Search

Drought poses a significant constraint on rice production, and, in this study, we have discovered a novel drought-sensitive mutant, designated as dsm3, arising from the progenies of indica rice variety Zhonghui8015 treated with ethyl methane sulphonate (EMS). Under drought stress conditions, dsm3 exhibited characteristic withered leaf tips, accompanied by increased levels of malondialdehyde (MDA) and H2O2, a reduced net photosynthetic rate (Pn), and decreased activity of peroxidase (POD) and superoxide dismutase (SOD). Genetic analysis revealed that the withered leaf tip phenotype was governed by a single recessive gene, designated as Osdsm3. To begin with, Osdsm3 was initially mapped to the short arm of chromosome 1 through a cross involving dsm3 and 02428. Subsequently, utilizing a population of 2591 F2 individuals, we narrowed down the location of Osdsm3 to a 78 Kb interval, encompassing 13 open reading frames (ORFs). Sequencing analysis unveiled a mutation (1275G → A) in the exon of the candidate gene (LOC_Os01g10680), leading to premature translation termination. Moreover, a quantitative RT-PCR assay demonstrated a high expression of OsDSM3 in the panicle and sheath, with a significant upregulation of drought-stress-related genes under drought conditions. Phylogenetic analyses indicated that Osdsm3 shares evolutionary homology with UNE1, an intracellular transport protein found in Arabidopsis thaliana. Subcellular studies further confirmed that OsDSM3 resides in the cytoplasm. In conclusion, the forthcoming cloning of Osdsm3 holds promise for delving deeper into the molecular mechanisms governing rice drought resistance. [ABSTRACT FROM AUTHOR]

Recently, the improvement of detection performance always relies on deeper convolutional layers and complex convolutional structures in remote sensing images, which significantly increases the storage space and computational complexity of the detector. Although previous work has designed various novel lightweight convolutions, when these convolutional structures are applied to remote sensing detection tasks, the inconsistency between features and targets as well as between features and tasks in the detection architecture is often ignored: (1) The features extracted by convolution sliding in a fixed direction make it difficult to effectively model targets with arbitrary direction distribution, which leads to the detector needing more parameters to encode direction information and the network parameters being highly redundant; (2) The detector shares features from the backbone, but the classification task requires rotation-invariant features while the regression task requires rotation-sensitive features. This inconsistency in the task can lead to inefficient convolutional structures. Therefore, this paper proposed a detector that uses the Feature Decoupling for Lightweight Oriented Object Detection (FDLO-Det). Specifically, we constructed a rotational separable convolution that extracts rotational equivariant features while significantly compressing network parameters and computational complexity through highly shared parameters. Next, we introduced an orthogonal polarization transformation module that decomposes rotational equivariant features in both horizontal and vertical orthogonal directions, and used polarization functions to filter out the required features for classification and regression tasks, effectively improving detector performance. Extensive experiments on DOTA, HRSC2016, and UCAS-AOD show that the proposed detector can achieve the best performance and achieve an effective balance between computational complexity and detection accuracy. [ABSTRACT FROM AUTHOR]

In recent years, object detectors based on convolutional neural networks have been widely used on remote sensing images. However, the improvement of their detection performance depends on a deeper convolution layer and a complex convolution structure, resulting in a significant increase in the storage space and computational complexity. Although previous works have designed a variety of new lightweight convolution and compression algorithms, these works often require complex manual design and cause the detector to be greatly modified, which makes it difficult to directly apply the algorithms to different detectors and general hardware. Therefore, this paper proposes an iterative pruning framework based on assistant distillation. Specifically, a structured sparse pruning strategy for detectors is proposed. By taking the channel scaling factor as a representation of the weight importance, the channels of the network are pruned and the detector is greatly slimmed. Then, a teacher assistant distillation model is proposed to recover the network performance after compression. The intermediate models retained in the pruning process are used as assistant models. By way of the teachers distilling the assistants and the assistants distilling the students, the students' underfitting caused by the difference in capacity between teachers and students is eliminated, thus effectively restoring the network performance. By using this compression framework, we can greatly compress the network without changing the network structure and can obtain the support of any hardware platform and deep learning library. Extensive experiments show that compared with existing detection networks, our method can achieve an effective balance between speed and accuracy on three commonly used remote sensing target datasets (i.e., NWPU VHR-10, RSOD, and DOTA). [ABSTRACT FROM AUTHOR]

• Proposed a novel two-layer fusion framework towards perceptual image fusion. • Introduced the concept of regular and irregular contents in neuroscience studies. • Presented a perceptual image decomposition model using a local regression method. • Fused regular and irregular layers separately with different fusion strategies. • Preserved more perceptual valuable information from source images in fusion. Recent studies in neuroscience indicate that the human visual system perceives regular and irregular contents separately: the former mainly illustrate primary visual information such as image structures; while the latter are generally messy and independent, and seem to be less important in perception. However, without any reference to such perceptual theory, the existing image fusion algorithms treat these two types of contents equally, and may not preserve the most perceptually important information in source images. In this work, we propose a new two-layer image fusion framework towards consistency with human perception. The main contributions are as follows: (1) We firstly explore the recently revealed perceptual theory and characterize perceptual significance from regular and irregular image contents in image fusion. This creates the possibilities to develop fusion algorithms towards consistency with human perception and preserve more desirable information in the fused result. (2) Following the concept of active inference mechanisms in perception, we present a perceptual image decomposition model with a local regression method to separate images into regular and irregular layers. In this way, we could treat these two kinds of image contents discriminatively, with elaborately selected fusion strategies based on sparse representation and local energy. We conduct extensive experiments including subjective evaluation, objective evaluation and perceptual assessment, and the experimental results demonstrate the superiority of the proposed model. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) feature representation has been drawing increasing attention, and most of the previous works devoted to learning discriminative features. However, we argue that such kind of features suffer from "categories bias" in target detection tasks, where the scope of the negatives (i.e., backgrounds) is naturally broader than that of the positives (i.e., targets). Technically, the learning of discriminative features aims to maximize positive-negative difference. In this case, the interclass-difference criteria for feature mapping and feature matching would increase model complexity while degrading detection robustness. To address these issues, we construct a generative feature learning framework in this paper. Unlike the discriminative feature representation, generative features tend to cluster the positives from negatives, and in this way, the unique and separable attributes of the positives can be learnt to facilitate the accurate detection of positives (targets). Practically, by exploiting ELM computational advantages, positives clustering oriented feature learning is implemented with a kernel-label alignment function, which guides random features of positives into clusters, while keeping away from the negatives. On the other hand, the density of positives cluster is estimated using a probabilistic model, and thus the likelihood that test samples belonged to the positive category can be approximately inferred. We experimentally evaluate our framework for target detection on synthetic data and Hyperspectral Imagery (HSI), in which reasonable improvements are observed over conventional ELM-based discriminative methods and backpropagation-based multilayer perceptron (MLP) in terms of detection accuracy or learning efficiency. [ABSTRACT FROM AUTHOR]

Spatiotemporal image fusion is considered as a promising way to provide Earth observations with both high spatial resolution and frequent coverage, and recently, learning-based solutions have been receiving broad attention. However, these algorithms treating spatiotemporal fusion as a single image super-resolution problem, generally suffers from the significant spatial information loss in coarse images, due to the large upscaling factors in real applications. To address this issue, in this paper, we exploit temporal information in fine image sequences and solve the spatiotemporal fusion problem with a two-stream convolutional neural network called StfNet. The novelty of this paper is twofold. First, considering the temporal dependence among image sequences, we incorporate the fine image acquired at the neighboring date to super-resolve the coarse image at the prediction date. In this way, our network predicts a fine image not only from the structural similarity between coarse and fine image pairs but also by exploiting abundant texture information in the available neighboring fine images. Second, instead of estimating each output fine image independently, we consider the temporal relations among time-series images and formulate a temporal constraint. This temporal constraint aiming to guarantee the uniqueness of the fusion result and encourages temporal consistent predictions in learning and thus leads to more realistic final results. We evaluate the performance of the StfNet using two actual data sets of Landsat-Moderate Resolution Imaging Spectroradiometer (MODIS) acquisitions, and both visual and quantitative evaluations demonstrate that our algorithm achieves state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Most of the existing image blurriness assessment algorithms are proposed based on measuring image edge width, gradient, high-frequency energy, or pixel intensity variation. However, these methods are content sensitive with little consideration of image content variations, which causes variant estimations for images with different contents but same blurriness degrees. In this paper, a content-insensitive blind image blurriness assessment metric is developed utilizing Weibull statistics. Inspired by the property that the statistics of image gradient magnitude (GM) follows Weibull distribution, we parameterize the GM using $\beta$ (scale parameter) and $\gamma$ (shape parameter) of Weibull distribution. We also adopt skewness ($\eta$) to measure the asymmetry of the GM distribution. In order to reduce the influence of image content and achieve more robust performance, divisive normalization is then incorporated to moderate the $\beta$ , $\gamma$ , and $\eta$. The final image quality is predicted using a sparse extreme learning machine. Performances evaluation on the blur image subsets in LIVE, CSIQ, TID2008, and TID2013 databases demonstrate that the proposed method is highly correlated with human perception and robust with image contents. In addition, our method has low computational complexity which is suitable for online applications. [ABSTRACT FROM AUTHOR]

For robust visual tracking, appearance modeling should be able to well separate the object from its backgrounds, while accurately adapt to its appearance variations. However, most of the existing tracking methods mainly focus on one of the two aspects; or design two different modules to combine them with the price of double computational cost. In this paper, by using pairwise metric learning, we present a novel appearance model for robust visual tracking. Specifically, visual tracking is viewed as a pairwise regression problem, and extreme learning machine (ELM) is utilized to construct the pairwise regression framework. In ELM-based pairwise training, two constraints are enforced: the target observations must have different regression outputs from those background ones; while the various target observations during tracking should have approximate regression outputs. Thus, the discriminative and generative capabilities are fully considered in a single object tracking model. Moreover, online sequential ELM (OS-ELM) is used to update the resulting appearance model, thereby leading to a more robust tracking process. Extensive experimental evaluations on challenging video sequences demonstrate the effectiveness and efficiency of the proposed tracker. [ABSTRACT FROM AUTHOR]

Variations of target appearances due to illumination changes, heavy occlusions, and target deformations are the major factors for tracking drift. In this paper, we show that the tracking drift can be effectively corrected by exploiting the relationship between the current tracker and its historical tracker snapshots. Here, a multi-expert framework is established by the current tracker and its historical trained tracker snapshots. The proposed scheme is formulated into a unified discrete graph optimization framework, whose nodes are modeled by the hypotheses of the multiple experts. Furthermore, an exact solution of the discrete graph exists giving the object state estimation at each time step. With the unary and binary compatibility graph scores defined properly, the proposed framework corrects the tracker drift via selecting the best expert hypothesis, which implicitly analyzes the recent performance of the multi-expert by only evaluating graph scores at the current frame. Three base trackers are integrated into the proposed framework to validate its effectiveness. We first integrate the online SVM on a budget algorithm into the framework with significant improvement. Then, the regression correlation filters with hand-crafted features and deep convolutional neural network features are introduced, respectively, to further boost the tracking performance. The proposed three trackers are extensively evaluated on three data sets: TB-50, TB-100, and VOT2015. The experimental results demonstrate the excellent performance of the proposed approaches against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The increasing number of demanding consumer digital multimedia applications has boosted interest in no-reference (NR) image quality assessment (IQA). In this paper, we propose a perceptual NR blur evaluation method using a new machine learning technique, i.e., extreme learning machine (ELM). The proposed metric, Blind Image Blur quality Evaluator (BIBE), exploits scene statistics of gradient magnitudes to model the properties of blurred images, and then the underlying blur features are derived by fitting gradient magnitudes distribution. The resultant feature is finally mapped into an associated quality score using ELM. As subjective evaluation scores by human beings are integrated into training, machine learning techniques can predict image quality more accurately than those traditional methods. Compared with other learning techniques such as support vector machine (SVM), ELM has better learning performance and faster learning speed. Experimental results on public databases show that the proposed BIBE correlates well with human perceived blurriness, and outperforms the state-of-the-art specific NR blur evaluation metrics as well as generic NR IQA methods. Moreover, the application of automatic focusing system for digital cameras further confirms the capability of BIBE. [ABSTRACT FROM AUTHOR]

Abstract: H.264/AVC FRExt (Fidelity Range Extensions) and Motion JPEG 2000 are the current respective inter-frame and intra-frame coding standards for high resolution (HR) (e.g., 4096×2160) visual signals. It is commonly believed that an inter-frame method could achieve higher coding efficiency compared with an intra-frame one, due to the exploitation of video temporal redundancy. However, Motion JPEG 2000 has been selected as the digital cinema compression standard, and some existing work has demonstrated that JPEG 2000 is more suitable at HR situations. In this paper, we compare the rate–distortion (R–D) performance of these two different schemes and give more insight from both theoretical and experimental point of view. We derive an entropy-based R–D model to analyze the test results and the impact of residual entropy and quantization for inter-frame coding. Several extensions are introduced into H.264/AVC FRExt for HR video content for better performance. Experimental results show that these extensions lead to significantly higher coding efficiency and make our extended version more suitable for HR video coding [Copyright &y& Elsevier]

The construction of diverse dictionaries for sparse representation of hyperspectral image (HSI) classification has been a hot topic over the past few years. However, compared with convolutional neural network (CNN) models, dictionary-based models cannot extract deeper spectral information, which will reduce their performance for HSI classification. Moreover, dictionary-based methods have low discriminative capability, which leads to less accurate classification. To solve the above problems, we propose a deep learning-based structure dictionary for HSI classification in this paper. The core ideas are threefold, as follows: (1) To extract the abundant spectral information, we incorporate deep residual neural networks in dictionary learning and represent input signals in the deep feature domain. (2) To enhance the discriminative ability of the proposed model, we optimize the structure of the dictionary and design sharing constraint in terms of sub-dictionaries. Thus, the general and specific feature of HSI samples can be learned separately. (3) To further enhance classification performance, we design two kinds of loss functions, including coding loss and discriminating loss. The coding loss is used to realize the group sparsity of code coefficients, in which within-class spectral samples can be represented intensively and effectively. The Fisher discriminating loss is used to enforce the sparse representation coefficients with large between-class scatter. Extensive tests performed on hyperspectral dataset with bright prospects prove the developed method to be effective and outperform other existing methods. [ABSTRACT FROM AUTHOR]

• A novel generative feature learning framework for TSR is proposed with clustering inductive bias. • Clustering-oriented feature mapping is learned based on a novel random neural network. • Computationally efficient feature mapping can be achieved with a fast Gaussian random projection. Reliable and fast traffic sign recognition (TSR) that locates the traffic sign from an image and then estimates its category is a crucial perception function for Advanced Driver Assistance Systems (ADAS) of autonomous vehicles. Most of the popular deep convolutional neural networks (DCNNs) based TSR techniques advocate discriminative feature learning for traffic signs against their appearance variability. However, such feature learning scheme may suffer from the diversity of traffic signs categories, especially when samples within each category are limited for model training (i.e., few-shot learning). Here, we present a generative feature learning based TSR network with well generalization capacity and high computational efficiency. Instead of relying on large amounts of supervision to learn discriminative features, our method devotes to learn common but unique properties of class-specific traffic signs with few training samples. Specifically, we combine clustering inductive bias with a random neural network, and then exploit computational advantages offered by a fast random projection algorithm. Experiments on two TSR benchmarks illustrate that our method achieves comparable or higher recognition accuracy than state-of-the-art DCNN-based methods with less training data and inference time consumption. [ABSTRACT FROM AUTHOR]

The seed-setting rate has a significant effect on grain yield in rice (Oryza sativa L.). Embryo sac development is essential for seed setting; however, the molecular mechanism underlying this process remains unclear. Here, we isolated defective embryo sac1 (des1), a rice mutant with a low seed-setting rate. Cytological examination showed degenerated embryo sacs and reduced fertilization capacity in des1. Map-based cloning revealed a nonsense mutation in OsDES1 , a gene that encodes a putative nuclear envelope membrane protein (NEMP)-domain-containing protein that is preferentially expressed in pistils. The OsDES1 mutation disrupts the normal formation of functional megaspores, which ultimately results in a degenerated embryo sac in des1. Reciprocal crosses showed that fertilization is abnormal and that the female reproductive organ is defective in des1. OsDES1 interacts with LONELY GUY (LOG), a cytokinin-activating enzyme that acts in the final step of cytokinin synthesis; mutation of LOG led to defective female reproductive organ development. These results demonstrate that OsDES1 functions in determining the rice seed-setting rate by regulating embryo sac development and fertilization. Our study sheds light on the function of NEMP-type proteins in rice reproductive development. [ABSTRACT FROM AUTHOR]

Traditional tracking-by-detection based methods treat the target and the background as a binary classification problem. This two class classification method suffers from two main drawbacks. Firstly, the learning result may be unreliable when the number of training samples is not large enough. Secondly, the binary classifier tends to drift because of the complex background tracking conditions. In this paper, we propose a new model called Time Varying Metric Learning (TVML) for visual tracking. We adopt the Wishart Process to model the time varying metrics for target features, and apply the Recursive Bayesian Estimation (RBE) framework to learn the metric from the data with “side information contraint”. Metric learning with side information is able to omit the clustering of negative samples, which is more preferable in complex background tracking scenarios. The recursive Bayesian model ensures the learned metric is accurate with limited training samples. The experimental results demonstrate the comparable performance of the TVML tracker compared to state-of-the-art methods, especially when there are background clutters. [ABSTRACT FROM AUTHOR]

Lithium (Li) metal batteries (LMBs) are still limited by lithium dendrite growth and solvated structure at low temperatures. A stable solid electrolyte interface (SEI) and solvent sheath structure are the future directions of liquid metal battery development. However, most artificial SEIs and electrolytes cannot meet the original objective of high conductivity and low nucleation potential multifunctional design. To address this challenge, an electrolyte with excellent high current density and low‐temperature performance is reported here. In this electrolyte environment, the thickness and microstructure of the "Chain Link Ships" SEI are formed. Moreover, the additives improve the desolvation ability of Li+ in the ester electrolytes. Under the harsh environment (−30 °C), the average coulombic efficiency (CE) of the Li||copper (Cu) battery reaches 98% after 200 cycles. Even at −40 °C, the Li||LiFePO4 (LFP) battery shows 90% capacity retention after 100 cycles at the cathode‐limited areal capacity (5 mAh cm−2). Furthermore, at 30 °C, the Li||LFP battery can cycle stably for 1200 cycles at 5 C, and the capacity retention reaches 93.5%. This addition strategy provides insights into the commercial application of new solvated structure electrolytes and a new approach for commercial low‐temperature LMBs. [ABSTRACT FROM AUTHOR]

• In this work, we propose a miniaturized customized filtering-wheel-based multispectral imaging system for target detection. • Our own-developed PCB-based small motor, a new layout of the filter and the least number of filtering channels offer the main design priority for our system. • Firstly, a new layout of filters is proposed that all the filtering channels are integrated by employing their own-developed technologies to make the whole filtering module extremely compact. • Then, we adopt the band selection strategy to extract the least number of filtering channels for specific targets, thus further reducing the volume of the system. • In the end, the resulting system is comprehended with a small volume (i.e., Φ38 mm × 23 mm) and lightweight (i.e., ∼98 g) for the recognition of the command post and camouflage net, for instance. • The detection capability of the system is verified in the field testing. Our proposed system supports modular functionality to accommodate diverse applications, showing flexibility and universality. Filtering-wheel-based multispectral imaging (FW-MSI) systems are utilized in various applications. However, the inherent drawbacks of existing FW-MSI systems, such as traditional motors with large volumes and the configuration of filters, pose challenges for miniaturization. Therefore, we propose a miniaturized customized filtering-wheel-based multispectral imaging (MCFW-MSI) system. Our own-developed PCB-based small motor, a new layout of the filter and the least number of filtering channels offer the main design priority for our system. Specifically, a new layout of the integrated multi-channel filter combining the developed motor is constructed, making the filtering module extremely compact. Furthermore, the least number of filtering channels is guaranteed through band selection, further ensuring miniaturization and customization. Finally, the MCFW-MSI system is obtained with the volume of Φ38mm × 23 mm and weight of ∼ 98 g for recognizing command post and camouflage net, for instance, to verify its detection capability. Our system supports modular functionality to accommodate different scenarios. [ABSTRACT FROM AUTHOR]

Since the human visual system (HVS) is the ultimate appreciator of most photorealistically rendered images, rendering process can be accelerated by exploiting the properties of the HVS. According to the concept of entropy masking, the HVS is not sensitive to visual distortions in unstructured visual signals. For structured regions, pixels are highly correlated, while the similarity among pixels in unstructured regions is low. In this paper, we detect unstructured regions by extracting local patches from each pixel and its neighboring pixels, and comparing the similarity between the local patches of the center pixel and the neighboring pixels. We further exploit entropy masking in perceptual rendering, and experimental results demonstrate that the proposed method can accelerate rendering, without degrading the perceived quality of resultant images. [ABSTRACT FROM AUTHOR]

All existing video coding standards developed so far deem video as a sequence of natural frames (formed in the XY plane), and treat spatial redundancy (redundancy along X and Y directions) and temporal redundancy (redundancy along T direction) differently and separately. In this paper, we investigate into a new compression (redundancy reduction) method for video in which the frames are allowed to be formed in a non-XY plane. We are to exploit fuller extent of video redundancy, and propose an adaptive optimal compression plane determination process to be used as a preprocessing step prior to any standard video coding scheme. The essence of the scheme is to form the frames in the plane formed by two axes (among X, Y, and T) corresponding to signal correlation evaluation, which enables better prediction (therefore better compression). In spite of the simplicity of the proposed method, it can be used for both lossless and lossy compression, and with and without interframe prediction. Extensive experimental results show that the new coding method improves the performance of the video coding for a number of coding methods (inclusive of lossless and near-lossless Motion JPEG-LS, Motion JPEG, Motion JPG2K, H.264 intraonly profile, and H.264) and videos with different visual content. [ABSTRACT FROM AUTHOR]

In just noticeable difference (JND) models, evaluation of contrast masking (CM) is a crucial step. More specifically, CM due to edge masking (EM) and texture masking (TM) needs to be distinguished due to the entropy masking property of the human visual system. However, TM is not estimated accurately in the existing JND models since they fail to distinguish TM from EM. In this letter, we propose an enhanced pixel domain JND model with a new algorithm for CM estimation. In our model, total-variation based image decomposition is used to decompose an image into structural image (i.e., cartoon like, piecewise smooth regions with sharp edges) and textural image for estimation of EM and TM, respectively. Compared with the existing models, the proposed one shows its advantages brought by the better EM and TM estimation. It has been also applied to noise shaping and visual distortion gauge, and favorable results are demonstrated by experiments on different images. [ABSTRACT FROM PUBLISHER]