Clustering of Human Movement Trajectories based on Distributional Representations Derived from Bi-directional LSTM Network with Geographical Coordinates

2021 ◽  
Author(s):  
Hiroki Tanaka ◽  
Takeshi Saga ◽  
Satoshi Nakamura
Keyword(s):  
Human Movement ◽  
Movement Trajectories ◽  
Lstm Network

scholarly journals Object detection and tracking in video sequences: formalization, metrics and results

Informatics ◽  
2021 ◽  
Vol 18 (1) ◽  
pp. 43-60
Author(s):  
R. P. Bohush ◽  
S. V. Ablameyko
Keyword(s):  
Moving Objects ◽  
Human Movement ◽  
Video Sequences ◽  
Multiple Objects ◽  
Movement Trajectories ◽  
Detection And Tracking ◽  
Form Features ◽  
One And Many ◽  
Tracking Objects

One of the promising areas of development and implementation of artificial intelligence is the automatic detection and tracking of moving objects in video sequence. The paper presents a formalization of the detection and tracking of one and many objects in video. The following metrics are considered: the quality of detection of tracked objects, the accuracy of determining the location of the object in a frame, the trajectory of movement, the accuracy of tracking multiple objects. Based on the considered generalization, an algorithm for tracking people has been developed that uses the tracking through detection method and convolutional neural networks to detect people and form features. Neural network features are included in a composite descriptor that also contains geometric and color features to describe each detected person in the frame. The results of experiments based on the considered criteria are presented, and it is experimentally confirmed that the improvement of the detector operation makes it possible to increase the accuracy of tracking objects. Examples of frames of processed video sequences with visualization of human movement trajectories are presented.

Evaluation of Control Interfaces for Desktop Virtual Environments

2015 ◽  
Vol 24 (4) ◽  
pp. 322-334 ◽  
Author(s):  
Tyler Thrash ◽  
Mubbasir Kapadia ◽  
Mehdi Moussaid ◽  
Christophe Wilhelm ◽  
Dirk Helbing ◽  
...  
Keyword(s):  
Virtual Environments ◽  
Real World ◽  
Precise Measurement ◽  
Movement Patterns ◽  
Human Movement ◽  
Transportation Systems ◽  
Spatial Behavior ◽  
Limited Resources ◽  
Movement Trajectories ◽  
Crowd Management

Tracking and analyzing the movement trajectories of individuals and groups is an important problem with applications in crowd management and the development of transportation systems. However, real-world tracking is limited due to the size of the trackable area and the precision with which a person can be tracked. Experiments in virtual environments have many advantages, including practically unlimited sizes and the precise measurement of spatial behavior. However, the generalizability of research using virtual environments to real-world scenarios is often limited by the translation of participants’ movements to those of their avatars. We compared human movement patterns in virtual environments with different control interfaces: a handheld joystick, a mouse-and-keyboard setup, and a keyboard-only setup. With each of these controls, participants completed several movement-related tasks of varying difficulty in a limited amount of time. Questionnaires indicated that participants preferred the mouse-and-keyboard setup over the other two setups. Standard performance measures suggested that the joystick underperformed in a variety of tasks. Movement trajectories in the final task indicated that each of the control setups produced somewhat realistic behavior, despite some apparent differences from real-world trajectories. Overall, the results indicated that, given limited resources, mouse-and-keyboard setups consistently outperform joysticks and produce realistic movement patterns.

The trajectory of human wrist movements

1988 ◽  
Vol 59 (6) ◽  
pp. 1814-1830 ◽  
Author(s):  
R. B. Stein ◽  
F. W. Cody ◽  
C. Capaday
Keyword(s):  
Nervous System ◽  
Energy Consumption ◽  
Human Movement ◽  
Normal Subjects ◽  
Kinematic Variable ◽  
Wrist Flexion ◽  
Movement Trajectories ◽  
Minimum Jerk ◽  
Inertial Loading ◽  
Third Derivative

1. To determine the form of human movement trajectories and the factors that determine this form, normal subjects performed wrist flexion movements against various elastic, viscous, and inertial loads. The subjects were instructed with visual and auditory feedback to make a movement of prescribed amplitude in a present period of time, but were free to choose any trajectory that fulfilled these constraints. 2. The trajectories were examined critically to determine if they corresponded to those which would minimize the root mean square (RMS) value of some kinematic variable or of energy consumption. The data agreed better with the trajectory that minimized the RMS value of jerk (the third derivative of length) than that of acceleration. However, systematic deviations from the minimum jerk predictions were consistently observed whenever movements were made against elastic and viscous loads. 3. Improved agreement could generally be obtained by assuming that the velocity profile varied according to a normal (Gaussian) curve. We conclude that minimization of jerk is not a general principle used by the nervous system in organizing voluntary movements, although movements may approach the predicted form, particularly under inertial loading conditions. 4. The EMG of the agonist muscles consisted of relatively simple waveforms containing ramplike increases and approximately exponential decays. The form of the movements could often be predicted quite well by using the EMG as an input to a linear second-order model of the muscle plus load. Rather than rigorously minimizing a kinematic variable or energy consumption, the nervous system may generate simple waveforms and adjust the parameters of these waveforms by trial and error until a trajectory is achieved that meets the requirements for a given load.

Reaching to Grasp With a Multi-Jointed Arm. I. Computational Model

2002 ◽  
Vol 88 (5) ◽  
pp. 2355-2367 ◽  
Author(s):  
Elizabeth B. Torres ◽  
David Zipser
Keyword(s):  
Error Correction ◽  
Constraint Satisfaction ◽  
Degrees Of Freedom ◽  
Computational Models ◽  
Reference Frames ◽  
Dimensional Space ◽  
Arm Movement ◽  
Human Movement ◽  
Path Selection ◽  
Movement Trajectories

The generation of goal-directed movements requires the solution of many difficult computational problems. Among these are transformations from extrinsic to intrinsic reference frames, specifying solution paths, removing under-specification due to excess degrees of freedom and path multiplicity, constraint satisfaction, and error correction. There are no current motor-control computational models that address these issues in the context of realistic arm movement with redundant degrees of freedom. In this paper, we conjecture there is a geometric stage between sensory input and physical execution. The geometric stage determines movement trajectories independently of forces. It uses a gradient technique that relies on the metric of the space of postures to resolve endpoint path selection, posture-change specification, error correction, and multiple constraint satisfaction on-line without preplanning. The model is instantiated in an arm with seven degrees of freedom that moves in three-dimensional space. Simulated orientation-matching movements are compared with actual human movement data to assess the validity of several of the model's behavioral predictions.

scholarly journals The impact of human mobility data scales and processing on movement predictability

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kamil Smolak ◽  
Katarzyna Siła-Nowicka ◽  
Jean-Charles Delvenne ◽  
Michał Wierzbiński ◽  
Witold Rohm
Keyword(s):  
Prediction Models ◽  
Human Mobility ◽  
Reference Value ◽  
Human Movement ◽  
Temporal Data ◽  
Movement Trajectories ◽  
Mobility Data ◽  
Wide Range ◽  
Spatio Temporal ◽  
The Impact

AbstractPredictability of human movement is a theoretical upper bound for the accuracy of movement prediction models, which serves as a reference value showing how regular a dataset is and to what extent mobility can be predicted. Over the years, the predictability of various human mobility datasets was found to vary when estimated for differently processed datasets. Although attempts at the explanation of this variability have been made, the extent of these experiments was limited. In this study, we use high-precision movement trajectories of individuals to analyse how the way we represent the movement impacts its predictability and thus, the outcomes of analyses made on these data. We adopt a number of methods used in the last 11 years of research on human mobility and apply them to a wide range of spatio-temporal data scales, thoroughly analysing changes in predictability and produced data. We find that spatio-temporal resolution and data processing methods have a large impact on the predictability as well as geometrical and numerical properties of human mobility data, and we present their nonlinear dependencies.

scholarly journals Dimensionality Reduction of Human Gait for Prosthetic Control

2021 ◽  
Vol 9 ◽  
Author(s):  
David Boe ◽  
Alexandra A. Portnova-Fahreeva ◽  
Abhishek Sharma ◽  
Vijeth Rai ◽  
Astrini Sie ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Principal Component ◽  
Human Movement ◽  
Individual Identification ◽  
Human Gait ◽  
Prosthetic Control ◽  
Movement Trajectories ◽  
Lower Limb Prosthesis ◽  
Flat Ground ◽  
Movement Classification

We seek to use dimensionality reduction to simplify the difficult task of controlling a lower limb prosthesis. Though many techniques for dimensionality reduction have been described, it is not clear which is the most appropriate for human gait data. In this study, we first compare how Principal Component Analysis (PCA) and an autoencoder on poses (Pose-AE) transform human kinematics data during flat ground and stair walking. Second, we compare the performance of PCA, Pose-AE and a new autoencoder trained on full human movement trajectories (Move-AE) in order to capture the time varying properties of gait. We compare these methods for both movement classification and identifying the individual. These are key capabilities for identifying useful data representations for prosthetic control. We first find that Pose-AE outperforms PCA on dimensionality reduction by achieving a higher Variance Accounted For (VAF) across flat ground walking data, stairs data, and undirected natural movements. We then find in our second task that Move-AE significantly outperforms both PCA and Pose-AE on movement classification and individual identification tasks. This suggests the autoencoder is more suitable than PCA for dimensionality reduction of human gait, and can be used to encode useful representations of entire movements to facilitate prosthetic control tasks.

Sign in / Sign up

Export Citation Format

Share Document