scholarly journals Visual Tracking Using Wang–Landau Reinforcement Sampler

2020 ◽  
Vol 10 (21) ◽  
pp. 7780
Author(s):  
Dokyeong Kwon ◽  
Junseok Kwon
Keyword(s):  
Visual Tracking ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Tracking System ◽  
Network Architectures ◽  
Tracking Accuracy ◽  
Algorithm Performance ◽  
Q Learning ◽  
Number Of Visits

In this study, we present a novel tracking system, in which the tracking accuracy can be considerably enhanced by state prediction. Accordingly, we present a new Q-learning-based reinforcement method, augmented by Wang–Landau sampling. In the proposed method, reinforcement learning is used to predict a target configuration for the subsequent frame, while Wang–Landau sampler balances the exploitation and exploration degrees of the prediction. Our method can adapt to control the randomness of policy, using statistics on the number of visits in a particular state. Thus, our method considerably enhances conventional Q-learning algorithm performance, which also enhances visual tracking performance. Numerical results demonstrate that our method substantially outperforms other state-of-the-art visual trackers and runs in realtime because our method contains no complicated deep neural network architectures.

scholarly journals An Analysis of State-of-the-art Activation Functions For Supervised Deep Neural Network

2021 ◽  
Author(s):  
Anh Nguyen ◽  
Khoa Pham ◽  
Dat Ngo ◽  
Thanh Ngo ◽  
Lam Pham
Keyword(s):  
Neural Network ◽  
Supervised Classification ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Network Architectures ◽  
Activation Functions ◽  
Scene Classification ◽  
Learning Network ◽  
Deep Learning Network

This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activation functions.Meanwhile, the second model, likely VGGish-based architecture, is applied for Acoustic Scene Classification (ASC) Task 1A in DCASE 2018 challenge, thus evaluate whether these activation functions work well in different datasets as well as different network architectures.

Image De-Noising Using Deep Learning

2014 ◽  
Vol 641-642 ◽  
pp. 1287-1290
Author(s):  
Lan Zhang ◽  
Yu Feng Nie ◽  
Zhen Hai Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Input Data ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Large Data ◽  
Image Database ◽  
Learning Problems ◽  
Deep Learning Algorithm

Deep neural network as a part of deep learning algorithm is a state-of-the-art approach to find higher level representations of input data which has been introduced to many practical and challenging learning problems successfully. The primary goal of deep learning is to use large data to help solving a given task on machine learning. We propose an methodology for image de-noising project defined by this model and conduct training a large image database to get the experimental output. The result shows the robustness and efficient our our algorithm.

scholarly journals Deep Reinforcement Learning on HVAC Control

2018 ◽  
Vol 21 ◽  
pp. 29-36 ◽  
Author(s):  
Ivars Namatēvs
Keyword(s):  
Reinforcement Learning ◽  
Predictive Control ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Building Energy ◽  
Computing Power ◽  
Smart Building ◽  
Q Learning ◽  
Sensory Inputs ◽  
Q Function

Due to increase of computing power and innovative approaches of an end-to-end reinforcement learning (RL) that feed data from high-dimensional sensory inputs, it is now plausible to combine RL and Deep learning to perform Smart Building Energy Control (SBEC) systems. Deep reinforcement learning (DRL) revolutionizes existing Q-learning algorithm to Deep Q-learning (DQL) profited by artificial neural networks. Deep Neural Network (DNN) is well trained to calculate the Q-function. To create comprehensive SBEC system it is crucial to choose appropriate mathematical background and benchmark the best framework of a model based predictive control to manage the building heating, ventilation, and air condition (HVAC) system. The main contribution of this paper is to explore a state-of-the-art DRL methodology to smart building control.

scholarly journals Adaptive visual tracking using the prioritized Q-learning algorithm: MDP-based parameter learning approach

2014 ◽  
Vol 32 (12) ◽  
pp. 1090-1101 ◽  
Author(s):  
Sarang Khim ◽  
Sungjin Hong ◽  
Yoonyoung Kim ◽  
Phill kyu Rhee
Keyword(s):  
Visual Tracking ◽  
Learning Algorithm ◽  
Learning Approach ◽  
Parameter Learning ◽  
Q Learning

scholarly journals Detection-Based Object Tracking Applied to Remote Ship Inspection

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 761
Author(s):  
Jing Xie ◽  
Erik Stensrud ◽  
Torbjørn Skramstad
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Tracking System ◽  
Simple Manner ◽  
Detection Model ◽  
Art Object ◽  
Digital Infrastructure ◽  
Inspection Process ◽  
Two Stages

We propose a detection-based tracking system for automatically processing maritime ship inspection videos and predicting suspicious areas where cracks may exist. This system consists of two stages. Stage one uses a state-of-the-art object detection model, i.e., RetinaNet, which is customized with certain modifications and the optimal anchor setting for detecting cracks in the ship inspection images/videos. Stage two is an enhanced tracking system including two key components. The first component is a state-of-the-art tracker, namely, Channel and Spatial Reliability Tracker (CSRT), with improvements to handle model drift in a simple manner. The second component is a tailored data association algorithm which creates tracking trajectories for the cracks being tracked. This algorithm is based on not only the intersection over union (IoU) of the detections and tracking updates but also their respective areas when associating detections to the existing trackers. Consequently, the tracking results compensate for the detection jitters which could lead to both tracking jitter and creation of redundant trackers. Our study shows that the proposed detection-based tracking system has achieved a reasonable performance on automatically analyzing ship inspection videos. It has proven the feasibility of applying deep neural network based computer vision technologies to automating remote ship inspection. The proposed system is being matured and will be integrated into a digital infrastructure which will facilitate the whole ship inspection process.

scholarly journals Deep Neural Network Architecture Search for Wearable Heart Rate Estimations

2021 ◽  
Author(s):  
Daniel Ray ◽  
Tim Collins ◽  
Prasad Ponnapalli
Keyword(s):  
Neural Network ◽  
Heart Rate ◽  
Deep Learning ◽  
Network Architecture ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Data Driven ◽  
Network Architectures ◽  
Learning Approaches ◽  
Neural Network Architecture

Extracting accurate heart rate estimations from wrist-worn photoplethysmography (PPG) devices is challenging due to the signal containing artifacts from several sources. Deep Learning approaches have shown very promising results outperforming classical methods with improvements of 21% and 31% on two state-of-the-art datasets. This paper provides an analysis of several data-driven methods for creating deep neural network architectures with hopes of further improvements.

scholarly journals Towards Automatic Motivator Selection for Autism Behavior Intervention Therapy

2021 ◽  
Author(s):  
Nur Siyam ◽  
Sherief Abdallah
Keyword(s):  
Learning Algorithm ◽  
Autism Spectrum ◽  
Mobile App ◽  
Influential Factors ◽  
Algorithm Performance ◽  
Q Learning ◽  
Academic Activities ◽  
Markov Decision ◽  
The Right ◽  
The Impact

Abstract Children with autism spectrum disorder (ASD) usually show little interest in academic activities and may display disruptive behavior when presented with assignments. Research indicates that incorporating motivational variables during interventions results in improvements in behavior and academic performance. However, the impact of such motivational variables varies between children. In this paper, we aim to solve the problem of selecting the right motivator for children with ASD using Reinforcement Learning by adapting to the most influential factors impacting the effectiveness of the contingent motivator used. We model the task of selecting a motivator as a Markov Decision Process problem. The states, actions and rewards design consider the factors that impact the effectiveness of a motivator based on Applied Behavior Analysis as well as learners’ individual preferences. We use a Q-Learning algorithm to solve the modelled problem. Our proposed solution is then implemented as a mobile application developed for special education plans coordination. To evaluate the motivator selection feature, we conduct a study involving a group of teachers and therapists and assess how the added feature aids the participants in their decision-making process of selecting a motivator. Preliminary results indicated that the motivator selection feature improved the usability of the mobile app. Analysis of the algorithm performance showed promising results and indicated improvement of the recommendations over time.

scholarly journals Visual Tracking Based on an Improved Online Multiple Instance Learning Algorithm

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Li Jia Wang ◽  
Hua Zhang
Keyword(s):  
Visual Tracking ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Multiple Instance Learning ◽  
Tracking Algorithm ◽  
Inner Product ◽  
Selection Strategy ◽  
Weak Classifier ◽  
Update Strategy ◽  
Appearance Changes

An improved online multiple instance learning (IMIL) for a visual tracking algorithm is proposed. In the IMIL algorithm, the importance of each instance contributing to a bag probability is with respect to their probabilities. A selection strategy based on an inner product is presented to choose weak classifier from a classifier pool, which avoids computing instance probabilities and bag probabilityMtimes. Furthermore, a feedback strategy is presented to update weak classifiers. In the feedback update strategy, different weights are assigned to the tracking result and template according to the maximum classifier score. Finally, the presented algorithm is compared with other state-of-the-art algorithms. The experimental results demonstrate that the proposed tracking algorithm runs in real-time and is robust to occlusion and appearance changes.

Two-level Q-learning: learning from conflict demonstrations

2019 ◽  
Vol 34 ◽  
Author(s):  
Mao Li ◽  
Yi Wei ◽  
Daniel Kudenko
Keyword(s):  
Learning Algorithm ◽  
State Of The Art ◽  
The State ◽  
Q Learning ◽  
Current State ◽  
Speed Up ◽  
Traditional Assumption ◽  
Optimal Action ◽  
Multiple Experts ◽  
Novel Algorithm

Abstract One way to address this low sample efficiency of reinforcement learning (RL) is to employ human expert demonstrations to speed up the RL process (RL from demonstration or RLfD). The research so far has focused on demonstrations from a single expert. However, little attention has been given to the case where demonstrations are collected from multiple experts, whose expertise may vary on different aspects of the task. In such scenarios, it is likely that the demonstrations will contain conflicting advice in many parts of the state space. We propose a two-level Q-learning algorithm, in which the RL agent not only learns the policy of deciding on the optimal action but also learns to select the most trustworthy expert according to the current state. Thus, our approach removes the traditional assumption that demonstrations come from one single source and are mostly conflict-free. We evaluate our technique on three different domains and the results show that the state-of-the-art RLfD baseline fails to converge or performs similarly to conventional Q-learning. In contrast, the performance level of our novel algorithm increases with more experts being involved in the learning process and the proposed approach has the capability to handle demonstration conflicts well.

scholarly journals Object Relocation Visual Tracking Based On Histogram Filter And Siamese Network

2022 ◽  
Author(s):  
Jianlong Zhang ◽  
Qiao Li ◽  
Bin Wang ◽  
Chen Chen ◽  
Tianhong Wang ◽  
...  
Keyword(s):  
Visual Tracking ◽  
Image Matching ◽  
Euclidean Distance ◽  
State Of The Art ◽  
Feature Representation ◽  
Tracking Accuracy ◽  
Match Filter ◽  
Siamese Network ◽  
Matching Process ◽  
Dynamic Template

Abstract Siamese network based trackers formulate the visual tracking mission as an image matching process by regression and classification branches, which simplifies the network structure and improves tracking accuracy. However, there remain many problems as described below. 1) The lightweight neural networks decreases feature representation ability. The tracker is easy to fail under the disturbing distractors (e.g., deformation and similar objects) or large changes in viewing angle. 2) The tracker cannot adapt to variations of the object. 3) The tracker cannot reposition the object that has failed to track. To address these issues, we first propose a novel match filter arbiter based on the Euclidean distance histogram between the centers of multiple candidate objects to automatically determine whether the tracker fails. Secondly, Hopcroft-Karp algorithm is introduced to select the winners from the dynamic template set through the backtracking process, and object relocation is achieved by comparing the Gradient Magnitude Similarity Deviation between the template and the winners. The experiments show that our method obtains better performance on several tracking benchmarks, i.e., OTB100, VOT2018, GOT-10k and LaSOT, compared with state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document