scholarly journals Real-Time Inland CCTV Ship Tracking

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Lei Xiao ◽  
Minghai Xu ◽  
Zhongyi Hu
Keyword(s):  
Real Time ◽  
State Of The Art ◽  
Random Projection ◽  
Feedback Mechanism ◽  
Face Tracking ◽  
Great Success ◽  
Short Term ◽  
Corner Points ◽  
Full Occlusion

The predator algorithm is a representative pioneering work that achieves state-of-the-art performance on several popular visual tracking benchmarks and with great success when commercially applied to real-time face tracking in long-term unconstrained videos. However, there are two major drawbacks of predator algorithm when applied to inland CCTV (closed-circuit television) ship tracking. First, the LK short-term tracker within predator algorithm easily tends to drift if the target ship suffers partial or even full occlusion, mainly because the corner-points-like features employed by LK tracker are very sensitive to occlusion appearance change. Second, the cascaded detector within the predator algorithm searches for candidate objects in a predefined scale set, usually including 3-5 elements, which hampers the tracker to adapt to the potential diverse scale variations of the target ship. In this paper, we design a random projection based short-term tracker which can dramatically ease the tracking drift when the ship is under occlusion. Furthermore, a forward-backward feedback mechanism is proposed to estimate the scale variation between two consecutive frames. We prove that these two strategies gain significant improvements over the predator algorithm and also show that the proposed method outperforms several other state-of-the-art trackers.

scholarly journals Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption

2020 ◽  
Vol 34 (05) ◽  
pp. 9571-9578 ◽  
Author(s):  
Wei Zhang ◽  
Yue Ying ◽  
Pan Lu ◽  
Hongyuan Zha
Keyword(s):  
State Of The Art ◽  
Natural Extension ◽  
Target Image ◽  
Short Term ◽  
Image Representations ◽  
High Level ◽  
Image Descriptions ◽  
Shed Light ◽  
Image Caption

Personalized image caption, a natural extension of the standard image caption task, requires to generate brief image descriptions tailored for users' writing style and traits, and is more practical to meet users' real demands. Only a few recent studies shed light on this crucial task and learn static user representations to capture their long-term literal-preference. However, it is insufficient to achieve satisfactory performance due to the intrinsic existence of not only long-term user literal-preference, but also short-term literal-preference which is associated with users' recent states. To bridge this gap, we develop a novel multimodal hierarchical transformer network (MHTN) for personalized image caption in this paper. It learns short-term user literal-preference based on users' recent captions through a short-term user encoder at the low level. And at the high level, the multimodal encoder integrates target image representations with short-term literal-preference, as well as long-term literal-preference learned from user IDs. These two encoders enjoy the advantages of the powerful transformer networks. Extensive experiments on two real datasets show the effectiveness of considering two types of user literal-preference simultaneously and better performance over the state-of-the-art models.

scholarly journals Learning from Interventions Using Hierarchical Policies for Safe Learning

2020 ◽  
Vol 34 (06) ◽  
pp. 10352-10360
Author(s):  
Jing Bi ◽  
Vikas Dhiman ◽  
Tianyou Xiao ◽  
Chenliang Xu
Keyword(s):  
Reaction Time ◽  
State Of The Art ◽  
The State ◽  
Policy Framework ◽  
Asymptotic Performance ◽  
Short Term ◽  
Learning From Demonstrations ◽  
Hierarchical Levels ◽  
Long Term Behavior

Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the algorithm is already well-trained. The recently proposed Learning from Interventions (LfI) overcomes this limitation by using an expert overseer. The expert overseer only intervenes when it suspects that an unsafe action is about to be taken. Although LfI significantly improves over LfD, the state-of-the-art LfI fails to account for delay caused by the expert's reaction time and only learns short-term behavior. We address these limitations by 1) interpolating the expert's interventions back in time, and 2) by splitting the policy into two hierarchical levels, one that generates sub-goals for the future and another that generates actions to reach those desired sub-goals. This sub-goal prediction forces the algorithm to learn long-term behavior while also being robust to the expert's reaction time. Our experiments show that LfI using sub-goals in a hierarchical policy framework trains faster and achieves better asymptotic performance than typical LfD.

scholarly journals Long-term target tracking combined with re-detection

2020 ◽  
Author(s):  
Juanjuan Wang ◽  
HaoRan Yang ◽  
Ning Xu ◽  
Chengqin Wu ◽  
ZengShun Zhao ◽  
...  
Keyword(s):  
Correlation Energy ◽  
State Of The Art ◽  
Tracking Algorithm ◽  
Correlation Filters ◽  
Short Term ◽  
Tracking Method ◽  
Tracking Tasks ◽  
Svm Model ◽  
Confidence Degree

Abstract The long-term visual tracking undergoes more challenges and is closer to realistic applications than short-term tracking. However, the performances of most existing methods have been limited in the long-term tracking tasks. In this work, we present a reliable yet simple long-term tracking method, which extends the state-of-the-art Learning Adaptive Discriminative Correlation Filters (LADCF) tracking algorithm with a re-detection component based on the SVM model. The LADCF tracking algorithm localizes the target in each frame and the re-detector is able to efficiently re-detect the target in the whole image when the tracking fails. We further introduce a robust confidence degree evaluation criterion that combines the maximum response criterion and the average peak-to correlation energy (APCE) to judge the confidence level of the predicted target. When the confidence degree is generally high, the SVM is updated accordingly. If the confidence drops sharply, the SVM re-detects the target. We perform extensive experiments on the OTB-2015 and UAV123 datasets. The experimental results demonstrate the effectiveness of our algorithm in long-term tracking.

scholarly journals Neural Architecture Search for a Highly Efficient Network with Random Skip Connections

2020 ◽  
Vol 10 (11) ◽  
pp. 3712
Author(s):  
Dongjing Shan ◽  
Xiongwei Zhang ◽  
Wenhua Shi ◽  
Li Li
Keyword(s):  
State Of The Art ◽  
Cell Structure ◽  
Frequency Discrimination ◽  
Search Space ◽  
Short Term ◽  
Cell Parameters ◽  
Neural Architecture ◽  
Proposed Model ◽  
Initialization Scheme

Regarding the sequence learning of neural networks, there exists a problem of how to capture long-term dependencies and alleviate the gradient vanishing phenomenon. To manage this problem, we proposed a neural network with random connections via a scheme of a neural architecture search. First, a dense network was designed and trained to construct a search space, and then another network was generated by random sampling in the space, whose skip connections could transmit information directly over multiple periods and capture long-term dependencies more efficiently. Moreover, we devised a novel cell structure that required less memory and computational power than the structures of long short-term memories (LSTMs), and finally, we performed a special initialization scheme on the cell parameters, which could permit unhindered gradient propagation on the time axis at the beginning of training. In the experiments, we evaluated four sequential tasks: adding, copying, frequency discrimination, and image classification; we also adopted several state-of-the-art methods for comparison. The experimental results demonstrated that our proposed model achieved the best performance.

Robust Inland Waterway Ship Tracking via Hybrid TLD and Kalman Filter

2014 ◽  
Vol 1037 ◽  
pp. 373-377 ◽  
Author(s):  
Teng Fei ◽  
Liu Qing ◽  
Lin Zhu ◽  
Jing Li
Keyword(s):  
Kalman Filter ◽  
Visual Tracking ◽  
State Of The Art ◽  
Experimental Results ◽  
Closed Circuit ◽  
Video Sequences ◽  
Inland Waterway ◽  
Cluttered Background ◽  
Full Occlusion

In this paper, we mainly address the problem of tracking a single ship in inland waterway CCTV (Closed-Circuit Television) video sequences. Although state-of-the-art performance has been demonstrated in TLD (Tracking-Learning-Detection) visual tracking, it is still challenging to perform long-term robust ship tracking due to factors such as cluttered background, scale change, partial or full occlusion and so forth. In this work, we focus on tracking a single ship when it suffers occlusion. To accomplish this goal, an effective Kalman filter is adopted to construct a novel online model to adapt to the rapid ship appearance change caused by occlusion. Experimental results on numerous inland waterway CCTV video sequences demonstrate that the proposed algorithm outperforms the original one.

The Effect of Behavioral Realism and Form Realism of Real-Time Avatar Faces on Verbal Disclosure, Nonverbal Disclosure, Emotion Recognition, and Copresence in Dyadic Interaction

2006 ◽  
Vol 15 (4) ◽  
pp. 359-372 ◽  
Author(s):  
Jeremy N Bailenson ◽  
Nick Yee ◽  
Dan Merget ◽  
Ralph Schroeder
Keyword(s):  
Virtual Environments ◽  
Real Time ◽  
Facial Expressions ◽  
State Of The Art ◽  
Face Tracking ◽  
Dyadic Interaction ◽  
Collaborative Virtual Environments ◽  
Self Disclosure ◽  
High Form ◽  
Tracking Technology

The realism of avatars in terms of behavior and form is critical to the development of collaborative virtual environments. In the study we utilized state of the art, real-time face tracking technology to track and render facial expressions unobtrusively in a desktop CVE. Participants in dyads interacted with each other via either a video-conference (high behavioral realism and high form realism), voice only (low behavioral realism and low form realism), or an “emotibox” that rendered the dimensions of facial expressions abstractly in terms of color, shape, and orientation on a rectangular polygon (high behavioral realism and low form realism). Verbal and non-verbal self-disclosure were lowest in the videoconference condition while self-reported copresence and success of transmission and identification of emotions were lowest in the emotibox condition. Previous work demonstrates that avatar realism increases copresence while decreasing self-disclosure. We discuss the possibility of a hybrid realism solution that maintains high copresence without lowering self-disclosure, and the benefits of such an avatar on applications such as distance learning and therapy.

scholarly journals Near-Real-Time Surveillance of Illnesses Related to Shellfish Consumption in British Columbia: Analysis of Poison Center Data (Preprint)

2017 ◽  
Author(s):  
Victoria Wan ◽  
Lorraine McIntyre ◽  
Debra Kent ◽  
Dennis Leong ◽  
Sarah B Henderson
Keyword(s):  
Public Health ◽  
Real Time ◽  
Public Health Surveillance ◽  
Data File ◽  
Health Surveillance ◽  
Poison Control ◽  
Short Term ◽  
Control Data

BACKGROUND Data from poison centers have the potential to be valuable for public health surveillance of long-term trends, short-term aberrations from those trends, and poisonings occurring in near-real-time. This information can enable long-term prevention via programs and policies and short-term control via immediate public health response. Over the past decade, there has been an increasing use of poison control data for surveillance in the United States, Europe, and New Zealand, but this resource still remains widely underused. OBJECTIVE The British Columbia (BC) Drug and Poison Information Centre (DPIC) is one of five such services in Canada, and it is the only one nested within a public health agency. This study aimed to demonstrate how DPIC data are used for routine public health surveillance in near-real-time using the case study of its alerting system for illness related to consumption of shellfish (ASIRCS). METHODS Every hour, a connection is opened between the WBM software Visual Dotlab Enterprise, which holds the DPIC database, and the R statistical computing environment. This platform is used to extract, clean, and merge all necessary raw data tables into a single data file. ASIRCS automatically and retrospectively scans a 24-hour window within the data file for new cases related to illnesses from shellfish consumption. Detected cases are queried using a list of attributes: the caller location, exposure type, reasons for the exposure, and a list of keywords searched in the clinical notes. The alert generates a report that is tailored to the needs of food safety specialists, who then assess and respond to detected cases. RESULTS The ASIRCS system alerted on 79 cases between January 2015 and December 2016, and retrospective analysis found 11 cases that were missed. All cases were reviewed by food safety specialists, and 58% (46/79) were referred to designated regional health authority contacts for follow-up. Of the 42% (33/79) cases that were not referred to health authorities, some were missing follow-up information, some were triggered by allergies to shellfish, and some were triggered by shellfish-related keywords appearing in the case notes for nonshellfish-related cases. Improvements were made between 2015 and 2016 to reduce the number of cases with missing follow-up information. CONCLUSIONS The surveillance capacity is evident within poison control data as shown from the novel use of DPIC data for identifying illnesses related to shellfish consumption in BC. The further development of surveillance programs could improve and enhance response to public health emergencies related to acute illnesses, chronic diseases, and environmental exposures.

Probability-Based Power Dispatch in Wind-Integrated Electrical Grid for Energy Storage Capacity Determination

2016 ◽  
Author(s):  
Tzu-Chieh Hung ◽  
Kuei-Yuan Chan
Keyword(s):  
Energy Storage ◽  
Wind Energy ◽  
Real Time ◽  
Current Trend ◽  
Electric Utility ◽  
Energy Access ◽  
Short Term ◽  
Power Dispatch ◽  
Time Operation

Implementing microgrids has become a current trend in the electric utility industry to either improve system reliability or energy access for energy sustainability. This study proposes a probability-based strategy for both long- and short-term power dispatch with wind and load uncertainty. The long-term power dispatch is used to determine a suitable capacity of energy storage, and the short-term power dispatch is used for real-time operation. For both short- and long-term power dispatch, the trends of wind energy and electricity demand are extracted using the wavelet packet analysis method and the moving average technique. The uncertainties from wind speed and power generation data are modeled with log-normal and extreme value distributions, respectively. From the obtained power dispatch and model forecasting, the capacity of energy storage is determined. To validate the proposed approach, a real-time operating simulation is used as a case study to observe the behavior of the wind-integrated electrical system. Results show that the proposed method can estimate the uncertainty variation range of wind energy and the state of charge of energy storage effectively.

scholarly journals Where to Go Next: Modeling Long- and Short-Term User Preferences for Point-of-Interest Recommendation

2020 ◽  
Vol 34 (01) ◽  
pp. 214-221 ◽  
Author(s):  
Ke Sun ◽  
Tieyun Qian ◽  
Tong Chen ◽  
Yile Liang ◽  
Quoc Viet Hung Nguyen ◽  
...  
Keyword(s):  
State Of The Art ◽  
User Preferences ◽  
Short Term ◽  
Preference Modeling ◽  
Point Of Interest ◽  
Proposed Model ◽  
Poi Recommendation ◽  
Novel Method ◽  
Real World Datasets

Point-of-Interest (POI) recommendation has been a trending research topic as it generates personalized suggestions on facilities for users from a large number of candidate venues. Since users' check-in records can be viewed as a long sequence, methods based on recurrent neural networks (RNNs) have recently shown promising applicability for this task. However, existing RNN-based methods either neglect users' long-term preferences or overlook the geographical relations among recently visited POIs when modeling users' short-term preferences, thus making the recommendation results unreliable. To address the above limitations, we propose a novel method named Long- and Short-Term Preference Modeling (LSTPM) for next-POI recommendation. In particular, the proposed model consists of a nonlocal network for long-term preference modeling and a geo-dilated RNN for short-term preference learning. Extensive experiments on two real-world datasets demonstrate that our model yields significant improvements over the state-of-the-art methods.

Short-term and long-term learners’ motivation modeling in Web-based educational systems

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Shahzad Shabbir ◽  
Muhammad Adnan Ayub ◽  
Farman Ali Khan ◽  
Jeffrey Davis
Keyword(s):  
Real Time ◽  
Learning Process ◽  
Educational Systems ◽  
Short Term ◽  
Web Based ◽  
Learner Motivation ◽  
Content Type ◽  
Model Based ◽  
Motivation Model

Purpose Short-term motivation encompasses specific, challenging and attainable goals that develop in the limited timespan. On the other hand, long-term motivation indicates a sort of continuing commitment that is required to complete assigned task. As short-term motivational problems span for a limited period of time, such as a session, therefore, they need to be addressed in real time to keep the learner engaged in the learning process. Similarly, long-term learners’ motivation plays an equally important role to retain the learner in the long run and minimize the risk of dropout. Therefore, the purpose of this study is to incorporate a comprehensive learner motivation model that is based on short-term and long-term aspects of the learners' motivation. This approach enables Web-based educational systems to identify the real-time motivational state of the learner and provide personalized interventions to keep the learners engaged in learning process. Design/methodology/approach Recent research regarding personalized Web-based educational systems demonstrates learner’s motivation to be an essential component of the learning model. This is because of the fact that low motivation results in either students’ less engagement or complete drop out from the learning activities. A learner motivation model is considered to be a set of perceptions and beliefs that the system has developed about a learner. This includes both short-term and long-term motivations of leaners. Findings This study proposed a framework of a domain independent learners’ motivation model based on firm educational theories. The proposed framework consists of two modules. The primary module deals with real-time identification of motivation and logging off activities such as login, forum participation and adherence to assessment deadline. Secondary module maintains the profile of leaners associated with both short-term and long-term motivation. A study was conducted to verify the impact of learners’ motivation model and personalized interventional strategies based on proposed model, using Systematical Information Education Method assessment standards. The results show an increase in motivational index and the characteristics associated with motivation during the conducted study. Originality/value Motivational diagnosis is important for both traditional classrooms and Web-based education systems. It is one of the major elements that contribute in the success of the learning process. However, dropout rate among online students is very high, which leads to incorporate motivational elements in more personalized way because motivated students will retain the course until they successfully complete it. Hence, identifying learner’s motivation, updating learners’ motivation model based on this identification and providing personalized interventions are the key for the success of Web-based educational systems.

Sign in / Sign up

Export Citation Format

Share Document