Tracking by segmentation with future motion estimation applied to person-following robots.

Person-following is a crucial capability for service robots, and the employment of vision technology is a leading trend in building environmental understanding. While most existing methodologies rely on a tracking-by-detection strategy, which necessitates extensive datasets for training and yet remains susceptible to environmental noise, we propose a novel approach: real-time tracking-by-segmentation with a future motion estimation framework. This framework facilitates pixel-level tracking of a target individual and predicts their future motion. Our strategy leverages a single-shot segmentation tracking neural network for precise foreground segmentation to track the target, overcoming the limitations of using a rectangular region of interest (ROI). Here we clarify that, while the ROI provides a broad context, the segmentation within this bounding box offers a detailed and more accurate position of the human subject. To further improve our approach, a classification-lock pre-trained layer is utilized to form a constraint that curbs feature outliers originating from the person being tracked. A discriminative correlation filter estimates the potential target region in the scene to prevent foreground misrecognition, while a motion estimation neural network anticipates the target's future motion for use in the control module. We validated our proposed methodology using the VOT, LaSot, YouTube-VOS, and Davis tracking datasets, demonstrating its effectiveness. Notably, our framework supports long-term person-following tasks in indoor environments, showing promise for practical implementation in service robots.

Differences in Gut Microbiota between Healthy Individuals and Patients with Perianal Abscess before and after Surgery.

Surgery is the most important treatment for perianal abscesses. However, the gut microbiota of patients with perianal abscess and the effects of perianal abscess on the gut microbiota after surgery are unknown. In this study, significant changes in interleukin 6 and tumor necrosis factor-α in the blood of healthy subjects, patients with perianal abscesses, and patients after perianal abscess surgery were identified. 16S rRNA gene sequencing technology was used to detect the changes in the gut microbiota among 30 healthy individuals and 30 patients with perianal abscess before and after surgery. Venn diagrams and alpha diversity analyses indicated differences in the abundance and uniformity of gut microbiota between the healthy individuals and patients with perianal abscesses before and after surgery. Beta diversity analysis indicated that the grouping effects among the control, abscess, and surgery groups were good. The classification and compositional analysis showed significant differences in the gut microbiota between healthy individuals and patients with perianal abscesses before and after surgery. LEfSe analysis, random forest analysis, and ROC curve analysis showed that Klebsiella (AUC = 0.7467) and Bilophila (AUC = 0.72) could be potential biomarkers for the diagnosis of perianal abscess. The functional prediction results showed that the differential microbiota is significantly enriched in the pathways related to nutrition and drug metabolism. This study may have important implications for the clinical management and prognostic assessment of patients with perianal abscesses.

Underwater Holothurian Target-Detection Algorithm Based on Improved CenterNet and Scene Feature Fusion.

Aiming at the common problems, such as noise pollution, low contrast, and color distortion in underwater images, and the characteristics of holothurian recognition, such as morphological ambiguity, high similarity with the background, and coexistence of special ecological scenes, this paper proposes an underwater holothurian target-detection algorithm (FA-CenterNet), based on improved CenterNet and scene feature fusion. First, to reduce the model's occupancy of embedded device resources, we use EfficientNet-B3 as the backbone network to reduce the model's Params and FLOPs. At the same time, EfficientNet-B3 increases the depth and width of the model, which improves the accuracy of the model. Then, we design an effective FPT (feature pyramid transformer) combination module to fully focus and mine the information on holothurian ecological scenarios of different scales and spaces (e.g., holothurian spines, reefs, and waterweeds are often present in the same scenario as holothurians). The co-existing scene information can be used as auxiliary features to detect holothurians, which can improve the detection ability of fuzzy and small-sized holothurians. Finally, we add the AFF module to realize the deep fusion of the shallow-detail and high-level semantic features of holothurians. The results show that the method presented in this paper yields better results on the 2020 CURPC underwater target-detection image dataset with an AP50 of 83.43%, Params of 15.90 M, and FLOPs of 25.12 G compared to other methods. In the underwater holothurian-detection task, this method improves the accuracy of detecting holothurians with fuzzy features, a small size, and dense scene. It also achieves a good balance between detection accuracy, Params, and FLOPs, and is suitable for underwater holothurian detection in most situations.

Classification of Building Damage Using a Novel Convolutional Neural Network Based on Post-Disaster Aerial Images.

The accurate and timely identification of the degree of building damage is critical for disaster emergency response and loss assessment. Although many methods have been proposed, most of them divide damaged buildings into two categories-intact and damaged-which is insufficient to meet practical needs. To address this issue, we present a novel convolutional neural network-namely, the earthquake building damage classification net (EBDC-Net)-for assessment of building damage based on post-disaster aerial images. The proposed network comprises two components: a feature extraction encoder module, and a damage classification module. The feature extraction encoder module is employed to extract semantic information on building damage and enhance the ability to distinguish between different damage levels, while the classification module improves accuracy by combining global and contextual features. The performance of EBDC-Net was evaluated using a public dataset, and a large-scale damage assessment was performed using a dataset of post-earthquake unmanned aerial vehicle (UAV) images. The results of the experiments indicate that this approach can accurately classify buildings with different damage levels. The overall classification accuracy was 94.44%, 85.53%, and 77.49% when the damage to the buildings was divided into two, three, and four categories, respectively.

Prediction of COVID-19 epidemic situation via fine-tuned IndRNN.

The COVID-19 pandemic is the most serious catastrophe since the Second World War. To predict the epidemic more accurately under the influence of policies, a framework based on Independently Recurrent Neural Network (IndRNN) with fine-tuning are proposed for predict the epidemic development trend of confirmed cases and deaths in the United Stated, India, Brazil, France, Russia, China, and the world to late May, 2021. The proposed framework consists of four main steps: data pre-processing, model pre-training and weight saving, the weight fine-tuning, trend predicting and validating. It is concluded that the proposed framework based on IndRNN and fine-tuning with high speed and low complexity, has great fitting and prediction performance. The applied fine-tuning strategy can effectively reduce the error by up to 20.94% and time cost. For most of the countries, the MAPEs of fine-tuned IndRNN model were less than 1.2%, the minimum MAPE and RMSE were 0.05%, and 1.17, respectively, by using Chinese deaths, during the testing phase. According to the prediction and validation results, the MAPEs of the proposed framework were less than 6.2% in most cases, and it generated lowest MAPE and RMSE values of 0.05% and 2.14, respectively, for deaths in China. Moreover, Policies that play an important role in the development of COVID-19 have been summarized. Timely and appropriate measures can greatly reduce the spread of COVID-19; untimely and inappropriate government policies, lax regulations, and insufficient public cooperation are the reasons for the aggravation of the epidemic situations. The code is available at https://github.com/zhhongsh/COVID19-Precdiction. And the prediction by IndRNN model with fine-tuning are now available online (http://47.117.160.245:8088/IndRNNPredict).

An interpretable machine learning method for homo-trimeric protein interface residue-residue interaction prediction.

Protein-protein interaction plays an important role in life activities. A more fine-grained analysis, such as residues and atoms level, will better benefit us to understand the mechanism for inter-protein interaction and drug design. The development of efficient computational methods to reduce trials and errors, as well as assisting experimental researchers to determine the complex structure are some of the ongoing studies in the field. The research of trimer protein interface, especially homotrimer, has been rarely studied. In this paper, we proposed an interpretable machine learning method for homo-trimeric protein interface residue pairs prediction. The structure, sequence, and physicochemical information are intergraded as feature input fed to model for training. Graph model is utilized to present spatial information for intra-protein. Matrix factorization captures the different features' interactions. Kernel function is designed to auto-acquire the adjacent information of our target residue pairs. The accuracy rate achieves 54.5% in an independent test set. Sequence and structure alignment exhibit the ability of model self-study. Our model indicates the biological significance between sequence and structure, and could be auxiliary for reducing trials and errors in the fields of protein complex determination and protein-protein docking, etc. SIGNIFICANCE: Protein complex structures are significant for understanding protein function and promising functional protein design. With data increasing, some computational tools have been developed for protein complex residue contact prediction, which is one of the most significant steps for complex structure prediction. But for homo-trimeric protein, the sequence-based deep learning predictors are infeasible for homologous sequences, and the algorithm black box prevents us from understanding of each step operation. In this way, we propose an interpreting machine learning method for homo-trimeric protein interface residue-residue interaction prediction, and the predictor shows a good performance. Our work provides a computational auxiliary way for determining the homo-trimeric proteins interface residue pairs which will be further verified by wet experiments, and and gives a hand for the downstream works, such as protein-protein docking, protein complex structure prediction and drug design.

Deep Supervised Residual Dense Network for Underwater Image Enhancement.

Underwater images are important carriers and forms of underwater information, playing a vital role in exploring and utilizing marine resources. However, underwater images have characteristics of low contrast and blurred details because of the absorption and scattering of light. In recent years, deep learning has been widely used in underwater image enhancement and restoration because of its powerful feature learning capabilities, but there are still shortcomings in detailed enhancement. To address the problem, this paper proposes a deep supervised residual dense network (DS_RD_Net), which is used to better learn the mapping relationship between clear in-air images and synthetic underwater degraded images. DS_RD_Net first uses residual dense blocks to extract features to enhance feature utilization; then, it adds residual path blocks between the encoder and decoder to reduce the semantic differences between the low-level features and high-level features; finally, it employs a deep supervision mechanism to guide network training to improve gradient propagation. Experiments results (PSNR was 36.2, SSIM was 96.5%, and UCIQE was 0.53) demonstrated that the proposed method can fully retain the local details of the image while performing color restoration and defogging compared with other image enhancement methods, achieving good qualitative and quantitative effects.

Spatiotemporal spread pattern of the COVID-19 cases in China.

The COVID-19 pandemic is currently spreading widely around the world, causing huge threats to public safety and global society. This study analyzes the spatiotemporal pattern of the COVID-19 pandemic in China, reveals China's epicenters of the pandemic through spatial clustering, and delineates the substantial effect of distance to Wuhan on the pandemic spread. The results show that the daily new COVID-19 cases mostly occurred in and around Wuhan before March 6, and then moved to the Grand Bay Area (Shenzhen, Hong Kong and Macau). The total COVID-19 cases in China were mainly distributed in the east of the Huhuanyong Line, where the epicenters accounted for more than 60% of the country's total in/on 24 January and 7 February, half in/on 31 January, and more than 70% from 14 February. The total cases finally stabilized at approximately 84,000, and the inflection point for Wuhan was on 14 February, one week later than those of Hubei (outside Wuhan) and China (outside Hubei). The generalized additive model-based analysis shows that population density and distance to provincial cities were significantly associated with the total number of the cases, while distances to prefecture cities and intercity traffic stations, and population inflow from Wuhan after 24 January, had no strong relationships with the total number of cases. The results and findings should provide valuable insights for understanding the changes in the COVID-19 transmission as well as implications for controlling the global COVID-19 pandemic spread.

A Classification-Lock Tracking Strategy Allowing a Person-Following Robot to Operate in a Complicated Indoor Environment.

Person-following technology is an important robot service. The major trend of person-following is to utilize computer vision technology to localize the target person, due to the wide view and rich information that is obtained from the real world through a camera. However, most existing approaches employ the detecting-by-tracking strategy, which suffers from low speed, accompanied with more complicated detecting models and unstable region of interest (ROI) outputs in unexpressed situations. In this paper, we propose a novel classification-lock strategy to localize the target person, which incorporates the visual tracking technology with object detection technology, to adapt the localization model to different environments online, and to keep a high frame-per-second (FPS) on the mobile platform. This person-following approach consists of three key parts. In the first step, a pairwise cluster tracker is employed to localize the person. A positive and negative classifier is then utilized to verify the tracker's result and to update the tracking model. In addition, a detector pre-trained by a CPU-optimized convolutional neural network is used to further improve the result of tracking. In the experiment, our approach is compared with other state-of-art approaches by a Vojir tracking dataset, with three sequences in the items of human to prove the quality of person localization. Moreover, the common challenges during the following task are evaluated by several image sequences in a static scene, and a dynamic scene is used to evaluate the improvement from the classification-lock strategy. Finally, our approach is deployed on a mobile robot to test its performance on the function of the person-following. Compared with other state-of-art methods, our approach achieves the highest score (0.91 recall rate). In the static and dynamic scene, the output of the ROI based on the classification-lock strategy is significantly better than that without it. Our approach also succeeds in a long-term following task in an indoor multi-floor scenario.

Sea Ice Detection Based on an Improved Similarity Measurement Method Using Hyperspectral Data.

Hyperspectral remote sensing technology can acquire nearly continuous spectrum information and rich sea ice image information, thus providing an important means of sea ice detection. However, the correlation and redundancy among hyperspectral bands reduce the accuracy of traditional sea ice detection methods. Based on the spectral characteristics of sea ice, this study presents an improved similarity measurement method based on linear prediction (ISMLP) to detect sea ice. First, the first original band with a large amount of information is determined based on mutual information theory. Subsequently, a second original band with the least similarity is chosen by the spectral correlation measuring method. Finally, subsequent bands are selected through the linear prediction method, and a support vector machine classifier model is applied to classify sea ice. In experiments performed on images of Baffin Bay and Bohai Bay, comparative analyses were conducted to compare the proposed method and traditional sea ice detection methods. Our proposed ISMLP method achieved the highest classification accuracies (91.18% and 94.22%) in both experiments. From these results the ISMLP method exhibits better performance overall than other methods and can be effectively applied to hyperspectral sea ice detection.