Predicting Object Trajectories from High-Speed Streaming Data

2015 ◽  
Author(s):  
Nikolaos Zorbas ◽  
Dimitrios Zissis ◽  
Konstantinos Tserpes ◽  
Dimosthenis Anagnostopoulos
Keyword(s):  
High Speed ◽  
Streaming Data ◽  
Object Trajectories

scholarly journals Tracking by Deblatting

2021 ◽  
Author(s):  
Denys Rozumnyi ◽  
Jan Kotera ◽  
Filip Šroubek ◽  
Jiří Matas
Keyword(s):  
High Speed ◽  
High Performance ◽  
Motion Blur ◽  
Velocity Estimation ◽  
High Speed Camera ◽  
Trajectory Function ◽  
Novel Approach ◽  
Blind Deblurring ◽  
Object Trajectories ◽  
Complex Trajectories

AbstractObjects 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.

Automatic Traffic Queue-End Identification using Location-Based Waze User Reports

2021 ◽  
pp. 036119812110133
Author(s):  
Yuandong Liu ◽  
Zhihua Zhang ◽  
Lee D. Han ◽  
Candace Brakewood
Keyword(s):  
Real Time ◽  
High Speed ◽  
Recurrent Events ◽  
Clustering Algorithm ◽  
Selection Procedure ◽  
The United States ◽  
Streaming Data ◽  
Data Sources ◽  
Sensor Data ◽  
Temporal Extent

Traffic queues, especially queues caused by non-recurrent events such as incidents, are unexpected to high-speed drivers approaching the end of queue (EOQ) and become safety concerns. Though the topic has been extensively studied, the identification of EOQ has been limited by the spatial-temporal resolution of traditional data sources. This study explores the potential of location-based crowdsourced data, specifically Waze user reports. It presents a dynamic clustering algorithm that can group the location-based reports in real time and identify the spatial-temporal extent of congestion as well as the EOQ. The algorithm is a spatial-temporal extension of the density-based spatial clustering of applications with noise (DBSCAN) algorithm for real-time streaming data with an adaptive threshold selection procedure. The proposed method was tested with 34 traffic congestion cases in the Knoxville,Tennessee area of the United States. It is demonstrated that the algorithm can effectively detect spatial-temporal extent of congestion based on Waze report clusters and identify EOQ in real-time. The Waze report-based detection are compared to the detection based on roadside sensor data. The results are promising: The EOQ identification time of Waze is similar to the EOQ detection time of traffic sensor data, with only 1.1 min difference on average. In addition, Waze generates 1.9 EOQ detection points every mile, compared to 1.8 detection points generated by traffic sensor data, suggesting the two data sources are comparable in respect of reporting frequency. The results indicate that Waze is a valuable complementary source for EOQ detection where no traffic sensors are installed.

scholarly journals A novel online multi-label classifier for high-speed streaming data applications

2016 ◽  
Vol 8 (4) ◽  
pp. 303-315 ◽  
Author(s):  
Rajasekar Venkatesan ◽  
Meng Joo Er ◽  
Mihika Dave ◽  
Mahardhika Pratama ◽  
Shiqian Wu
Keyword(s):  
High Speed ◽  
Streaming Data

scholarly journals Smoothness preserving layout for dynamic labels by hybrid optimization

2021 ◽  
Vol 8 (1) ◽  
pp. 149-163
Author(s):  
Yu He ◽  
Guo-Dong Zhao ◽  
Song-Hai Zhang
Keyword(s):  
Global Optimization ◽  
High Speed ◽  
Optimization Methods ◽  
Optimization Method ◽  
Streaming Data ◽  
Resultant Force ◽  
Hybrid Optimization ◽  
Global Optimization Method ◽  
Trade Off ◽  
Global Optimization Methods

AbstractStable label movement and smooth label trajectory are critical for effective information understanding. Sudden label changes cannot be avoided by whatever forced directed methods due to the unreliability of resultant force or global optimization methods due to the complex trade-off on the different aspects. To solve this problem, we proposed a hybrid optimization method by taking advantages of the merits of both approaches. We first detect the spatial-temporal intersection regions from whole trajectories of the features, and initialize the layout by optimization in decreasing order by the number of the involved features. The label movements between the spatial-temporal intersection regions are determined by force directed methods. To cope with some features with high speed relative to neighbors, we introduced a force from future, called temporal force, so that the labels of related features can elude ahead of time and retain smooth movements. We also proposed a strategy by optimizing the label layout to predict the trajectories of features so that such global optimization method can be applied to streaming data.

Stream-Based Short-Term Demand Forecasting Model Using ARIMA

2012 ◽  
Vol 220-223 ◽  
pp. 315-318
Author(s):  
Tao Liu ◽  
Rui Min Chen ◽  
Yong Xiao ◽  
Jin Feng Yang
Keyword(s):  
High Speed ◽  
Power Grid ◽  
Demand Forecasting ◽  
Streaming Data ◽  
Forecasting Model ◽  
Short Term ◽  
Smart Meters ◽  
Short Term Load Forecasting ◽  
Demand Forecasting Model ◽  
And Control

Short-term load forecasting for streaming load data is an important issue for power system planning, operation and control. Smart meters of Advanced Meter Infrastructure distributed around the distribution power grid produce streams of load at high-speed. The collected data can be characterized as a non-stationary continuous flow. A stream-based short-term demand forecasting model based on ARIMA is proposed. This method is used to forecast hourly electricity demand for next few days ahead. The performance of this methodology is validated with streaming data collected in real-time from the power grid.

Resource Allocation for Multi Access MIMO Systems

2011 ◽  
Vol 3 (3) ◽  
pp. 36-50
Author(s):  
Shailendra Mishra ◽  
D. S. Chauhan
Keyword(s):  
Resource Allocation ◽  
High Speed ◽  
New Technologies ◽  
Data Transfer ◽  
Mimo Systems ◽  
Data Access ◽  
Streaming Data ◽  
The Other ◽  
Packet Data ◽  
Multi Access

In this paper, the authors discuss the emergence of new technologies related to the topic of the high-speed packet data access in wireless networks. The authors propose an algorithm for MIMO systems that optimizes the number of the transmit antennas according to the user’s QoS. Scheduling performance under two types of traffic modes is also discussed: one is voice or web-browsing and the other is for data transfer and streaming data.

scholarly journals Stream-Based Lossless Data Compression Applying Adaptive Entropy Coding for Hardware-Based Implementation

Algorithms ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 159 ◽  
Author(s):  
Shinichi Yamagiwa ◽  
Eisaku Hayakawa ◽  
Koichi Marumo
Keyword(s):  
Big Data ◽  
Data Compression ◽  
Data Stream ◽  
High Speed ◽  
Data Communication ◽  
Streaming Data ◽  
Entropy Coding ◽  
Big Data Applications ◽  
Lossless Data Compression ◽  
Compressed Data

Toward strong demand for very high-speed I/O for processors, physical performance growth of hardware I/O speed was drastically increased in this decade. However, the recent Big Data applications still demand the larger I/O bandwidth and the lower latency for the speed. Because the current I/O performance does not improve so drastically, it is the time to consider another way to increase it. To overcome this challenge, we focus on lossless data compression technology to decrease the amount of data itself in the data communication path. The recent Big Data applications treat data stream that flows continuously and never allow stalling processing due to the high speed. Therefore, an elegant hardware-based data compression technology is demanded. This paper proposes a novel lossless data compression, called ASE coding. It encodes streaming data by applying the entropy coding approach. ASE coding instantly assigns the fewest bits to the corresponding compressed data according to the number of occupied entries in a look-up table. This paper describes the detailed mechanism of ASE coding. Furthermore, the paper demonstrates performance evaluations to promise that ASE coding adaptively shrinks streaming data and also works on a small amount of hardware resources without stalling or buffering any part of data stream.

Fast Mining of Closed Frequent Itemsets in Data Streams

2012 ◽  
Vol 263-266 ◽  
pp. 231-240
Author(s):  
Yi Min Mao ◽  
Zhi Gang Chen ◽  
Li Xin Liu
Keyword(s):  
Data Structure ◽  
Data Streams ◽  
High Speed ◽  
Search Space ◽  
Frequent Itemsets ◽  
Streaming Data ◽  
Closed Frequent Itemsets ◽  
Item List ◽  
Online Mining ◽  
Mining Data Streams

With the emergence of large-volume and high-speed streaming data, traditional techniques for mining closed frequent itemsets has become inefficient. Online mining of closed frequent itemsets over streaming data is one of the most important issues in mining data streams. In this paper, a combinative data structure is designed by using an effective bit-victor to represent items and an extended dictionary frequent item list to record the current closed frequent information in streams. For tremendous reduction of search space, some new search strategies are proposed to avoid a large number of intermediate itemsets generated. Meanwhile, some new pruning strategies are also proposed for the purpose of efficiently and dynamically maintaining of all the closure check operations. Experimental results show that the method proposed is efficient in time, with sound scalability as the number of transactions processed increases and adapts rapidly to the changes in data streams.

Resource Allocation for Multi Access MIMO Systems

2012 ◽  
pp. 221-235
Author(s):  
Shailendra Mishra ◽  
Durg Singh Chauhan
Keyword(s):  
Resource Allocation ◽  
High Speed ◽  
New Technologies ◽  
Data Transfer ◽  
Mimo Systems ◽  
Data Access ◽  
Streaming Data ◽  
The Other ◽  
Packet Data ◽  
Multi Access

In this paper, the authors discuss the emergence of new technologies related to the topic of the high-speed packet data access in wireless networks. The authors propose an algorithm for MIMO systems that optimizes the number of the transmit antennas according to the user’s QoS. Scheduling performance under two types of traffic modes is also discussed: one is voice or web-browsing and the other is for data transfer and streaming data.

Sign in / Sign up

Export Citation Format

Share Document