Object detection in remote sensing imagery using a discriminatively trained mixture model

Cheng, Gong; Han, Junwei; Guo, Lei; Qian, Xiaoliang; Zhou, Peicheng; Yao, Xiwen; Hu, Xintao

doi:10.1016/j.isprsjprs.2013.08.001

Cited by 149 publications

(90 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In these experiments, we employ the precision-recall (PR) curve, average precision (AP) [13], IoU-Recall (IR) curve [34], and F1-measure [28] to quantitatively evaluate the performance of our HEM-CNN method. They are standard and widely used metrics in many target detection works, such as those in [1,11,13,24,26,28,35].…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…So many scholars tried to mine the more representative hard examples to balance the proportion of foreground-background class examples. Some promising works were reported in [23,[28][29][30]. Cheng et al [28] adopted a two-step iterative training strategy that alternates between updating the detection model given the training set, and selecting hard negative examples using a updated detection model.…”

Section: Introductionmentioning

confidence: 99%

“…Some promising works were reported in [23,[28][29][30]. Cheng et al [28] adopted a two-step iterative training strategy that alternates between updating the detection model given the training set, and selecting hard negative examples using a updated detection model. In order to reduce the spurious targets in candidate regions and improve the accuracy of the region proposal network, Zhang et al [23] used the output score map of the region proposal network to collect the hard negative examples and employed an iterative process for retraining the network.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Airport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining

et al. 2017

View full text Add to dashboard Cite

Abstract:Deep convolutional neural network (CNN) achieves outstanding performance in the field of target detection. As one of the most typical targets in remote sensing images (RSIs), airport has attracted increasing attention in recent years. However, the essential challenge for using deep CNN to detect airport is the great imbalance between the number of airports and background examples in large-scale RSIs, which may lead to over-fitting. In this paper, we develop a hard example mining and weight-balanced strategy to construct a novel end-to-end convolutional neural network for airport detection. The initial motivation of the proposed method is that backgrounds contain an overwhelming number of easy examples and a few hard examples. Therefore, we design a hard example mining layer to automatically select hard examples by their losses, and implement a new weight-balanced loss function to optimize CNN. Meanwhile, the cascade design of proposal extraction and object detection in our network releases the constraint on input image size and reduces spurious false positives. Compared with geometric characteristics and low-level manually designed features, the hard example mining based network could extract high-level features, which is more robust for airport detection in complex environment. The proposed method is validated on a multi-scale dataset with complex background collected from Google Earth. The experimental results demonstrate that our proposed method is robust, and superior to the state-of-the-art airport detection models.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Airport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining

et al. 2017

View full text Add to dashboard Cite

show abstract

“…A more difficult problem is when only a single degraded image is available. Solutions for such cases have been introduced only in recent times [6]- [10].…”

Section: Introductionmentioning

confidence: 99%

Color Attenuation Prior (CAP) for Single Image Dehazing

Navale¹,

Sawant²,

Bagal³

2018

int. jour. eng. com. sci

View full text Add to dashboard Cite

Abstract:Single image haze removal has been a challenging problem due to its ill-posed nature. In this paper, we have used a simple but powerful color attenuation prior for haze removal from a single input hazy image. By creating a linear model for modeling the scene depth of the hazy image under this novel prior and learning the parameters of the model with a supervised learning method, the depth information can be well recovered. With the depth map of the hazy image, we can easily estimate the transmission and restore the scene radiance via the atmospheric scattering model, and thus effectively remove the haze from a single image. Experimental results show that the proposed approach outperforms state-of-the-art haze removal algorithms in terms of both efficiency and the dehazing effect.

show abstract

“…Huang et al presented a new ship-detection method based on multi-scale heterogeneities with few parameters to be determined [13]. To draw on the advantages of the above methods, the rich information of a target, such as its texture, spatial relationship, shape and structure has been considered for better target-detection results in SAR imagery [14][15][16]. In [17], regional features were utilized to implement the global scattering center model-based region-to-point match scheme to improve the detection performance.…”

Section: Introductionmentioning

confidence: 99%

Mixture Statistical Distribution Based Multiple Component Model for Target Detection in High Resolution SAR Imagery

Liu

et al. 2017

IJGI

View full text Add to dashboard Cite

This paper proposes an innovative Mixture Statistical Distribution Based MultipleComponent (MSDMC) model for target detection in high spatial resolution Synthetic Aperture Radar (SAR) images. Traditional detection algorithms usually ignore the spatial relationship among the target's components. In the presented method, however, both the structural information and the statistical distribution are considered to better recognize the target. Firstly, the method based on compressed sensing reconstruction is used to recover the SAR image. Then, the multiple component model composed of a root filter and some corresponding part filters is applied to describe the structural information of the target. In the following step, mixture statistical distributions are utilised to discriminate the target from the background, and the Method of Logarithmic Cumulants (MoLC) based Expectation Maximization (EM) approach is adopted to estimate the parameters of the mixture statistical distribution model, which will be finally merged into the proposed MSDMC framework together with the multiple component model. In the experiment, the aeroplanes and the electrical power towers in TerraSAR-X SAR images are detected at three spatial resolutions. The results indicate that the presented MSDMC Model has potential for improving the detection performance compared with the state-of-the-art SAR target detection methods.

show abstract

Object detection in remote sensing imagery using a discriminatively trained mixture model

Cited by 149 publications

References 38 publications

Airport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining

Airport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining

Color Attenuation Prior (CAP) for Single Image Dehazing

Mixture Statistical Distribution Based Multiple Component Model for Target Detection in High Resolution SAR Imagery

Contact Info

Product

Resources

About