A Mountain Summit Recognition Method Based on Improved Faster R-CNN

Mountain summits are vital topographic feature points, which are essential for understanding landform processes and their impacts on the environment and ecosystem. Traditional summit detection methods operate on handcrafted features extracted from digital elevation model (DEM) data and apply parametric detection algorithms to locate mountain summits. However, these methods may no longer be effective to achieve desirable recognition results in small summits and suffer from the objective criterion lacking problem. Thus, to address these problems, we propose an improved Faster region-convolutional neural network (R-CNN) to accurately detect the mountain summits from DEM data. Based on Faster R-CNN, the improved network adopts a residual convolution block to replace the traditional part and adds a feature pyramid network (FPN) to fuse the features with adjacent layers to better address the mountain summit detection task. The residual convolution is employed to capture the deep correlation between visual and physical morphological features. The FPN is utilized to integrate the location and semantic information in the extracted feature maps to effectively represent the mountain summit area. The experimental results demonstrate that the proposed network could achieve the highest recall and precision without manually designed summit features and accurately identify small summits.

Download Full-text

Elevation-Dependent Removal of Cirrus Clouds in Satellite Imagery

Remote Sensing ◽

10.3390/rs12030494 ◽

2020 ◽

Vol 12 (3) ◽

pp. 494

Author(s):

Daniel Schläpfer ◽

Rudolf Richter ◽

Peter Reinartz

Keyword(s):

Satellite Imagery ◽

Atmospheric Correction ◽

Cirrus Clouds ◽

Landsat 8 ◽

Surface Reflectance ◽

Detection Algorithms ◽

Digital Elevation ◽

Variable Nature ◽

Critical Issues ◽

Elevation Model

Masking of cirrus clouds in optical satellite imagery is an important step in automated processing chains. Firstly, it is a prerequisite to a subsequent removal of cirrus effects, and secondly, it affects the atmospheric correction, i.e., aerosol and surface reflectance retrievals. Cirrus clouds can be detected with a narrow bandwidth channel near 1.38 μ m and operational detection algorithms have been developed for Landsat-8 and Sentinel-2 images. However, concerning cirrus removal in the case of elevated surfaces, current methods do not separate the ground reflected signal from the cirrus signal in the 1.38 μ m channel when performing an atmospheric correction, often resulting in an overcorrection of the cirrus influence. We propose a new operational algorithm using a Digital Elevation Model (DEM) to estimate the surface and cirrus cloud contributions in the 1.38 μ m channel and to remove cirrus effects during the surface reflectance retrieval. Due to the highly variable nature of cirrus clouds and terrain conditions, no generic quantitative results could be derived. However, results for typical cases and the achieved improvement in cirrus removal are given for selected scenes and critical issues and limitations of the approach are discussed.

Download Full-text

Automatic Fabric Defect Detection Using Cascaded Mixed Feature Pyramid with Guided Localization

Sensors ◽

10.3390/s20030871 ◽

2020 ◽

Vol 20 (3) ◽

pp. 871 ◽

Cited By ~ 3

Author(s):

You Wu ◽

Xiaodong Zhang ◽

Fengzhou Fang

Keyword(s):

Defect Detection ◽

Large Scale ◽

Region Of Interest ◽

Feature Maps ◽

Detection Algorithms ◽

Multi Scale ◽

Fabric Defect Detection ◽

Fabric Defect ◽

Feature Pyramid ◽

Set Up

Generic object detection algorithms for natural images have been proven to have excellent performance. In this paper, fabric defect detection on optical image datasets is systematically studied. In contrast to generic datasets, defect images are multi-scale, noise-filled, and blurred. Back-light intensity would also be sensitive for visual perception. Large-scale fabric defect datasets are collected, selected, and employed to fulfill the requirements of detection in industrial practice in order to address these imbalanced issues. An improved two-stage defect detector is constructed for achieving better generalization. Stacked feature pyramid networks are set up to aggregate cross-scale defect patterns on interpolating mixed depth-wise block in stage one. By sharing feature maps, center-ness and shape branches merges cascaded modules with deformable convolution to filter and refine the proposed guided anchors. After balanced sampling, the proposals are down-sampled by position-sensitive pooling for region of interest, in order to characterize interactions among fabric defect images in stage two. The experiments show that the end-to-end architecture improves the occluded defect performance of region-based object detectors as compared with the current detectors.

Download Full-text

A Simple GIS-Based Tool for the Detection of Landslide-Prone Zones on a Coastal Slope in Scotland

Land ◽

10.3390/land10070685 ◽

2021 ◽

Vol 10 (7) ◽

pp. 685

Author(s):

Alejandro Gonzalez-Ollauri ◽

Slobodan B. Mickovski

Keyword(s):

Natural Hazards ◽

Slope Failure ◽

Spatial Scales ◽

Detection Methods ◽

Limited Information ◽

Multiple Spatial Scales ◽

Coastal Slope ◽

Digital Elevation ◽

Negative Impacts ◽

Elevation Model

Effective landslide detection is crucial to mitigate the negative impacts derived from the occurrence of these natural hazards. Research on landslide detection methods has been extensively undertaken. However, simplified methods for landslide detection requiring a minimum amount of data inputs are still lacking. Simple approaches for landslide detection should be particularly interesting for geographical areas with limited information or resources availability. The aim of this paper is to present a refined, simple, GIS-based tool for the detection of landslide-prone and slope restoration zones. The tool only requires a digital elevation model (DEM) dataset as input, it is interoperable at multiple spatial scales, and it can be implemented on any GIS platform. The tool was applied on a coastal slope prone to instability, located in Scotland, in order to verify the functionality of the tool. The results indicated that the proposed tool is able to detect both shallow and deeper landslides satisfactorily, suggesting that the spatial combination of steep and potentially wet soil zones is effective for detecting areas prone to slope failure.

Download Full-text

COMPARISON OF PIXEL-BASED AND FEATURE-BASED APPROACH FOR SMALL OBJECT CHANGE DETECTION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xliii-b3-2021-353-2021 ◽

2021 ◽

Vol XLIII-B3-2021 ◽

pp. 353-357

Author(s):

J. Seo ◽

T. Kim

Keyword(s):

Change Detection ◽

Satellite Images ◽

Rate Of Change ◽

Image Resolution ◽

Detection Methods ◽

Small Object ◽

Feature Points ◽

Detection Algorithms ◽

Change Detection Algorithms ◽

Feature Based

Abstract. Satellite image resolution has evolved to daily revisit and sub-meter GSD. Main targets of previous remote sensing were forest, vegetation, damage area by disasters, land use and land cover. Developments in satellite images have brought expectations on more sophisticated and various change detection of objects. Accordingly, we focused on unsupervised change detection of small objects, such as vehicles and ships. In this paper, existing change detection methods were applied to analyze their performances for pixel-based and feature-based change of small objects. We used KOMPSAT-3A images for tests. Firstly, we applied two change detection algorithms, MAD and IR-MAD, which are most well-known pixel-based change detection algorithms, to the images. We created a change magnitude map using the change detection methods. Thresholding was applied to determine change and non-change pixels. Next, the satellite images were transformed as 8-bit images for extracting feature points. We extracted feature points using SIFT and SURF methods to analyze feature-based change detection. We assumed to remove false alarms by eliminating feature points of non-changed objects. Therefore, we applied a feature-based matcher and matched feature points on identical image locations were eliminated. We used non-matched feature points for change/non-change analysis. We observed changes by creating a 5x5 size ROI around extracted feature points in the change/non-change map. We determined that change has occurred on feature points if the rate of change pixels with ROI was more than 50%. We analyzed the performance of pixel-based and feature-based change detection using ground truths. The F1-score, AUC value, and ROC were used to compare the performance of change detection. Performance showed that feature-based approaches performed better than pixel-based approaches.

Download Full-text

Generating Anchor Boxes Based on Attention Mechanism for Object Detection in Remote Sensing Images

Remote Sensing ◽

10.3390/rs12152416 ◽

2020 ◽

Vol 12 (15) ◽

pp. 2416 ◽

Cited By ~ 1

Author(s):

Zhuangzhuang Tian ◽

Ronghui Zhan ◽

Jiemin Hu ◽

Wei Wang ◽

Zhiqiang He ◽

...

Keyword(s):

Remote Sensing ◽

Object Detection ◽

Attention Mechanism ◽

Detection Methods ◽

Optical Remote Sensing ◽

Remote Sensing Images ◽

Feature Maps ◽

Wide Range ◽

Feature Pyramid ◽

Comprehensive Evaluations

Nowadays, object detection methods based on deep learning are applied more and more to the interpretation of optical remote sensing images. However, the complex background and the wide range of object sizes in remote sensing images increase the difficulty of object detection. In this paper, we improve the detection performance by combining the attention information, and generate adaptive anchor boxes based on the attention map. Specifically, the attention mechanism is introduced into the proposed method to enhance the features of the object regions while reducing the influence of the background. The generated attention map is then used to obtain diverse and adaptable anchor boxes using the guided anchoring method. The generated anchor boxes can match better with the scene and the objects, compared with the traditional proposal boxes. Finally, the modulated feature adaptation module is applied to transform the feature maps to adapt to the diverse anchor boxes. Comprehensive evaluations on the DIOR dataset demonstrate the superiority of the proposed method over the state-of-the-art methods, such as RetinaNet, FCOS and CornerNet. The mean average precision of the proposed method is 4.5% higher than the feature pyramid network. In addition, the ablation experiments are also implemented to further analyze the respective influence of different blocks on the performance improvement.

Download Full-text

Object Detection Using Improved Bi-Directional Feature Pyramid Network

Electronics ◽

10.3390/electronics10060746 ◽

2021 ◽

Vol 10 (6) ◽

pp. 746

Author(s):

Tran Ngoc Quang ◽

Seunghyun Lee ◽

Byung Cheol Song

Keyword(s):

Object Detection ◽

Local Information ◽

Single Stage ◽

Detection Methods ◽

Feature Maps ◽

Feature Pyramid ◽

Non Local ◽

Aggregation Scheme ◽

Global And Local ◽

New Framework

Conventional single-stage object detectors have been able to efficiently detect objects of various sizes using a feature pyramid network. However, because they adopt a too simple manner of aggregating feature maps, they cannot avoid performance degradation due to information loss. To solve this problem, this paper proposes a new framework for single-stage object detection. The proposed aggregation scheme introduces two independent modules to extract global and local information. First, the global information extractor is designed so that each feature vector can reflect the information of the entire image through a non-local neural network (NLNN). Next, the local information extractor aggregates each feature map more effectively through the improved bi-directional network. The proposed method can achieve better performance than the existing single-stage object detection methods by providing improved feature maps to the detection heads. For example, the proposed method shows 1.6% higher average precision (AP) than the efficient featurized image pyramid network (EFIPNet) for the MicroSoft Common Objects in COntext (MS COCO) dataset.

Download Full-text

Multiscale Feature Learning Based on Enhanced Feature Pyramid for Vehicle Detection

Complexity ◽

10.1155/2021/5555121 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Hoanh Nguyen

Keyword(s):

Computational Cost ◽

Feature Learning ◽

Vehicle Detection ◽

Autonomous Driving ◽

Detection Methods ◽

Feature Maps ◽

Feature Representations ◽

Backbone Network ◽

Discriminative Feature ◽

Feature Pyramid

Vehicle detection is a crucial task in autonomous driving systems. Due to large variance of scales and heavy occlusion of vehicle in an image, this task is still a challenging problem. Recent vehicle detection methods typically exploit feature pyramid to detect vehicles at different scales. However, the drawbacks in the design prevent the multiscale features from being completely exploited. This paper introduces a feature pyramid architecture to address this problem. In the proposed architecture, an improving region proposal network is designed to generate intermediate feature maps which are then used to add more discriminative representations to feature maps generated by the backbone network, as well as improving the computational cost of the network. To generate more discriminative feature representations, this paper introduces multilayer enhancement module to reweight feature representations of feature maps generated by the backbone network to increase the discrimination of foreground objects and background regions in each feature map. In addition, an adaptive RoI pooling module is proposed to pool features from all pyramid levels for each proposal and fuse them for the detection network. Experimental results on the KITTI vehicle detection benchmark and the PASCAL VOC 2007 car dataset show that the proposed approach obtains better detection performance compared with recent methods on vehicle detection.

Download Full-text

An Effective Lunar Crater Recognition Algorithm Based on Convolutional Neural Network

Remote Sensing ◽

10.3390/rs12172694 ◽

2020 ◽

Vol 12 (17) ◽

pp. 2694

Author(s):

Song Wang ◽

Zizhu Fan ◽

Zhengming Li ◽

Hong Zhang ◽

Chao Wei

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Template Matching ◽

Input Image ◽

Recognition Algorithm ◽

Lunar Crater ◽

Learning Methods ◽

Objective Criterion ◽

Digital Elevation ◽

Elevation Model

The lunar crater recognition plays a key role in lunar exploration. Traditional crater recognition methods are mainly based on the human observation that is usually combined with classical machine learning methods. These methods have some drawbacks, such as lacking the objective criterion. Moreover, they can hardly achieve desirable recognition results in small or overlapping craters. To address these problems, we propose a new convolutional neural network termed effective residual U-Net (ERU-Net) to recognize craters from lunar digital elevation model (DEM) images. ERU-Net first detects crater edges in lunar DEM data. Then, it uses template matching to compute the position and size of craters. ERU-Net is based on U-Net and uses the residual convolution block instead of the traditional convolution, which combines the advantages of U-Net and residual network. In ERU-Net, the size of the input image is the same as that of the output image. Since our network uses residual units, the training process of ERU-Net is simple, and the proposed model can be easily optimized. ERU-Net gets better recognition results when its network structure is deepened. The method targets at the rim of the crater, and it can recognize overlap craters. In theory, our proposed network can recognize all kinds of impact craters. In the lunar crater recognition, our model achieves high recall (83.59%) and precision (84.80%) on DEM. The recall of our method is higher than those of other deep learning methods. The experiment results show that it is feasible to exploit our network to recognize craters from the lunar DEM.

Download Full-text

Self-Adaptive Aspect Ratio Anchor for Oriented Object Detection in Remote Sensing Images

Remote Sensing ◽

10.3390/rs13071318 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1318

Author(s):

Jie-Bo Hou ◽

Xiaobin Zhu ◽

Xu-Cheng Yin

Keyword(s):

Remote Sensing ◽

Aspect Ratio ◽

Object Detection ◽

Detection Methods ◽

Remote Sensing Images ◽

Feature Maps ◽

Aspect Ratios ◽

Feature Pyramid ◽

Oriented Object ◽

Self Adaptive

Object detection is a significant and challenging problem in the study of remote sensing. Since remote sensing images are typically captured with a bird’s-eye view, the aspect ratios of objects in the same category may obey a Gaussian distribution. Generally, existing object detection methods ignore exploring the distribution character of aspect ratios for improving performance in remote sensing tasks. In this paper, we propose a novel Self-Adaptive Aspect Ratio Anchor (SARA) to explicitly explore aspect ratio variations of objects in remote sensing images. To be concrete, our SARA can self-adaptively learn an appropriate aspect ratio for each category. In this way, we can only utilize a simple squared anchor (related to the strides of feature maps in Feature Pyramid Networks) to regress objects in various aspect ratios. Finally, we adopt an Oriented Box Decoder (OBD) to align the feature maps and encode the orientation information of oriented objects. Our method achieves a promising mAP value of 79.91% on the DOTA dataset.

Download Full-text