- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - High Resolution SAR Image Classification with Deeper Convolutional Neural Network
摘要： Deeper architectures are proven to be beneficial for the classification performance obviously in computer vision field. Inspired by this, deep CNNs are expected to make progress in the SAR target classification problem as well. However, it is hard to train deeper CNNs for SAR images. Such CNNs have millions of parameters to be determined in the network (for example the VGGNet has more than 130 million parameters), hence large-scale dataset is indispensable when training a deep CNN. But there is no large-scale annotated SAR target dataset, and data acquisition and annotation is much more costly for SAR images. With inadequate data, the network is easy to be overfitting. Several methods based on deep learning have been proposed for SAR image classifications, but they cannot get rid of the aforementioned data limitation of labelled SAR images. To solve this problem, this paper proposes a microarchitecture called CompressUnit (CU). With CU, we design a deeper CNN. Compared with the network with the fewest parameters for SAR image classification in literature so far, our network is 2X deeper with only about 10% of parameters. In this way, we get a deeper network with much fewer parameters. This network is easier to be trained with limited SAR data and is more likely to get rid of overfitting.
关键词： Deeper CNN,CompressUnit,SAR images
更新于2025-09-23 15:21:21
-
Road Segmentation Based on Hybrid Convolutional Network for High-Resolution Visible Remote Sensing Image
摘要： Road segmentation plays an important role in many applications, such as intelligent transportation system and urban planning. Various road segmentation methods have been proposed for visible remote sensing images, especially the popular convolutional neural network-based methods. However, high-accuracy road segmentation from high-resolution visible remote sensing images is still a challenging problem due to complex background and multiscale roads in these images. To handle this problem, a hybrid convolutional network (HCN), fusing multiple subnetworks, is proposed in this letter. The HCN contains a fully convolutional network, a modi?ed U-Net, and a VGG subnetwork; these subnetworks obtain a coarse-grained, a medium-grained, and a ?ne-grained road segmentation map. Moreover, the HCN uses a shallow convolutional subnetwork to fuse these multigrained segmentation maps for ?nal road segmentation. Bene?tting from multigrained segmentation, our HCN shows impressing results in processing both multiscale roads and complex background. Four testing indicators, including pixel accuracy, mean accuracy, mean region intersection over union (IU), and frequency weighted IU, are computed to evaluate the proposed HCN on two testing data sets. Compared with ?ve state-of-the-art road segmentation methods, our HCN has higher segmentation accuracy than them.
关键词： high-resolution visible remote sensing image,Convolutional neural network (CNN),road segmentation
更新于2025-09-23 15:21:21
-
[IEEE 2018 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) - Las Vegas, NV (2018.4.8-2018.4.10)] 2018 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) - Estimating Plant Centers Using A Deep Binary Classifier
摘要： Phenotyping is the process of estimating the physical and chemical properties of a plant. Traditional phenotyping is labor intensive and time consuming. These measurements can be obtained faster by collecting aerial images with an Unmanned Aerial Vehicle (UAV) and analyzing them using modern image analysis technologies. We propose a method to estimate plant centers by classifying each pixel as a plant center or not a plant center. We then label the center of each cluster as the plant location. We studied the performance of our method on two datasets. We achieved 84% precision and 90% recall on one dataset consisting of early stage plants and 62% precision and 77% recall on another dataset consisting of later stage plants.
关键词： Color Image Processing,Plant Phenotyping,CNN,Machine Learning
更新于2025-09-23 15:21:21
-
Detection of surface defects on solar cells by fusing Multi-channel convolution neural networks
摘要： Manufacturing process defects or artificial operation mistakes may lead to solar cells having surface cracks, over welding, black edges, unsoldered areas, and other minor defects on their surfaces. These defects will reduce the efficiency of solar cells or even make them completely useless. In this paper, a detection algorithm of surface defects on solar cells is proposed by fusing multi-channel convolution neural networks. The detection results from two different convolution neural networks, i.e., Faster R-CNN and R-FCN, are combined to improve detection precision and position accuracy. In addition, according to the inherent characteristics of the surface defects in solar cells, two other strategies are used to further improve the detection performance. First, the anchor points of the region proposal network (RPN) are set by adding multi-scale and multi-aspect regions to overcome the problem of high false negative rate caused by the limitation of anchor points. Second, in view of the subtle and concealed defects of solar cells, the hard negative sample mining strategy is used to solve the problem of low detection precision caused by the negative sample space being too large. The experimental results showed that the proposed method effectively reduced the false negative rate and the false positive rate of a single network, and it greatly improved the accuracy of the locations of defects while improving the object recall rate.
关键词： Deep learning,Defects detection,Faster R-CNN,Solar cell,R-FCN
更新于2025-09-23 15:21:01
-
[IEEE NAECON 2019 - IEEE National Aerospace and Electronics Conference - Dayton, OH, USA (2019.7.15-2019.7.19)] 2019 IEEE National Aerospace and Electronics Conference (NAECON) - In Situ Process Monitoring for Laser-Powder Bed Fusion using Convolutional Neural Networks and Infrared Tomography
摘要： Additive Manufacturing (AM) is a growing field for various industries of avionics, biomedical, automotive and manufacturing. The onset of Laser Powder Bed Fusion (LPBF) technologies for metal printing has shown exceptional growth in the past 15 years. Quality of parts for LPBF is a concern for the industry, as many parts produced are high risk, such as biomedical implants. To address these needs, a LPBF machine was designed with in-situ sensors to monitor the build process. Image processing and machine learning algorithms provide an efficient means to take bulk data and assess part quality, validating specific internal geometries and build defects. This research will analyze infrared (IR) images from a Selective Laser Melting (SLM) machine using a Computer Aided Design (CAD) designed part, featuring specific geometries (squares, circles, and triangles) of varying sizes (0.75-3.5 mm) on multiple layers for feature detection. Applying image processing to denoise, then Principal Component Analysis (PCA) for further denoising and applying Convolution Neural Networks (CNN) to identify the features and identifying a class which does not belong to a dataset, where a dataset are created from CAD images. Through this automated process, 300 geometric elements detected, classified, and validated against the build file through CNN. In addition, several build anomalies were detected and saved for end-user inspection.
关键词： Laser Powder Bed Fusion (LPBF),Principal Component Analysis (PCA),infrared image (IR),Convolution Neural Networks (CNN),Additive Manufacturing (AM),Computer Aided Design (CAD)
更新于2025-09-23 15:21:01
-
[Lecture Notes in Computer Science] Pattern Recognition and Computer Vision Volume 11257 (First Chinese Conference, PRCV 2018, Guangzhou, China, November 23-26, 2018, Proceedings, Part II) || Prohibited Item Detection in Airport X-Ray Security Images via Attention Mechanism Based CNN
摘要： Automation of security inspections is crucial for improving the efficiency and reducing security risks. In this paper, we focus on automatically recognizing and localizing prohibited items in airport X-ray security images. A top-down attention mechanism is applied to enhance a CNN classifier to additionally locate the prohibited items. We introduce a high-level semantic feedback loop to map the targets semantic signal to the input X-ray image space for generating task-specic attention maps. And the attention maps indicate the location and general outline of prohibited items in the input images. Furthermore, to obtain more accurate location information, we combine the lateral inhibition and contrastive attention to suppress noise and non-target interference in attention maps. The experiments on the GDX-ray image dataset have demonstrated the efficiency and stability of the proposed scheme in both single target detection and multi-target detection.
关键词： CNN,Detection,Prohibited item,Attention
更新于2025-09-23 15:21:01
-
[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) - Convolutional Neural Network for Blind Mesh Visual Quality Assessment Using 3D Visual Saliency
摘要： In this work, we propose a convolutional neural network (CNN) framework to estimate the perceived visual quality of 3D meshes without having access to the reference. The proposed CNN architecture is fed by small patches selected carefully according to their level of saliency. To do so, the visual saliency of the 3D mesh is computed, then we render 2D projections from the 3D mesh and its corresponding 3D saliency map. Afterward, the obtained views are split to obtain 2D small patches that pass through a saliency filter to select the most relevant patches. Experiments are conducted on two MVQ assessment databases, and the results show that the trained CNN achieves good rates in terms of correlation with human judgment.
关键词： blind mesh visual quality assessment,Convolutional neural network (CNN),mesh visual saliency
更新于2025-09-23 15:21:01
-
[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) - Gestalt Interest Points with a Neural Network for Makeup-Robust Face Recognition
摘要： In this paper, we propose a novel approach for the domain of makeup-robust face recognition. Most face recognition schemes usually fail to generalize well on these data where there is a large difference between the training and testing sets, e.g., makeup changes. Our method focuses on the problem of determining whether face images before and after makeup refer to the same identity. The work on this fundamental research topic benefits various real-world applications, for example automated passport control, security in general, and surveillance. Experiments show that our method is highly effective in comparison to state-of-the-art methods.
关键词： CNN,Face recognition,makeup-robust,GIP,person identification
更新于2025-09-23 15:21:01
-
Identification of Citrus Trees from Unmanned Aerial Vehicle Imagery Using Convolutional Neural Networks
摘要： Remote sensing is important to precision agriculture and the spatial resolution provided by Unmanned Aerial Vehicles (UAVs) is revolutionizing precision agriculture workflows for measurement crop condition and yields over the growing season, for identifying and monitoring weeds and other applications. Monitoring of individual trees for growth, fruit production and pest and disease occurrence remains a high research priority and the delineation of each tree using automated means as an alternative to manual delineation would be useful for long-term farm management. In this paper, we detected citrus and other crop trees from UAV images using a simple convolutional neural network (CNN) algorithm, followed by a classification refinement using superpixels derived from a Simple Linear Iterative Clustering (SLIC) algorithm. The workflow performed well in a relatively complex agricultural environment (multiple targets, multiple size trees and ages, etc.) achieving high accuracy (overall accuracy = 96.24%, Precision (positive predictive value) = 94.59%, Recall (sensitivity) = 97.94%). To our knowledge, this is the first time a CNN has been used with UAV multi-spectral imagery to focus on citrus trees. More of these individual cases are needed to develop standard automated workflows to help agricultural managers better incorporate large volumes of high resolution UAV imagery into agricultural management operations.
关键词： UAS,tree identification,citrus,precision agriculture,CNN,feature extraction,deep learning,superpixels
更新于2025-09-23 15:21:01
-
Real-time penetration state monitoring using convolutional neural network for laser welding of tailor rolled blanks
摘要： In this paper, an innovative monitoring system capable of diagnosing the penetration state during the laser welding process is introduced, which consists of two main blocks: a coaxial visual monitoring platform and a penetration state diagnosis unit. The platform can capture coaxial images of the interaction zone during the laser welding through a partially transmitting mirror and a high-speed camera. An image dataset representing four welding states was created for training and validation. The unit mainly consists of an embedded power-efficient computing TX2 and image processing algorithms based on a convolution neural network (CNN). Experiment results show that the platform can stably capture state-of-the-art welding images. The CNN used for a diagnosis of the penetration state is optimized using an optimal network structure and hyperparameters, applying a super-Gaussian function to initialize the weights of the convolutional layer. Its latency on TX2 is less than 2 ms, satisfying the real-time requirement. During the real laser welding of tailor-rolled blanks, a penetration state diagnosis with an accuracy of 94.6 % can be achieved even if the illumination changes significantly. The similar accuracy between the validating set and a real laser welding demonstrates that the proposed monitoring system has strong robustness. The precision and recall ratios of the CNN are higher than those of other methods such as a histogram of oriented gradients and local binary pattern.
关键词： Laser welding,Coaxial visual monitoring,Penetration state diagnosis,Convolutional neural network (CNN),Tailor-rolled blank
更新于2025-09-23 15:19:57