Search

Detecting faint and diminutive infrared targets devoid of clearly defined shape and texture details in intricate surroundings remains a formidable challenge within the domain of target detection. Current methodologies employing deep neural networks and pooling operations can easily cause small target loss, resulting in suboptimal detection outcomes. To address these issues, we design an innovative dynamic context-aware pyramid network. It comprises three core modules: dynamic context modulation (DCM), dynamic pyramid context (DPC), and shuffle attention fusion (SAF). Specifically, the DCM module is designed to adaptively capture diverse-scale information from input images, adapting to various target dimensions, and enhancing the feature representation capabilities crucial for effective target detection. Subsequently, the DPC module adaptively captures multiscale features and better utilizes contextual information by aggregating multiple DCM modules. This facilitates the retention of essential semantic information about small infrared targets within deeper network layers. Finally, through the designed SAF module, we facilitate the exchange of information within the same layer and establish correlations between different layers, ensuring the fusion of shallow spatial positional information and deep semantic information to enhance the overall detection performance. Furthermore, comprehensive ablation studies are conducted to substantiate the efficacy of the designed modules within the proposed network architecture. Simultaneously, we conducted a comparative analysis of the proposed network algorithm against several state-of-the-art methodologies for infrared small target detection, employing multiple evaluation metrics. The results consistently demonstrated the proposed model attains superior detection performance on the publicly available IRSTD-1 k, SIRST-Aug, and NUDT-SIRST datasets.

The camera response function (CRF) establishes a numerical mapping between focal plane radiance, camera imaging parameters, and the intensity of output images. It plays a significant role in areas such as high dynamic range imaging and image processing. To establish an accurate response model for time delay integration (TDI) complementary metal–oxide–semiconductor (CMOS) imaging systems, this article proposes a radiometric calibration method for TDI CMOS imaging systems based on complex real-world scene images. The study begins by conducting an extensive analysis of the data link within the TDI CMOS imaging system, which serves as the foundation for establishing its a priori theoretical response model. Subsequently, the problem of solving the CRF model is transformed into an overdetermined equation established through the least square method. The optimal solution for this equation is obtained by singular value decomposition, which leads to the derivation of a 3-D response function for the imaging system. Finally, under consistent optical radiation conditions, radiation calibration experiments are performed on various targets using a self-developed TDI CMOS imaging system. The CRF is obtained based on the captured experimental image data. Furthermore, this article's approach is compared with the widely adopted linear fitting method commonly used within the respective field. The experimental results show that the visually perceived quality, structural similarity, mean grayscale, mean gradient, entropy, and standard deviation of images synthesized using the CRF proposed in this article are closer to those of actual captured images. The proposed method demonstrates higher accuracy and can provide a reliable basis for applications such as radiation response calibration of on-orbit spaceborne payloads, selection of imaging parameters, and multiexposure fusion of remote sensing images.

The intricate web of cancer biology is governed by the active participation of long non-coding RNAs (lncRNAs), playing crucial roles in cancer cells’ proliferation, migration, and drug resistance. Pioneering research driven by machine learning algorithms has unveiled the profound ability of specific combinations of lncRNAs to predict the prognosis of cancer patients. These findings highlight the transformative potential of lncRNAs as powerful therapeutic targets and prognostic markers. In this comprehensive review, we meticulously examined the landscape of lncRNAs in predicting the prognosis of the top five cancers and other malignancies, aiming to provide a compelling reference for future research endeavours. Leveraging the power of machine learning techniques, we explored the predictive capabilities of diverse lncRNA combinations, revealing their unprecedented potential to accurately determine patient outcomes.

When a remote sensing camera work in push-broom mode, the obtained image usually contains significant stripe noise and random noise due to differences in detector response and environmental factors. Traditional approaches typically treat them as two independent problems and process the image sequentially, which not only increases the risk of information loss and structural damage, but also faces the situation of noise mutual influence. To overcome the drawbacks of traditional methods, this paper leverages the double low-rank characteristics in the underlying prior of degraded images and presents a novel approach for addressing both destriping and denoising tasks simultaneously. We utilize the commonality that both can be treated as inverse problems and place them in the same optimization framework, while designing an alternating direction method of multipliers (ADMM) strategy for solving them, achieving the synchronous removal of both stripe noise and random noise. Compared with traditional approaches, synchronous denoising technology can more accurately evaluate the distribution characteristics of noise, better utilize the original information of the image, and achieve better destriping and denoising results. To assess the efficacy of the proposed algorithm, extensive simulations and experiments were conducted in this paper. The results show that compared with state-of-the-art algorithms, the proposed method can more effectively suppress random noise, achieve better synchronous denoising results, and it exhibits a stronger robustness.

In order to obtain high-quality images, the application of low-illumination image enhancement techniques plays a vital role in enhancing the overall visual appeal. However, it is particularly difficult to enhance an image while maintaining the original information of the scene. The augmentation method based on Retinex theory is widely considered as one of the representative techniques for such problems, but this method still has some limitations. First of all, noise is easily ignored in the process of model building, and the robustness of the model needs to be improved. Secondly, the image decomposition is less effective, so that part of the image information is not effectively presented. Finally, the optimization procedure is computationally complicated. This paper introduces a novel approach for enhancing low-illumination images by utilizing the relative deviation of local gradients. The proposed method aims to address the challenges associated with low-illumination images and offers a solution to these issues. In this paper, local gradient relative deviation is used as a constraint term and a noise term is added to highlight the image texture and structure and improve the robustness of the models, considering that LP achieves piecewise smoothing with better sparsity compared to the sum norm commonly used by L1 and L2 norms. In this paper, the L2−LP norm is used to constrain the model, which smooths the illumination component and better preserves the details of the reflectance component. In addition, to efficiently solve the optimization problem, the alternating direction multiplier method is chosen to transform the optimization process into the solution of several sub-problems. In comparison to traditional Retinex models, the proposed method excels in its ability to simultaneously enhance the image and suppress noise effectively. The experimental outcomes demonstrate the effectiveness of the proposed model in enhancing both simulated and real data. This approach can be applied to low-illumination remote sensing images to obtain high-quality remote sensing image data.

Abstract Background Endophytic actinomycetes, as emerging sources of bioactive metabolites, have been paid great attention over the years. Recent reports demonstrated that endophytic streptomycetes could yield compounds with potent anticancer properties that may be developed as chemotherapeutic drugs. Results Here, a total of 15 actinomycete-like isolates were obtained from the root tissues of Lilium davidii var. unicolor (Hoog) Cotton based on their morphological appearance, mycelia coloration and diffusible pigments. The preliminary screening of antagonistic capabilities of the 15 isolates showed that isolate LRE541 displayed antimicrobial activities against all of the seven tested pathogenic microorganisms. Further in vitro cytotoxicity test of the LRE541 extract revealed that this isolate possesses potent anticancer activities with IC50 values of 0.021, 0.2904, 1.484, 4.861, 6.986, 8.106, 10.87, 12.98, and 16.94 μg/mL against cancer cell lines RKO, 7901, HepG2, CAL-27, MCF-7, K562, Hela, SW1990, and A549, respectively. LRE541 was characterized and identified as belonging to the genus Streptomyces based on the 16S rRNA gene sequence analysis. It produced extensively branched red substrate and vivid pink aerial hyphae that changed into amaranth, with elliptic spores sessile to the aerial mycelia. To further explore the mechanism underlying the decrease of cancer cell viability following the LRE541 extract treatment, cell apoptosis and cell cycle arrest assays were conducted in two cancer cell lines, RKO and 7901. The result demonstrated that LRE541 extract inhibited cell proliferation of RKO and 7901 by causing cell cycle arrest both at the S phase and inducing apoptosis in a dose-dependent manner. The chemical profile of LRE541 extract performed by the UHPLC-MS/MS analysis revealed the presence of thirty-nine antitumor compounds in the extract. Further chemical investigation of the LRE541 extract led to the discovery of one prenylated indole diketopiperazine (DKP) alkaloid, elucidated as neoechinulin A, a known antitumor agent firstly detected in Streptomyces; two anthraquinones 4-deoxy-ε-pyrromycinone (1) and epsilon-pyrromycinone (2) both displaying anticancer activities against RKO, SW1990, A549, and HepG2 with IC50 values of 14.96 ± 2.6 − 20.42 ± 4.24 μg/mL for (1); 12.9 ± 2.13, 19.3 ± 4.32, 16.8 ± 0.75, and 18.6 ± 3.03 μg/mL for (2), respectively. Conclusion Our work evaluated the anticarcinogenic potential of the endophyte, Streptomyces sp. LRE541 and obtained one prenylated indole diketopiperazine alkaloid and two anthraquinones. Neoechinulin A, as a known antitumor agent, was identified for the first time in Streptomyces. Though previously found in Streptomyces, epsilon-pyrromycinone and 4-deoxy-ε-pyrromycinone were firstly shown to possess anticancer activities. Graphical Abstract

Soil fungal community characteristics of alpine timberlines are unclear. In this study, soil fungal communities in five vegetation zones across timberlines on the south and north slopes of Sejila Mountain in Tibet, China were investigated. The results show that the alpha diversity of soil fungi was not different between the north- and south-facing timberlines or among the five vegetation zones. Archaeorhizomyces (Ascomycota) was a dominant genus at the south-facing timberline, whereas the ectomycorrhizal genus Russula (Basidiomycota) decreased with decreasing Abies georgei coverage and density at the north-facing timberline. Saprotrophic soil fungi were dominant, but their relative abundance changed little among the vegetation zones at the south timberline, whereas ectomycorrhizal fungi decreased with tree hosts at the north timberline. Soil fungal community characteristics were related to coverage and density, soil pH and ammonium nitrogen at the north timberline, whereas they had no associations with the vegetation and soil factors at the south timberline. In conclusion, timberline and A. georgei presence exerted apparent influences on the soil fungal community structure and function in this study. The findings may enhance our understanding of the distribution of soil fungal communities at the timberlines of Sejila Mountain.

The traditional signature-based detection method requires detailed manual analysis to extract the signatures of malicious samples, and requires a large number of manual markers to maintain the signature library, which brings a great time and resource costs, and makes it difficult to adapt to the rapid generation and mutation of malware. Methods based on traditional machine learning often require a lot of time and resources in sample labeling, which results in a sufficient inventory of unlabeled samples but not directly usable. In view of these issues, this paper proposes an effective malware classification framework based on malware visualization and semi-supervised learning. This framework includes mainly three parts: malware visualization, feature extraction, and classification algorithm. Firstly, binary files are processed directly through visual methods, without assembly, decompression, and decryption; Then the global and local features of the gray image are extracted, and the visual image features extracted are fused on the whole by a special feature fusion method to eliminate the exclusion between different feature variables. Finally, an improved collaborative learning algorithm is proposed to continuously train and optimize the classifier by introducing features of inexpensive unlabeled samples. The proposed framework was evaluated over two extensively researched benchmark datasets, i.e., Malimg and Microsoft. The results show that compared with traditional machine learning algorithms, the improved collaborative learning algorithm can not only reduce the cost of sample labeling but also can continuously improve the model performance through the input of unlabeled samples, thereby achieving higher classification accuracy.

A dynamic vision sensor is an optical sensor that focuses on dynamic changes and outputs event information containing only position, time, and polarity. It has the advantages of high temporal resolution, high dynamic range, low data volume, and low power consumption. However, a single event can only indicate that the increase or decrease in light exceeds the threshold at a certain pixel position and a certain moment. In order to further study the ability and characteristics of event information to represent targets, this paper proposes an event information visualization method with adaptive temporal resolution. Compared with methods with constant time intervals and a constant number of events, it can better convert event information into pseudo-frame images. Additionally, in order to explore whether the pseudo-frame image can efficiently complete the task of target detection according to its characteristics, this paper designs a target detection network named YOLOE. Compared with other algorithms, it has a more balanced detection effect. By constructing a dataset and conducting experimental verification, the detection accuracy of the image obtained by the event information visualization method with adaptive temporal resolution was 5.11% and 4.74% higher than that obtained using methods with a constant time interval and number of events, respectively. The average detection accuracy of pseudo-frame images in the YOLOE network designed in this paper is 85.11%, and the number of detection frames per second is 109. Therefore, the effectiveness of the proposed visualization method and the good performance of the designed detection network are verified.

Abstract Objective We aimed to understand the basic characteristics of the underground seed bank of Pinus densata forest and its relationship with aboveground vegetation, to provide a theoretical basis for vegetation restoration. Methods The study sites were Dongjiu Bridge (DJ), Linji Bridge (LZ), and Birishen Mountain Scenic Spot (RB) in Gongbu Nature Reserve, Southeast Tibet, China. Species composition and distribution pattern of the underground seed bank in P. densata forest were analyzed. Germination data and field investigations were used to examine the similarities between aboveground vegetation and underground seed banks, and their responses to the environment. Results There were 47 species belonging to 27 families in the underground seed bank of the P. densata forest. Asteraceae, Rosaceae, Labiatae, and Poaceae were dominant, accounting for 40.4% of the total number of families. Underground seed density was 2,114, 1,952, and 1,141 seeds/m2 in DJ, LZ, and BR, respectively. The percentage of different life‐forms in each sampling location was shown to be perennial herbs > shrubs > annual herbs > trees > subshrubs. The Shannon–Wiener diversity index, Margalef richness index, and Simpson's dominance index of each sample showed that species decreased with higher elevation, while the Pielou evenness index showed the opposite trend. Elevation, slope position, slope aspect, and slope were positively correlated with the Pielou evenness index and negatively correlated with the Shannon–Wiener diversity index, Margalef richness index, and Simpson's dominance index. The Sørensen index, comparing the similarity between the underground seed bank and aboveground vegetation of DJ, LZ, and BR was 0.46, 0.35, and 0.31, respectively. Conclusion The underground seed bank of P. densata forest has high seed density and high species richness, but there was little similarity between aboveground vegetation and underground seed bank. Elevation and slope position had a great influence on the uniformity of species distribution.

The traditional label propagation algorithm (LPA) iteratively propagates labels from a small number of labeled samples to many unlabeled ones based on the sample similarities. However, due to the randomness of label propagations, and LPA's weak ability to deal with uncertain points, the label error may be continuously expanded during the propagation process. In this paper, the algorithm label propagation based on roll-back detection and credibility assessment (LPRC) is proposed. A credit evaluation of the unlabeled samples is carried out before the selection of samples in each round of label propagation, which makes sure that the samples with more certainty can be labeled first. Furthermore, a roll-back detection mechanism is introduced in the iterative process to improve the label propagation accuracy. At last, our method is compared with 9 algorithms based on UCI datasets, and the results demonstrated that our method can achieve better classification performance, especially when the number of labeled samples is small. When the labeled samples only account for 1% of the total sample number of each synthetic dataset, the classification accuracy of LPRC improved by at least 26.31% in dataset circles, and more than 13.99%, 15.22% than most of the algorithms compared in dataset moons and varied, respectively. When the labeled samples account for 2% of the total sample number of each dataset in UCI datasets, the accuracy (take the average value of 50 experiments) of LPRC improved in an average value of 23.20% in dataset wine, 20.82% in dataset iris, 4.25% in dataset australian, and 6.75% in dataset breast. And the accuracy increases with the number of labeled samples.

The remote sensing imaging environment is complex, in which many factors cause image blur. Thus, without prior knowledge, the restoration model established to obtain clear images can only rely on the observed blurry images. We still build the prior with extreme pixels but no longer traverse all pixels, such as the extreme channels. The features are extracted in units of patches, which are segmented from an image and partially overlap with each other. In this paper, we design a new prior, i.e., overlapped patches’ non-linear (OPNL) prior, derived from the ratio of extreme pixels affected by blurring in patches. The analysis of more than 5000 remote sensing images confirms that OPNL prior prefers clear images rather than blurry images in the restoration process. The complexity of the optimization problem is increased due to the introduction of OPNL prior, which makes it impossible to solve it directly. A related solving algorithm is established based on the projected alternating minimization (PAM) algorithm combined with the half-quadratic splitting method, the fast iterative shrinkage-thresholding algorithm (FISTA), fast Fourier transform (FFT), etc. Numerous experiments prove that this algorithm has excellent stability and effectiveness and has obtained competitive processing results in restoring remote sensing images.

Infrared dim small target detection is the critical technology in the situational awareness field currently. The detection algorithm of the infrared patch image (IPI) model combined with the total variation term is a recent research hotspot in this field, but there is an obvious staircase effect in target detection, which reduces the detection accuracy to some extent. This paper further investigates the problem of accurate detection of infrared dim small targets and a novel method based on total variation weighted low-rank constraint (TVWLR) is proposed. According to the overlapping edge information of image background structure characteristics, the weights of constraint low-rank items are adaptively determined to effectively suppress the staircase effect and enhance the details. Moreover, an optimization algorithm combined with the augmented Lagrange multiplier method is proposed to solve the established TVWLR model. Finally, the experimental results of multiple sequence images indicate that the proposed algorithm has obvious improvements in detection accuracy, including receiver operating characteristic (ROC) curve, background suppression factor (BSF) and signal-to-clutter ratio gain (SCRG). Furthermore, the proposed method has stronger robustness under complex background conditions such as buildings and trees.

In this paper, an algorithm based on local binary pattern (LBP) is proposed to obtain clear remote sensing images under the premise of unknown causes of blurring. We find that LBP can completely record the texture features of the images, which will not change widely due to the generation of blur. Therefore, LBP prior is proposed, which can filter out the pixels containing important textures in the blurry image through the mapping relationship. The corresponding processing methods are adopted for different types of pixels to cope with the challenges brought by the rich texture and details of remote sensing images and prevent over-sharpening. However, the existence of LBP prior increases the difficulty of solving the model. To solve the model, we construct the projected alternating minimization (PAM) algorithm that involves the construction of the mapping matrix, the fast iterative shrinkage-thresholding algorithm (FISTA) and the half-quadratic splitting method. Experiments with the AID dataset show that the proposed method can achieve highly competitive processing results for remote sensing images.

Stripe noise is a common condition that has a considerable impact on the quality of the images. Therefore, stripe noise removal (destriping) is a tremendously important step in image processing. Since the existing destriping models cause different degrees of ripple effects, in this paper a new model, based on total variation (TV) regularization, global low rank and directional sparsity constraints, is proposed for the removal of vertical stripes. TV regularization is used to preserve details, and the global low rank and directional sparsity are used to constrain stripe noise. The directional and structural characteristics of stripe noise are fully utilized to achieve a better removal effect. Moreover, we designed an alternating minimization scheme to obtain the optimal solution. Simulation and actual experimental data show that the proposed model has strong robustness and is superior to existing competitive destriping models, both subjectively and objectively.

The improper setting of exposure time for the space camera will cause serious image quality degradation (overexposure or underexposure) in the imaging process. In order to solve the problem of insufficient utilization of the camera’s dynamic range to obtain high-quality original images, an automatic exposure method for plane array remote sensing images based on two-dimensional entropy is proposed. First, a two-dimensional entropy-based image exposure quality evaluation model is proposed. The two-dimensional entropy matrix of the image is partitioned to distinguish the saturated areas (region of overexposure and underexposure) and the unsaturated areas (region of propitious exposure) from the original image. The ratio of the saturated area is used as an evaluating indicator of image exposure quality, which is more sensitive to the brightness, edges, information volume, and signal-to-noise ratio of the image. Then, the cubic spline interpolation method is applied to fit the exposure quality curve to efficiently improve the camera’s exposure accuracy. A series of experiments have been carried out for different targets in different environments using the existing imaging system to verify the superiority and robustness of the proposed method. Compared with the conventional automatic exposure method, the signal-to-noise ratio of the image obtained by the proposed algorithm is increased by at least 1.6730 dB, and the number of saturated pixels is reduced to at least 2.568%. The method is significant to improve the on-orbit autonomous operating capability and on-orbit application efficiency of space camera.

With the successful production of artemisinic acid in yeast, the promising potential of synthetic biology for natural product biosynthesis is now being realized. The recent total biosynthesis of opioids in microbes is considered to be another landmark in this field. The importance and significance of enzymes in natural product biosynthetic pathways have been re-emphasized by these advancements. Therefore, the characterization and elucidation of enzymatic function in natural product biosynthesis are undoubtedly fundamental for the development of new drugs and the heterologous biosynthesis of active natural products. Here, discoveries regarding enzymatic function in natural product biosynthesis over the past year are briefly reviewed.