Plant counting runs through almost every stage of agricultural production from seed breeding, germination, cultivation, fertilization, pollination to yield estimation, and harvesting. With the ...prevalence of digital cameras, graphics processing units and deep learning-based computer vision technology, plant counting has gradually shifted from traditional manual observation to vision-based automated solutions. One of popular solutions is a state-of-the-art object detection technique called Faster R-CNN where plant counts can be estimated from the number of bounding boxes detected. It has become a standard configuration for many plant counting systems in plant phenotyping. Faster R-CNN, however, is expensive in computation, particularly when dealing with high-resolution images. Unfortunately high-resolution imagery is frequently used in modern plant phenotyping platforms such as unmanned aerial vehicles, engendering inefficient image analysis. Such inefficiency largely limits the throughput of a phenotyping system. The goal of this work hence is to provide an effective and efficient tool for high-throughput plant counting from high-resolution RGB imagery. In contrast to conventional object detection, we encourage another promising paradigm termed object counting where plant counts are directly regressed from images, without detecting bounding boxes. In this work, by profiling the computational bottleneck, we implement a fast version of a state-of-the-art plant counting model TasselNetV2 with several minor yet effective modifications. We also provide insights why these modifications make sense. This fast version, TasselNetV2+, runs an order of magnitude faster than TasselNetV2, achieving around 30 fps on image resolution of 1980 × 1080, while it still retains the same level of counting accuracy. We validate its effectiveness on three plant counting tasks, including wheat ears counting, maize tassels counting, and sorghum heads counting. To encourage the use of this tool, our implementation has been made available online at https://tinyurl.com/TasselNetV2plus.
This paper proposes a novel local feature descriptor, called a local feature statistics histogram (LFSH), for efficient 3D point cloud registration. An LFSH forms a comprehensive description of local ...shape geometries by encoding their statistical properties on local depth, point density, and angles between normals. The sub-features in the LFSH descriptor are low-dimensional and quite efficient to compute. In addition, an optimized sample consensus (OSAC) algorithm is developed to iteratively estimate the optimum transformation from point correspondences. OSAC can handle the challenging cases of matching highly self-similar models. Based on the proposed LFSH and OSAC, a coarse-to-fine algorithm can be formed for 3D point cloud registration. Experiments and comparisons with the state-of-the-art descriptors demonstrate that LFSH is highly discriminative, robust, and significantly faster than other descriptors. Meanwhile, the proposed coarse-to-fine registration algorithm is demonstrated to be robust to common nuisances, including noise and varying point cloud resolutions, and can achieve high accuracy on both model data and scene data.
Display omitted
•Quantitative analysis is used to evaluate the removal of microplastics in global WWTPs.•The filter-based technologies perform better microplastics removal efficiency.•Mechanisms of ...critical treatment technologies in microplastics removal are summarized.•An average of 7.2 billion day−1 microplastics entered the river from WWTPs.•Specific microplastics shall be highlighted besides the common microplastics.
Wastewater treatment plants (WWTPs) are considered to be the main sources of microplastic contaminants in the aquatic environment, and an in-depth understanding of the behavior of microplastics among the critical treatment technologies in WWTPs is urgently needed. In this paper, the characteristics and removal of microplastics in 38 WWTPs in 11 countries worldwide were reviewed. The abundance of microplastics in the influent, effluent, and sludge was compared. Then, based on existing data, the removal efficiency of microplastics in critical treatment technologies were compared by quantitative analysis. Particularly, detailed mechanisms of critical treatment technologies including primary settling treatment with flocculation, bioreactor system, advanced oxidation and membrane filtration were discussed. Thereafter, the abundance load and ecological hazard of the microplastics discharged from WWTPs into the aquatic and soil environments were summarized. The abundance of microplastics in the influent ranged from 0.28 particles L−1 to 3.14 × 104 particles L−1, while that in the effluent ranged from 0.01 particles L−1 to 2.97 × 102 particles L−1. The microplastic abundance in the sludge within the range of 4.40 × 103–2.40 × 105 particles kg−1. In addition, there are still 5.00 × 105–1.39 × 1010 microplastic particles discharged into the aquatic environment each day Moreover, among the critical treatment technologies, the quantitative analysis revealed that filter-based treatment technologies exhibited the best microplastics removal efficiency. Fibers and microplastics with large particle sizes (0.5–5 mm) were easily separated by primary settling. Polyethene and small-particle size microplastics (<0.5 mm) were easily trapped by bacteria in the activated sludge of bioreactor system. The negative impact of microplastics from wastewater treatment plant was worthy of attention. Moreover, unknown transformation products of microplastics and their corresponding toxicity need in-depth research.
Display omitted
•Natural organic matter promoted the photoaging of PA MPs in water.•Aged MPs had higher bioaccumulation and oxidative stress in fish than virgin MPs.•Aged MPs exhibit higher growth ...inhibition and intestinal injury in developing fish.•Lipid metabolism disorder in zebrafish induced by PA was aggravated after aging.•Aged PA exposure disturbed genes related to lipid digestion, transfer and absorption.
The safety of microplastics (MPs) and associated health effects has been one of the major concerns worldwide. However, the role of photoaging toward the risk of MPs in water ecosystems remains inconclusive yet. In this study, the size of polyamide (PA, ∼32.50 μm) MPs was obviously decreased after photoaging in water containing fulvic acid (FA) and humic acid (HA) (∼19.75 and ∼24.30 μm, respectively). Nanoplastics were formed (4.65% and 2.03%, respectively) and hydrophilia and colloidal stability was improved due to the formation of oxygen-containing functional groups. FA-aged PA exhibited higher inhibition on body length and weight of developing zebrafish than HA-aged and pristine PA. Photoaged MPs in intestine were more difficult to be depurated by zebrafish, leading to the disappearance of intestinal folding, shedding of more enterocytes, and emaciation of intestinal microvilli. Dietary lipid digestion in larvae was inhibited by aged PA due to oxidative stress-triggered lipid peroxidation and inhibition of lipase activities and bile acids secretion. Exposure of photoaged MPs down-regulated genes (cd36, dgat1a, dgat2, mttp, etc.) associated with triglyceride resynthesis and transportation, resulting in lipid maladsorption and growth inhibition. Our findings highlight the potential negative effects of environmentally aged MPs on diet digestion and nutrient assimilation in fish.
Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the ...representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods.
Brominated flame retardants (BFRs) which were detected extensively in environmental and biota samples worldwide, have raised significant concerns during past decades for their persistence, ...bioaccumulation and potential toxicity to ecological environment and human health. In this paper, we have compiled and reviewed existing literature on the contamination status of BFRs in abiotic and biotic environments in China, including polybrominated diphenyl ethers (PBDEs), hexabromocyclododecane, tetrabromobisphenol A and new BFRs. Temporal trends were also summarized and evaluated. Based on this review, it has been concluded that (1) high concentrations of PBDEs were generally related to the e-waste disposal processing, while the spatial distribution pattern of other BFRs was not necessarily in accordance with this; (2) extremely high concentrations of BFRs in indoor dust emphasized the importance of indoor contamination to human body burdens, while more work need to be done to confirm its contribution; (3) PBDEs in electronics dismantling workers were higher compared to the general population, indicating the occupational exposure should be of particular concern; (4) more data are now becoming available for BFRs in aquatic and terrestrial organisms not previously studied, while studies that consider the occurrence of BFRs in organisms of different trophic levels are still of urgent need for evaluating the fate of BFRs in the food web; and (5) limited data showed a decreasing trend for PBDEs, while more data on time trends of BFR contamination in various matrices and locations are still needed before the impact of regulation of BFRs can be assessed.
•Contamination of major BFRs in China were reviewed comprehensively.•High levels of PBDEs were observed around e-waste dismantling areas.•Decreasing trend of PBDEs in human milk was observed in some regions.•Indoor dust was highlighted due to the possible high human exposure.•High exposure of residents and workers in e-waste dismantling areas was indicated.
The local reference frame (LRF), as an independent coordinate system constructed on the local 3D surface, is broadly employed in 3D local feature descriptors. The benefits of the LRF include ...rotational invariance and full 3D spatial information, thereby greatly boosting the distinctiveness of a 3D feature descriptor. There are numerous LRF methods in the literature; however, no comprehensive study comparing their repeatability and robustness performance under different application scenarios and nuisances has been conducted. This paper evaluates eight state-of-the-art LRF proposals on six benchmarks with different data modalities (e.g., LiDAR, Kinect, and Space Time) and application contexts (e.g., shape retrieval, 3D registration, and 3D object recognition). In addition, the robustness of each LRF to a variety of nuisances, including varying support radii, Gaussian noise, outliers (shot noise), mesh resolution variation, distance to boundary, keypoint localization error, clutter, occlusion, and partial overlap, is assessed. The experimental study also measures the performance under different keypoint detectors, descriptor matching performance when using different LRFs and feature representation combinations, as well as computational efficiency. Considering the evaluation outcomes, we summarize the traits, advantages, and current limitations of the tested LRF methods.
Microplastics (MPs) are ubiquitous in the environment and pose substantial threats to the water ecosystem. However, the impact of natural aging of MPs on their toxicity has rarely been considered. ...This study found that visible light irradiation with hydrogen peroxide at environmentally relevant concentration for 90 days significantly altered the physicochemical properties and mitigated the toxicity of polyamide (PA) fragments to infantile zebrafish. The size of PA particles was reduced from ∼8.13 to ∼6.37 μm, and nanoparticles were produced with a maximum yield of 5.03%. The end amino groups were volatilized, and abundant oxygen-containing groups (e.g., hydroxyl and carboxyl) and carbon-centered free radicals were generated, improving the hydrophilicity and colloidal stability of degraded MPs. Compared with pristine PA, the depuration of degraded MPs mediated by multixenobiotics resistance was much quicker, leading to markedly lower bioaccumulation in fish and weaker inhibition on musculoskeletal development. By integrating transcriptomics and transgenic zebrafish Tg(lyz:EGFP) tests, differences in macrophages-triggered proinflammatory effects, apoptosis via IL-17 signaling pathway, and antioxidant damages were identified as the underlying mechanisms for the attenuated toxicity of degraded MPs. This work highlights the importance of natural degradation on the toxicity of MPs, which has great implications for risk assessment of MPs.
Accurately counting maize tassels is important for monitoring the growth status of maize plants. This tedious task, however, is still mainly done by manual efforts. In the context of modern plant ...phenotyping, automating this task is required to meet the need of large-scale analysis of genotype and phenotype. In recent years, computer vision technologies have experienced a significant breakthrough due to the emergence of large-scale datasets and increased computational resources. Naturally image-based approaches have also received much attention in plant-related studies. Yet a fact is that most image-based systems for plant phenotyping are deployed under controlled laboratory environment. When transferring the application scenario to unconstrained in-field conditions, intrinsic and extrinsic variations in the wild pose great challenges for accurate counting of maize tassels, which goes beyond the ability of conventional image processing techniques. This calls for further robust computer vision approaches to address in-field variations.
This paper studies the in-field counting problem of maize tassels. To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment. With 361 field images collected in four experimental fields across China between 2010 and 2015 and corresponding manually-labelled dotted annotations, a novel
(
) dataset is created and will be released with this paper. To alleviate the in-field challenges, a deep convolutional neural network-based approach termed
is proposed. TasselNet can achieve good adaptability to in-field variations via modelling the local visual characteristics of field images and regressing the local counts of maize tassels. Extensive results on the MTC dataset demonstrate that TasselNet outperforms other state-of-the-art approaches by large margins and achieves the overall best counting performance, with a mean absolute error of 6.6 and a mean squared error of 9.6 averaged over 8 test sequences.
TasselNet can achieve robust in-field counting of maize tassels with a relatively high degree of accuracy. Our experimental evaluations also suggest several good practices for practitioners working on maize-tassel-like counting problems. It is worth noting that, though the counting errors have been greatly reduced by TasselNet, in-field counting of maize tassels remains an open and unsolved problem.
We show that it is possible to achieve high-quality domain adaptation without explicit adaptation. The nature of the classification problem means that when samples from the same class in different ...domains are sufficiently close, and samples from differing classes are separated by large enough margins, there is a high probability that each will be classified correctly. Inspired by this, we propose an embarrassingly simple yet effective approach to domain adaptation-only the class mean is used to learn class-specific linear projections. Learning these projections is naturally cast into a linear-discriminant-analysis-like framework, which gives an efficient, closed form solution. Furthermore, to enable to application of this approach to unsupervised learning, an iterative validation strategy is developed to infer target labels. Extensive experiments on cross-domain visual recognition demonstrate that, even with the simplest formulation, our approach outperforms existing non-deep adaptation methods and exhibits classification performance comparable with that of modern deep adaptation methods. An analysis of potential issues effecting the practical application of the method is also described, including robustness, convergence, and the impact of small sample sizes.