STOCHASTIC NOISE TOLERANCE:ENHANCED FULL STATE OBSERVER VS. KALMAN FILTER FROM VIDEO TRACKING PERSPECTIVE

A control-based full state observer scheme is explored for video target tracking application, and is enhanced with a lowpass filter for improving the tracking precision, thus forming an Enhanced Full State Observer (EFSO). The whole design is based on the given lab-generated video sequence with motion of an articulate target. To evaluate the EFSO’s stochastic noise tolerance, a Kalman Filter (KF) is intentionally employed in tracking the same target with the given Gaussian white noises. The comparison results indicate that, for system noises of certain statistics, the proposed EFSO has its own noise resistance capacity that is superior to that of KF and is more advantageous for implementation.

Parametric Evaluation of Video Motion Tracking Data Sets

Video tracking is a complex problem because the environment, in which video motion needs to be tracked, is widely varied based on the application and poses several constraints on the design and performance of the tracking system. Current datasets that are used to evaluate and compare video motion tracking algorithms use a cumulative performance measure without thoroughly analyzing the effect of these different constraints imposed by the environment. But it needs to analyze these constraints as parameters. The objective of this paper is to identify these parameters and define quantitative measures for these parameters to compare video datasets for motion tracking.

VIDEO MULTI-TARGET TRACKING BASED ON PROBABILISTIC GRAPHICAL MODEL

In the technique of video multi-target tracking,the common particle filter can not deal well with uncertain relations among multiple targets.To solve this problem,many researchers use data association method to reduce the multi-target uncertainty.However,the traditional data association method is difficult to track accurately when the target is occluded.To remove the occlusion in the video,combined with the theory of data association,this paper adopts the probabilistic graphical model for multi-target modeling and analysis of the targets relationship in the particle filter framework.Ex-perimental results show that the proposed algorithm can solve the occlusion problem better compared with the traditional algorithm.

INFLUENCE OF STOCHASTIC NOISE STATISTICS ON KALMAN FILTER PERFORMANCE BASED ON VIDEO TARGET TRACKING

The system stochastic noises involved in Kalman filtering are preconditioned on being ideally white and Gaussian distributed. In this research, efforts are exerted on exploring the influence of the noise statistics on Kalman filtering from the perspective of video target tracking quality. The correlation of tracking precision to both the process and measurement noise covariance is investigated; the signal-to-noise power density ratio is defined; the contribution of predicted states and measured outputs to Kalman filter behavior is discussed; the tracking precision relative sensitivity is derived and applied in this study case. The findings are expected to pave the way for future study on how the actual noise statistics deviating from the assumed ones impacts on the Kalman filter optimality and degra-dation in the application of video tracking.

Performance of Resampling Algorithms Based on Particle Filter in Video Target Tracking

Particle filter is a common algorithm in video target tracking.But there are still some shortcomings,for example,particle degradation phenomenon.For solving this problem,the general solution is to introduce resampling step.At present,four kinds of resampling algorithms are widely used:multinomial resampling,residual resampling,stratified resampling and systematic resampling algorithms.In this paper,the performances of these four resampling algorithms were analyzed from realization principle,uniform distribution theory and computational complexity.Finally,through a series of video target tracking experiments,the systematic resampling algorithm had the smallest calculation load,the shortest running time and the maximum number of effective particles.So,it can be concluded that in the field of video target tracking,the systematic resampling algorithm has more advantages than other three algorithms both in the running time and the number of effective particles.

Multi-view video color correction using dynamic programming

Color inconsistency between views is an important problem to be solved in multi-view video systems. A multi-view video color correction method using dynamic programming is proposed. Three-dimensional histograms are constructed with sequential conditional probability in HSI color space. Then, dynamic programming is used to seek the best color mapping relation with the minimum cost path between target image histogram and source image histogram. Finally, video tracking technique is performed to correct multi-view video. Experimental results show that the proposed method can obtain better subjective and objective performance in color correction.

Video-based pedestrian grouping model considering longspan space in a big hall

Pedestrian group detection is a challenging but significant issue in pedestrian flow control and public safety management.To address the issue that most conventional pedestrian grouping models(PGMs)can only identify a pedestrian group at a limited distance of less than 2 m,this study extended the pedestrian distance constraint of conventional PGMs with a reconstruction of the normal group detection criterion and development of a novelgroup detection criterion suitable for long-span space.To measure the movement behaviorsimilarity with normal distance,five necessary constraints:velocity difference,moving direction offset,distance limitation,distance fluctuation,and group-keeping duration were studied quantitatively to form the criterion to detect normal groups.Meanwhile,a long-span group detection criterion was proposed with extended distance and direction con-sistency constraints.Therefore,this study proposed an improved PGM that considers long-span spaces(PGMLS).In the PGMLS workflow,the MMTrack algorithm was used to obtainpedestrian trajectories.A difference measurement method based on sequential pattern analysis(SPA)was adopted to analyze the velocity similarity of pedestrians.To validate the proposed grouping model,experiments based on pedestrian movement videos in the exit hall of the Shanghai Hongqiao International Airport were conducted.The results indicate that the proposed model can detect both normal and widely separated pedestrian groups,with a long span range of 2-12 m.

基于残差密集孪生网络的视频目标跟踪

针对现有基于孪生网络的视频目标跟踪(video object tracking, VOT)方法存在的特征提取能力不足以及对外观变化过大或平面外旋转等目标跟踪效果不佳的问题,提出一种基于残差密集孪生网络的VOT方法.首先,使用嵌入卷积注意力的残差密集网络对模板帧图像和检测帧图像分别提取不同层次的特征;然后,将不同层次的特征通过相互独立的区域候选网络进行互相关操作;最后,将多个区域候选网络的输出自适应加权求和,得到最终的跟踪结果.实验结果表明,该方法在应对目标表观变化过大、平面外旋转等挑战时,能够获得较好的跟踪效果.

Automatic tracking of multi-fruit targets with oscillation under natural growth conditions

It is important for intelligent orchards to be able to achieve automatic monitoring of fruit growth information within a natural growing environment.The issue of how to track green and oscillating fruits under the influence of wind and farming operations is a key aspect of monitoring of the growth state of the fruit.In order to realize the accurate tracking of green fruit targets,a new method based on target tracking is proposed.First,an optical flow method is applied to realize the automatic detection of green fruit targets,and this lays the foundation for the accurate and automatic tracking of these targets.Then,Kalman and kernelized correlation filter(KCF)algorithms are applied to achieve multi-target tracking and prediction.In order to verify the performance of these different algorithms on various types of green fruit targets,experiments were carried out based on nine video sequences.The experimental results for the tracking of single,double and triple green fruit targets show that the average tracking success rates of the Kalman algorithm are 88.15%,82.30%and 53.10%,respectively,and those of the KCF algorithm are 94.07%,87.35%and 61.46%,respectively,meaning that the average tracking results from KCF are 5.92%,5.05%and 8.36%higher than those from the Kalman algorithm.The time consumed is also reduced by 35.40%,36.27%and 40.86%,respectively.The results show that it is feasible to apply the KCF algorithm to the tracking of green fruit targets.

To eat or get heat： Behavioral trade-offs between thermoregulation and feeding in gregarious necrophagous larvae

The thermoregulation behavior ofLucilia sericata larvae （Diptera： Calliphori- dae）, a necrophagous species that feeds on vertebrate cadavers, was investigated. These larvae require high heat incomes to develop, and can elevate temperatures by forming large aggregates. We hypothesized that L. sericata larvae should continue to feed at temperatures up to 38 ℃, which can be reached inside larval masses. Thermal regulation behavior such as movement between a hot food spot and colder areas was also postulated. The hypotheses were tested by tracking for 1 h the activity of single, starved third instar larvae in a Petri dish containing 1 food spot （FS） that was heated to a constant temperature of 25 ℃, 34 ℃ or 38 ℃ with an ambient temperature of 25 ℃. The influence of previous conspecific activity in the food on larval behavior was also tested. The crops of larvae were dissected to monitor food content in the digestive systems. Based on relative crop measurements, larvae fed at all food temperatures, but temperature strongly affected larval behavior and kinematics. The total time spent by larvae in FS and the duration of each stay decreased at high FS temperature. Previous activity of conspecifics in the food slightly increased the time spent by larvae in FS and also decreased the average distance to FS. Therefore, necrophagous L. sericata larvae likely thermoregulate during normal feeding activities by adjusting to local fluctuations in temperature, particularly inside maggot masses. By maintaining a steady internal body temperature, larvae likely reduce their development time.