- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Triplet-Based Semantic Relation Learning for Aerial Remote Sensing Image Change Detection
摘要： This letter presents a novel supervised change detection method based on a deep siamese semantic network framework, which is trained by using improved triplet loss function for optical aerial images. The proposed framework can not only extract features directly from image pairs which include multiscale information and are more abstract as well as robust, but also enhance the interclass separability and the intraclass inseparability by learning semantic relation. The feature vectors of the pixels pair with the same label are closer, and at the same time, the feature vectors of the pixels with different labels are farther from each other. Moreover, we use the distance of the feature map to detect the changes on the difference map between the image pair. Binarized change map can be obtained by a simple threshold. Experiments on optical aerial image data set validate that the proposed approach produces comparable, even better results, favorably to the state-of-the-art methods in terms of F-measure.
关键词： triplet loss function,Change detection,semantic relation,optical aerial images,siamese semantic network
更新于2025-09-23 15:23:52
-
Statistical validation of utility of head-mounted display projection-based experimental impression evaluation for sequential streetscapes
摘要： This study compared the impression structure of streetscapes gained from field experiments with that from head-mounted display virtual reality experiments. The results were as follows: (1) the field experiment experience had a slight influence on the impressions reported from the head-mounted display experiment; (2) few items exhibited significant differences in impression values for the two experiments; (3) the impression structure comprised three factors—'Openness,' 'Balance,' and 'Activity'—in both experiments, and (4) no significant difference appeared between the two experiments relative to the subscale scores of these three factors. These results show that head-mounted display experiments can substitute field experiments.
关键词： semantic differential method,virtual reality,Impression evaluation,omnidirectional camera,head-mounted display
更新于2025-09-23 15:23:52
-
A top-down approach for semantic segmentation of big remote sensing images
摘要： The increasing amount of remote sensing data has opened the door to new challenging research topics. Nowadays, significant efforts are devoted to pixel and object based classification in case of massive data. This paper addresses the problem of semantic segmentation of big remote sensing images. To do this, we proposed a top-down approach based on two main steps. The first step aims to compute features at the object-level. These features constitute the input of a multi-layer feed-forward network to generate a structure for classifying remote sensing objects. The goal of the second step is to use this structure to label every pixel in new images. Several experiments are conducted based on real datasets and results show good classification accuracy of the proposed approach. In addition, the comparison with existing classification techniques proves the effectiveness of the proposed approach especially for big remote sensing data.
关键词： Neural networks,Remote sensing images,Big data,Semantic segmentation
更新于2025-09-23 15:23:52
-
FRED-Net: Fully Residual Encoder-Decoder Network for Accurate Iris Segmentation
摘要： Iris recognition is now developed enough to recognize a person from a distance. The process of iris segmentation plays a vital role in maintaining the accuracy of the iris-based recognition systems by limiting the errors at the current stage. However, its performance is affected by non-ideal situations created by environmental light noise and user non-cooperation. The existing local feature-based segmentation methods are unable to find the true iris boundary in these non-ideal situations, and the error created at the segmentation stage traverses to all the subsequent stages, which results in reduced accuracy and reliability. In addition, it is necessary to segment the true iris boundary without the extra cost of denoising as preprocessing. To overcome these challenging issues during iris segmentation, a deep learning-based fully residual encoder-decoder network (FRED-Net) is proposed to determine the true iris region with the flow of high-frequency information from the preceding layers via residual skip connection. The main four impacts and significances of this study are as follows. First, FRED-Net is an end-to-end semantic segmentation network that does not use conventional image processing schemes, and does not have a preprocessing overhead. It is a standalone network in which eyelid, eyelash, and glint detections are not required to obtain the true iris boundary. Second, the proposed FRED-Net is the final resultant structure of a step-by-step development, and in each step, a new complete variant network is created for semantic segmentation considering the detailed descriptions of the networks. Third, FRED-Net uses the residual connectivity between convolutional layers by the residual shortcut for both encoder and decoder, which enables a high-frequency component to flow through the network and achieve higher accuracy with few layers. Fourth, the performance of the proposed FRED-Net is tested with five different iris datasets under visible and NIR light environments, and two general road scene segmentation datasets. To achieve fair comparisons with other studies, our trained FRED-Net models, along with the algorithms, are made publicly available through our website (Dongguk FRED-Net Model with Algorithm. accessed on 16 May 2018). The experiments include two datasets: Noisy Iris Challenge Evaluation - Part II (NICE-II) selected from the UBIRIS.v2 database and Mobile Iris Challenge Evaluation (MICHE-I), for the visible light environment and three datasets: Institute of Automation, Chinese Academy of Sciences (CASIA) v4.0 interval, v4.0 distance, and IIT Delhi v1.0, for the near-infrared (NIR) light environment. Moreover, to evaluate the performance of the proposed network in general segmentation, experiments with two famous road scene segmentation datasets: Cambridge-driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI), are included. The experimental results showed the optimum performance of the proposed FRED-Net on the above-mentioned seven datasets of iris and general road scene segmentation.
关键词： iris segmentation,full residual encoder-decoder network,Iris recognition,semantic segmentation
更新于2025-09-23 15:23:52
-
norm constraint
摘要： Current zero shot learning methods mostly focus on applying the knowledge learnt by seen images to the unseen images. However, there is a big distribution difference between seen and unseen data, also called source and target domain. Thus, there are many irrelevant seen samples for unseen samples. We want to partially transfer the seen samples to target domain by selecting relevant seen samples. In this paper, we propose a method, zero shot learning by partial transfer from source domain with L2,1 norm constraint, called ZSLPT which embeds visual similarity and semantic similarity to transfer partial source samples. The relevant source samples are selected, while the irrelevant are eliminated. What’s more, we train source classification model used for transferring to target domain with the selected source samples, making the transferred target model more accurate. We have experimented on the state-of-the-art zero shot learning datasets, demonstrating that ZSLPT has good performance.
关键词： Zero shot learning,L2,1 norm,Partial transfer,Semantic similarity,Visual similarity
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Change Detection in Semantic Level for SAR Images
摘要： Considering that the traditional change detection algorithms only focus on extracting the change area but ignore the change content identification, a novel change detection framework for synthetic aperture radar (SAR) images is proposed. The framework integrates the merits of unsupervised and supervised learning to detect changes in semantic level. First, the residual convolutional auto-encoder (RCAE) is designed to convert SAR image slices to the histogram representation. Then, we calculate the difference vectors and extract the change area by their norms. Finally, we classify the difference vectors of change region and identify the content of change. Experimental results indicate that the proposed method significantly achieves performance improvement over existing algorithms.
关键词： semantic,bag of visual words,synthetic aperture radar,auto-encoder,change detection
更新于2025-09-23 15:23:52
-
SCN: Switchable Context Network for Semantic Segmentation of RGB-D Images
摘要： Context representations have been widely used to profit semantic image segmentation. The emergence of depth data provides additional information to construct more discriminating context representations. Depth data preserves the geometric relationship of objects in a scene, which is generally hard to be inferred from RGB images. While deep convolutional neural networks (CNNs) have been successful in solving semantic segmentation, we encounter the problem of optimizing CNN training for the informative context using depth data to enhance the segmentation accuracy. In this paper, we present a novel switchable context network (SCN) to facilitate semantic segmentation of RGB-D images. Depth data is used to identify objects existing in multiple image regions. The network analyzes the information in the image regions to identify different characteristics, which are then used selectively through switching network branches. With the content extracted from the inherent image structure, we are able to generate effective context representations that are aware of both image structures and object relationships, leading to a more coherent learning of semantic segmentation network. We demonstrate that our SCN outperforms state-of-the-art methods on two public datasets.
关键词： Context representation,convolutional neural network (CNN),RGB-D images,semantic segmentation
更新于2025-09-23 15:23:52
-
Dense Semantic Labeling with Atrous Spatial Pyramid Pooling and Decoder for High-Resolution Remote Sensing Imagery
摘要： Dense semantic labeling is significant in high-resolution remote sensing imagery research and it has been widely used in land-use analysis and environment protection. With the recent success of fully convolutional networks (FCN), various types of network architectures have largely improved performance. Among them, atrous spatial pyramid pooling (ASPP) and encoder-decoder are two successful ones. The former structure is able to extract multi-scale contextual information and multiple effective field-of-view, while the latter structure can recover the spatial information to obtain sharper object boundaries. In this study, we propose a more efficient fully convolutional network by combining the advantages from both structures. Our model utilizes the deep residual network (ResNet) followed by ASPP as the encoder and combines two scales of high-level features with corresponding low-level features as the decoder at the upsampling stage. We further develop a multi-scale loss function to enhance the learning procedure. In the postprocessing, a novel superpixel-based dense conditional random field is employed to refine the predictions. We evaluate the proposed method on the Potsdam and Vaihingen datasets and the experimental results demonstrate that our method performs better than other machine learning or deep learning methods. Compared with the state-of-the-art DeepLab_v3+ our model gains 0.4% and 0.6% improvements in overall accuracy on these two datasets respectively.
关键词： dense semantic labeling,encoder-decoder,superpixel-based DenseCRF,remote sensing imagery,fully convolutional networks,atrous spatial pyramid pooling
更新于2025-09-23 15:23:52
-
[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) - Semantically Invariant Text-to-Image Generation
摘要： Image captioning has demonstrated models that are capable of generating plausible text given input images or videos. Further, recent work in image generation has shown significant improvements in image quality when text is used as a prior. Our work ties these concepts together by creating an architecture that can enable bidirectional generation of images and text. We call this network Multi-Modal Vector Representation (MMVR). Along with MMVR, we propose two improvements to the text conditioned image generation. Firstly, an n-gram metric based cost function is introduced that generalizes the caption with respect to the image. Secondly, multiple semantically similar sentences are shown to help in generating better images. Qualitative and quantitative evaluations demonstrate that MMVR improves upon existing text conditioned image generation results by over 20%, while integrating visual and text modalities.
关键词： text-to-image generation,multi-modal learning,n-gram metric,semantic invariance,multiple captions
更新于2025-09-23 15:22:29
-
[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) - Adversarial Domain Adaptation with a Domain Similarity Discriminator for Semantic Segmentation of Urban Areas
摘要： Existing semantic segmentation models of urban areas have shown to perform well in a supervised setting. However, collecting lots of annotated images from each city to train such models is time-consuming or difficult. In addition, when transferring the segmentation model from the trained city (source domain) to an unseen city (target domain), the performance will largely degrade due to the domain shift. For this reason, we propose a domain adaptation method with a domain similarity discriminator to eliminate such domain shift in the framework of adversarial learning. Contrary to the single-input adversarial network, our domain similarity discriminator, which consists of a Siamese network, is able to measure the similarity of the pairwise-input data. In this way, we can use more information about the pairwise-input to measure the similarity between different distributions so as to address the problem of domain shift. Experimental results demonstrate that our approach outperforms the competing methods on three different cities.
关键词： domain adaptation,urban areas,semantic segmentation,domain shift,Siamese network
更新于2025-09-23 15:22:29