- Browse by Subject
Browsing by Subject "Feature extraction"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item A two-branch multi-scale residual attention network for single image super-resolution in remote sensing imagery(IEEE, 2024) Patnaik, Allen; Bhuyan, Manas K.; MacDorman, Karl F.High-resolution remote sensing imagery finds applications in diverse fields, such as land-use mapping, crop planning, and disaster surveillance. To offer detailed and precise insights, reconstructing edges, textures, and other features is crucial. Despite recent advances in detail enhancement through deep learning, disparities between original and reconstructed images persist. To address this challenge, we propose a two-branch multiscale residual attention network for single-image super-resolution reconstruction. The network gathers complex information about input images from two branches with convolution layers of different kernel sizes. The two branches extract both low-level and high-level features from the input image. The network incorporates multiscale efficient channel attention and spatial attention blocks to capture channel and spatial dependencies in the feature maps. This results in more discriminative features and more accurate predictions. Moreover, residual modules with skip connections can help to overcome the vanishing gradient problem. We trained the proposed model on the WHU-RS19 dataset, collated from Google Earth satellite imagery, and validated it on the UC Merced, RSSCN7, AID, and real-world satellite datasets. The experimental results show that our network uses features at different levels of detail more effectively than state-of-the-art models.Item Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation(IEEE, 2021) Jing, Taotao; Ding, Zhengming; Electrical and Computer Engineering, School of Engineering and TechnologyUnsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. Conventional UDA concentrates on extracting domain-invariant features through deep adversarial networks. However, most of them seek to match the different domain feature distributions, without considering the task-specific decision boundaries across various classes. In this paper, we propose a novel Adversarial Dual Distinct Classifiers Network (AD 2 CN) to align the source and target domain data distribution simultaneously with matching task-specific category boundaries. To be specific, a domain-invariant feature generator is exploited to embed the source and target data into a latent common space with the guidance of discriminative cross-domain alignment. Moreover, we naturally design two different structure classifiers to identify the unlabeled target samples over the supervision of the labeled source domain data. Such dual distinct classifiers with various architectures can capture diverse knowledge of the target data structure from different perspectives. Extensive experimental results on several cross-domain visual benchmarks prove the model's effectiveness by comparing it with other state-of-the-art UDA.Item Automated Microaneurysms Detection in Retinal Images Using Radon Transform and Supervised Learning: Application to Mass Screening of Diabetic Retinopathy(IEEE, 2021) Tavakoli, Meysam; Mehdizadeh, Alireza; Aghayan, Afshin; Shahri, Reza Pourreza; Ellis, Tim; Dehmeshki, Jamshid; Physics, School of ScienceDetection of red lesions in color retinal images is a critical step to prevent the development of vision loss and blindness associated with diabetic retinopathy (DR). Microaneurysms (MAs) are the most frequently observed and are usually the first lesions to appear as a consequence of DR. Therefore, their detection is necessary for mass screening of DR. However, detecting these lesions is a challenging task because of the low image contrast, and the wide variation of imaging conditions. Recently, the emergence of computer-aided diagnosis systems offers promising approaches to detect these lesions for diagnostic purposes. In this paper we focus on developing unsupervised and supervised techniques to cope intelligently with the MAs detection problem. In the first step, the retinal images are preprocessed to remove background variation in order to achieve a high level of accuracy in the detection. In the main processing step, important landmarks such as the optic nerve head and retinal vessels are detected and masked using the Radon transform (RT) and multi-overlapping windows. Finally, the MAs are detected and numbered by using a combination of RT and a supervised support vector machine classifier. The method was tested on three publicly available datasets and a local database comprising a total of 749 images. Detection performance was evaluated using sensitivity, specificity, and FROC analysis. From the image analysis viewpoint, DR was detected with a sensitivity of 100% and a specificity of 93% on average across all of these databases. Moreover, from lesion-based analysis the proposed approach detected the MAs with sensitivity of 95.7% with an average of 7 false positives per image. These results compare favourably with the best of the published results to date.Item Modeling Spatiotemporal Pedestrian-Environment Interactions for Predicting Pedestrian Crossing Intention from the Ego-View(2021-08) Chen, Chen (Tina); Li, Lingxi; Tian, Renran; Lauren, Christopher; Ding, ZhengmingFor pedestrians and autonomous vehicles (AVs) to co-exist harmoniously and safely in the real-world, AVs will need to not only react to pedestrian actions, but also anticipate their intentions. In this thesis, we propose to use rich visual and pedestrian-environment interaction features to improve pedestrian crossing intention prediction from the ego-view.We do so by combining visual feature extraction, graph modeling of scene objects and their relationships, and feature encoding as comprehensive inputs for an LSTM encoder-decoder network. Pedestrians react and make decisions based on their surrounding environment, and the behaviors of other road users around them. The human-human social relationship has al-ready been explored for pedestrian trajectory prediction from the bird’s eye view in stationary cameras. However, context and pedestrian-environment relationships are often missing incurrent research into pedestrian trajectory, and intention prediction from the ego-view. To map the pedestrian’s relationship to its surrounding objects we use a star graph with the pedestrian in the center connected to all other road objects/agents in the scene. The pedestrian and road objects/agents are represented in the graph through visual features extracted using state of the art deep learning algorithms. We use graph convolutional networks, and graph autoencoders to encode the star graphs in a lower dimension. Using the graph en-codings, pedestrian bounding boxes, and human pose estimation, we propose a novel model that predicts pedestrian crossing intention using not only the pedestrian’s action behaviors(bounding box and pose estimation), but also their relationship to their environment. Through tuning hyperparameters, and experimenting with different graph convolutions for our graph autoencoder, we are able to improve on the state of the art results. Our context-driven method is able to outperform current state of the art results on benchmark datasetPedestrian Intention Estimation (PIE). The state of the art is able to predict pedestrian crossing intention with a balanced accuracy (to account for dataset imbalance) score of 0.61, while our best performing model has a balanced accuracy score of 0.79. Our model especially outperforms in no crossing intention scenarios with an F1 score of 0.56 compared to the state of the art’s score of 0.36. Additionally, we also experiment with training the state of the art model and our model to predict pedestrian crossing action, and intention jointly. While jointly predicting crossing action does not help improve crossing intention prediction, it is an important distinction to make between predicting crossing action versus intention.Item Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence(IEEE, 2021) Chang, Wennan; Dang, Pengdao; Wan, Changlin; Lu, Xiaoyu; Fang, Yue; Zhao, Tong; Zang, Yong; Li, Bo; Zhang, Chi; Cao, Sha; Biostatistics, School of Public HealthIn this paper, we propose a Spatial Robust Mixture Regression model to investigate the relationship between a response variable and a set of explanatory variables over the spatial domain, assuming that the relationships may exhibit complex spatially dynamic patterns that cannot be captured by constant regression coefficients. Our method integrates the robust finite mixture Gaussian regression model with spatial constraints, to simultaneously handle the spatial non-stationarity, local homogeneity, and outlier contaminations. Compared with existing spatial regression models, our proposed model assumes the existence a few distinct regression models that are estimated based on observations that exhibit similar response-predictor relationships. As such, the proposed model not only accounts for non-stationarity in the spatial trend, but also clusters observations into a few distinct and homogenous groups. This provides an advantage on interpretation with a few stationary sub-processes identified that capture the predominant relationships between response and predictor variables. Moreover, the proposed method incorporates robust procedures to handle contaminations from both regression outliers and spatial outliers. By doing so, we robustly segment the spatial domain into distinct local regions with similar regression coefficients, and sporadic locations that are purely outliers. Rigorous statistical hypothesis testing procedure has been designed to test the significance of such segmentation. Experimental results on many synthetic and real-world datasets demonstrate the robustness, accuracy, and effectiveness of our proposed method, compared with other robust finite mixture regression, spatial regression and spatial segmentation methods.