Sig-NMS-Based Faster R-CNN Combining Transfer Learning for Small Target Detection in VHR Optical Remote Sensing Imagery

With the development of deep learning, target detection from vision sensor has achieved high accuracy and efficiency. However, small target detection remains a challenge due to inadequate use of semantic information and detailed texture information of underlying features. To solve the above problems, this paper proposes a small target detection algorithm based on Mask R-CNN model which integrates transfer learning and deep separable network. Firstly, the feature pyramid fusion structure is introduced to enhance the learning effect of low-level and high-level features, especially to strengthen the information channel of low-level feature and meanwhile optimize the feature information of small target. Secondly, the ELU function is used as the activation function to solve the problem that the original activation function disappears in the negative half axis gradient. Finally, a new loss function F-Softmax combined with Focal Loss was adopted to solve the imbalance of positive and negative sample proportions. In this paper, self-made data set is used to carry out experiments, and the experimental results show that the proposed algorithm makes the detection accuracy of small targets reach 66.5%.

Download Full-text

Small Target Detection Algorithm in Remote Sensing Image Based on Improved Yolo

Lecture Notes in Electrical Engineering - Advanced Manufacturing and Automation X ◽

10.1007/978-981-33-6318-2_76 ◽

2021 ◽

pp. 612-620

Author(s):

Chaoliang Peng ◽

Xianwu Chu ◽

Yunming Wang ◽

Xiue Gao

Keyword(s):

Remote Sensing ◽

Target Detection ◽

Remote Sensing Image ◽

Detection Algorithm ◽

Small Target ◽

Small Target Detection

Download Full-text

A New Method of Different Neural Network Depth and Feature Map Size on Remote Sensing Small Target Detection

INTELIGENCIA ARTIFICIAL ◽

10.4114/intartif.vol24iss68pp21-32 ◽

2021 ◽

Vol 24 (68) ◽

pp. 21-32

Author(s):

Yaming Cao ◽

ZHEN YANG ◽

CHEN GAO

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Neural Networks ◽

Target Detection ◽

Detection Efficiency ◽

Detection Accuracy ◽

Small Target ◽

Remote Sensing Images ◽

Feature Maps ◽

Small Target Detection

Convolutional neural networks (CNNs) have shown strong learning capabilities in computer vision tasks such as classification and detection. Especially with the introduction of excellent detection models such as YOLO (V1, V2 and V3) and Faster R-CNN, CNNs have greatly improved detection efficiency and accuracy. However, due to the special angle of view, small size, few features, and complicated background, CNNs that performs well in the ground perspective dataset, fails to reach a good detection accuracy in the remote sensing image dataset. To this end, based on the YOLO V3 model, we used feature maps of different depths as detection outputs to explore the reasons for the poor detection rate of small targets in remote sensing images by deep neural networks. We also analyzed the effect of neural network depth on small target detection, and found that the excessive deep semantic information of neural network has little effect on small target detection. Finally, the verification on the VEDAI dataset shows, that the fusion of shallow feature maps with precise location information and deep feature maps with rich semantics in the CNNs can effectively improve the accuracy of small target detection in remote sensing images.

Download Full-text

Small Target Detection in Hyperspectral Remote Sensing Image Based on Adaptive Parameter SVM

Acta Optica Sinica ◽

10.3788/aos201535.0928001 ◽

2015 ◽

Vol 35 (9) ◽

pp. 0928001

Author(s):

吴一全 Wu Yiquan ◽

周杨 Zhou Yang ◽

龙云淋 Long Yunlin

Keyword(s):

Remote Sensing ◽

Target Detection ◽

Remote Sensing Image ◽

Hyperspectral Remote Sensing ◽

Small Target ◽

Small Target Detection ◽

Adaptive Parameter ◽

Hyperspectral Remote Sensing Image

Download Full-text

A Small Target Detection Research Based on Dynamic Convolution Neural Network

10.21203/rs.3.rs-916747/v1 ◽

2021 ◽

Author(s):

Chenshuai Bai ◽

Kaijun Wu ◽

Dicong Wang ◽

Hong Li ◽

Mingjun Yan ◽

...

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Convolutional Neural Network ◽

Target Detection ◽

Image Data ◽

Remote Sensing Image ◽

Convolution Neural Network ◽

Small Target ◽

Training Process ◽

Small Target Detection

Abstract Because the detection effect of EfficientNet-YOLOv3 target detection algorithm is not very good, this paper proposes a small target detection research based on dynamic convolution neural network. Firstly, the dynamic convolutional neural network is introduced to replace the traditional convolutional neural network, which makes the algorithm model more robust; Secondly, in the training process, the optimization parameters are continuously adjusted to further strengthen the model structure; Finally, in order to prevent over fitting, the Learning Rate and Batch Size parameters are modified during the training process. remote sensing image The results of the proposed algorithm on RSOD remote sensing image data sets show that compared with the original EfficientNet-YOLOv3 algorithm, the (Average Precision, AP) value is increased by 1.93% and the (Log Average Miss Rate ,LAMR) value is reduced by 0.0500; The results of the proposed algorithm on TGRS-HRRSD remote sensing image data set show that compared with the original EfficientNet-YOLOv3 algorithm, the mAP value is increased by 0.07% and the mLAMR value is reduced by 0.0007.

Download Full-text

Improved SSD Algorithm and Its Performance Analysis of Small Target Detection in Remote Sensing Images

Acta Optica Sinica ◽

10.3788/aos201939.0628005 ◽

2019 ◽

Vol 39 (6) ◽

pp. 0628005 ◽

Cited By ~ 2

Author(s):

王俊强 Junqiang Wang ◽

李建胜 Jiansheng Li ◽

周学文 Xuewen Zhou ◽

张旭 Xu Zhang

Keyword(s):

Remote Sensing ◽

Performance Analysis ◽

Target Detection ◽

Small Target ◽

Remote Sensing Images ◽

Small Target Detection

Download Full-text

High-Resolution Remotely Sensed Small Target Detection by Imitating Fly Visual Perception Mechanism

Computational and Mathematical Methods in Medicine ◽

10.1155/2012/789429 ◽

2012 ◽

Vol 2012 ◽

pp. 1-9 ◽

Cited By ~ 1

Author(s):

Fengchen Huang ◽

Lizhong Xu ◽

Min Li ◽

Min Tang

Keyword(s):

Remote Sensing ◽

High Resolution ◽

Visual Perception ◽

Visual System ◽

Target Detection ◽

Hot Spot ◽

Remote Sensing Data ◽

Small Target ◽

Sensing Data ◽

Small Target Detection

The difficulty and limitation of small target detection methods for high-resolution remote sensing data have been a recent research hot spot. Inspired by the information capture and processing theory of fly visual system, this paper endeavors to construct a characterized model of information perception and make use of the advantages of fast and accurate small target detection under complex varied nature environment. The proposed model forms a theoretical basis of small target detection for high-resolution remote sensing data. After the comparison of prevailing simulation mechanism behind fly visual systems, we propose a fly-imitated visual system method of information processing for high-resolution remote sensing data. A small target detector and corresponding detection algorithm are designed by simulating the mechanism of information acquisition, compression, and fusion of fly visual system and the function of pool cell and the character of nonlinear self-adaption. Experiments verify the feasibility and rationality of the proposed small target detection model and fly-imitated visual perception method.

Download Full-text

R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery

Remote Sensing ◽

10.3390/rs11060631 ◽

2019 ◽

Vol 11 (6) ◽

pp. 631 ◽

Cited By ~ 28

Author(s):

Shaoming Zhang ◽

Ruize Wu ◽

Kunyuan Xu ◽

Jianmei Wang ◽

Weiwei Sun

Keyword(s):

Neural Network ◽

Remote Sensing ◽

High Resolution ◽

Convolutional Neural Network ◽

Target Detection ◽

Detection Methods ◽

Optical Remote Sensing ◽

Remote Sensing Imagery ◽

Ship Detection ◽

Inland River

Offshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. However, the classic ship detection methods based on SAR images can cause a high false alarm ratio and be influenced by the sea surface model, especially on inland rivers and in offshore areas. The classic detection methods based on optical images do not perform well on small and gathering ships. This paper adopts the idea of deep networks and presents a fast regional-based convolutional neural network (R-CNN) method to detect ships from high-resolution remote sensing imagery. First, we choose GaoFen-2 optical remote sensing images with a resolution of 1 m and preprocess the images with a support vector machine (SVM) to divide the large detection area into small regions of interest (ROI) that may contain ships. Then, we apply ship detection algorithms based on a region-based convolutional neural network (R-CNN) on ROI images. To improve the detection result of small and gathering ships, we adopt an effective target detection framework, Faster-RCNN, and improve the structure of its original convolutional neural network (CNN), VGG16, by using multiresolution convolutional features and performing ROI pooling on a larger feature map in a region proposal network (RPN). Finally, we compare the most effective classic ship detection method, the deformable part model (DPM), another two widely used target detection frameworks, the single shot multibox detector (SSD) and YOLOv2, the original VGG16-based Faster-RCNN, and our improved Faster-RCNN. Experimental results show that our improved Faster-RCNN method achieves a higher recall and accuracy for small ships and gathering ships. Therefore, it provides a very effective method for offshore and inland river ship detection based on high-resolution remote sensing imagery.

Download Full-text