- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) - Vancouver, BC, Canada (2018.8.29-2018.8.31)] 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) - A Cloud Detection Algorithm for Remote Sensing Images Using Fully Convolutional Neural Networks
摘要： This paper presents a deep-learning based framework for addressing the problem of accurate cloud detection in remote sensing images. This framework benefits from a Fully Convolutional Neural Network (FCN), which is capable of pixel-level labeling of cloud regions in a Landsat 8 image. Also, a gradient-based identification approach is proposed to identify and exclude regions of snow/ice in the ground truths of the training set. We show that using the hybrid of the two methods (threshold-based and deep-learning) improves the performance of the cloud identification process without the need to manually correct automatically generated ground truths. In average the Jaccard index and recall measure are improved by 4.36% and 3.62%, respectively.
关键词： deep-learning,Landsat 8,FCN,image segmentation,U-Net,remote sensing,CNN,Cloud detection
更新于2025-09-09 09:28:46
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Near InfraRed Imagery Colorization
摘要： This paper proposes a stacked conditional Generative Adversarial Network-based method for Near InfraRed (NIR) imagery colorization. We propose a variant architecture of Generative Adversarial Network (GAN) that uses multiple loss functions over a conditional probabilistic generative model. We show that this new architecture/loss-function yields better generalization and representation of the generated colored IR images. The proposed approach is evaluated on a large test dataset and compared to recent state of art methods using standard metrics.
关键词： Convolutional Neural Networks (CNN),Infrared Imagery colorization,Generative Adversarial Network (GAN)
更新于2025-09-04 15:30:14
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - RelationNet: Learning Deep-Aligned Representation for Semantic Image Segmentation
摘要： Semantic image segmentation, which assigns labels in pixel level, plays a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning. However, one central problem of these methods is that deep convolutional neural network gives little consideration to the correlation among pixels. To handle this issue, in this paper, we propose a novel deep neural network named RelationNet, which utilizes CNN and RNN to aggregate context information. Besides, a spatial correlation loss is applied to train RelationNet to align features of spatial pixels belonging to same category. Importantly, since it is expensive to obtain pixel-wise annotations, we exploit a new training method to combine the coarsely and finely labeled data. Experiments show the detailed improvements of each proposal. Experimental results demonstrate the effectiveness of our proposed method to the problem of semantic image segmentation, which obtains state-of-the-art performance on the Cityscapes benchmark and Pascal Context dataset.
关键词： Spatial correlation loss,CNN,Semantic image segmentation,RNN,Deep learning,RelationNet
更新于2025-09-04 15:30:14
-
DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering
摘要： Nonlinear electromagnetic (EM) inverse scattering is a quantitative and super-resolution imaging technique, in which more realistic interactions between the internal structure of scene and EM wavefield are taken into account in the imaging procedure, in contrast to conventional tomography. However, it poses important challenges arising from its intrinsic strong nonlinearity, ill-posedness, and expensive computation costs. To tackle these difficulties, we, for the first time to our best knowledge, exploit a connection between the deep neural network (DNN) architecture and the iterative method of nonlinear EM inverse scattering. This enables the development of a novel DNN-based methodology for nonlinear EM inverse problems (termed here DeepNIS). The proposed DeepNIS consists of a cascade of multi-layer complex-valued residual convolutional neural network (CNN) modules. We numerically and experimentally demonstrate that the DeepNIS outperforms conventional nonlinear inverse scattering methods in terms of both the image quality and computational time. We show that DeepNIS can learn a general model approximating the underlying EM inverse scattering system. It is expected that the DeepNIS will serve as powerful tool in treating highly nonlinear EM inverse scattering problems over different frequency bands, which are extremely hard and impractical to solve using conventional inverse scattering methods.
关键词： Complex-valued Residual CNN,Nonlinear Inverse Scattering,Convolutional Neural Network
更新于2025-09-04 15:30:14
-
Recognition of incorrect assembly of internal components by X-ray CT and deep learning
摘要： It is important to make sure that all components of a complex product are assembled correctly. Because in many cases, some components are enclosed in an opaque shell, x-ray imaging is currently used to extract their characteristics and match prior-known ones. However, x-ray imaging is not very robust in recognition of incorrect assembly of internal components, because some of them may overlap. To solve this problem, we propose a new method to detect internal component assembly fault, by x-ray computed tomography (CT) and convolutional neural network (CNN). Multi-view imaging is implemented by mechanical rotation of a product in respect with an x-ray CT machine to capture multiple projection information on each internal component, and then the component can be recognized by making use of deep learning. A CNN model is trained to classify the internal components and give the coordinates of each component. Based on the CNN recognition results and the CT projection sinogram, a projection corresponding to a reference in a projection data set of a standard product can be found. By comparing and matching the locations of each component, transposition or dislocation can be recognized. Both simulation and experiment show that this new method can effectively identify incorrect assembly, missing assembly, transposition, and other problems, improving the product quality.
关键词： Projection sinogram,Assembly recognition,Convolution neural network (CNN),x-ray CT
更新于2025-09-04 15:30:14
-
RGB-D static gesture recognition based on convolutional neural network
摘要： In the area of human–computer interaction (HCI) and computer vision, gesture recognition has always been a research hotspot. With the appearance of depth camera, gesture recognition using RGB-D camera has gradually become mainstream in this field. However, how to effectively use depth information to construct a robust gesture recognition system is still a problem. In this paper, an RGB-D static gesture recognition method based on fine-tuning Inception V3 is proposed, which can eliminate the steps of gesture segmentation and feature extraction in traditional algorithms. Compared with general CNN algorithms, the authors adopt a two-stage training strategy to fine-tune the model. This method sets a feature concatenate layer of RGB and depth images in the CNN structure, using depth information to promote the performance of gesture recognition. Finally, on the American Sign Language (ASL) Recognition dataset, the authors compared their method with other traditional machine learning methods, CNN algorithms, and the RGB input only method. Among three groups of comparative experiments, the authors’ method reached the highest accuracy of 91.35%, reaching the state-of-the-art currently on ASL dataset.
关键词： RGB-D,Inception V3,gesture recognition,human–computer interaction,CNN
更新于2025-09-04 15:30:14
-
[IEEE 2018 IEEE International Conference on Intelligent Transportation Systems (ITSC) - Maui, HI, USA (2018.11.4-2018.11.7)] 2018 21st International Conference on Intelligent Transportation Systems (ITSC) - Multimodal CNN Pedestrian Classification: A Study on Combining LIDAR and Camera Data
摘要： This paper presents a study on pedestrian classification based on deep learning using data from a monocular camera and a 3D LIDAR sensor, separately and in combination. Early and late multi-modal sensor fusion approaches are revisited and compared in terms of classification performance. The problem of pedestrian classification finds applications in advanced driver assistance system (ADAS) and autonomous driving, and it has regained particular attention recently because, among other reasons, safety involving self-driving vehicles. Convolutional Neural Networks (CNN) is used in this work as classifier in distinct situations: having a single sensor data as input, and by combining data from both sensors in the CNN input layer. Range (distance) and intensity (reflectance) data from LIDAR are considered as separate channels, where data from the LIDAR sensor is feed to the CNN in the form of dense maps, as the result of sensor coordinate transformation and spatial filtering; this allows a direct implementation of the same CNN-based approach on both sensors data. In terms of late-fusion, the outputs from individual CNNs are combined by means of learning and non-learning approaches. Pedestrian classification is evaluated on a 'binary classification' dataset created from the KITTI Vision Benchmark Suite, and results are shown for each sensor-modality individually, and for the fusion strategies.
关键词： pedestrian classification,camera,deep learning,sensor fusion,LIDAR,CNN
更新于2025-09-04 15:30:14
-
[IEEE 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Guangzhou, China (2018.10.8-2018.10.12)] 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - R-PCNN Method to Rapidly Detect Objects on THz Images in Human Body Security Checks
摘要： Terahertz human body security images have low resolution and a low signal-to-noise ratio. In the traditional method, image segmentation, positioning, and identification are applied to detect objects carried by humans in the THz images. However, it is difficult to satisfy the requirements of detection accuracy and speed with this approach. The current research presents a faster detection framework (R-PCNN) combining the preprocessing and structure optimization of Faster R-CNN. The experiment results show that this method can effectively improve the accuracy and speed of object detection in human body THz images. A detection accuracy of 84.5% can be achieved in dense flow scenes, with an average detection time of less than 20 milliseconds for each image.
关键词： Image enhancement,Terahertz image,Faster R-CNN,Human body security check,Object detection
更新于2025-09-04 15:30:14
-
[IEEE 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Guangzhou, China (2018.10.8-2018.10.12)] 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Automatic Detection of Optic Disc in Retina Image Using CNN and CRF
摘要： In this paper, we propose an optic disc detection method based on convolutional neural network (CNN) and conditional random field (CRF). We pre-classify the color fundus retinal images by CNN, and construct first-order potential functions of CRF. Then the linear combination of Gaussian kernel functions is used to construct the second-order potential function of CRF model. Finally, regional restricts method is applied that analyzes the consistency of the connected region labels and corrects the labels of each pixel by calculating the posterior probability mean of the super-pixel region. The combination of CNN and CRF not only uses the pixel’s intrinsic features, but also the spatial context information to make the detection more accurate. The added constraints further preserve the local information of the target and infer the entire model through a mean field approximation algorithm. This improves the accuracy of detection of optic discs in color fundus retina images. Experiments show that the CNN-CRF model performs better than the existing algorithms for the optic disc detection in pathological images. It provides an effective solution to optic disc detection problem by inhibiting its vulnerability to noise interference such as peripheral lesions and pigmentation. We compare our results to recent published results on several retina databases and show that the CNN-CRF model outperforms the current state-of-the-art methods.
关键词： CRF,Optic Disc,Automatic Recognition,CNN
更新于2025-09-04 15:30:14
-
[IEEE 2018 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) - Bangkok, Thailand (2018.10.21-2018.10.24)] 2018 International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) - Multi-Scale Deep Neural Network for Mitosis Detection in Histological Images
摘要： Mitotic figure detection in breast cancer images plays an important role to measure aggressiveness of the cancer tumor. Currently, in clinic environment the pathologist visualized the multiple high power fields (HPFs) on a glass slide under super microscope which is an extremely tedious and time consuming process. Development of the automatic mitotic detection methods is need of time, however it also bears, scale invariance, deficiency of data, improper image staining and sample class unbalanced dilemma. These limitations are however; prohibit the automatic histopathology image analysis to be applied in clinical practice. In this paper, an automatic domain agnostic deep multi-scale fused fully convolutional neural network (MFF-CNN) is presented to detect mitoses in Hematoxylin and eosin (H&E) images. The intended model fuses the multi-level and multi-scale features and context information for accurate mitotic count and in training phase multi-step fine-tuning strategy is used to reduce the over-fitting. Moreover, the training image samples efficiently built by stain normalized the poorly stained (H&E) images and by applying an automatic strategy. Preliminarily selection validation on the public MITOS-ATYPIA-14 challenge dataset, demonstrate the efficiency of proposed work. The proposed method achieves better performance in term of detection accuracy with an acceptable detection speed compared to other state-of-the-art designs.
关键词： Multi-scale feature,CNN,Mitosis detection,Breast cancer,Stain-normalization
更新于2025-09-04 15:30:14