Motion Feature Retrieval in Basketball Match Video Based on Multisource Motion Feature Fusion

Both the human body and its motion are three-dimensional information, while the traditional feature description method of two-person interaction based on RGB video has a low degree of discrimination due to the lack of depth information. According to the respective advantages and complementary characteristics of RGB video and depth video, a retrieval algorithm based on multisource motion feature fusion is proposed. Firstly, the algorithm uses the combination of spatiotemporal interest points and word bag model to represent the features of RGB video. Then, the directional gradient histogram is used to represent the feature of the depth video frame. The statistical features of key frames are introduced to represent the histogram features of depth video. Finally, the multifeature image fusion algorithm is used to fuse the two video features. The experimental results show that multisource feature fusion can greatly improve the retrieval accuracy of motion features.

Demonstrating the first postulate of relativity in a lift

The first of the two postulates of relativity states that the laws of physics are the same in all inertial reference frames. Often it is assumed that the postulates are mainly concerned with objects moving at a significant fraction of the speed of light. However, the postulates are applicable at all speeds from a snail to a photon. To practically demonstrate the first postulate, the time for a ball to drop a known distance was measured in a stationary and moving lift. An accelerometer app on an iPhone 7 was used to measure the vertical acceleration while the lift travelled between floors and verified that the lift ascended and descended at a constant speed when the ball was dropped. The slow-motion feature of the iPhone 7 (240 fps) was used to capture videos of the falling ball. The number of frames for the ball to fall in a stationary, descending, and ascending lift was respectively 102.4 ± 0.55 , 102.3 ± 1.64 , 99.8 ± 4.21. A t-test revealed no significant difference between these values, confirming the validity of the first postulate. The accelerometer signal was integrated to estimate the average speed of the lift between the bottom and top floor, which was then used to estimate the height difference. An electronic balance placed on the floor of the lift was used to demonstrate the first postulate and the equivalence principle of General Relativity that states that gravitational and inertial mass are equivalent.

Temporal Video Segmentation Using Optical Flow Estimation

Shot boundary detection is the process of segmenting a video into basic units known as shots by discovering transition frames between shots. Researches have been conducted to accurately detect the shot boundaries. However, the acceleration of the shot detection process with higher accuracy needs improvement. A new method was introduced in this paper to find out the boundaries of abrupt shots in the video with high accuracy and lower computational cost. The proposed method consists of two stages. First, projection features were used to distinguish non boundary transitions and candidate transitions that may contain abrupt boundary. Only candidate transitions were conserved for next stage. Thus, the speed of shot detection was improved by reducing the detection scope. In the second stage, the candidate segments were refined using motion feature derived from the optical flow to remove non boundary frames. The results manifest that the proposed method achieved excellent detection accuracy (0.98 according to F-Score) and effectively speeded up detection process. In addition, the comparative analysis results confirmed the superior performance of the proposed method versus other methods.

Numerical Simulation on the Diffusion of Alien Phytoplankton in Bohai Bay

In order to investigate the motion feature of alien phytoplankton in the Bohai Bay area, this manuscript builds a two-dimensional tide hydrodynamic model coupled with a particle tracking model to simulate the alien phytoplankton movement trajectory and the diffusion processes with different specific growth rates in three major ports of Bohai Bay (Caofeidian port, Tianjin port, and Huanghua port). The results show that the movement of alien phytoplankton is mainly affected by the tidal circulation near the port, and the diffusion trend is basically consistent with the residual flow in Bohai Bay. The distribution density of alien phytoplankton is directly affected by the specific growth rate of the population and is positively related to specific growth rate. The released alien phytoplankton in the three major ports are all concentrated around the ports area. The largest distribution density is in Tianjin port, and the possibility of red tide disasters is also greatest here compared with the other two major ports. It is necessary to strengthen the monitoring of alien organisms in the port area and actively prevent alien phytoplankton from entering Bohai Bay through ship ballast water.

The New Development of Soft Microgel Particle Flooding Technology –From Theoretical Research in Laboratory to Field Trial

Although polymer flooding technology has been widely applied and achieved remarkable effect of increasing oil. Yet the "entry profile inversion" phenomenon occurs inevitably in its later stage, which seriously affects the development effect. In recent years, the soft microgel particle dispersion is a novel developed flooding system. Due to its excellent performance and advanced mechanism, it can slow down the process of profile inversion, and achieve the goal of deep fluid diversion and expanding swept volume. The soft microgel particle dispersion consists of microgel particles and its carrier fluid. After coming into porous media, it shows the properties of "plugging large pore and leave the small one open" and the motion feature of "trapping, deformation, migration". In this paper, reservoir adaptability evaluation, plugging and deformation characteristics of soft microgel particle dispersion in pore throat is explored by using the microfluidic technology and 3D Printing technology. On this basis, by adopting the NMR and CT tomography technology, the research on its oil displacement mechanism is further carried out. Furthermore, the typical field application case is analyzed. Results show that, soft microgel particles have good performance and transport ability in porous media. According to the reservoir adaptability evaluation, the size relationships between particles and core pore throat is obtained, to provide basis for field application scheme design. Through microfluidic experiments, the temporary plugging and deformation characteristics of particles in the pore throat are explored. Also, when injecting soft microgel particle into the core, the particle phase separation happens, which makes the particles enter and plug the large pore in the high permeability layer. Therefore, their carrier fluid displace oil in the small pore, which works in cooperation and causes no damage to the low permeability layer. Furthermore, by using NMR and CT techniques, its micro percolation law in porous media and remaining oil distribution during displacement process is analyzed. During the experiment, microgels presents the motion feature of "migration, trapping, and deformation" in the core pore, which can realize deep fluid diversion and expand swept volume. From 3D macro experiment, microgels can realize the goal of enhance oil recovery. Finally, the soft microgel particle dispersion flooding technology has been applied in different oilfields, such as Oman, Bohai and other oilfields, which all obtained great success. Through interdisciplinary innovative research methods, the oil displacement mechanism and field application of soft microgel particle dispersion is researched, which proves its progressiveness and superiority. The research results provide theoretical basis and technical support for the enhancing oil recovery significantly.

Background Invariant Faster Motion Modeling for Drone Action Recognition

Visual data collected from drones has opened a new direction for surveillance applications and has recently attracted considerable attention among computer vision researchers. Due to the availability and increasing use of the drone for both public and private sectors, it is a critical futuristic technology to solve multiple surveillance problems in remote areas. One of the fundamental challenges in recognizing crowd monitoring videos’ human action is the precise modeling of an individual’s motion feature. Most state-of-the-art methods heavily rely on optical flow for motion modeling and representation, and motion modeling through optical flow is a time-consuming process. This article underlines this issue and provides a novel architecture that eliminates the dependency on optical flow. The proposed architecture uses two sub-modules, FMFM (faster motion feature modeling) and AAR (accurate action recognition), to accurately classify the aerial surveillance action. Another critical issue in aerial surveillance is a deficiency of the dataset. Out of few datasets proposed recently, most of them have multiple humans performing different actions in the same scene, such as a crowd monitoring video, and hence not suitable for directly applying to the training of action recognition models. Given this, we have proposed a novel dataset captured from top view aerial surveillance that has a good variety in terms of actors, daytime, and environment. The proposed architecture has shown the capability to be applied in different terrain as it removes the background before using the action recognition model. The proposed architecture is validated through the experiment with varying investigation levels and achieves a remarkable performance of 0.90 validation accuracy in aerial action recognition.