In recent times, deep learning methods have been employed to learn anatomical and functional brain changes from high discriminative features extracted from neuroimaging data such as Magnetic Resonance Imaging (MRI) which can enhance the performance in the classification and early diagnosis of neurodegenerative diseases. However, features that exist between brain regions that are farther apart are usually not captured by most state-of-the-art deep learning methods. Thus, an effective and robust model for the extraction of high-dimensional descriptive features especially from brain MRI remains an open challenge. In this paper, we investigate the applicability of an enhanced 3D Residual Network (ResNet) for the extraction of high-dimensional descriptive features for an improved classification of neurodegenerative disease using MRI scans. In particular, we enhanced the ResNet-18 by using a dilated convolutional layer instead of the typical convolution layer to expand the receptive field for effective feature extraction and an attention mechanism to the residual blocks to help focus on the relevant extracted features for improved classification. Our proposed method was evaluated on MRI images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Three MRI scan groups were considered: Alzheimer’s Disease (AD), Mild Cognitive Impairment (MCI), and Normal Cognitive (NC). Meanwhile, a three-binary classification task was developed (AD vs. NC, AD vs. MCI, and NC vs. MCI) to test the efficacy of our proposed model. The accuracy of our proposed model for each binary task is 92.12%, 74.07%, and 87.16%, respectively. We further compared the robustness of our proposed model to two state-of-the-art architectures and our model performed better due to its ability to extract discriminative features from the MRI data relevant for the classification tasks. Thus, revealing the effectiveness of our proposed method on the MRI scans.
Semantic segmentation on medical Computed Tomography (CT) images is of great significance to research and clinical diagnosis. However, methods based on neural network have competitive advantages for segmentation of dental CT images. In this paper, a 3D multi-feature fusion method for tooth segmentation is proposed. In order to obtain the body space of the data, first of all, the dental CT training set is compressed in NII format, and the body space data is processed; then the proposed 3D convolution network is used to train the data, extract the feature vectors, and obtain the probability distribution; to handle the situation that 3D neural network always leads to fuzzy boundary and unclear topology, the new CRF algorithm is used to refine the probability distribution which removes the redundant information generated by the neural network model, and makes the segmentation results more accurate. Compared with diverse contemporary segmentation algorithms, the effectiveness and superiority of our proposed method are verified, proving the conclusion that the supervision mechanism, neural network model components, and optimization proposed methods can improve the accuracy of tooth segmentation is reliable and valid.
Research on characteristics of helicopter rotor blade tip vortex (BTV) is one of the key elements for helicopter rotor aerodynamic characteristics research. The existing traditional computational fluid dynamics (CFD) based detection methods of vortex core area in the flow field mainly use points or lines in the flow field for calculation. However, the traditional CFD-based model is complex, huge computational cost and without effective vortex core model. So the manual analysis will be necessary in some scenarios to simplify the work of vortex detection, such as vortex region detection for helicopter rotor BTV in domestic. In order to decrease the workload of manual analysis, we draw on the advanced research results in the field of computer vision and machine learning, especially target detection, and firstly propose a vortex region detection method in blade tip vortex based on You Only Look Once (YOLO) network. First of all, the vortex region is marked in flow field images under the guidance of domain experts to construct the vortex data set. Secondly, we propose an improved model based on yolo v3-tiny. Finally, the self-built vortex data set is used to train models. Experiments show that the CNN-based method has better result than traditional methods.
Word embedding have been used in numerous Natural Language Processing and Machine Learning tasks. However, it is a high-dimensional vector field that propagate stereotypes to software applications. Its current debiasing frameworks do not completely capture its embedded patterns. In this paper, we propose deb2viz, a visual debiasing approach that explores and manipulates the high-dimensional patterns of word embedding field. First, we partition this vector field into interrelated low-dimensional subspaces to equalize and neutralize distances between gender-definitional and gender-neutral words. To further reduce gender bias, we update the distances of appropriate nearest neighbors for gender-neutral words to be arbitrarily close. Experimental results on several benchmark standards show the competitiveness of our proposed method in mitigating bias within pre-trained word2vec embedding model.
Pedestrian detection (PD) is an important application domain in computer vision and pattern recognition. Conventional PD in real life scene is usually based on a fixed camera, which can detect and track the pedestrians in the monitoring region. However, when the pedestrian leaves the visible area of the fixed camera, it is usually difficult, if not impossible, to monitor the pedestrian. In response to the limitations of the conventional pedestrian detection application scenarios, a four-rotor unmanned aerial vehicle (UAV) system equipped with a high-definition (HD) camera is designed and implemented to detect human targets. Considering the size of human body in aerial image is small and easily to be occluded, we draw on the advanced research results in the field of target detection and propose a robust pedestrian detection method based on YOLO (You Only Look Once) network. The flow of the proposed approach is as follows. Firstly, the HD camera, which is installed on the monitoring UAV, is used for capturing images of the designated outdoor area. Secondly, image sequences are collected and processed using the airborne embedded NVIDIA Jason TX1 and Ubuntu as the core and operating system, respectively. Finally, YOLO is used to train the pedestrian classifier and perform the pedestrian detection. Experimental results show that our method has good detection results under the complicated conditions of detecting small-scale pedestrians and pedestrian occlusion.
Outdoor target tracking UAV (Unmanned Aerial Vehicle), which is a research hotspot in the field of computer vision and unmanned aerial system, needs robust target-tracking algorithms with good real-time performance, accurate position estimator of UAV and the corresponding control strategy of the system. In this paper, we designed an outdoor drone tracking system using PCA (Principal Component Analysis) face recognition algorithm and KCF (Kernel Correlation Filter) target tracking algorithm. Firstly, an image acquisition unit is constructed by using an on-board pan-and-tilt camera to capture an outdoor monitored area. Secondly, the PCA algorithm is used for face matching, then the tracking mode is automatically transferred when the expected face target is recognized. Finally, the target tracking is performed by the KCF algorithm. After that, the position error is calculated and sent to the flight control system through the MavLink protocol, thereby performing posture adjustment and completing the tracking and monitoring task. Experimental results show that the performance of outdoor target tracking flight robot is stable and reliable, which meets the requirements of outdoor target tracking and has a good application prospect.
We present a multiexposure image fusion method that can enhance details, yet effectively improve brightness in the final result. In addition, a valid weight measurement is developed to remove motion objects in dynamic scenes. During the fusion process, each source image is first decomposed into one low-pass sub-band and a series of high-pass directional sub-bands using the nonsubsampled contourlet transform. Then the blended sub-bands are constructed by weight maps of the source images. To preserve the details of source images and adjust brightness of final image, gain control maps are used for each fused sub-band. Experimental results demonstrate that the proposed method significantly outperforms the traditional methods in terms of both visual inspection and objective evaluation, especially in cases which the regions of interest are in dark areas.
In order to efficiently enhance the dark nighttime videos, the high-quality daytime information of the same scene is often introduced to help the enhancement. However, due to camera motion, the introduced daytime may not have exactly the same scene of the nighttime videos. Thus, the final fused moving objects may not produce reasonable results. In this paper, we make the following two contributions: 1. we propose a global motion estimation-based scheme to address the problem of scene differences between daytime and nighttime videos. 2. Based on this, we further propose an improved framework for nighttime video enhancement which can efficiently recover the unreasonable enhancement results due to scene differences. Experimental results show the effectiveness of the proposed algorithm.
In this paper, a novel image-based fusion video enhancement algorithm is proposed for night-time video surveillance applications by a combination of illumination fusion and based on moving objects fusion. The proposed algorithm fuses video frames from high quality day-time and night-time background with low quality night-time videos. For improving the perception quality of the moving objects, based on moving objects of region fusion method is proposed. Experimental results show the effectiveness of the proposed algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.