Motion Of Dynamic Objects Research Articles

Kalman Filter for a Particular Class of Dynamic Object Images

We discuss the problem of estimating the state of a dynamic object by using observed images generated by an optical system. The work aims to implement a novel approach that would ensure improved accuracy of dynamic object tracking using a sequence of images. We utilize a vector model that describes the object image as a limited number of vertexes (reference points). Upon imaging, the object of interest is assumed to be retained at the center of each frame, so that the motion parameters can be considered as projections onto the axes of a coordinate system matched with the camera's optical axis. The novelty of the approach is that the observed parameters (the distance along the optical axis and angular attitude) of the object are calculated using the coordinates of specified points in the object images. For estimating the object condition, a Kalman-Bucy filter is constructed on the assumption that the dynamic object motion is described by a set of equations for the translational motion of the center of mass along the optical axis and variations in the angular attitude relative to the image plane. The efficiency of the proposed method is illustrated by an example of estimating the object's angular attitude.

Blur-Robust Object Detection Using Feature-Level Deblurring via Self-Guided Knowledge Distillation

Images captured from real-world environments often include blur artifacts resulting from camera movement, dynamic object motion, or out-of-focus. Although such blur artifacts are inevitable, most object detection methods do not have special considerations for them; therefore, they may fail to detect objects in blurry images. One possible solution is applying image deblurring prior to object detection. However, this solution is computationally demanding and its performance heavily depends on image deblurring results. In this study, we propose a novel blur-aware object detection framework. First, we construct a synthetic but realistic dataset by applying a diverse set of motion blur kernels to blur-free images. Subsequently, we leverage self-guided knowledge distillation between the teacher and student networks that perform object detection using blur-free and blurry images, respectively. The teacher and student networks share most of their network parameters and jointly learn in a fully-supervised manner. The teacher network provides image features as hints for feature-level deblurring and also renders soft labels for the training of the student network. Guided by the hints and the soft labels from the teacher, the student network learns and expands their knowledge on object detection in blurry images. Experimental results show that the proposed framework improves the robustness of several widely used object detectors against image blurs.

The Effects of Vibratory Frequency and Temporal Interval on Tactile Apparent Motion.

Vibrotactile stimuli can be used to generate the haptic sensation of a static object or the motion of a dynamic object. Here, in this article, we investigated the effects of vibratory frequency and temporal interval on tactile apparent motion. In the experiment, we examined the effect of vibratory frequency with different temporal intervals on tactile apparent motion that results from two successive tactile stimuli on the index fingerpad. Results indicated that tactile apparent motion was perceived not only when both stimuli were either "flutter" or "vibration" stimuli, but also when one of each type was used. Specifically, when the first stimulus was introduced at 40Hz, "continuous motion" was viewed at all combinations of stimulus frequency, and "continuous motion" was clearly noted at the high-frequency combination instead of the low-frequency combination. Also, tactile apparent motion was predominantly viewed in the SOA range of 105 ms to 125 ms. We anticipate that our findings and further research will be essential resources for the design of tactile devices to represent the motion of dynamic objects.

Robustness of the Algorithm of Identification of the Type of Dynamic Object Found at the Finite Sequence of 2D Background Frames of the Optoelectron Device

Here are proposed robustness characteristics of the algorithm of identification of the type of the dynamic object (DO) and the law of probability distribution of identification sufficient statistics, formed by the algorithm under prior uncertainty. The law is applied for verification and validation of the algorithm. Wavelet fractal correlation algorithm (WFCA) implements vectorial criterion of ratio of likelihood functions of simple alternative hypotheses—types of DOs, this criterion being invariant to specific features of DO motion trajectories. The likelihood functions are reconstructed by simulation according to sufficiently representative complexes of implementations of fractal dimensions, energies, wavelet spectra and maximum eigenvalues of biased correlation matrices as functional of the measured coordinates of spatial attitude of various types of real DOs located by the optoelectron device (OED). The simulation proved robustness and high efficiency of the algorithm of identification of the type of DOs.

Motion Maps and Their Applications for Dynamic Object Monitoring

In this paper, dynamic object behavior analysis task is considered. We use basic optical flow to form integral optical flow and use it to separate background and foreground and obtain intensive motion regions. Based on information extracted from integral optical flow, we introduce notion of motion maps and show how it can be used for dynamic object motion analysis. In motion maps, we analyze pixel motions statistically for each frame to obtain quantity of pixels moving toward or away from each position and their comprehensive motion at each position. We then define and compute regional motion indicators to describe motions at regional level. These indicators are further used for analysis of dynamic object behavior. We conduct a set of experiments on real world videos. Experimental results show that motion maps can be effectively used for dynamic object monitoring.

Improvement of methods of compensating motion of dynamic objects in a video stream in a video conferencing system

The article deals with issues related to the speed of the video stream of video information, depending on the quality of video data required, from spatial resolution and frame rate. With the tendency of growth of volumes of video information and not providing the corresponding data volumes of the productivity of technologies of transmission and processing of video information in complexes videoconferencing - it is necessary to improve the coding methods. In order to increase the efficiency of management and operational activities, it is proposed to improve the existing methods of encoding a dynamic video stream object with algorithms for motion compensation for video conferencing in the control system.

Real-time 3D scene reconstruction with dynamically moving object using a single depth camera

Online 3D reconstruction of real-world scenes has been attracting increasing interests from both the academia and industry, especially with the consumer-level depth cameras becoming widely available. Recent most online reconstruction systems take live depth data from a moving Kinect camera and incrementally fuse them to a single high-quality 3D model in real time. Although most real-world scenes have static environment, the daily objects in a scene often move dynamically, which are non-trivial to reconstruct especially when the camera is also not still. To solve this problem, we propose a single depth camera-based real-time approach for simultaneous reconstruction of dynamic object and static environment, and provide solutions for its key issues. In particular, we first introduce a robust optimization scheme which takes advantage of raycasted maps to segment moving object and background from the live depth map. The corresponding depth data are then fused to the volumes, respectively. These volumes are raycasted to extract views of the implicit surface which can be used as a consistent reference frame for the next iteration of segmentation and tracking. Particularly, in order to handle fast motion of dynamic object and handheld camera in the fusion stage, we propose a sequential 6D pose prediction method which largely increases the registration robustness and avoids registration failures occurred in conventional methods. Experimental results show that our approach can reconstruct moving object as well as static environment with rich details, and outperform conventional methods in multiple aspects.

On the Recovery of Motion of Dynamic Objects from Stereo Images

An approach to the recovery of trajectories of objects in a dynamic scene from stereo images is proposed. The approach is based on the use of a point representation of objects, visual odometry, and a set of algorithms that produce point models of objects and calculate their trajectories using matched 3D point clouds. Results of numerical experiments for synthetic scenes are discussed.

Self-Expressive Dictionary Learning for Dynamic 3D Reconstruction.

We target the problem of sparse 3D reconstruction of dynamic objects observed by multiple unsynchronized video cameras with unknown temporal overlap. To this end, we develop a framework to recover the unknown structure without sequencing information across video sequences. Our proposed compressed sensing framework poses the estimation of 3D structure as the problem of dictionary learning, where the dictionary is defined as an aggregation of the temporally varying 3D structures. Given the smooth motion of dynamic objects, we observe any element in the dictionary can be well approximated by a sparse linear combination of other elements in the same dictionary (i.e., self-expression). Our formulation optimizes a biconvex cost function that leverages a compressed sensing formulation and enforces both structural dependency coherence across video streams, as well as motion smoothness across estimates from common video sources. We further analyze the reconstructability of our approach under different capture scenarios, and its comparison and relation to existing methods. Experimental results on large amounts of synthetic data as well as real imagery demonstrate the effectiveness of our approach.

Integral Optical Flow and its Application for Monitoring Dynamic Objects from a Video Sequence

We propose an algorithm for monitoring dynamic objects using integral optical flow, based on constructing a zone of interest for the motion and determining the vector structures, which let us determine the state of moving objects as the nature of the motion changes. Using the algorithm, we can analyze not only the motion of the object as a whole but also its internal changes. Determining the stages for development of the dynamic object using integral optical flow improves the accuracy in predicting the evolution of such objects and improves the quality of solutions to many problems involving automation of monitoring complex motion of dynamic objects.

Learned Non-Rigid Object Motion is a View-Invariant Cue to Recognizing Novel Objects

There is evidence that observers use learned object motion to recognize objects. For instance, studies have shown that reversing the learned direction in which a rigid object rotated in depth impaired recognition accuracy. This motion reversal can be achieved by playing animation sequences of moving objects in reverse frame order. In the current study, we used this sequence-reversal manipulation to investigate whether observers encode the motion of dynamic objects in visual memory, and whether such dynamic representations are encoded in a way that is dependent on the viewing conditions. Participants first learned dynamic novel objects, presented as animation sequences. Following learning, they were then tested on their ability to recognize these learned objects when their animation sequence was shown in the same sequence order as during learning or in the reverse sequence order. In Experiment 1, we found that non-rigid motion contributed to recognition performance; that is, sequence-reversal decreased sensitivity across different tasks. In subsequent experiments, we tested the recognition of non-rigidly deforming (Experiment 2) and rigidly rotating (Experiment 3) objects across novel viewpoints. Recognition performance was affected by viewpoint changes for both experiments. Learned non-rigid motion continued to contribute to recognition performance and this benefit was the same across all viewpoint changes. By comparison, learned rigid motion did not contribute to recognition performance. These results suggest that non-rigid motion provides a source of information for recognizing dynamic objects, which is not affected by changes to viewpoint.

326 ダ・ヴィンチのヘリコプターは飛ぶか?

We have proposed a fluid repulsion computation method as an environment field force to simulate the object motion in fluid. It is capable of simulating fast, real-time and dynamic object motion in the fluid. This study verifies that the proposed method is more applicable for simulating the object motion in many situations in the fluid. We especially focus on a simple helicopter equipped with a circular wing. Numerical experiments show the followings; (1) the helicopter flight can be controlled by Artificial neural network, (2) fluid repulsion force can be figured out by uniformly dividing the wing area, (3) it is possible to compute the fluid repulsion force by the fewer number of dividing wing area, and (4) we find a better wing shape of da Vinci helicopter by analyzing da Vinci's helicopter in simulation and making a model of da Vinci's helicopter in the real world.

An Evolutionary Model for Optimizing Sensor Pose in Object Motion Estimation Applications

Abstract An evolutionary control pazadigm for vision-system pose planning for object motion estimation is proposed. The control of the vision system is embedded in the motion estimation process so as to adapt to the dynamic object motion behavior. A Kalman filter is employed as the motion estimator. In the Kalman filter formulation, a noise influence matrix is introduced to model the influence of vision system parameters on the measurement uncertainties. The estimation uncertainties in the Kalman filter formulation are represented in the form of a Riccati equation. This equation describes the estimation uncertainties as an evolution process that is controlled by the vision system pazameters. The control task is formulated as an optimization problem. A novel transformation of the vision system parameters is developed to relax the computational complexity of the optimization process. A hybrid genetic algorithm is proposed to search for the optimal vision system pose that is occlusion free. A series of exper...

Modeling and adaptive control of robots interacting with environment

The adaptive control of multiple robot manipulators handling a dynamic object motion of which is constrained by the dynamic environment, when object and/or environment parameters are not known in advance, is proposed. It may be implemented when: (i) there is no good understanding of all physical effects incorporated in the multiple robots/object/environment system; (ii) the parameters of the system are not precisely known; (iii) the system parameters do vary in a known regions about their nominal values.

Dynamic Environment's Range Data Analysis by a Moving Observer

The use of mobile robots in dynamic environment is constrained by their environment sensing capabilities. Especially for motion execution and local trajectory planning, data about the egomotion of the robot and data about the motion of dynamic objects in the vicinity are necessary. This paper gives an overview of range sensor systems and data analysis methods which are used to perform detection of egomotion on one hand and estimation of motion of other objects on the other hand. The outline of a new method for motion estimation of a moving observer in the presence of moving objects is presented.