Search

With the rapid development of artificial intelligence and computer vision, deep learning has become widely used for aircraft detection. However, aircraft detection is still a challenging task due to the small target size and dense arrangement of aircraft and the complex backgrounds in remote sensing images. Existing remote sensing aircraft detection methods were mainly designed based on algorithms employed in general object detection methods. However, these methods either tend to ignore the key structure and size information of aircraft targets or have poor detection effects on densely distributed aircraft targets. In this paper, we propose a novel multi-task aircraft detection algorithm. Firstly, a multi-task joint training method is proposed, which provides richer semantic structure features for bounding box localization through landmark detection. Secondly, a multi-task inference algorithm is introduced that utilizes landmarks to provide additional supervision for bounding box NMS (non-maximum suppression) filtering, effectively reducing false positives. Finally, a novel loss function is proposed as a constrained optimization between bounding boxes and landmarks, which further improves aircraft detection accuracy. Experiments on the UCAS-AOD dataset demonstrated the state-of-the-art precision and efficiency of our proposed method compared to existing approaches. Furthermore, our ablation study revealed that the incorporation of our designed modules could significantly enhance network performance. [ABSTRACT FROM AUTHOR]

Recognizing and classifying natural or artificial geo-objects under complex geo-scenes using remotely sensed data remains a significant challenge due to the heterogeneity in their spatial distribution and sampling bias. In this study, we propose a deep learning method of surface complexity analysis based on multiscale entropy. This method can be used to reduce sampling bias and preserve entropy-based invariance in learning for the semantic segmentation of land use and land cover (LULC) images. Our quantitative models effectively identified and extracted local surface complexity scores, demonstrating their broad applicability. We tested our method using the Gaofen-2 image dataset in mainland China and accurately estimated multiscale complexity. A downstream evaluation revealed that our approach achieved similar or better performance compared to several representative state-of-the-art deep learning methods. This highlights the innovative and significant contribution of our entropy-based complexity analysis and its applicability in improving LULC semantic segmentations through optimal stratified sampling and constrained optimization, which can also potentially be used to enhance semantic segmentation under complex geo-scenes using other machine learning methods. [ABSTRACT FROM AUTHOR]

Mixed (random and stripe) noise will cause serious degradation of optical remotely sensed image quality, making it hard to analyze their contents. In order to remove such noise, various inverse problems are usually constructed with different priors, which can be solved by either model-based optimization methods or discriminative learning methods. However, they have their own drawbacks, such as the former methods are flexible but are time-consuming for the pursuit of good performance; while the later methods are fast but are limited for extensive applications due to their specialized tasks. To fast obtain pleasing results with combination of their merits, in this paper, we propose a novel denoising strategy, namely, Dual Denoiser Driven Convolutional Neural Networks (D3CNNs), to remove both random and stripe noise. The D3CNNs includes the following two key parts: one is that two auxiliary variables respective for the denoised image and the stripe noise are introduced to reformulate the inverse problem as a constrained optimization problem, which can be iteratively solved by employing the alternating direction method of multipliers (ADMM). The other is that the U-shape network is used for the denoised auxiliary variable while the residual CNN (RCNN) for the stripe auxiliary variable. The subjectively and objectively comparable results of experiments on both synthetic and real-world remotely sensed images verify that the proposed method is effective and is even better than the state-of-the-arts. [ABSTRACT FROM AUTHOR]

With the development of spaceborne processing technologies, the demand for on-board processing has risen sharply. Against this background, spaceborne Interferometric Synthetic Aperture Radar (InSAR) processing has become an important research area. In many cases, high processing capacity is required during on-board InSAR processing, yet Field-Programmable Gate Array (FPGA) resources on the satellites are limited. To improve the performance of spaceborne remote sensing processing, this paper designs a high-performing FPGA system for the coarse registration and interferogram generation process of InSAR. Moreover, to address this dual-constraint problem of resource and processing capacity, the paper proposes an FPGA design method based on the gradient descent theory, which can identify the optimum trade-off scheme between two such constraints. Finally, the proposed system design and method are implemented in FPGA. Experiments showed that the FPGA system outperformed the NVIDIA (Santa Clara, CA, USA) GTX Titan Black Graphics Processing Unit (GPU), and the optimum trade-off scheme only increases the entire time by 1.1% but reduces the FPGA BRAM usage by 8.7%. The experimental results proved the effectiveness and validity of the proposed system and method. [ABSTRACT FROM AUTHOR]

Aiming at maximizing waveform diversity gain when designing a phase-coded multiple-input multiple-output (MIMO) radar waveform set, it is desirable that all waveforms are orthogonal to each other. Hence, the lowest possible peak cross-correlation ratio (PCCR) is expected. Meanwhile, low peak auto-correlation side-lobe ratio (PASR) is needed for good detection performance. However, it is difficult to obtain a closed form solution to the waveform set from the expected values of the PASR and PCCR. In this paper, the waveform set design problem is modeled as a multi-objective, NP-hard constrained optimization problem. Unlike conventional approaches that design the waveform set through optimizing a weighted sum objective function, the proposed optimization model evaluates the performance of multi-objective functions based on Pareto level and obtains a set of Pareto non-dominated solutions. That means that the MIMO radar system can trade off each objective function for different requirements. To solve this problem, this paper presents a multi-objective quantum genetic algorithm (MoQGA) based on the framework of quantum genetic algorithm. A new population update strategy for the MoQGA is designed based on the proposed model. Compared to the state-of-the-art methods, like BiST and Multi-CAN, the PASR and PCCR metrics of the waveform set are 0.95–3.91 dB lower with the parameters of the numerical simulation. The MoQGA is able to minimize PASR and PCCR of the MIMO radar waveform set simultaneously. [ABSTRACT FROM AUTHOR]

Segmentation, which is usually the first step in object-based image analysis (OBIA), greatly influences the quality of final OBIA results. In many existing multi-scale segmentation algorithms, a common problem is that under-segmentation and over-segmentation always coexist at any scale. To address this issue, we propose a new method that integrates the newly developed constrained spectral variance difference (CSVD) and the edge penalty (EP). First, initial segments are produced by a fast scan. Second, the generated segments are merged via a global mutual best-fitting strategy using the CSVD and EP as merging criteria. Finally, very small objects are merged with their nearest neighbors to eliminate the remaining noise. A series of experiments based on three sets of remote sensing images, each with different spatial resolutions, were conducted to evaluate the effectiveness of the proposed method. Both visual and quantitative assessments were performed, and the results show that large objects were better preserved as integral entities while small objects were also still effectively delineated. The results were also found to be superior to those from eCongnition's multi-scale segmentation. [ABSTRACT FROM AUTHOR]

The problem of detecting point like targets over a glistening surface is investigated in this manuscript, and the design of an optimal waveform through a two-step process for a multipath exploitation radar is proposed. In the first step, a non-adaptive waveform is transmitted and a constrained Generalized Likelihood Ratio Test (GLRT) detector is deduced at reception which exploits multipath returns in the range cell under test by modelling the target echo as a superposition of the direct plus the multipath returns. Under the hypothesis of heterogeneous environments, thus by assuming a compound-Gaussian distribution for the clutter return, this latter is estimated in the range cell under test through the secondary data, which are collected from the out-of-bin cells. The Fixed Point Estimate (FPE) algorithm is applied in the clutter estimation, then used to design the adaptive waveform for transmission in the second step of the algorithm, in order to suppress the clutter coming from the adjacent cells. The proposed GLRT is also used at the end of the second transmission for the final decision. Extensive performance evaluation of the proposed detector and adaptive waveform for various multipath scenarios is presented. The performance analysis prove that the proposed method improves the Signal-to-Clutter Ratio (SCR) of the received signal, and the detection performance with multipath exploitation. [ABSTRACT FROM AUTHOR]

We propose a new constrained optimization approach to hyperspectral (HS) image restoration. Most existing methods restore a desirable HS image by solving some optimization problems, consisting of a regularization term(s) and a data-fidelity term(s). The methods have to handle a regularization term(s) and a data-fidelity term(s) simultaneously in one objective function; therefore, we need to carefully control the hyperparameter(s) that balances these terms. However, the setting of such hyperparameters is often a troublesome task because their suitable values depend strongly on the regularization terms adopted and the noise intensities on a given observation. Our proposed method is formulated as a convex optimization problem, utilizing a novel hybrid regularization technique named Hybrid Spatio-Spectral Total Variation (HSSTV) and incorporating data-fidelity as hard constraints. HSSTV has a strong noise and artifact removal ability while avoiding oversmoothing and spectral distortion, without combining other regularizations such as low-rank modeling-based ones. In addition, the constraint-type data-fidelity enables us to translate the hyperparameters that balance between regularization and data-fidelity to the upper bounds of the degree of data-fidelity that can be set in a much easier manner. We also develop an efficient algorithm based on the alternating direction method of multipliers (ADMM) to efficiently solve the optimization problem. We illustrate the advantages of the proposed method over various HS image restoration methods through comprehensive experiments, including state-of-the-art ones. [ABSTRACT FROM AUTHOR]

Pseudo-Invariant Calibration Sites (PICS) have been widely used by the remote sensing community in recent decades for post-launch absolute calibration, cross-calibration, and the monitoring of radiometric stability. The Committee on Earth Observation Satellites (CEOS) has established several official PICS for these purposes. Of these, Libya-4 is the most commonly used, due to its high uniformity and stability. The site was chosen as a large-area site for medium resolution sensors, and with high-resolution sensors now common, smaller sites are being identified. This work has identified an improved area of interest (AOI) within Libya-4 by using combined Landsat 8 and Sentinel 2 data. The Optimized Ground Target (OGT) was determined by calculating the coefficient of variation along with the use of a quasi-Newton optimization algorithm combined with the Basin–Hopping global optimization technique to constrain a search area small enough to perform a final brute-force refinement. The Coefficient of Variation CV of the proposed OGT is significantly lower than that in the original CEOS area, with differences between the CV of both zones in the order of 1% in the visible near-infrared (VNIR) bands. This new AOI has the potential to improve the cross-calibration between high-resolution sensors using the PICS methodology through an OGT with more homogeneous and stable characteristics. [ABSTRACT FROM AUTHOR]