scholarly journals FCC-Net: A Full-Coverage Collaborative Network for Weakly Supervised Remote Sensing Object Detection

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1356
Author(s):  
Suting Chen ◽  
Dongwei Shao ◽  
Xiao Shu ◽  
Chuang Zhang ◽  
Jun Wang
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Large Scale ◽  
Detection Accuracy ◽  
Collaborative Network ◽  
Full Coverage ◽  
High Resolution Images ◽  
Multi Level ◽  
Weakly Supervised

With an ever-increasing resolution of optical remote-sensing images, how to extract information from these images efficiently and effectively has gradually become a challenging problem. As it is prohibitively expensive to label every object in these high-resolution images manually, there is only a small number of high-resolution images with detailed object labels available, highly insufficient for common machine learning-based object detection algorithms. Another challenge is the huge range of object sizes: it is difficult to locate large objects, such as buildings and small objects, such as vehicles, simultaneously. To tackle these problems, we propose a novel neural network based remote sensing object detector called full-coverage collaborative network (FCC-Net). The detector employs various tailored designs, such as hybrid dilated convolutions and multi-level pooling, to enhance multiscale feature extraction and improve its robustness in dealing with objects of different sizes. Moreover, by utilizing asynchronous iterative training alternating between strongly supervised and weakly supervised detectors, the proposed method only requires image-level ground truth labels for training. To evaluate the approach, we compare it against a few state-of-the-art techniques on two large-scale remote-sensing image benchmark sets. The experimental results show that FCC-Net significantly outperforms other weakly supervised methods in detection accuracy. Through a comprehensive ablation study, we also demonstrate the efficacy of the proposed dilated convolutions and multi-level pooling in increasing the scale invariance of an object detector.

scholarly journals Geospatial Object Detection on High Resolution Remote Sensing Imagery Based on Double Multi-Scale Feature Pyramid Network

2019 ◽  
Vol 11 (7) ◽  
pp. 755 ◽  
Author(s):  
Xiaodong Zhang ◽  
Kun Zhu ◽  
Guanzhou Chen ◽  
Xiaoliang Tan ◽  
Lifei Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Large Scale ◽  
Training Data ◽  
Validation Dataset ◽  
Remote Sensing Imagery ◽  
Scale Feature ◽  
Multi Scale ◽  
Feature Pyramid

Object detection on very-high-resolution (VHR) remote sensing imagery has attracted a lot of attention in the field of image automatic interpretation. Region-based convolutional neural networks (CNNs) have been vastly promoted in this domain, which first generate candidate regions and then accurately classify and locate the objects existing in these regions. However, the overlarge images, the complex image backgrounds and the uneven size and quantity distribution of training samples make the detection tasks more challenging, especially for small and dense objects. To solve these problems, an effective region-based VHR remote sensing imagery object detection framework named Double Multi-scale Feature Pyramid Network (DM-FPN) was proposed in this paper, which utilizes inherent multi-scale pyramidal features and combines the strong-semantic, low-resolution features and the weak-semantic, high-resolution features simultaneously. DM-FPN consists of a multi-scale region proposal network and a multi-scale object detection network, these two modules share convolutional layers and can be trained end-to-end. We proposed several multi-scale training strategies to increase the diversity of training data and overcome the size restrictions of the input images. We also proposed multi-scale inference and adaptive categorical non-maximum suppression (ACNMS) strategies to promote detection performance, especially for small and dense objects. Extensive experiments and comprehensive evaluations on large-scale DOTA dataset demonstrate the effectiveness of the proposed framework, which achieves mean average precision (mAP) value of 0.7927 on validation dataset and the best mAP value of 0.793 on testing dataset.

scholarly journals Elongated Small Object Detection from Remote Sensing Images Using Hierarchical Scale-Sensitive Networks

2021 ◽  
Vol 13 (16) ◽  
pp. 3182
Author(s):  
Zheng He ◽  
Li Huang ◽  
Weijiang Zeng ◽  
Xining Zhang ◽  
Yongxin Jiang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Large Scale ◽  
Small Scale ◽  
Detection Accuracy ◽  
Small Object ◽  
Direction Vector ◽  
Remote Sensing Images ◽  
Ship Detection ◽  
Hierarchical Scale

The detection of elongated objects, such as ships, from satellite images has very important application prospects in marine transportation, shipping management, and many other scenarios. At present, the research of general object detection using neural networks has made significant progress. However, in the context of ship detection from remote sensing images, due to the elongated shape of ship structure and the wide variety of ship size, the detection accuracy is often unsatisfactory. In particular, the detection accuracy of small-scale ships is much lower than that of the large-scale ones. To this end, in this paper, we propose a hierarchical scale sensitive CenterNet (HSSCenterNet) for ship detection from remote sensing images. HSSCenterNet adopts a multi-task learning strategy. First, it presents a dual-direction vector to represent the posture or direction of the tilted bounding box, and employs a two-layer network to predict the dual direction vector, which improves the detection block of CenterNet, and cultivates the ability of detecting targets with tilted posture. Second, it divides the full-scale detection task into three parallel sub-tasks for large-scale, medium-scale, and small-scale ship detection, respectively, and obtains the final results with non-maximum suppression. Experimental results show that, HSSCenterNet achieves a significant improved performance in detecting small-scale ship targets while maintaining a high performance at medium and large scales.

scholarly journals Deep Fusion Feature Based Object Detection Method for High Resolution Optical Remote Sensing Images

2019 ◽  
Vol 9 (6) ◽  
pp. 1130 ◽  
Author(s):  
Eric Wang ◽  
Yueping Li ◽  
Zhe Nie ◽  
Juntao Yu ◽  
Zuodong Liang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Fine Tuning ◽  
Detection Accuracy ◽  
Optical Remote Sensing ◽  
Remote Sensing Images ◽  
Feature Extraction Method ◽  
Feature Based ◽  
Fusion Feature

With the rapid growth of high-resolution remote sensing image-based applications, one of the fundamental problems in managing the increasing number of remote sensing images is automatic object detection. In this paper, we present a fusion feature-based deep learning approach to detect objects in high-resolution remote sensing images. It employs fine-tuning from ImageNet as a pre-training model to address the challenge of it lacking a large amount of training datasets in remote sensing. Besides, we improve the binarized normed gradients algorithm by multiple weak feature scoring models for candidate window selection and design a deep fusion feature extraction method with the context feature and object feature. Experiments are performed on different sizes of high-resolution optical remote sensing images. The results show that our model is better than regular models, and the average detection accuracy is 8.86% higher than objNet.

scholarly journals Object detection in high resolution images based on multiscale and block processing

Informatics ◽  
2020 ◽  
Vol 17 (2) ◽  
pp. 7-16
Author(s):  
R. P. Bohush ◽  
I. Yu. Zakharava ◽  
S. V. Ablameyko
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Image Representation ◽  
Input Image ◽  
Image Resolution ◽  
Detection Accuracy ◽  
Block Processing ◽  
High Resolution Images

In the paper the algorithm for object detection in high resolution images is proposed. The approach uses multiscale image representation followed by block processing with the overlapping value. For each block the object detection with convolutional neural network was performed. Number of pyramid layers is limited by the Convolutional Neural Network layer size and input image resolution. Overlapping blocks splitting to improve the classification and detection accuracy is performed on each layer of pyramid except the highest one. Detected areas are merged into one if they have high overlapping value and the same class. Experimental results for the algorithm are presented in the paper.

scholarly journals A Lightweight Object Detection Framework for Remote Sensing Images

2021 ◽  
Vol 13 (4) ◽  
pp. 683
Author(s):  
Lang Huyan ◽  
Yunpeng Bai ◽  
Ying Li ◽  
Dongmei Jiang ◽  
Yanning Zhang ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Real Time ◽  
Large Scale ◽  
Feature Fusion ◽  
Computational Cost ◽  
Feature Representation ◽  
Detection Accuracy ◽  
Remote Sensing Images ◽  
Low Level

Onboard real-time object detection in remote sensing images is a crucial but challenging task in this computation-constrained scenario. This task not only requires the algorithm to yield excellent performance but also requests limited time and space complexity of the algorithm. However, previous convolutional neural networks (CNN) based object detectors for remote sensing images suffer from heavy computational cost, which hinders them from being deployed on satellites. Moreover, an onboard detector is desired to detect objects at vastly different scales. To address these issues, we proposed a lightweight one-stage multi-scale feature fusion detector called MSF-SNET for onboard real-time object detection of remote sensing images. Using lightweight SNET as the backbone network reduces the number of parameters and computational complexity. To strengthen the detection performance of small objects, three low-level features are extracted from the three stages of SNET respectively. In the detection part, another three convolutional layers are designed to further extract deep features with rich semantic information for large-scale object detection. To improve detection accuracy, the deep features and low-level features are fused to enhance the feature representation. Extensive experiments and comprehensive evaluations on the openly available NWPU VHR-10 dataset and DIOR dataset are conducted to evaluate the proposed method. Compared with other state-of-art detectors, the proposed detection framework has fewer parameters and calculations, while maintaining consistent accuracy.

scholarly journals Parallel Regional Segmentation Method of High-Resolution Remote Sensing Image Based on Minimum Spanning Tree

2020 ◽  
Vol 12 (5) ◽  
pp. 783 ◽  
Author(s):  
Wenjie Lin ◽  
Yu Li
Keyword(s):  
Remote Sensing ◽  
Parallel Processing ◽  
High Resolution ◽  
Spanning Tree ◽  
Large Scale ◽  
Minimum Spanning Tree ◽  
Process Efficiency ◽  
Qualitative Assessment ◽  
Segmentation Method ◽  
High Resolution Images

With finer spatial scale, high-resolution images provide complex, spatial, and massive information on the earth’s surface, which brings new challenges to remote sensing segmentation methods. In view of these challenges, finding a more effective segmentation model and parallel processing method is crucial to improve the segmentation accuracy and process efficiency of large-scale high-resolution images. To this end, this study proposed a minimum spanning tree (MST) model integrated into a regional-based parallel segmentation method. First, an image was decomposed into several blocks by regular tessellation. The corresponding homogeneous regions were obtained using the minimum heterogeneity rule (MHR) partitioning technique in a multicore parallel processing mode, and the initial segmentation results were obtained by the parallel block merging method. On this basis, a regionalized fuzzy c-means (FCM) method based on master-slave parallel mode was proposed to achieve fast and optimal segmentation. The proposed segmentation approach was tested on high-resolution images. The results from the qualitative assessment, quantitative evaluation, and parallel analysis verified the feasibility and validity of the proposed method.

scholarly journals Class-Specific Anchor Based and Context-Guided Multi-Class Object Detection in High Resolution Remote Sensing Imagery with a Convolutional Neural Network

2019 ◽  
Vol 11 (3) ◽  
pp. 272 ◽  
Author(s):  
Nan Mo ◽  
Li Yan ◽  
Ruixi Zhu ◽  
Hong Xie
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Shape Change ◽  
Context Information ◽  
False Detection ◽  
Multi Scale

In this paper, the problem of multi-scale geospatial object detection in High Resolution Remote Sensing Images (HRRSI) is tackled. The different flight heights, shooting angles and sizes of geographic objects in the HRRSI lead to large scale variance in geographic objects. The inappropriate anchor size to propose the objects and the indiscriminative ability of features for describing the objects are the main causes of missing detection and false detection in multi-scale geographic object detection. To address these challenges, we propose a class-specific anchor based and context-guided multi-class object detection method with a convolutional neural network (CNN), which can be divided into two parts: a class-specific anchor based region proposal network (RPN) and a discriminative feature with a context information classification network. A class-specific anchor block providing better initial values for RPN is proposed to generate the anchor of the most suitable scale for each category in order to increase the recall ratio. Meanwhile, we proposed to incorporate the context information into the original convolutional feature to improve the discriminative ability of the features and increase classification accuracy. Considering the quality of samples for classification, the soft filter is proposed to select effective boxes to improve the diversity of the samples for the classifier and avoid missing or false detection to some extent. We also introduced the focal loss in order to improve the classifier in classifying the hard samples. The proposed method is tested on a benchmark dataset of ten classes to prove the superiority. The proposed method outperforms some state-of-the-art methods with a mean average precision (mAP) of 90.4% and better detects the multi-scale objects, especially when objects show a minor shape change.

scholarly journals YOLOv4-Lite–Based Urban Plantation Tree Detection and Positioning With High-Resolution Remote Sensing Imagery

2022 ◽  
Vol 9 ◽  
Author(s):  
Yueyuan Zheng ◽  
Gang Wu
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Object Detection ◽  
Template Matching ◽  
Large Scale ◽  
Local Maximum ◽  
High Rate ◽  
Detection Methods ◽  
Tree Detection ◽  
Single Tree

Automatic tree identification and position using high-resolution remote sensing images are critical for ecological garden planning, management, and large-scale environmental quality detection. However, existing single-tree detection methods have a high rate of misdetection in forests not only due to the similarity of background and crown colors but also because light and shadow caused abnormal crown shapes, resulting in a high rate of misdetections and missed detection. This article uses urban plantations as the primary research sample. In conjunction with the most recent deep learning method for object detection, a single-tree detection method based on the lite fourth edition of you only look once (YOLOv4-Lite) was proposed. YOLOv4’s object detection framework has been simplified, and the MobileNetv3 convolutional neural network is used as the primary feature extractor to reduce the number of parameters. Data enhancement is performed for categories with fewer single-tree samples, and the loss function is optimized using focal loss. The YOLOv4-Lite method is used to detect single trees on campus, in an orchard, and an economic plantation. Not only is the YOLOv4-Lite method compared to traditional methods such as the local maximum value method and the watershed method, where it outperforms them by nearly 46.1%, but also to novel methods such as the Chan-Vese model and the template matching method, where it outperforms them by nearly 26.4%. The experimental results for single-tree detection demonstrate that the YOLOv4-Lite method improves accuracy and robustness by nearly 36.2%. Our work establishes a reference for the application of YOLOv4-Lite in additional agricultural and plantation products.

Sign in / Sign up

Export Citation Format

Share Document