accele...
详细信息
MRI reconstruction is one of the critical processes of MRI machines, along with the acquisition. Due to a slow processing time of signal acquiring, parallel imaging and reconstruction techniques are applied for acceleration. To accelerate the acquisition process, fewer raw data are sampled simultaneously with all RF coils acquisition. Then, the reconstruction uses under-sampled data from all RF coils to restore the final MR image that resembles the fully sampled MR image. These processes have been a traditional procedure inside the MRI system since the invention of the multi-coils MRI machine. This paper proposes the deep learning technique with a lightweight network. The deep neural network is capable of generating the high-quality reconstructed MR image with a high peak signal-to-noise ratio (PSNR). This also opens a high acceleration factor for MR data acquisition. The lightweight network is called Multi-Level Pooling encoder-decoder Net (MLPED Net). The proposed network outperforms the traditional encoder-decoder networks on 4-fold acceleration with a significant margin on every evaluation metric. The network can be trained end-to-end, and it is a lightweight structure that can reduce training time significantly. Experimental results are based on a publicly available MRI Knee dataset from the fastMRl competition.
Identification of burn depth with sufficient accuracy is a challenging problem. This paper presents a deep convolutional neural network to classify burn depth based on altered tissue morphology of burned skin manifest...
详细信息
Identification of burn depth with sufficient accuracy is a challenging problem. This paper presents a deep convolutional neural network to classify burn depth based on altered tissue morphology of burned skin manifested as texture patterns in the ultrasound images. The network first learns a low-dimensional manifold of the unburned skin images using an encoder-decoder architecture that reconstructs it from ultrasound images of burned skin. The encoder is then re-trained to classify burn depths. The encoder-decoder network is trained using a dataset comprised of B-mode ultrasound images of unburned and burned ex vivo porcine skin samples. The classifier is developed using B-mode images of burned in situ skin samples obtained from freshly euthanized postmortem pigs. The performance metrics obtained from 20-fold cross-validation show that the model can identify deeppartial thickness burns, which is the most difficult to diagnose clinically, with 99% accuracy, 98% sensitivity, and 100% specificity. The diagnostic accuracy of the classifier is further illustrated by the high area under the curve values of 0.99 and 0.95, respectively, for the receiver operating characteristic and precision-recall curves. A post hoc explanation indicates that the classifier activates the discriminative textural features in the B-mode images for burn classification. The proposed model has the potential for clinical utility in assisting the clinical assessment of burn depths using a widely available clinical imaging device.
Background subtraction or change detection aims to segment the moving object from the background, and it has become a vital task in many video analysis and surveillance systems. There are different approaches were pro...
详细信息
ISBN:
(纸本)9781728151632
Background subtraction or change detection aims to segment the moving object from the background, and it has become a vital task in many video analysis and surveillance systems. There are different approaches were proposed to solve this problem effectively. In the past, all background subtraction methods use low-level handcraft features such as raw color space or local pattern. Recently, there are many background subtraction methods based on a convolutional neural network that have demonstrated astonishing results. Therefore, in this paper, we introduce an end-to-end convolutional neural network for background subtraction. The network is based on the idea of encoder-decoder deep neural network. In the encoder part, deep features from target frame and reference frame are extracted and compared to measure the difference. Then the decoder converts these features from an encoder to into segmentation map with fine detail. The experimental results tested on CDNet 2014 dataset show that the proposed structure archives the state-of-the-art performance.
暂无评论