The scene rigidity is a strong assumption in typical visual Simultaneous Localization and Mapping (vSLAM) algorithms. Such strong assumption limits the usage of most vSLAM in dynamic real-world ...environments, which are the target of several relevant applications such as augmented reality, semantic mapping, unmanned autonomous vehicles, and service robotics. Many solutions are proposed that use different kinds of semantic segmentation methods (e.g., Mask R-CNN, SegNet) to detect dynamic objects and remove outliers. However, as far as we know, such kind of methods wait for the semantic results in the tracking thread in their architecture, and the processing time depends on the segmentation methods used. In this paper, we present RDS-SLAM, a real-time visual dynamic SLAM algorithm that is built on ORB-SLAM3 and adds a semantic thread and a semantic-based optimization thread for robust tracking and mapping in dynamic environments in real-time. These novel threads run in parallel with the others, and therefore the tracking thread does not need to wait for the semantic information anymore. Besides, we propose an algorithm to obtain as the latest semantic information as possible, thereby making it possible to use segmentation methods with different speeds in a uniform way. We update and propagate semantic information using the moving probability, which is saved in the map and used to remove outliers from tracking using a data association algorithm. Finally, we evaluate the tracking accuracy and real-time performance using the public TUM RGB-D datasets and Kinect camera in dynamic indoor scenarios.
Source code and demo: https://github.com/yubaoliu/RDS-SLAM.git
It is important to measure and analyze people behavior to design systems which interact with people. This article describes a portable people behavior measurement system using a three-dimensional ...LIDAR. In this system, an observer carries the system equipped with a three-dimensional Light Detection and Ranging (LIDAR) and follows persons to be measured while keeping them in the sensor view. The system estimates the sensor pose in a three-dimensional environmental map and tracks the target persons. It enables long-term and wide-area people behavior measurements which are hard for existing people tracking systems. As a field test, we recorded the behavior of professional caregivers attending elderly persons with dementia in a hospital. The preliminary analysis of the behavior reveals how the caregivers decide the attending position while checking the surrounding people and environment. Based on the analysis result, empirical rules to design the behavior of attendant robots are proposed.
Visual simultaneous localization and mapping (vSLAM) are considered a fundamental technology for augmented reality and intelligent mobile robots. However, rigid scene assumption is common in vSLAM, ...which limits the wide usage in populated real-world environments. Recently, with the widespread use of artificial neural networks, many solutions have tried to eliminate the influence of dynamic objects using semantic information provided by object detection or semantic segmentation. Mask R-CNN is popular in many applications, but is usually slow and limits the speed of vSLAM because it waits for the semantic results before camera ego-motion estimation. We had previously introduced a real-time vSLAM, RDS-SLAM, which isolates tracking and semantic segmentation by adding a semantic thread and moving probability estimation. However, Mask R-CNN only supplies a small amount of semantic information because only a few keyframes can be segmented within a short time. Therefore, in this study, we propose a novel vSLAM, RDMO-SLAM, which can leverage more semantic information while ensuring the real-time nature by adding semantic label prediction using dense optical flow. Besides, we also estimate the velocity of each landmark and use them as constraints to reduce the influence of dynamic objects in tracking. Demonstrations are presented, which compare the proposed method to comparable state-of-the-art approaches using dynamic sequences. We improved the real-time performance from 15 Hz (RDS-SLAM) to 30 Hz while keeping robust tracking in dynamic scenes.
In this work, we introduce DeepIPC, a novel end-to-end model tailored for autonomous driving, which seamlessly integrates perception and control tasks. Unlike traditional models that handle these ...tasks separately, DeepIPC innovatively combines a perception module, which processes RGBD images for semantic segmentation and generates bird's eye view (BEV) mappings, with a controller module that utilizes these insights along with GNSS and angular speed measurements to accurately predict navigational waypoints. This integration allows DeepIPC to efficiently translate complex environmental data into actionable driving commands. Our comprehensive evaluation demonstrates DeepIPC's superior performance in terms of drivability and multi-task efficiency across diverse real-world scenarios, setting a new benchmark for end-to-end autonomous driving systems with a leaner model architecture. The experimental results underscore DeepIPC's potential to significantly enhance autonomous vehicular navigation, promising a step forward in the development of autonomous driving technologies. For further insights and replication, we will make our code and datasets available at https://github.com/oskarnatan/DeepIPC.
Biological oxidation of arsenite (As(III)) in synthetic groundwater was examined by using arsenite oxidising bacteria (AOB) isolated from an activated sludge. The phylogenetic analysis indicated that ...the isolated AOB was closely related to Ensifer adhaerens. Batch experiments showed that for an As(III) oxidation with the isolated AOB the optimum ratio of nitrogen source (NH4-N) concentration to As(III) concentration was 0.5 (52 mg/L–110 mg/L) and the isolated AOB preferred pH values ranging from 6 to 8, and water temperatures greater than 20 °C. Further continuous experiments were conducted using a bioreactor with immobilised AOB. With an initial As(III) concentration of 1 mg/L at a hydraulic retention time (HRT) of 1 h, an As(III) oxidation rate was around 1 × 10−9 μg/cell/min and an As(III) oxidation efficiency of 92% was achieved. Although the maximum oxidation rate measured at an HRT of 0.5 h was 2.1 × 10−9 μg/cell/min, the oxidation efficiency decreased to 87%.
These results advocate that a biological process involving immobilised AOB may be useful as an economical and environmentally friendly pre-treatment step for As removal from groundwater.
Display omitted
► As(III) oxidising bacteria were isolated from activated sludge. ► Some optimum conditions were obtained for microbial As(III) oxidation. ► Continuous As(III) oxidation was achieved using a bioreactor at an HRT of 0.5 h.
Mucosa‐associated lymphoid tissue (MALT) is a low‐grade lymphoma, but cases in which it has transformed into a high‐grade lymphoma have been reported, necessitating an accurate diagnosis. The patient ...was a 79‐year‐old nonsmoking Japanese female with history of ocular sarcoidosis. A computed tomography scan of her chest revealed a 35‐mm nodule in the left S1 + 2, contiguous with the lymph nodes. Additional nodules were observed around the left B5 and B10a. Bronchoscopy revealed stenosis caused by a white, glossy, elevated lesion with angiogenesis at the orifice of the left upper lobe bronchus. The biopsy specimen demonstrated the dominance of lymphoid cells and tested positive for CD20, CD79a, Bcl‐2, and IRTA‐1, which is consistent with the findings in MALT lymphoma. Therefore, in the presence of multiple infiltrative shadows along the bronchi with glossy elevated lesions without necrosis on bronchoscopy, it is important to consider MALT lymphoma as a differential diagnosis.
This article is a case of pulmonary primary MALT lymphoma with characteristic bronchoscopy findings. Immunochemical staining of IRTA‐1 was especially useful for diagnosis.
This paper presents a new approach to view-based localization and navigation in outdoor environments, which are indispensable functions for mobile robots. Several approaches have been proposed for ...autonomous navigation. GPS-based systems are widely used especially in the case of automobiles, however, they can be unreliable or non-operational near tall buildings. Localization with a precise 3D digital map of the target environment also enables mobile robots equipped with range sensors to estimate accurate poses, but maintaining a large-scale outdoor map is often costly. We have therefore developed a novel view-based localization method SeqSLAM++ by extending the conventional SeqSLAM in order not only to robustly estimate the robot position comparing image sequences but also to cope with changes in a robot’s heading and speed as well as view changes using wide-angle images and a Markov localization scheme. According to the direction to move provided by the SeqSLAM++, the local-level path planner navigates the robot by setting subgoals repeatedly considering the structure of the surrounding environment using a 3D LiDAR. The entire navigation system has been implemented in the ROS framework, and the effectiveness and accuracy of the proposed method was evaluated through off-line/on-line navigation experiments.
This study aimed to assess the association between the degree of varus thrust (VT) assessed by an inertial measurement unit (IMU) and patient-reported outcome measures (PROMs) in patients with knee ...osteoarthritis. Seventy patients (mean age: 59.8 ± 8.6 years; women: n = 40) were instructed to walk on a treadmill with an IMU attached to the tibial tuberosity. For the index of VT during walking (VT-index), the swing-speed adjusted root mean square of acceleration in the mediolateral direction was calculated. As the PROMs, the Knee Injury and Osteoarthritis Outcome Score were used. Data on age, sex, body mass index, static alignment, central sensitization, and gait speed were collected as potential confounders. After adjusting for potential confounders, multiple linear regression analysis revealed that the VT-index was significantly associated with the pain score (standardized β = -0.295;
= 0.026), symptoms score (standardized β = -0.287;
= 0.026), and activities of the daily living score (standardized β = -0.256;
= 0.028). Our results indicated that larger VT values during gait are associated with worse PROMs, suggesting that an intervention to reduce VT might be an option for clinicians trying to improve PROMs.
This paper describes a method of estimating the traversability of plant parts covering a path and navigating through them for mobile robots operating in plant-rich environments. Conventional mobile ...robots rely on scene recognition methods that consider only the geometric information of the environment. Those methods, therefore, cannot recognize paths as traversable when they are covered by flexible plants. In this paper, we present a novel framework of image-based scene recognition to realize navigation in such plant-rich environments. Our recognition model exploits a semantic segmentation branch for general object classification and a traversability estimation branch for estimating pixel-wise traversability. The semantic segmentation branch is trained using an unsupervised domain adaptation method and the traversability estimation branch is trained with label images generated from the robot's traversal experience during the data acquisition phase, coined traversability masks . The training procedure of the entire model is, therefore, free from manual annotation. In our experiment, we show that the proposed recognition framework is capable of distinguishing traversable plants more accurately than a conventional semantic segmentation with traversable plant and non-traversable plant classes, and an existing image-based traversability estimation method. We also conducted a real-world experiment and confirmed that the robot with the proposed recognition method successfully navigated in plant-rich environments.
A 69‐year‐old female Japanese patient presented with an abnormal shadow on chest computed tomography (CT). She had received a mastectomy 14 years prior. Under the diagnosis of primary lung cancer, ...left upper lobectomy was conducted. Pathology showed a lepidic adenocarcinoma with mediastinal lymph node metastases with pT2aN2M0. Upon retrospective analysis, the chest CT at the time of mastectomy depicted a ground‐glass nodule (GGN) of less than 20 mm. Over the previous 10.5 years, the concentration of the central part of the GGN increased. Conclusively, a pure GGN developed into lung adenocarcinoma with mediastinal lymph node involvement over 14 years. She had bone metastases 4 years after the lobectomy but has survived for five and a half years after surgery with treatment with osimertinib. Comparison readings of films should be performed throughout the patient's clinical history to detect subtle shadow alterations indicative of tumour progression.
We had an interesting case of a pure ground‐glass nodule that developed into lung adenocarcinoma with mediastinal lymph node involvement over 14 years. Here we report the temporal change in the opacity of the GGN and the concept of image interpretation.