Change detection (CD) is one of the main applications of remote sensing. With the increasing popularity of deep learning, most recent developments of CD methods have introduced the use of deep learning techniques to increase the accuracy and automation level over traditional methods. However, when using supervised CD methods, a large amount of labeled data is needed to train deep convolutional networks with millions of parameters. These labeled data are difficult to acquire for CD tasks. To address this limitation, a novel semisupervised convolutional network for CD (SemiCDNet) is proposed based on a generative adversarial network (GAN). First, both the labeled data and unlabeled data are input into the segmentation network to produce initial predictions and entropy maps. Then, to exploit the potential of unlabeled data, two discriminators are adopted to enforce the feature distribution consistency of segmentation maps and entropy maps between the labeled and unlabeled data. During the competitive training, the generator is continuously regularized by utilizing the unlabeled information, thus improving its generalization capability. The effectiveness and reliability of our proposed method are verified on two high-resolution remote sensing data sets. Extensive experimental results demonstrate the superiority of the proposed method against other state-of-the-art approaches.

SemiCDNet: A Semisupervised Convolutional Neural Network for Change Detection in High Resolution Remote-Sensing Images

Stripe and random noise are two different degradation phenomena that commonly coexist in optical remote sensing images, and they are often modeled as inverse problems. In model-based inverse problems, analysis and synthesis sparse representations (SSRs) are used as regularization terms to obtain approximate solutions due to their respective merits, i.e., the nonzero coefficients in SSR are usually used to describe an image, while the indexes of zeros in analysis sparse representation (ASR) are used to characterize the stripe. Inspired by these merits, we propose a unified variational framework, called a joint analysis and weighted synthesis (JAWS) sparsity model, to simultaneously separate the clean image and the stripe from a single optical remote sensing image. To solve the JAWS sparsity model efficiently, an alternating minimization optimization strategy is first employed to separate it into two subproblems that are used for different tasks. One called as weighted SSR (WSSR) is the main for optical remote sensing image denoising, which can be effectively solved by employing the weighted singular value thresholding operator, while the other called as ASR is the main approach for optical remote sensing image destriping, which is optimized by adopting the split Bregman iteration. By minimizing the two subproblems alternatively, the proposed JAWS sparsity model is efficiently solved. Finally, both quantitative and qualitative results of experiments on synthetic and real-world optical remote sensing images validate that the proposed approach is effective and even better than the state of the arts.

Joint Analysis and Weighted Synthesis Sparsity Priors for Simultaneous Denoising and Destriping Optical Remote Sensing Images

Stripe and random noise are two different degradation phenomena commonly co-existing in optical remote sensing images, which are often modelled as inverse problems, respectively. When solvi...

Unidirectional variation and deep CNN denoiser priors for simultaneously destriping and denoising optical remote sensing images

Image enhancement with the preservation of brightness and structures by employing contrast limited dynamic quadri-histogram equalization

Robust contact-point detection from pantograph-catenary infrared images by employing horizontal-vertical enhancement operator

Optical remote sensing image enhancement with weak structure preservation via spatially adaptive gamma correction

The invention discloses a multi-transducer fusion-based super-near distance autonomous navigation device and method. The super-near distance autonomous navigation device comprises a transducer subsystem, an information fusion subsystem, a sensor scanning structure and an indication guide structure, wherein a visible light imaging sensor and an infrared imaging sensor are combined together, and data are acquired in a passive measurement mode that the visible light imaging sensor and the infrared imaging sensor are combined with an optical imaging sensor, or in an active measurement mode that the visible light imaging sensor and the infrared imaging sensor are combined with a laser distance measurement sensor. Autonomous navigation can be completed in three periods, that is, a navigation mode that the visible light imaging sensor and a double-lens infrared imaging sensor are combined is adopted in a remote distance section, a navigation mode that a double-lens visible light imaging sensor and the double-lens infrared imaging sensor are combined is adopted in a near distance section, and a navigation mode of a laser distance measurement sensor array is adopted in a very near distance section. By adopting the device and the method, the view field and the detection range are widened, the problem of shielding in passive measurement is effectively solved, the precision of measured data is ensured, and the navigation efficiency and the security and the reliability of navigation are improved.

Multi-transducer fusion-based super-near distance autonomous navigation device and method

Infrared small-target detection is a key technology for the infrared search and track system (IRST), but some problems still exist, such as false detections in complex backgrounds and clutter. To solve these problems, a novel image patch tensor (IPT) model for infrared small-target detection is proposed. First, to better estimate the background component, we utilize the Laplace operator to approximate the background tensor rank. Secondly, we combined local gradient features and highlighted area indicators to model the local targets prior, which can effectively suppress the complex background clutter. The proposed model was solved by the alternating direction method of multipliers (ADMM). The experimental results on various scenes show that our model achieves an excellent performance in suppressing strong edge clutter and estimating small targets.

/pdf/an-enhanced-image-patch-tensor-decompostion-for-infrared-31i65zp4.pdf

An Enhanced Image Patch Tensor Decompostion for Infrared Small Target Detection

The present invention discloses a multi-sensor merging based super-close distance autonomous navigation apparatus and method. The apparatus includes a sensor subsystem, an information merging subsystem, a sensor scanning structure, and an orientation guiding structure, wherein a visible light imaging sensor and an infrared imaging sensor are combined together, and data are acquired by combining a passive measurement mode composed of an optical imaging sensor and an active measurement mode composed of a laser distance measuring sensor. Autonomous navigation is divided into three stages, that is, a remote distance stage, implemented by adopting a navigation mode where a binocular visible light imaging sensor and a binocular infrared imaging sensor are combined, a close distance stage, implemented by adopting a navigation mode where a binocular visible light imaging sensor, a binocular infrared imaging sensor and a laser distance measuring sensor array are combined, and an ultra-close distance stage, implemented by adopting a navigation mode of a laser distance measuring sensor array. Through the present invention, the field of view and the exploration range are widened, the problem of shielding existing in passive measurement is effectively solved, the precision of data measurement is ensured, and the navigation efficiency and the safety and reliability of navigation are improved.

Zhengtao Li

Papers

Optical remote sensing image enhancement with weak structure preservation via spatially adaptive gamma correction

Unidirectional variation and deep CNN denoiser priors for simultaneously destriping and denoising optical remote sensing images

Multi-transducer fusion-based super-near distance autonomous navigation device and method

An Enhanced Image Patch Tensor Decompostion for Infrared Small Target Detection

Multi-sensor merging based super-close distance autonomous navigation apparatus and method