Search

Protection of urban critical infrastructures (CIs) from GPS-denied, bomb-carrying kamikaze drones (G-BKDs) is very challenging. Previous approaches based on drone jamming, spoofing, communication interruption and hijacking cannot be applied in the case under examination, since G-B-KDs are uncontrolled. On the other hand, drone capturing schemes and electromagnetic pulse (EMP) weapons seem to be effective. However, again, existing approaches present various limitations, while most of them do not examine the case of G-B-KDs. This paper, focuses on the aforementioned under-researched field, where the G-B-KD is confronted by two defensive drones. The first neutralizes and captures the kamikaze drone, while the second captures the bomb. Both defensive drones are equipped with a net-gun and an innovative algorithm, which, among others, estimates the locations of interception, using a real-world trajectory model. Additionally, one of the defensive drones is also equipped with an EMP weapon to damage the electronics equipment of the kamikaze drone and reduce the capturing time and the overall risk. Extensive simulated experiments and comparisons to state-of-art methods, reveal the advantages and limitations of the proposed approach. More specifically, compared to state-of-art, the proposed approach improves: (a) time to neutralize the target by at least 6.89%, (b) maximum number of missions by at least 1.27% and (c) total cost by at least 5.15%. [ABSTRACT FROM AUTHOR]

This study introduces a new method for precise acoustic drone localization and tracking via the noise generated by the drone. Drone noises include harmonic frequency components which are related to the rotational speed of the propeller and the number of blades. This study integrates utilization of the frequency components around harmonics into Steered Response Power - Phase Transform (SRP-PHAT). First, a custom discrete Fourier transform (namely DFT-Harmonics) is defined which concentrates only on the vicinities of harmonics to capture the frequency components possibly related to the drone sound. Then, DFT-Harmonics is integrated into SRP-PHAT, which is named SRP-Harmonics. The benefits of SRP-Harmonics are explained and illustrated via SRP maps and videos. Experiments with real microphone array data show that SRP-Harmonics is precise in localizing and tracking a drone, while the ordinary SRP-PHAT can not be reasonably successful. Moreover, SRP-Harmonics after Kaiser window can maintain its performance even when significant level of artificial white noise or natural wind noise exists in the data. [ABSTRACT FROM AUTHOR]

Protection of urban critical infrastructures (CIs) from GPS-denied, bomb-carrying kamikaze drones (G-B-KDs) is very challenging. Previous approaches based on drone jamming, spoofing, communication interruption and hijacking cannot be applied in the case under examination, since G-B-KDs are uncontrolled. On the other hand, drone capturing schemes and electromagnetic pulse (EMP) weapons seem to be effective. However, again, existing approaches present various limitations, while most of them do not examine the case of G-B-KDs. This paper, focuses on the aforementioned under-researched field, where the G-B-KD is confronted by two defensive drones. The first neutralizes and captures the kamikaze drone, while the second captures the bomb. Both defensive drones are equipped with a net-gun and an innovative algorithm, which, among others, estimates the locations of interception, using a real-world trajectory model. Additionally, one of the defensive drones is also equipped with an EMP weapon to damage the electronics equipment of the kamikaze drone and reduce the capturing time and the overall risk. Extensive simulated experiments and comparisons to state-of-art methods, reveal the advantages and limitations of the proposed approach. More specifically, compared to state-of-art, the proposed approach improves: (a) time to neutralize the target by at least 6.89%, (b) maximum number of missions by at least 1.27% and (c) total cost by at least 5.15%.

To improve the effect of table tennis tactical analysis, this study proposed a table tennis video tactical analysis method based on image fuzzy edge recognition algorithm. This algorithm can effectively recognize edges in images to improve recognition accuracy and reduce errors and rejection rates. In addition, this research combines the methods of target tracking and trajectory estimation to build a table tennis video game tactical analysis platform. The experimental data show that the recognition accuracy of the proposed fuzzy edge recognition algorithm is 98.1%, and the error and rejection rates are less than 1.6%. Compared with the image edge detection algorithm based on interval value fuzzy, the proposed algorithm has better performance. When the positioning error is 10%, the precision of the table tennis target tracking algorithm can reach 94.3%, which is 9.3% higher than that of the direct linear transform algorithm. The table tennis video game tactical analysis platform can analyze the velocity of ping-pong ball according to the video, and records the droppoint of ping-pong ball, which helps the players to develop more effective tactics and strategies to improve their competitive level and achievements.

In indoor highly dynamic scenes or scenes with missing a priori dynamic information, most current schemes cannot effectively avoid the impact of moving objects on the performance of SLAM (Simultaneous Localization and Mapping) systems. In order to solve the problem of accurate localization and map building for mobile robots in indoor highly dynamic environments, we propose a dynamic RGB-D visual SLAM dense map building method based on pyramidal L-K (Lucas-Kanade) optical flow with multi-view geometric constraints. Our proposed method consists of three stages: dynamic object culling, camera position estimation, and dense map construction based on the TSDF (truncated signed distance function) model. First, dynamic elements in the scene are detected and culled by combining pyramidal L-K optical flow with a multi-view geometric constraint method. Then, the estimation of the camera pose is achieved by minimizing the SDF error function. Finally, the estimated camera poses and static depth images are used to construct TSDF dense maps and indexed using dynamic voxel assignment and spatial hashing techniques. We evaluated our method on dynamic sequences of the Bonn dataset and the TUM dataset, and proved the effectiveness of the algorithm on a real scene dataset of our own making. The experimental results show that our method can effectively improve the camera position estimation accuracy and realize the construction of dense maps after processing dynamic objects, which improves the robustness of the system as well as the accuracy of environment reconstruction.

For this work, a preliminary study proposed virtual interfaces for remote psychotherapy and psychology practices. This study aimed to verify the efficacy of such approaches in obtaining results comparable to in-presence psychotherapy, when the therapist is physically present in the room. In particular, we implemented several joint machine-learning techniques for distance detection, camera calibration and eye tracking, assembled to create a full virtual environment for the execution of a psychological protocol for a self-induced mindfulness meditative state. Notably, such a protocol is also applicable for the desensitization phase of EMDR therapy. This preliminary study has proven that, compared to a simple control task, such as filling in a questionnaire, the application of the mindfulness protocol in a fully virtual setting greatly improves concentration and lowers stress for the subjects it has been tested on, therefore proving the efficacy of a remote approach when compared to an in-presence one. This opens up the possibility of deepening the study, to create a fully working interface which will be applicable in various on-field applications of psychotherapy where the presence of the therapist cannot be always guaranteed. [ABSTRACT FROM AUTHOR]

Potential field theory, as a theory that can also be applied to vehicle control, is an emerging risk quantification approach to accommodate the connected and self-driving vehicle environment. Vehicles have different risk impact effects on other road participants in each direction under the influence of road rules. This variability exhibited by vehicles in each direction is not considered in the previous potential field model. Therefore, this paper proposed a potential field model that takes the anisotropy of vehicle impact into account: (1) introducing equivalent distances to separate the potential field area in the different directions before and after the vehicle; (2) introducing co-virtual forces to characterize the effect of the side-by-side travel phenomenon on vehicle car-following travel; (3) introducing target forces and lane resistance, which regress the control of desired speed to control the acceptable risk of drivers. The Next Generation Simulation (NGSIM) dataset is used in this study to create the model's initial parameter values based on the artificial swarm algorithm. The simulation findings indicate that when the vehicle is given the capacity to perceive the surrounding traffic environment, the suggested the anisotropic safety potential field model (ASPFM) performs better in terms of driving safety.

The development of ship technology and information technology has been driving the continuous improvement of ship intelligence, with safety being an inevitable requirement in the shipping industry. A machine vision-based ship collision warning method is proposed for high monitoring system cost and limited information acquisition in safety design of autonomous ship navigation. The method combines machine learning with image algorithms. Firstly, the backbone of YOLOv7 detector is replaced by EfficientFormerV2 network to achieve model lightweight while ensuring detection accuracy. Public datasets SeaShips, Flow and self-made ship pictures are combined, and the network is trained on this dataset. StrongSORT is used for target tracking. Secondly, a data fusion algorithm is introduced to determine the target point at the bow-bottom of the ship based on the time-varying attitude of the camera and the time-series features of the bounding boxes. Ship navigation trajectory estimation is performed using image algorithms. Finally, a collision evaluation model is established to calculate the collision risk index. Experimental results demonstrate that the improved YOLOv7 network maintains similar mAP.5 and Recall compared to the original model, while reducing the parameters by 31.2 % and GFLOPs by 58.4 %. The accuracy of target ship trajectory estimation is high, with MAE values below 1.5 % and RMSE values below 2 % in experiments. In ship collision warning experiments, the proposed method accurately identifies navigating vessels, estimates the trajectories, and provides timely warnings for imminent collision accidents. Compared to traditional ship collision warning methods, this paper offers a more intelligent and lightweight solution.

In this paper, we propose a nonlinear tracking solution for maneuvering aerial targets based on an adaptive interacting multiple model (IMM) framework and unscented Kalman filters (UKFs), termed as AIMM-UKF. The purpose is to obtain more accurate estimates, better consistency of the tracker, and more robust prediction during sensor outages. The AIMM-UKF framework provides quick switching between two UKFs by adapting the transition probabilities between modes based on a distance function. Two modes are implemented: a uniform motion model and a maneuvering model. The experimental validation is performed with Monte Carlo simulations of three scenarios with ACAS Xa tracking logic as a benchmark, which is the next generation of airborne collision avoidance systems. The two algorithms are compared using hypothesis testing of the root mean square errors. In addition, we determine the normalized estimation error squared (NEES), a new proposed noise reduction factor to compare the estimation errors against the measurement errors, and an estimated maximum error of the tracker during sensor dropouts. The experimental results illustrate the superior performance of the proposed solution with respect to the tracking accuracy, consistency, and expected maximum error. [ABSTRACT FROM AUTHOR]

The development of high-performance, low-cost unmanned aerial vehicles paired with rapid progress in vision-based perception systems herald a new era of autonomous flight systems with mission-ready capabilities. One of the key features of an autonomous UAV is a robust mid-air collision avoidance strategy. This paper proposes a vision-based in-flight collision avoidance system based on background subtraction using an embedded computing system for unmanned aerial vehicles (UAVs). The pipeline of proposed in-flight collision avoidance system is as follows: (i) subtract dynamic background subtraction to remove it and to detect moving objects, (ii) denoise using morphology and binarization methods, (iii) cluster the moving objects and remove noise blobs, using Euclidean clustering, (iv) distinguish independent objects and track the movement using the Kalman filter, and (v) avoid collision, using the proposed decision-making techniques. This work focuses on the design and the demonstration of a vision-based fast-moving object detection and tracking system with decision-making capabilities to perform evasive maneuvers to replace a high-vision system such as event camera. The novelty of our method lies in the motion-compensating moving object detection framework, which accomplishes the task with background subtraction via a two-dimensional transformation approximation. Clustering and tracking algorithms process detection data to track independent objects, and stereo-camera-based distance estimation is conducted to estimate the three-dimensional trajectory, which is then used during decision-making procedures. The examination of the system is conducted with a test quadrotor UAV, and appropriate algorithm parameters for various requirements are deduced. [ABSTRACT FROM AUTHOR]

Newell's simplified kinematic wave model has been widely used in studying traffic dynamics in a road network. However, it cannot account for First-In-First-Out violation among vehicles on multi-lane roads. In this study, we present an extension of the model in the Lagrangian coordinates. In particular, we define a new variable of a vehicle's order as its corresponding cumulative flows at different times and locations. The new kinematic wave model is consistent at the aggregate level with Newell's simplified kinematic wave model, but allows for FIFO violation among individual vehicles. Based on the new model, we then present two algorithms to estimate vehicles’ trajectories from Eulerian data (cumulative flows provided by loop detectors) and Lagrangian data (the vehicle's entry and exit times provided by reidentification technologies) at two boundaries of a road segment. In the first algorithm, we assume that vehicles follow the First-In-First-Out (FIFO) principle on a multi-lane road, and their orders are constant and equal the average of the entry and exit orders; in the second algorithm, we introduce a linear order-changing model to interpolate a vehicle's orders at different times according to its entry and exit times. With Next Generation Simulation (NGSIM) datasets, we demonstrate that both algorithms are effective, but the second one, with an estimation error of around 10%, greatly outperforms the first one, with an estimation error of around 13%. This verifies the advantage of incorporating FIFO violation in the new model.

Newell's simplified kinematic wave model has been widely used in studying traffic dynamics in a road network. However, it cannot account for First-In-First-Out violation among vehicles on multi-lane roads. In this study, we present an extension of the model in the Lagrangian coordinates. In particular, we define a new variable of a vehicle's order as its corresponding cumulative flows at different times and locations. The new kinematic wave model is consistent at the aggregate level with Newell's simplified kinematic wave model, but allows for FIFO violation among individual vehicles. Based on the new model, we then present two algorithms to estimate vehicles’ trajectories from Eulerian data (cumulative flows provided by loop detectors) and Lagrangian data (the vehicle's entry and exit times provided by reidentification technologies) at two boundaries of a road segment. In the first algorithm, we assume that vehicles follow the First-In-First-Out (FIFO) principle on a multi-lane road, and their orders are constant and equal the average of the entry and exit orders; in the second algorithm, we introduce a linear order-changing model to interpolate a vehicle's orders at different times according to its entry and exit times. With Next Generation Simulation (NGSIM) datasets, we demonstrate that both algorithms are effective, but the second one, with an estimation error of around 10%, greatly outperforms the first one, with an estimation error of around 13%. This verifies the advantage of incorporating FIFO violation in the new model.

Inertial localisation is an important technique as it enables ego-motion estimation in conditions where external observers are unavailable. However, low-cost inertial sensors are inherently corrupted by bias and noise, which lead to unbound errors, making straight integration for position intractable. Traditional mathematical approaches are reliant on prior system knowledge, geometric theories and are constrained by predefined dynamics. Recent advances in deep learning, which benefit from ever-increasing volumes of data and computational power, allow for data-driven solutions that offer more comprehensive understanding. Existing deep inertial odometry solutions rely on estimating the latent states, such as velocity, or are dependent on fixed-sensor positions and periodic motion patterns. In this work, we propose taking the traditional state estimation recursive methodology and applying it in the deep learning domain. Our approach, which incorporates the true position priors in the training process, is trained on inertial measurements and ground truth displacement data, allowing recursion and learning both motion characteristics and systemic error bias and drift. We present two end-to-end frameworks for pose invariant deep inertial odometry that utilises self-attention to capture both spatial features and long-range dependencies in inertial data. We evaluate our approaches against a custom 2-layer Gated Recurrent Unit, trained in the same manner on the same data, and tested each approach on a number of different users, devices and activities. Each network had a sequence length weighted relative trajectory error mean ≤ 0.4594 m, highlighting the effectiveness of our learning process used in the development of the models. [ABSTRACT FROM AUTHOR]

Motion planning algorithms for automated vehicles need to assess the intended behavior of other Traffic Participants (TPs), in order to predict the likely future trajectory of TPs and plan the motion consequently. Information resulting from several sources, like sensors, must be gathered and combined into a reliable estimate of the intended behavior of TPs. Such estimates must be sufficiently steady and quantify the inherent uncertainty around the assessment. We present a novel information fusion algorithm to combine information from different sources into a coherent and reliable estimate. To explicitly account for the uncertainty of estimates, we leverage the Belief Function Theory and evaluate and handle possible disagreements between estimates individually provided by the sources. The algorithm is flexible and can also handle sources that do not discern between some of the considered behaviors and are only capable of assessing the probability of unions or clusters of different behaviors. We discuss the strengths of the approach through simulations in SUMO, comparing it to the Interactive Multiple Model algorithm.

For this work, a preliminary study proposed virtual interfaces for remote psychotherapy and psychology practices. This study aimed to verify the efficacy of such approaches in obtaining results comparable to in-presence psychotherapy, when the therapist is physically present in the room. In particular, we implemented several joint machine-learning techniques for distance detection, camera calibration and eye tracking, assembled to create a full virtual environment for the execution of a psychological protocol for a self-induced mindfulness meditative state. Notably, such a protocol is also applicable for the desensitization phase of EMDR therapy. This preliminary study has proven that, compared to a simple control task, such as filling in a questionnaire, the application of the mindfulness protocol in a fully virtual setting greatly improves concentration and lowers stress for the subjects it has been tested on, therefore proving the efficacy of a remote approach when compared to an in-presence one. This opens up the possibility of deepening the study, to create a fully working interface which will be applicable in various on-field applications of psychotherapy where the presence of the therapist cannot be always guaranteed.

In this paper, we propose a nonlinear tracking solution for maneuvering aerial targets based on an adaptive interacting multiple model (IMM) framework and unscented Kalman filters (UKFs), termed as AIMM-UKF. The purpose is to obtain more accurate estimates, better consistency of the tracker, and more robust prediction during sensor outages. The AIMM-UKF framework provides quick switching between two UKFs by adapting the transition probabilities between modes based on a distance function. Two modes are implemented: a uniform motion model and a maneuvering model. The experimental validation is performed with Monte Carlo simulations of three scenarios with ACAS Xa tracking logic as a benchmark, which is the next generation of airborne collision avoidance systems. The two algorithms are compared using hypothesis testing of the root mean square errors. In addition, we determine the normalized estimation error squared (NEES), a new proposed noise reduction factor to compare the estimation errors against the measurement errors, and an estimated maximum error of the tracker during sensor dropouts. The experimental results illustrate the superior performance of the proposed solution with respect to the tracking accuracy, consistency, and expected maximum error.

The development of high-performance, low-cost unmanned aerial vehicles paired with rapid progress in vision-based perception systems herald a new era of autonomous flight systems with mission-ready capabilities. One of the key features of an autonomous UAV is a robust mid-air collision avoidance strategy. This paper proposes a vision-based in-flight collision avoidance system based on background subtraction using an embedded computing system for unmanned aerial vehicles (UAVs). The pipeline of proposed in-flight collision avoidance system is as follows: (i) subtract dynamic background subtraction to remove it and to detect moving objects, (ii) denoise using morphology and binarization methods, (iii) cluster the moving objects and remove noise blobs, using Euclidean clustering, (iv) distinguish independent objects and track the movement using the Kalman filter, and (v) avoid collision, using the proposed decision-making techniques. This work focuses on the design and the demonstration of a vision-based fast-moving object detection and tracking system with decision-making capabilities to perform evasive maneuvers to replace a high-vision system such as event camera. The novelty of our method lies in the motion-compensating moving object detection framework, which accomplishes the task with background subtraction via a two-dimensional transformation approximation. Clustering and tracking algorithms process detection data to track independent objects, and stereo-camera-based distance estimation is conducted to estimate the three-dimensional trajectory, which is then used during decision-making procedures. The examination of the system is conducted with a test quadrotor UAV, and appropriate algorithm parameters for various requirements are deduced.

Multi-robot motion and observation generally have nonlinear characteristics; in response to the problem that the existing extended Kalman filter (EKF) algorithm used in robot position estimation only considers first-order expansion and ignores the higher-order information, this paper proposes a multi-robot formation trajectory based on the high-order Kalman filter method. The joint estimation method uses Taylor expansion of the state equation and observation equation and introduces remainder variables on this basis, which effectively improves the estimation accuracy. In addition, the truncation error and rounding error of the filtering algorithm before and after the introduction of remainder variables, respectively, are compared. Our analysis shows that the rounding error is much smaller than the truncation error, and the nonlinear estimation performance is greatly improved. [ABSTRACT FROM AUTHOR]

Inertial localisation is an important technique as it enables ego-motion estimation in conditions where external observers are unavailable. However, low-cost inertial sensors are inherently corrupted by bias and noise, which lead to unbound errors, making straight integration for position intractable. Traditional mathematical approaches are reliant on prior system knowledge, geometric theories and are constrained by predefined dynamics. Recent advances in deep learning, which benefit from ever-increasing volumes of data and computational power, allow for data-driven solutions that offer more comprehensive understanding. Existing deep inertial odometry solutions rely on estimating the latent states, such as velocity, or are dependent on fixed-sensor positions and periodic motion patterns. In this work, we propose taking the traditional state estimation recursive methodology and applying it in the deep learning domain. Our approach, which incorporates the true position priors in the training process, is trained on inertial measurements and ground truth displacement data, allowing recursion and learning both motion characteristics and systemic error bias and drift. We present two end-to-end frameworks for pose invariant deep inertial odometry that utilises self-attention to capture both spatial features and long-range dependencies in inertial data. We evaluate our approaches against a custom 2-layer Gated Recurrent Unit, trained in the same manner on the same data, and tested each approach on a number of different users, devices and activities. Each network had a sequence length weighted relative trajectory error mean ≤0.4594 m, highlighting the effectiveness of our learning process used in the development of the models.

The rapid developments in the field of Artificial Intelligence are bringing enhancements in the area of intelligent transport systems by overcoming the challenges of safety concerns. Traffic surveillance systems based on CCTV cameras can help us to achieve safe and sustainable transport systems. Trajectory estimation of vehicles is an important part of traffic surveillance systems and self-driving cars. The task is challenging due to the variations in illumination intensities, object sizes and real-time detection. We propose tracking by detection based trajectory estimation pipeline which consists of two stages: The first stage is the detection and localization of vehicles and the second stage is building associations in bounding boxes and track the associated bounding boxes. We analyze the performance of the Mask RCNN benchmark and YOLOv3 on the UA-DETRAC dataset and evaluate certain metrics like Intersection over Union, Precision-Recall curve, and Mean Average Precision. Experiments show that Mask RCNN Benchmark outperforms YOLOv3 in terms of accuracy. SORT tracker is applied on detected bounding boxes to estimate trajectories. The tracker is evaluated using mean absolute error. We demonstrate that the developed technique works successfully in crowded and crossroad scenarios.

This paper investigates the use of supervised Deep Learning (DL) networks to process sonar images for underwater navigation. State-of-the-art DL techniques for micro-navigation using sequences of optical images have been adapted to work with sonar images. Specifically, the DL networks estimate the Forward-Looking Sonar (FLS) motion in three degrees of freedom corresponding to $x$ - and $y$ -translation and rotation around $z$ -axis. The state-of-the-art DL architectures and a proposed new architecture are investigated for motion estimation. They are trained using images generated by a FLS simulator. The data sets are made using pairs of consecutive images associated with labels that represent the motion of the sonar platform between images. The results show the effectiveness of using the DL architectures, which can provide millimeter accuracy for translation motion and below 0.1° for rotation motion between two consecutive sonar images. Examples of trajectory estimation and mosaic building using simulated and real sonar images are also presented.

This paper presents a new constrained optimization-based smoothing algorithm for walking step length estimation using waist-mounted inertial sensors, where the total walking distance is known. The walking trajectory is estimated by double integrating acceleration. Due to sensor noises, the walking step length estimation accuracy degrades as the walking distance becomes longer. To tackle this problem, we introduce a known distance straight-line walking trajectory constraint and a constant speed constraint to the smoothing algorithm. These constraints reduce the walking step estimation accuracy degradation even for long walking distance. Two experiments are conducted to evaluate the pedestrian trajectory and walking step length estimation accuracy. The accuracy of a 20 m walking trajectory estimation has been investigated in the first experiment. This experiment compares the estimated position and velocity with Lidar-based references. The second experiment is to demonstrate the usefulness of the proposed walking step length estimation method. The result shows that the average of mean relative errors is 0.6801% for three different walking speed levels. The proposed method can be applied to generate training data for walking step length estimation without requiring spatial infrastructure.

The study of the contrast between fundamental aspects of spatial and temporal awareness offers a good opportunity to bring to light the relation between philosophical and scientific theories of consciousness. In this paper we critically examine important work by Rick Grush on spatial and temporal experience, and we show that while there is a valid claim for the relevant neuroscientific model to be one that supports Gareth Evans's stance on "behavioral space", there is not at present any scientific model that offers comparable support for philosophical theories of temporal experience, despite some claims by Grush that might suggest the contrary. Moreover, we argue that careful attention to the spatial case allows us to locate the point at which even relatively successful cases of neuroscientific modeling and explanation are left wanting when their aim is to show that phenomenal features of experience are a function of the representational structures produced by our neural information-processing machinery: an aim widely shared by the predominant programmatic stance in current neuroscience research. [ABSTRACT FROM AUTHOR]

Objects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects travel a considerable distance during exposure time of a single frame, and therefore, their position in the frame is not well defined. They appear as semi-transparent streaks due to the motion blur and cannot be reliably tracked by general trackers. We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. By postprocessing, non-causal Tracking by Deblatting estimates continuous, complete, and accurate object trajectories for the whole sequence. Tracked objects are precisely localized with higher temporal resolution than by conventional trackers. Energy minimization by dynamic programming is used to detect abrupt changes of motion, called bounces. High-order polynomials are then fitted to smooth trajectory segments between bounces. The output is a continuous trajectory function that assigns location for every real-valued time stamp from zero to the number of frames. The proposed algorithm was evaluated on a newly created dataset of videos from a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms the baselines both in recall and trajectory accuracy. Additionally, we show that from the trajectory function precise physical calculations are possible, such as radius, gravity, and sub-frame object velocity. Velocity estimation is compared to the high-speed camera measurements and radars. Results show high performance of the proposed method in terms of Trajectory-IoU, recall, and velocity estimation. [ABSTRACT FROM AUTHOR]

Multi-robot motion and observation generally have nonlinear characteristics; in response to the problem that the existing extended Kalman filter (EKF) algorithm used in robot position estimation only considers first-order expansion and ignores the higher-order information, this paper proposes a multi-robot formation trajectory based on the high-order Kalman filter method. The joint estimation method uses Taylor expansion of the state equation and observation equation and introduces remainder variables on this basis, which effectively improves the estimation accuracy. In addition, the truncation error and rounding error of the filtering algorithm before and after the introduction of remainder variables, respectively, are compared. Our analysis shows that the rounding error is much smaller than the truncation error, and the nonlinear estimation performance is greatly improved.

To achieve human-level object manipulation capability, a robot must be able to handle objects not only with prehensile manipulation, such as pick-and-place, but also with nonprehensile manipulation. To study nonprehensile manipulation, we studied robotic batting, a primitive form of nonprehensile manipulation. Batting is a challenging research area because it requires sophisticated and fast manipulation of moving objects and requires considerable improvement. In this paper, we designed a batting system for dynamic manipulation of a moving ball and proposed several algorithms to improve the task performance of batting. To improve the recognition accuracy of the ball, we proposed a circle-fitting method that complements color segmentation. This method enabled robust ball recognition against illumination. To accurately estimate the trajectory of the recognized ball, weighted least-squares regression considering the accuracy according to the distance of a stereo vision sensor was used for trajectory estimation, which enabled more accurate and faster trajectory estimation of the ball. Further, we analyzed the factors influencing the success rate of ball direction control and applied a constant posture control method to improve the success rate. Through the proposed methods, the ball direction control performance is improved. [ABSTRACT FROM AUTHOR]

Fresh market apples are one of the high‐value crops in the United States. Washington alone has produced two‐thirds of the annual national production in the past 10 years. However, the availability of seasonal labor is increasingly uncertain. Shake‐and‐catch automated harvesting solutions have, therefore, become attractive for addressing this challenge. One of the significant challenges in applying this harvesting system is effectively positioning the end‐effector at appropriate excitation locations. A computer vision system was used for automatically identifying appropriate locations. Convolutional neural networks (CNNs) were utilized to identify the tree trunks and branches for supporting the automated excitation locations determination. Three CNN architectures were employed: Deeplab v3+ ResNet‐18, VGG‐16, and VGG‐19. Four pixel classes were predefined as branches, trunks, apples, and leaves to segment the canopies trained to simple, narrow, accessible, and productive tree architectures with varying foliage density. Results on Fuji cultivar showed that ResNet‐18 outperformed the VGGs in identifying branches and trunks based on all three evaluation measures: per‐class accuracy (PcA), intersection over union (IoU), and boundary‐F1 score (BFScore). ResNet‐18 achieved a PcA of 97%, IoU of 0.69, and BFScore of 0.89. The ResNet‐18 was further evaluated for its robustness with other test canopy images. When applied this method to one of the highest density cultivars of Scifresh, results showed it can achieve IoUs of 0.41 and 0.62 and BFScores of 0.71 and 0.86 for branches and trunks. Such identification result helped to get a 72% of auto‐determined shaking points being the "good" category identified by human experts. [ABSTRACT FROM AUTHOR]

Large-scale 3D point clouds (LS3DPCs) captured by terrestrial LiDAR scanners often include virtual points which are generated by glass reflection. The virtual points may degrade the performance of various computer vision techniques when applied to LS3DPCs. In this paper, we propose a virtual point removal algorithm for LS3DPCs with multiple glass planes. We first estimate multiple glass regions by modeling the reliability with respect to each glass plane, respectively, such that the regions are assigned high reliability when they have multiple echo pulses for each emitted laser pulse. Then we detect each point whether it is a virtual point or not. For a given point, we recursively traverse all the possible trajectories of reflection, and select the optimal trajectory which provides a point with a similar geometric feature to a given point at the symmetric location. We evaluate the performance of the proposed algorithm on various LS3DPC models with diverse numbers of glass planes. Experimental results show that the proposed algorithm estimates multiple glass regions faithfully and detects the virtual points successfully. Moreover, we also show that the proposed algorithm yields a much better performance of reflection artifact removal compared with the existing method qualitatively and quantitatively. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of National University of Defense Technology / Guofang Keji Daxue Xuebao is the property of NUDT Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Driver situation awareness is critical for safety. In this paper, we propose a fast, accurate method for obtaining real-time situation awareness using a single type of sensor: monocular cameras. The system tracks the host vehicle’s trajectory using sparse optical flow and tracks vehicles in the surrounding environment using convolutional neural networks. Optical flow is used to measure the linear and angular velocity of the host vehicle. The convolutional neural networks are used to measure target vehicles’ positions relative to the host vehicle using image-based detections. Finally, the system fuses host and target vehicle trajectories in the world coordinate system using the velocity of the host vehicle and the target vehicles’ relative positions with the aid of an Extended Kalman Filter (EKF). We implement and test our model quantitatively in simulation and qualitatively on real-world test video. The results show that the algorithm is superior to state-of-the-art sequential state estimation methods such as visual SLAM in performing accurate global localization and trajectory estimation for host and target vehicles.