Depth Density Achieves a Better Result for Semantic Segmentation with the Kinect System.

Image segmentation is one of the most important methods for animal phenome research. Since the advent of deep learning, many researchers have looked at multilayer convolutional neural networks to solve the problems of image segmentation. A network simplifies the task of image segmentation with automatic feature extraction. Many networks struggle to output accurate details when dealing with pixel-level segmentation. In this paper, we propose a new concept: Depth density. Based on a depth image, produced by a Kinect system, we design a new function to calculate the depth density value of each pixel and bring this value back to the result of semantic segmentation for improving the accuracy. In the experiment, we choose Simmental cattle as the target of image segmentation and fully convolutional networks (FCN) as the verification networks. We proved that depth density can improve four metrics of semantic segmentation (pixel accuracy, mean accuracy, mean intersection over union, and frequency weight intersection over union) by 2.9%, 0.3%, 11.4%, and 5.02%, respectively. The result shows that depth information produced by Kinect can improve the accuracy of the semantic segmentation of FCN. This provides a new way of analyzing the phenotype information of animals.

Application of amodal segmentation for shape reconstruction and occlusion recovery in occluded tomatoes.

Common object detection and image segmentation methods are unable to accurately estimate the shape of the occluded fruit. Monitoring the growth status of shaded crops in a specific environment is challenging, and certain studies related to crop harvesting and pest detection are constrained by the natural shadow conditions. Amodal segmentation can focus on the occluded part of the fruit and complete the overall shape of the fruit. We proposed a Transformer-based amodal segmentation algorithm to infer the amodal shape of occluded tomatoes. Considering the high cost of amodal annotation, we only needed modal dataset to train the model. The dataset was taken from two greenhouses on the farm and contains rich occlusion information. We introduced boundary estimation in the hourglass structured network to provide a priori information about the completion of the amodal shapes, and reconstructed the occluded objects using a GAN network (with discriminator) and GAN loss. The model in this study showed accuracy, with average pairwise accuracy of 96.07%, mean intersection-over-union (mIoU) of 94.13% and invisible mIoU of 57.79%. We also examined the quality of pseudo-amodal annotations generated by our proposed model using Mask R-CNN. Its average precision (AP) and average precision with intersection over union (IoU) 0.5 (AP50) reached 63.91%,86.91% respectively. This method accurately and rationally achieves the shape of occluded tomatoes, saving the cost of manual annotation, and is able to deal with the boundary information of occlusion while decoupling the relationship of occluded objects from each other. Future work considers how to complete the amodal segmentation task without overly relying on the occlusion order and the quality of the modal mask, thus promising applications to provide technical support for the advancement of ecological monitoring techniques and ecological cultivation.

Efficacy of Huangma Ding or autologous platelet-rich gel for the diabetic lower extremity arterial disease patients with foot ulcers.

BACKGROUND: Diabetes foot is one of the most serious complications of diabetes and an important cause of death and disability, traditional treatment has poor efficacy and there is an urgent need to develop a practical treatment method. AIM: To investigate whether Huangma Ding or autologous platelet-rich gel (APG) treatment would benefit diabetic lower extremity arterial disease (LEAD) patients with foot ulcers. METHODS: A total of 155 diabetic LEAD patients with foot ulcers were enrolled and divided into three groups: Group A (62 patients; basal treatment), Group B (38 patients; basal treatment and APG), and Group C (55 patients; basal treatment and Huangma Ding). All patients underwent routine follow-up visits for six months. After follow-up, we calculated the changes in all variables from baseline and determined the differences between groups and the relationships between parameters. RESULTS: The infection status of the three groups before treatment was the same. Procalcitonin (PCT) improved after APG and Huangma Ding treatment more than after traditional treatment and was significantly greater in Group C than in Group B. Logistic regression analysis revealed that PCT was positively correlated with total amputation, primary amputation, and minor amputation rates. The ankle-brachial pressure and the transcutaneous oxygen pressure in Groups B and C were greater than those in Group A. The major amputation rate, minor amputation rate, and total amputation times in Groups B and C were lower than those in Group A. CONCLUSION: Our research indicated that diabetic foot ulcers (DFUs) lead to major amputation, minor amputation, and total amputation through local infection and poor microcirculation and macrocirculation. Huangma Ding and APG were effective attreating DFUs. The clinical efficacy of Huangma Ding was better than that of autologous platelet gel, which may be related to the better control of local infection by Huangma Ding. This finding suggested that in patients with DFUs combined with coinfection, controlling infection is as important as improving circulation.

DFSP: A fast and automatic distance field-based stem-leaf segmentation pipeline for point cloud of maize shoot.

The 3D point cloud data are used to analyze plant morphological structure. Organ segmentation of a single plant can be directly used to determine the accuracy and reliability of organ-level phenotypic estimation in a point-cloud study. However, it is difficult to achieve a high-precision, automatic, and fast plant point cloud segmentation. Besides, a few methods can easily integrate the global structural features and local morphological features of point clouds relatively at a reduced cost. In this paper, a distance field-based segmentation pipeline (DFSP) which could code the global spatial structure and local connection of a plant was developed to realize rapid organ location and segmentation. The terminal point clouds of different plant organs were first extracted via DFSP during the stem-leaf segmentation, followed by the identification of the low-end point cloud of maize stem based on the local geometric features. The regional growth was then combined to obtain a stem point cloud. Finally, the instance segmentation of the leaf point cloud was realized using DFSP. The segmentation method was tested on 420 maize and compared with the manually obtained ground truth. Notably, DFSP had an average processing time of 1.52 s for about 15,000 points of maize plant data. The mean precision, recall, and micro F1 score of the DFSP segmentation algorithm were 0.905, 0.899, and 0.902, respectively. These findings suggest that DFSP can accurately, rapidly, and automatically achieve maize stem-leaf segmentation tasks and could be effective in maize phenotype research. The source code can be found at https://github.com/syau-miao/DFSP.git.

Label3DMaize: toolkit for 3D point cloud data annotation of maize shoots.

BACKGROUND: The 3D point cloud is the most direct and effective data form for studying plant structure and morphology. In point cloud studies, the point cloud segmentation of individual plants to organs directly determines the accuracy of organ-level phenotype estimation and the reliability of the 3D plant reconstruction. However, highly accurate, automatic, and robust point cloud segmentation approaches for plants are unavailable. Thus, the high-throughput segmentation of many shoots is challenging. Although deep learning can feasibly solve this issue, software tools for 3D point cloud annotation to construct the training dataset are lacking. RESULTS: We propose a top-to-down point cloud segmentation algorithm using optimal transportation distance for maize shoots. We apply our point cloud annotation toolkit for maize shoots, Label3DMaize, to achieve semi-automatic point cloud segmentation and annotation of maize shoots at different growth stages, through a series of operations, including stem segmentation, coarse segmentation, fine segmentation, and sample-based segmentation. The toolkit takes ∼4-10 minutes to segment a maize shoot and consumes 10-20% of the total time if only coarse segmentation is required. Fine segmentation is more detailed than coarse segmentation, especially at the organ connection regions. The accuracy of coarse segmentation can reach 97.2% that of fine segmentation. CONCLUSION: Label3DMaize integrates point cloud segmentation algorithms and manual interactive operations, realizing semi-automatic point cloud segmentation of maize shoots at different growth stages. The toolkit provides a practical data annotation tool for further online segmentation research based on deep learning and is expected to promote automatic point cloud processing of various plants.

Conditions that promote the formation of black bloom in aquatic microcosms and its effects on sediment bacteria related to iron and sulfur cycling.

Black bloom occurs frequently in eutrophic waters. We investigated the conditions promoted the formation of black bloom via in-situ measurement in two aquatic microcosms and the effects of black bloom on the bacterial community composition. Although larger changes in dissolved oxygen (DO) were detected in the Hydrilla verticillata-dominated microcosm over the 90-day simulation, black bloom occurred more readily in the phytoplankton-dominated than macrophyte-dominated microcosm under conditions of O2 depletion and temperature above 30 °C. The sediment bacterial community composition shifted after black bloom; the relative abundance of Thiobacillus and Sideroxydans, which oxidize iron (Fe) and sulfur (S), decreased by 47% and 48%, respectively, in the phytoplankton-dominated microcosm and by 18% and 20% in the macrophyte-dominated microcosm. By contrast, Desulfatiglans increased by 13% and 19%, respectively, after black bloom. Furthermore, inter-taxa correlations remarkably changed according to co-occurrence network analysis. Thirty-six different taxa from the phylum to the genus level were identified as biomarkers of sediments collected before and after the black bloom event. Most of these biomarkers are related to Fe/S cycling in aquatic ecosystems.

Chiral Liquid Crystalline Elastomer for Twisting Motion without Preset Alignment of Mesogens.

A chiral liquid crystalline elastomer (CLCE) actuator is demonstrated. The solution-cast polydomain film of CLCE can twist upon order-disorder phase transition without any preset alignment of mesogens. The handedness of twisting is specific to the molecular chirality of the chiral dopant in the CLCE structure, while the degree of twisting, in terms of helical pitch and diameter, is sensitive to the aspect ratio and the thickness of the CLCE strip as well as the chiral dopant content. This phenomenon appears to stem from the local twisting forces and deformations of randomly oriented helical domains, which cannot cancel each other out due to the chirality and thus result in a macroscopic "chiral" force acting on the CLCE actuator. This finding reveals a materials design for preparing twisting LCE actuators.

Facile synthesis of metal nanoparticles decorated magnetic hierarchical carbon microtubes with polydopamine-derived carbon layer for catalytic applications.

It is highly desirable but challenging to fabricate a unique hybrid material comprising nanosized copper/cobalt/nickel nanoparticles (NPs) uniformly distributed on magnetic supports. Herein in this work, hierarchical magnetic metal silicate hollow microtubes were prepared using silica coated magnetic N-doped carbon microtubes (NCMTs@Fe3O4@SiO2) as a chemical template; then polydopamine (PDA) was employed to coat onto magnetic metal silicate carbon microtubes (NCMTs@Fe3O4@CuSNTs/CoSNTs/NiSNTs), which can be carbonized to form hierarchical hybrid composites with uniformly-dispersed metallic copper/cobalt/nickel NPs embedded in PDA-derived carbon layers (NCMTs@Fe3O4@SiO2@C/Cu-Co-Ni). Owing to its hierarchical structure, large specific surface area as well as the high density of metal NPs, the resultant NCMTs@Fe3O4@SiO2@C/Ni-Co-Cu could be applied as catalysts towards the reduction of 4-nitrophenol (4-NP). Furthermore, the NCMTs@Fe3O4@SiO2@C/Ni-Co-Cu catalysts could be easily collected and separated by applying an external magnetic field. In particular, it was found that NCMTs@Fe3O4@SiO2@C/Ni exhibited ultra-high catalytic activity on 4-NP reduction in comparison with Cu and Co supported catalysts. In addition, this unique hierarchical structure combined with magnetic recyclability make NCMTs@Fe3O4@SiO2@C/Ni a highly promising candidate for diverse applications.