Spatial Information Inference Net: Road Extraction Using Road-Specific Contextual Information

2019 ◽  
Author(s):  
Ji Qi ◽  
Chao Tao ◽  
Hao Wang ◽  
Yuqi Tang ◽  
Zhenqi Cui
Keyword(s):  
Spatial Information ◽  
Contextual Information ◽  
Road Extraction

scholarly journals A Robust Lane Detection Model Using Vertical Spatial Features and Contextual Driving Information

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 708
Author(s):  
Wenbo Liu ◽  
Fei Yan ◽  
Jiyong Zhang ◽  
Tao Deng
Keyword(s):  
Information Exchange ◽  
Information Transfer ◽  
Spatial Information ◽  
Contextual Information ◽  
Great Influence ◽  
Light Condition ◽  
Lane Detection ◽  
Detection Model ◽  
Spatial Features ◽  
Proposed Model

The quality of detected lane lines has a great influence on the driving decisions of unmanned vehicles. However, during the process of unmanned vehicle driving, the changes in the driving scene cause much trouble for lane detection algorithms. The unclear and occluded lane lines cannot be clearly detected by most existing lane detection models in many complex driving scenes, such as crowded scene, poor light condition, etc. In view of this, we propose a robust lane detection model using vertical spatial features and contextual driving information in complex driving scenes. The more effective use of contextual information and vertical spatial features enables the proposed model more robust detect unclear and occluded lane lines by two designed blocks: feature merging block and information exchange block. The feature merging block can provide increased contextual information to pass to the subsequent network, which enables the network to learn more feature details to help detect unclear lane lines. The information exchange block is a novel block that combines the advantages of spatial convolution and dilated convolution to enhance the process of information transfer between pixels. The addition of spatial information allows the network to better detect occluded lane lines. Experimental results show that our proposed model can detect lane lines more robustly and precisely than state-of-the-art models in a variety of complex driving scenarios.

A CNN based Hybrid approach towards automatic image registration

2013 ◽  
Vol 62 (1) ◽  
pp. 33-49 ◽  
Author(s):  
Pattathal V. Arun ◽  
Sunil K. Katiyar
Keyword(s):  
Neural Network ◽  
Image Registration ◽  
Feature Matching ◽  
Spatial Information ◽  
Contextual Information ◽  
Hybrid Approach ◽  
Cellular Neural Network ◽  
Contextual Knowledge ◽  
Neural Network Approach ◽  
Statistical Measures

Abstract Image registration is a key component of various image processing operations which involve the analysis of different image data sets. Automatic image registration domains have witnessed the application of many intelligent methodologies over the past decade; however inability to properly model object shape as well as contextual information had limited the attainable accuracy. In this paper, we propose a framework for accurate feature shape modeling and adaptive resampling using advanced techniques such as Vector Machines, Cellular Neural Network (CNN), SIFT, coreset, and Cellular Automata. CNN has found to be effective in improving feature matching as well as resampling stages of registration and complexity of the approach has been considerably reduced using corset optimization The salient features of this work are cellular neural network approach based SIFT feature point optimisation, adaptive resampling and intelligent object modelling. Developed methodology has been compared with contemporary methods using different statistical measures. Investigations over various satellite images revealed that considerable success was achieved with the approach. System has dynamically used spectral and spatial information for representing contextual knowledge using CNN-prolog approach. Methodology also illustrated to be effective in providing intelligent interpretation and adaptive resampling.

scholarly journals Cortical Integration of Contextual Information across Objects

2016 ◽  
Vol 28 (7) ◽  
pp. 948-958 ◽  
Author(s):  
Tomer Livne ◽  
Moshe Bar
Keyword(s):  
Visual Information ◽  
Spatial Information ◽  
Contextual Information ◽  
Spatial Relations ◽  
Brain Regions ◽  
Specific Context ◽  
Medial Lobe ◽  
Parahippocampal Cortex ◽  
Contextual Association ◽  
Processing Of Visual Information

Recognizing objects in the environment and understanding our surroundings often depends on context: the presence of other objects and knowledge about their relations with each other. Such contextual information activates a set of medial lobe brain regions, the parahippocampal cortex and the retrosplenial complex. Both regions are more activated by single objects with a unique contextual association than by objects not associated with any specific context. Similarly they are more activated by spatially coherent arrangements of objects when those are consistent with their known spatial relations. The current study tested how context in multiple-object displays is represented in these regions in the absence of relevant spatial information. Using an fMRI slow-event-related design, we show that the precuneus (a subpart of the retrosplenial complex) is more activated by simultaneously presented contextually related objects than by unrelated objects. This suggests that the representation of context in this region is cumulative, representing integrated information across objects in the display. We discuss these findings in relation to processing of visual information and relate them to previous findings of contextual effects in perception.

scholarly journals A Hierarchical Feature Extraction Network for Fast Scene Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7730
Author(s):  
◽  
Keyword(s):  
Feature Extraction ◽  
Spatial Information ◽  
Contextual Information ◽  
Semantic Segmentation ◽  
Superior Performance ◽  
Scene Segmentation ◽  
Research Topics ◽  
Time Performance ◽  
Segmentation Accuracy ◽  
Active Research

Semantic segmentation is one of the most active research topics in computer vision with the goal to assign dense semantic labels for all pixels in a given image. In this paper, we introduce HFEN (Hierarchical Feature Extraction Network), a lightweight network to reach a balance between inference speed and segmentation accuracy. Our architecture is based on an encoder-decoder framework. The input images are down-sampled through an efficient encoder to extract multi-layer features. Then the extracted features are fused via a decoder, where the global contextual information and spatial information are aggregated for final segmentations with real-time performance. Extensive experiments have been conducted on two standard benchmarks, Cityscapes and Camvid, where our network achieved superior performance on NVIDIA 2080Ti.

scholarly journals Multiple Classifiers and Graph Cut Methods for Spectral Spatial Classification of Hyperspectral Image

2014 ◽  
Vol XL-8 ◽  
pp. 683-688
Author(s):  
D. B. Bhushan ◽  
R. R. Nidamanuri
Keyword(s):  
Land Cover ◽  
Supervised Classification ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Contextual Information ◽  
Graph Cut ◽  
Spectral Information ◽  
Cut Method ◽  
Multiple Classifier ◽  
The One

Hyperspectral image contains fine spectral and spatial resolutions for generating accurate land use and land cover maps. Supervised classification is the one of method used to exploit the information from the hyperspectral image. The traditional supervised classification methods could not be able to overcome the limitations of the hyperspectral image. The multiple classifier system (MCS) has the potential to increase the classification accuracy and reliability of the hyperspectral image. However, the MCS extracts only the spectral information from the hyperspectral image and neglects the spatial contextual information. Incorporating spatial contextual information along with spectral information is necessary to obtain smooth classification maps. Our objective of this paper is to design a methodology to fully exploit the spectral and spatial information from the hyperspectral image for land cover classification using MCS and Graph cut (GC) method. The problem is modelled as the energy minimization problem and solved using α-expansion based graph cut method. Experiments are conducted with two hyperspectral images and the result shows that the proposed MCS based graph cut method produces good quality classification map.

scholarly journals Cascaded Residual Attention Enhanced Road Extraction from Remote Sensing Images

2021 ◽  
Vol 11 (1) ◽  
pp. 9
Author(s):  
Shengfu Li ◽  
Cheng Liao ◽  
Yulin Ding ◽  
Han Hu ◽  
Yang Jia ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
Long Distance ◽  
Features Fusion ◽  
Multi Scale ◽  
Boundary Recognition ◽  
Benchmark Datasets

Efficient and accurate road extraction from remote sensing imagery is important for applications related to navigation and Geographic Information System updating. Existing data-driven methods based on semantic segmentation recognize roads from images pixel by pixel, which generally uses only local spatial information and causes issues of discontinuous extraction and jagged boundary recognition. To address these problems, we propose a cascaded attention-enhanced architecture to extract boundary-refined roads from remote sensing images. Our proposed architecture uses spatial attention residual blocks on multi-scale features to capture long-distance relations and introduce channel attention layers to optimize the multi-scale features fusion. Furthermore, a lightweight encoder-decoder network is connected to adaptively optimize the boundaries of the extracted roads. Our experiments showed that the proposed method outperformed existing methods and achieved state-of-the-art results on the Massachusetts dataset. In addition, our method achieved competitive results on more recent benchmark datasets, e.g., the DeepGlobe and the Huawei Cloud road extraction challenge.

scholarly journals BSIRNet: A Road Extraction Network with Bidirectional Spatial Information Reasoning

2022 ◽  
Vol 2022 ◽  
pp. 1-11
Author(s):  
Hai Tan ◽  
Hao Xu ◽  
Jiguang Dai
Keyword(s):  
Spatial Information ◽  
Feature Fusion ◽  
Extraction Methods ◽  
Automatic Extraction ◽  
Processing Unit ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
The Public ◽  
Automatic Navigation ◽  
Neural Network Structure

Automatic extraction of road information from remote sensing images is widely used in many fields, such as urban planning and automatic navigation. However, due to interference from noise and occlusion, the existing road extraction methods can easily lead to road discontinuity. To solve this problem, a road extraction network with bidirectional spatial information reasoning (BSIRNet) is proposed, in which neighbourhood feature fusion is used to capture spatial context dependencies and expand the receptive field, and an information processing unit with a recurrent neural network structure is used to capture channel dependencies. BSIRNet enhances the connectivity of road information through spatial information reasoning. Using the public Massachusetts road dataset and Wuhan University road dataset, the superiority of the proposed method is verified by comparing its results with those of other models.

scholarly journals Self-Training Classification Framework with Spatial-Contextual Information for Local Climate Zones

2019 ◽  
Vol 11 (23) ◽  
pp. 2828
Author(s):  
Zhao ◽  
Ma ◽  
Zhong ◽  
Zhao ◽  
Cao
Keyword(s):  
Spatial Information ◽  
Conditional Random Field ◽  
Contextual Information ◽  
Spatial Smoothing ◽  
Unified Framework ◽  
Climate Zones ◽  
Local Climate ◽  
Remote Sensing Classification ◽  
Classification Framework ◽  
Local Climate Zones

Local climate zones (LCZ) have become a generic criterion for climate analysis among global cities, as they can describe not only the urban climate but also the morphology inside the city. LCZ mapping based on the remote sensing classification method is a fundamental task, and the protocol proposed by the World Urban Database and Access Portal Tools (WUDAPT) project, which consists of random forest classification and filter-based spatial smoothing, is the most common approach. However, the classification and spatial smoothing lack a unified framework, which causes the appearance of small, isolated areas in the LCZ maps. In this paper, a spatial-contextual information-based self-training classification framework (SCSF) is proposed to solve this LCZ classification problem. In SCSF, conditional random field (CRF) is used to integrate the classification and spatial smoothing processing into one model and a self-training method is adopted, considering that the lack of sufficient expert-labeled training samples is always a big issue, especially for the complex LCZ scheme. Moreover, in the unary potentials of CRF modeling, pseudo-label selection using a self-training process is used to train the classifier, which fuses the regional spatial information through segmentation and the local neighborhood information through moving windows to provide a more reliable probabilistic classification map. In the pairwise potential function, SCSF can effectively improve the classification accuracy by integrating the spatial-contextual information through CRF. The experimental results prove that the proposed framework is efficient when compared to the traditional mapping product of WUDAPT in LCZ classification.

scholarly journals Land Cover Mapping with Higher Order Graph-Based Co-Occurrence Model

2018 ◽  
Vol 10 (11) ◽  
pp. 1713 ◽  
Author(s):  
Wenzhi Zhao ◽  
William Emery ◽  
Yanchen Bo ◽  
Jiage Chen
Keyword(s):  
Deep Learning ◽  
Land Cover ◽  
Spatial Information ◽  
Conditional Random Field ◽  
Contextual Information ◽  
Learning Algorithms ◽  
Classification Performance ◽  
Higher Order ◽  
Land Cover Mapping ◽  
Initial Classification

Deep learning has become a standard processing procedure in land cover mapping for remote sensing images. Instead of relying on hand-crafted features, deep learning algorithms, such as Convolutional Neural Networks (CNN) can automatically generate effective feature representations, in order to recognize objects with complex image patterns. However, the rich spatial information still remains unexploited, since most of the deep learning algorithms only focus on small image patches that overlook the contextual information at larger scales. To utilize these contextual information and improve the classification performance for high-resolution imagery, we propose a graph-based model in order to capture the contextual information over semantic segments of the image. First, we explore semantic segments which build on the top of deep features and obtain the initial classification result. Then, we further improve the initial classification results with a higher-order co-occurrence model by extending the existing conditional random field (HCO-CRF) algorithm. Compared to the pixel- and object-based CNN methods, the proposed model achieved better performance in terms of classification accuracy.

Sign in / Sign up

Export Citation Format

Share Document